diff --git a/.bumpversion.cfg b/.bumpversion.cfg index de22a2783..d9e4a2831 100644 --- a/.bumpversion.cfg +++ b/.bumpversion.cfg @@ -1,5 +1,5 @@ [bumpversion] -current_version = 2.1.0 +current_version = 2.5.0 commit = True tag = True tag_name = {new_version} diff --git a/.flake8 b/.flake8 new file mode 100644 index 000000000..1c503fb0b --- /dev/null +++ b/.flake8 @@ -0,0 +1,19 @@ +[flake8] + +max-line-length = 119 +ignore = W503 + +exclude = +# Exclude files that are meant to provide top-level imports +# E402: Module level import not at top of file +# F401: Module imported but unused + scrapy/__init__.py E402 + scrapy/core/downloader/handlers/http.py F401 + scrapy/http/__init__.py F401 + scrapy/linkextractors/__init__.py E402 F401 + scrapy/selector/__init__.py F401 + scrapy/spiders/__init__.py E402 F401 + + # Issues pending a review: + scrapy/utils/url.py F403 F405 + tests/test_loader.py E741 diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 000000000..dfbdf4208 --- /dev/null +++ b/.gitattributes @@ -0,0 +1 @@ +tests/sample_data/** binary diff --git a/.github/workflows/checks.yml b/.github/workflows/checks.yml new file mode 100644 index 000000000..6bdfcb5dc --- /dev/null +++ b/.github/workflows/checks.yml @@ -0,0 +1,45 @@ +name: Checks +on: [push, pull_request] + +jobs: + checks: + runs-on: ubuntu-18.04 + strategy: + fail-fast: false + matrix: + include: + - python-version: 3.9 + env: + TOXENV: security + - python-version: 3.9 + env: + TOXENV: flake8 + # Pylint requires installing reppy, which does not support Python 3.9 + # https://github.com/seomoz/reppy/issues/122 + - python-version: 3.8 + env: + TOXENV: pylint + TOX_PIP_VERSION: 20.3.3 + - python-version: 3.9 + env: + TOXENV: typing + - python-version: 3.8 # Keep in sync with .readthedocs.yml + env: + TOXENV: docs + + steps: + - uses: actions/checkout@v2 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v2 + with: + python-version: ${{ matrix.python-version }} + + - name: Run check + env: ${{ matrix.env }} + run: | + if [[ ! -z "$TOX_PIP_VERSION" ]]; then + pip install tox-pip-version + fi + pip install -U tox + tox diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml new file mode 100644 index 000000000..b48066ea4 --- /dev/null +++ b/.github/workflows/publish.yml @@ -0,0 +1,31 @@ +name: Publish +on: [push] + +jobs: + publish: + runs-on: ubuntu-18.04 + if: startsWith(github.event.ref, 'refs/tags/') + + steps: + - uses: actions/checkout@v2 + + - name: Set up Python 3.9 + uses: actions/setup-python@v2 + with: + python-version: 3.9 + + - name: Check Tag + id: check-release-tag + run: | + if [[ ${{ github.event.ref }} =~ ^refs/tags/[0-9]+[.][0-9]+[.][0-9]+(rc[0-9]+|[.]dev[0-9]+)?$ ]]; then + echo ::set-output name=release_tag::true + fi + + - name: Publish to PyPI + if: steps.check-release-tag.outputs.release_tag == 'true' + run: | + pip install --upgrade setuptools wheel twine + python setup.py sdist bdist_wheel + export TWINE_USERNAME=__token__ + export TWINE_PASSWORD=${{ secrets.PYPI_TOKEN }} + twine upload dist/* diff --git a/.github/workflows/tests-macos.yml b/.github/workflows/tests-macos.yml new file mode 100644 index 000000000..095ca1013 --- /dev/null +++ b/.github/workflows/tests-macos.yml @@ -0,0 +1,26 @@ +name: macOS +on: [push, pull_request] + +jobs: + tests: + runs-on: macos-10.15 + strategy: + fail-fast: false + matrix: + python-version: [3.6, 3.7, 3.8, 3.9] + + steps: + - uses: actions/checkout@v2 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v2 + with: + python-version: ${{ matrix.python-version }} + + - name: Run tests + run: | + pip install -U tox + tox -e py + + - name: Upload coverage report + run: bash <(curl -s https://codecov.io/bash) diff --git a/.github/workflows/tests-ubuntu.yml b/.github/workflows/tests-ubuntu.yml new file mode 100644 index 000000000..57188bd63 --- /dev/null +++ b/.github/workflows/tests-ubuntu.yml @@ -0,0 +1,80 @@ +name: Ubuntu +on: [push, pull_request] + +jobs: + tests: + runs-on: ubuntu-18.04 + strategy: + fail-fast: false + matrix: + include: + - python-version: 3.7 + env: + TOXENV: py + - python-version: 3.8 + env: + TOXENV: py + - python-version: 3.9 + env: + TOXENV: py + - python-version: pypy3 + env: + TOXENV: pypy3 + PYPY_VERSION: 3.6-v7.3.1 + + # pinned deps + - python-version: 3.6.12 + env: + TOXENV: pinned + - python-version: 3.6.12 + env: + TOXENV: asyncio-pinned + - python-version: pypy3 + env: + TOXENV: pypy3-pinned + PYPY_VERSION: 3.6-v7.2.0 + + # extras + # extra-deps includes reppy, which does not support Python 3.9 + # https://github.com/seomoz/reppy/issues/122 + - python-version: 3.8 + env: + TOXENV: extra-deps + TOX_PIP_VERSION: 20.3.3 + - python-version: 3.9 + env: + TOXENV: asyncio + + steps: + - uses: actions/checkout@v2 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v2 + with: + python-version: ${{ matrix.python-version }} + + - name: Install system libraries + if: matrix.python-version == 'pypy3' || contains(matrix.env.TOXENV, 'pinned') + run: | + sudo apt-get update + # libxml2 2.9.12 from ondrej/php PPA breaks lxml so we pin it to the bionic-updates repo version + sudo apt-get install libxml2-dev/bionic-updates libxslt-dev + + - name: Run tests + env: ${{ matrix.env }} + run: | + if [[ ! -z "$PYPY_VERSION" ]]; then + export PYPY_VERSION="pypy$PYPY_VERSION-linux64" + wget "https://downloads.python.org/pypy/${PYPY_VERSION}.tar.bz2" + tar -jxf ${PYPY_VERSION}.tar.bz2 + $PYPY_VERSION/bin/pypy3 -m venv "$HOME/virtualenvs/$PYPY_VERSION" + source "$HOME/virtualenvs/$PYPY_VERSION/bin/activate" + fi + if [[ ! -z "$TOX_PIP_VERSION" ]]; then + pip install tox-pip-version + fi + pip install -U tox + tox + + - name: Upload coverage report + run: bash <(curl -s https://codecov.io/bash) diff --git a/.github/workflows/tests-windows.yml b/.github/workflows/tests-windows.yml new file mode 100644 index 000000000..30fda33e8 --- /dev/null +++ b/.github/workflows/tests-windows.yml @@ -0,0 +1,37 @@ +name: Windows +on: [push, pull_request] + +jobs: + tests: + runs-on: windows-latest + strategy: + fail-fast: false + matrix: + include: + - python-version: 3.6 + env: + TOXENV: windows-pinned + - python-version: 3.7 + env: + TOXENV: py + - python-version: 3.8 + env: + TOXENV: py + # https://twistedmatrix.com/trac/ticket/9990 + #- python-version: 3.9 + #env: + #TOXENV: py + + steps: + - uses: actions/checkout@v2 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v2 + with: + python-version: ${{ matrix.python-version }} + + - name: Run tests + env: ${{ matrix.env }} + run: | + pip install -U tox + tox diff --git a/.gitignore b/.gitignore index ff6e2ea65..d77d24624 100644 --- a/.gitignore +++ b/.gitignore @@ -14,7 +14,12 @@ htmlcov/ .coverage .pytest_cache/ .coverage.* +coverage.* +test-output.* .cache/ +.mypy_cache/ +/tests/keys/localhost.crt +/tests/keys/localhost.key # Windows Thumbs.db diff --git a/.readthedocs.yml b/.readthedocs.yml index e4d3f02cc..80a1cd036 100644 --- a/.readthedocs.yml +++ b/.readthedocs.yml @@ -3,10 +3,14 @@ formats: all sphinx: configuration: docs/conf.py fail_on_warning: true + +build: + image: latest + python: # For available versions, see: # https://docs.readthedocs.io/en/stable/config-file/v2.html#build-image - version: 3.7 # Keep in sync with .travis.yml + version: 3.8 # Keep in sync with .github/workflows/checks.yml install: - requirements: docs/requirements.txt - path: . diff --git a/.travis.yml b/.travis.yml deleted file mode 100644 index d6ec88e06..000000000 --- a/.travis.yml +++ /dev/null @@ -1,75 +0,0 @@ -language: python -dist: xenial -branches: - only: - - master - - /^\d\.\d+$/ - - /^\d\.\d+\.\d+(rc\d+|\.dev\d+)?$/ -matrix: - include: - - env: TOXENV=security - python: 3.8 - - env: TOXENV=flake8 - python: 3.8 - - env: TOXENV=pylint - python: 3.8 - - env: TOXENV=docs - python: 3.7 # Keep in sync with .readthedocs.yml - - - env: TOXENV=pypy3 - - env: TOXENV=pinned - python: 3.5.1 - dist: trusty - - env: TOXENV=asyncio - python: 3.5.1 # We use additional code to support 3.5.3 and earlier - dist: trusty - - env: TOXENV=py - python: 3.5 - - env: TOXENV=asyncio - python: 3.5 # We use specific code to support >= 3.5.4, < 3.6 - - env: TOXENV=py - python: 3.6 - - env: TOXENV=py - python: 3.7 - - env: TOXENV=py PYPI_RELEASE_JOB=true - python: 3.8 - dist: bionic - - env: TOXENV=extra-deps - python: 3.8 - dist: bionic - - env: TOXENV=asyncio - python: 3.8 - dist: bionic -install: - - | - if [ "$TOXENV" = "pypy3" ]; then - export PYPY_VERSION="pypy3.5-5.9-beta-linux_x86_64-portable" - wget "https://bitbucket.org/squeaky/portable-pypy/downloads/${PYPY_VERSION}.tar.bz2" - tar -jxf ${PYPY_VERSION}.tar.bz2 - virtualenv --python="$PYPY_VERSION/bin/pypy3" "$HOME/virtualenvs/$PYPY_VERSION" - source "$HOME/virtualenvs/$PYPY_VERSION/bin/activate" - fi - - pip install -U tox twine wheel codecov - -script: tox -after_success: - - codecov -notifications: - irc: - use_notice: true - skip_join: true - channels: - - irc.freenode.org#scrapy -cache: - directories: - - $HOME/.cache/pip -deploy: - provider: pypi - distributions: "sdist bdist_wheel" - user: scrapy - password: - secure: JaAKcy1AXWXDK3LXdjOtKyaVPCSFoCGCnW15g4f65E/8Fsi9ZzDfmBa4Equs3IQb/vs/if2SVrzJSr7arN7r9Z38Iv1mUXHkFAyA3Ym8mThfABBzzcUWEQhIHrCX0Tdlx9wQkkhs+PZhorlmRS4gg5s6DzPaeA2g8SCgmlRmFfA= - on: - tags: true - repo: scrapy/scrapy - condition: "$PYPI_RELEASE_JOB == true && $TRAVIS_TAG =~ ^[0-9]+[.][0-9]+[.][0-9]+(rc[0-9]+|[.]dev[0-9]+)?$" diff --git a/AUTHORS b/AUTHORS index bcaa1ecd3..9706adf42 100644 --- a/AUTHORS +++ b/AUTHORS @@ -1,8 +1,8 @@ Scrapy was brought to life by Shane Evans while hacking a scraping framework prototype for Mydeco (mydeco.com). It soon became maintained, extended and improved by Insophia (insophia.com), with the initial sponsorship of Mydeco to -bootstrap the project. In mid-2011, Scrapinghub became the new official -maintainer. +bootstrap the project. In mid-2011, Scrapinghub (now Zyte) became the new +official maintainer. Here is the list of the primary authors & contributors: diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md index d1cd3e517..902cd523e 100644 --- a/CODE_OF_CONDUCT.md +++ b/CODE_OF_CONDUCT.md @@ -55,7 +55,7 @@ further defined and clarified by project maintainers. ## Enforcement Instances of abusive, harassing, or otherwise unacceptable behavior may be -reported by contacting the project team at opensource@scrapinghub.com. All +reported by contacting the project team at opensource@zyte.com. All complaints will be reviewed and investigated and will result in a response that is deemed necessary and appropriate to the circumstances. The project team is obligated to maintain confidentiality with regard to the reporter of an incident. @@ -72,3 +72,6 @@ available at [http://contributor-covenant.org/version/1/4][version]. [homepage]: http://contributor-covenant.org [version]: http://contributor-covenant.org/version/1/4/ + +For answers to common questions about this code of conduct, see +https://www.contributor-covenant.org/faq diff --git a/README.rst b/README.rst index fd84e127e..5750e2c0f 100644 --- a/README.rst +++ b/README.rst @@ -10,9 +10,17 @@ Scrapy :target: https://pypi.python.org/pypi/Scrapy :alt: Supported Python Versions -.. image:: https://img.shields.io/travis/scrapy/scrapy/master.svg - :target: https://travis-ci.org/scrapy/scrapy - :alt: Build Status +.. image:: https://github.com/scrapy/scrapy/workflows/Ubuntu/badge.svg + :target: https://github.com/scrapy/scrapy/actions?query=workflow%3AUbuntu + :alt: Ubuntu + +.. image:: https://github.com/scrapy/scrapy/workflows/macOS/badge.svg + :target: https://github.com/scrapy/scrapy/actions?query=workflow%3AmacOS + :alt: macOS + +.. image:: https://github.com/scrapy/scrapy/workflows/Windows/badge.svg + :target: https://github.com/scrapy/scrapy/actions?query=workflow%3AWindows + :alt: Windows .. image:: https://img.shields.io/badge/wheel-yes-brightgreen.svg :target: https://pypi.python.org/pypi/Scrapy @@ -34,13 +42,20 @@ Scrapy is a fast high-level web crawling and web scraping framework, used to crawl websites and extract structured data from their pages. It can be used for a wide range of purposes, from data mining to monitoring and automated testing. +Scrapy is maintained by Zyte_ (formerly Scrapinghub) and `many other +contributors`_. + +.. _many other contributors: https://github.com/scrapy/scrapy/graphs/contributors +.. _Zyte: https://www.zyte.com/ + Check the Scrapy homepage at https://scrapy.org for more information, including a list of features. + Requirements ============ -* Python 3.5.1+ +* Python 3.6+ * Works on Linux, Windows, macOS, BSD Install @@ -81,7 +96,7 @@ Please note that this project is released with a Contributor Code of Conduct (see https://github.com/scrapy/scrapy/blob/master/CODE_OF_CONDUCT.md). By participating in this project you agree to abide by its terms. -Please report unacceptable behavior to opensource@scrapinghub.com. +Please report unacceptable behavior to opensource@zyte.com. Companies using Scrapy ====================== diff --git a/appveyor.yml b/appveyor.yml deleted file mode 100644 index 7fd636864..000000000 --- a/appveyor.yml +++ /dev/null @@ -1,25 +0,0 @@ -platform: x86 -version: '{branch}-{build}' -environment: - matrix: - - PYTHON: "C:\\Python36" - TOX_ENV: py36 - -branches: - only: - - master - - /d+\.\d+\.\d+[\w\-]*$/ - -install: - - "SET PATH=%PYTHON%;%PYTHON%\\Scripts;%PATH%" - - "SET PYTHONPATH=%APPVEYOR_BUILD_FOLDER%" - - "SET TOX_TESTENV_PASSENV=HOME HOMEDRIVE HOMEPATH PYTHONPATH USERPROFILE" - - "pip install -U tox" - -build: false -skip_tags: true -test_script: - - "tox -e %TOX_ENV%" - -cache: - - '%LOCALAPPDATA%\pip\cache' diff --git a/conftest.py b/conftest.py index b39d644a5..05b4ccdad 100644 --- a/conftest.py +++ b/conftest.py @@ -1,6 +1,11 @@ from pathlib import Path import pytest +from twisted.web.http import H2_ENABLED + +from scrapy.utils.reactor import install_reactor + +from tests.keys import generate_keys def _py_files(folder): @@ -14,14 +19,21 @@ collect_ignore = [ *_py_files("tests/CrawlerProcess"), # contains scripts to be run by tests/test_crawler.py::CrawlerRunnerSubprocess *_py_files("tests/CrawlerRunner"), - # Py36-only parts of respective tests - *_py_files("tests/py36"), ] -for line in open('tests/ignores.txt'): - file_path = line.strip() - if file_path and file_path[0] != '#': - collect_ignore.append(file_path) +with open('tests/ignores.txt') as reader: + for line in reader: + file_path = line.strip() + if file_path and file_path[0] != '#': + collect_ignore.append(file_path) + +if not H2_ENABLED: + collect_ignore.extend( + ( + 'scrapy/core/downloader/handlers/http2.py', + *_py_files("scrapy/core/http2"), + ) + ) @pytest.fixture() @@ -40,6 +52,14 @@ def pytest_collection_modifyitems(session, config, items): pass +def pytest_addoption(parser): + parser.addoption( + "--reactor", + default="default", + choices=["default", "asyncio"], + ) + + @pytest.fixture(scope='class') def reactor_pytest(request): if not request.cls: @@ -53,3 +73,12 @@ def reactor_pytest(request): def only_asyncio(request, reactor_pytest): if request.node.get_closest_marker('only_asyncio') and reactor_pytest != 'asyncio': pytest.skip('This test is only run with --reactor=asyncio') + + +def pytest_configure(config): + if config.getoption("--reactor") == "asyncio": + install_reactor("twisted.internet.asyncioreactor.AsyncioSelectorReactor") + + +# Generate localhost certificate files, needed by some tests +generate_keys() diff --git a/docs/Makefile b/docs/Makefile index ff68bf1ae..87d5d3047 100644 --- a/docs/Makefile +++ b/docs/Makefile @@ -8,7 +8,7 @@ PYTHON = python SPHINXOPTS = PAPER = SOURCES = -SHELL = /bin/bash +SHELL = /usr/bin/env bash ALLSPHINXOPTS = -b $(BUILDER) -d build/doctrees \ -D latex_elements.papersize=$(PAPER) \ diff --git a/docs/_ext/scrapydocs.py b/docs/_ext/scrapydocs.py index 192123473..640660943 100644 --- a/docs/_ext/scrapydocs.py +++ b/docs/_ext/scrapydocs.py @@ -17,7 +17,7 @@ class SettingsListDirective(Directive): def is_setting_index(node): if node.tagname == 'index': # index entries for setting directives look like: - # [(u'pair', u'SETTING_NAME; setting', u'std:setting-SETTING_NAME', '')] + # [('pair', 'SETTING_NAME; setting', 'std:setting-SETTING_NAME', '')] entry_type, info, refid = node['entries'][0][:3] return entry_type == 'pair' and info.endswith('; setting') return False diff --git a/docs/_static/custom.css b/docs/_static/custom.css new file mode 100644 index 000000000..64f16939c --- /dev/null +++ b/docs/_static/custom.css @@ -0,0 +1,10 @@ +/* Move lists closer to their introducing paragraph */ +.rst-content .section ol p, .rst-content .section ul p { + margin-bottom: 0px; +} +.rst-content p + ol, .rst-content p + ul { + margin-top: -18px; /* Compensates margin-top: 24px of p */ +} +.rst-content dl p + ol, .rst-content dl p + ul { + margin-top: -6px; /* Compensates margin-top: 12px of p */ +} \ No newline at end of file diff --git a/docs/_templates/layout.html b/docs/_templates/layout.html index a6f6cbda8..18a5231ee 100644 --- a/docs/_templates/layout.html +++ b/docs/_templates/layout.html @@ -3,14 +3,9 @@ {% block footer %} {{ super() }} {% endblock %} diff --git a/docs/conf.py b/docs/conf.py index 29b2fc406..406c4d94a 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -49,7 +49,7 @@ master_doc = 'index' # General information about the project. project = 'Scrapy' -copyright = '2008–{}, Scrapy developers'.format(datetime.now().year) +copyright = f'2008–{datetime.now().year}, Scrapy developers' # The version info for the project you're documenting, acts as replacement for # |version| and |release|, also used in various other places throughout the @@ -122,7 +122,6 @@ html_theme = 'sphinx_rtd_theme' import sphinx_rtd_theme html_theme_path = [sphinx_rtd_theme.get_html_theme_path()] - # The style sheet to use for HTML and HTML Help pages. A file of that name # must exist either in Sphinx' static/ path, or in one of the custom paths # given in html_static_path. @@ -183,6 +182,10 @@ html_copy_source = True # Output file base name for HTML help builder. htmlhelp_basename = 'Scrapydoc' +html_css_files = [ + 'custom.css', +] + # Options for LaTeX output # ------------------------ @@ -281,8 +284,11 @@ coverage_ignore_pyobjects = [ # ------------------------------------- intersphinx_mapping = { + 'attrs': ('https://www.attrs.org/en/stable/', None), 'coverage': ('https://coverage.readthedocs.io/en/stable', None), + 'cryptography' : ('https://cryptography.io/en/latest/', None), 'cssselect': ('https://cssselect.readthedocs.io/en/latest', None), + 'itemloaders': ('https://itemloaders.readthedocs.io/en/latest/', None), 'pytest': ('https://docs.pytest.org/en/latest', None), 'python': ('https://docs.python.org/3', None), 'sphinx': ('https://www.sphinx-doc.org/en/master', None), @@ -304,3 +310,15 @@ hoverxref_role_types = { "ref": "tooltip", } hoverxref_roles = ['command', 'reqmeta', 'setting', 'signal'] + + +def setup(app): + app.connect('autodoc-skip-member', maybe_skip_member) + + +def maybe_skip_member(app, what, name, obj, skip, options): + if not skip: + # autodocs was generating a text "alias of" for the following members + # https://github.com/sphinx-doc/sphinx/issues/4422 + return name in {'default_item_class', 'default_selector_class'} + return skip diff --git a/docs/contributing.rst b/docs/contributing.rst index aed5ab92e..4d2580a6c 100644 --- a/docs/contributing.rst +++ b/docs/contributing.rst @@ -108,6 +108,11 @@ Well-written patches should: tox -e docs-coverage +* if you are removing deprecated code, first make sure that at least 1 year + (12 months) has passed since the release that introduced the deprecation. + See :ref:`deprecation-policy`. + + .. _submitting-patches: Submitting patches @@ -135,7 +140,7 @@ original pull request author hasn't had time to address them. In this case consider picking up this pull request: open a new pull request with all commits from the original pull request, as well as additional changes to address the raised issues. Doing so helps a lot; it is -not considered rude as soon as the original author is acknowledged by keeping +not considered rude as long as the original author is acknowledged by keeping his/her commits. You can pull an existing pull request to a local branch @@ -155,6 +160,9 @@ Finally, try to keep aesthetic changes (:pep:`8` compliance, unused imports removal, etc) in separate commits from functional changes. This will make pull requests easier to review and more likely to get merged. + +.. _coding-style: + Coding style ============ @@ -163,7 +171,7 @@ Scrapy: * Unless otherwise specified, follow :pep:`8`. -* It's OK to use lines longer than 80 chars if it improves the code +* It's OK to use lines longer than 79 chars if it improves the code readability. * Don't put your name in the code you contribute; git provides enough @@ -191,6 +199,17 @@ In any case, if something is covered in a docstring, use the documentation instead of duplicating the docstring in files within the ``docs/`` directory. +Documentation updates that cover new or modified features must use Sphinx’s +:rst:dir:`versionadded` and :rst:dir:`versionchanged` directives. Use +``VERSION`` as version, we will replace it with the actual version right before +the corresponding release. When we release a new major or minor version of +Scrapy, we remove these directives if they are older than 3 years. + +Documentation about deprecated features must be removed as those features are +deprecated, so that new readers do not run into it. New deprecations and +deprecation removals are documented in the :ref:`release notes `. + + Tests ===== diff --git a/docs/faq.rst b/docs/faq.rst index c06cb945b..16903daea 100644 --- a/docs/faq.rst +++ b/docs/faq.rst @@ -64,20 +64,6 @@ Here's an example spider using BeautifulSoup API, with ``lxml`` as the HTML pars .. _BeautifulSoup's official documentation: https://www.crummy.com/software/BeautifulSoup/bs4/doc/#specifying-the-parser-to-use -.. _faq-python-versions: - -What Python versions does Scrapy support? ------------------------------------------ - -Scrapy is supported under Python 3.5.1+ -under CPython (default Python implementation) and PyPy (starting with PyPy 5.9). -Python 3 support was added in Scrapy 1.1. -PyPy support was added in Scrapy 1.4, PyPy3 support was added in Scrapy 1.5. -Python 2 support was dropped in Scrapy 2.0. - -.. note:: - For Python 3 support on Windows, it is recommended to use - Anaconda/Miniconda as :ref:`outlined in the installation guide `. Did Scrapy "steal" X from Django? --------------------------------- @@ -159,6 +145,41 @@ How can I make Scrapy consume less memory? See previous question. +How can I prevent memory errors due to many allowed domains? +------------------------------------------------------------ + +If you have a spider with a long list of +:attr:`~scrapy.Spider.allowed_domains` (e.g. 50,000+), consider +replacing the default +:class:`~scrapy.spidermiddlewares.offsite.OffsiteMiddleware` spider middleware +with a :ref:`custom spider middleware ` that requires +less memory. For example: + +- If your domain names are similar enough, use your own regular expression + instead joining the strings in + :attr:`~scrapy.Spider.allowed_domains` into a complex regular + expression. + +- If you can `meet the installation requirements`_, use pyre2_ instead of + Python’s re_ to compile your URL-filtering regular expression. See + :issue:`1908`. + +See also other suggestions at `StackOverflow`_. + +.. note:: Remember to disable + :class:`scrapy.spidermiddlewares.offsite.OffsiteMiddleware` when you enable + your custom implementation:: + + SPIDER_MIDDLEWARES = { + 'scrapy.spidermiddlewares.offsite.OffsiteMiddleware': None, + 'myproject.middlewares.CustomOffsiteMiddleware': 500, + } + +.. _meet the installation requirements: https://github.com/andreasvc/pyre2#installation +.. _pyre2: https://github.com/andreasvc/pyre2 +.. _re: https://docs.python.org/library/re.html +.. _StackOverflow: https://stackoverflow.com/q/36440681/939364 + Can I use Basic HTTP Authentication in my spiders? -------------------------------------------------- @@ -250,15 +271,15 @@ Simplest way to dump all my scraped items into a JSON/CSV/XML file? To dump into a JSON file:: - scrapy crawl myspider -o items.json + scrapy crawl myspider -O items.json To dump into a CSV file:: - scrapy crawl myspider -o items.csv + scrapy crawl myspider -O items.csv To dump into a XML file:: - scrapy crawl myspider -o items.xml + scrapy crawl myspider -O items.xml For more information see :ref:`topics-feed-exports` @@ -342,15 +363,15 @@ method for this purpose. For example:: from copy import deepcopy - from scrapy.item import Item - + from itemadapter import is_item, ItemAdapter class MultiplyItemsMiddleware: def process_spider_output(self, response, result, spider): for item in result: - if isinstance(item, (Item, dict)): - for _ in range(item['multiply_by']): + if is_item(item): + adapter = ItemAdapter(item) + for _ in range(adapter['multiply_by']): yield deepcopy(item) Does Scrapy support IPv6 addresses? @@ -377,11 +398,12 @@ How can I cancel the download of a given response? -------------------------------------------------- In some situations, it might be useful to stop the download of a certain response. -For instance, if you only need the first part of a large response and you would like -to save resources by avoiding the download of the whole body. -In that case, you could attach a handler to the :class:`~scrapy.signals.bytes_received` -signal and raise a :exc:`~scrapy.exceptions.StopDownload` exception. Please refer to -the :ref:`topics-stop-response-download` topic for additional information and examples. +For instance, sometimes you can determine whether or not you need the full contents +of a response by inspecting its headers or the first bytes of its body. In that case, +you could save resources by attaching a handler to the :class:`~scrapy.signals.bytes_received` +or :class:`~scrapy.signals.headers_received` signals and raising a +:exc:`~scrapy.exceptions.StopDownload` exception. Please refer to the +:ref:`topics-stop-response-download` topic for additional information and examples. .. _has been reported: https://github.com/scrapy/scrapy/issues/2905 diff --git a/docs/index.rst b/docs/index.rst index 11aa5c9be..433798aa8 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -78,7 +78,6 @@ Basic concepts topics/settings topics/exceptions - :doc:`topics/commands` Learn about the command-line tool used to manage your Scrapy project. @@ -228,6 +227,7 @@ Extending Scrapy topics/extensions topics/api topics/signals + topics/scheduler topics/exporters @@ -249,6 +249,9 @@ Extending Scrapy :doc:`topics/signals` See all available signals and how to work with them. +:doc:`topics/scheduler` + Understand the scheduler component. + :doc:`topics/exporters` Quickly export your scraped items to a file (XML, CSV, etc). diff --git a/docs/intro/install.rst b/docs/intro/install.rst index 4af80d801..8581dde0b 100644 --- a/docs/intro/install.rst +++ b/docs/intro/install.rst @@ -4,12 +4,19 @@ Installation guide ================== +.. _faq-python-versions: + +Supported Python versions +========================= + +Scrapy requires Python 3.6+, either the CPython implementation (default) or +the PyPy 7.2.0+ implementation (see :ref:`python:implementations`). + +.. _intro-install-scrapy: + Installing Scrapy ================= -Scrapy runs on Python 3.5.1 or above under CPython (default Python -implementation) and PyPy (starting with PyPy 5.9). - If you're using `Anaconda`_ or `Miniconda`_, you can install the package from the `conda-forge`_ channel, which has up-to-date packages for Linux, Windows and macOS. @@ -23,13 +30,13 @@ you can install Scrapy and its dependencies from PyPI with:: pip install Scrapy +We strongly recommend that you install Scrapy in :ref:`a dedicated virtualenv `, +to avoid conflicting with your system packages. + Note that sometimes this may require solving compilation issues for some Scrapy dependencies depending on your operating system, so be sure to check the :ref:`intro-install-platform-notes`. -We strongly recommend that you install Scrapy in :ref:`a dedicated virtualenv `, -to avoid conflicting with your system packages. - For more detailed and platform specifics instructions, as well as troubleshooting information, read on. @@ -63,10 +70,9 @@ In case of any trouble related to these dependencies, please refer to their respective installation instructions: * `lxml installation`_ -* `cryptography installation`_ +* :doc:`cryptography installation ` .. _lxml installation: https://lxml.de/installation.html -.. _cryptography installation: https://cryptography.io/en/latest/installation/ .. _intro-using-virtualenv: @@ -112,6 +118,27 @@ Once you've installed `Anaconda`_ or `Miniconda`_, install Scrapy with:: conda install -c conda-forge scrapy +To install Scrapy on Windows using ``pip``: + +.. warning:: + This installation method requires “Microsoft Visual C++” for installing some + Scrapy dependencies, which demands significantly more disk space than Anaconda. + +#. Download and execute `Microsoft C++ Build Tools`_ to install the Visual Studio Installer. + +#. Run the Visual Studio Installer. + +#. Under the Workloads section, select **C++ build tools**. + +#. Check the installation details and make sure following packages are selected as optional components: + + * **MSVC** (e.g MSVC v142 - VS 2019 C++ x64/x86 build tools (v14.23) ) + + * **Windows SDK** (e.g Windows 10 SDK (10.0.18362.0)) + +#. Install the Visual Studio Build Tools. + +Now, you should be able to :ref:`install Scrapy ` using ``pip``. .. _intro-install-ubuntu: @@ -205,8 +232,8 @@ PyPy We recommend using the latest PyPy version. The version tested is 5.9.0. For PyPy3, only Linux installation was tested. -Most Scrapy dependencides now have binary wheels for CPython, but not for PyPy. -This means that these dependecies will be built during installation. +Most Scrapy dependencies now have binary wheels for CPython, but not for PyPy. +This means that these dependencies will be built during installation. On macOS, you are likely to face an issue with building Cryptography dependency, solution to this problem is described `here `_, @@ -259,10 +286,10 @@ For details, see `Issue #2473 `_. .. _cryptography: https://cryptography.io/en/latest/ .. _pyOpenSSL: https://pypi.org/project/pyOpenSSL/ .. _setuptools: https://pypi.python.org/pypi/setuptools -.. _AUR Scrapy package: https://aur.archlinux.org/packages/scrapy/ .. _homebrew: https://brew.sh/ .. _zsh: https://www.zsh.org/ -.. _Scrapinghub: https://scrapinghub.com .. _Anaconda: https://docs.anaconda.com/anaconda/ .. _Miniconda: https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html +.. _Visual Studio: https://docs.microsoft.com/en-us/visualstudio/install/install-visual-studio +.. _Microsoft C++ Build Tools: https://visualstudio.microsoft.com/visual-cpp-build-tools/ .. _conda-forge: https://conda-forge.org/ diff --git a/docs/intro/overview.rst b/docs/intro/overview.rst index 01986b594..dd80c7bd0 100644 --- a/docs/intro/overview.rst +++ b/docs/intro/overview.rst @@ -42,30 +42,18 @@ http://quotes.toscrape.com, following the pagination:: if next_page is not None: yield response.follow(next_page, self.parse) - Put this in a text file, name it to something like ``quotes_spider.py`` and run the spider using the :command:`runspider` command:: - scrapy runspider quotes_spider.py -o quotes.json + scrapy runspider quotes_spider.py -o quotes.jl +When this finishes you will have in the ``quotes.jl`` file a list of the +quotes in JSON Lines format, containing text and author, looking like this:: -When this finishes you will have in the ``quotes.json`` file a list of the -quotes in JSON format, containing text and author, looking like this (reformatted -here for better readability):: - - [{ - "author": "Jane Austen", - "text": "\u201cThe person, be it gentleman or lady, who has not pleasure in a good novel, must be intolerably stupid.\u201d" - }, - { - "author": "Groucho Marx", - "text": "\u201cOutside of a dog, a book is man's best friend. Inside of a dog it's too dark to read.\u201d" - }, - { - "author": "Steve Martin", - "text": "\u201cA day without sunshine is like, you know, night.\u201d" - }, - ...] + {"author": "Jane Austen", "text": "\u201cThe person, be it gentleman or lady, who has not pleasure in a good novel, must be intolerably stupid.\u201d"} + {"author": "Steve Martin", "text": "\u201cA day without sunshine is like, you know, night.\u201d"} + {"author": "Garrison Keillor", "text": "\u201cAnyone who thinks sitting in church can make you a Christian must also think that sitting in a garage can make you a car.\u201d"} + ... What just happened? diff --git a/docs/intro/tutorial.rst b/docs/intro/tutorial.rst index 5f35dc936..438f3d6df 100644 --- a/docs/intro/tutorial.rst +++ b/docs/intro/tutorial.rst @@ -78,7 +78,7 @@ Our first Spider Spiders are classes that you define and that Scrapy uses to scrape information from a website (or a group of websites). They must subclass -:class:`~scrapy.spiders.Spider` and define the initial requests to make, +:class:`~scrapy.Spider` and define the initial requests to make, optionally how to follow links in the pages, and how to parse the downloaded page content to extract data. @@ -101,32 +101,32 @@ This is the code for our first Spider. Save it in a file named def parse(self, response): page = response.url.split("/")[-2] - filename = 'quotes-%s.html' % page + filename = f'quotes-{page}.html' with open(filename, 'wb') as f: f.write(response.body) - self.log('Saved file %s' % filename) + self.log(f'Saved file {filename}') -As you can see, our Spider subclasses :class:`scrapy.Spider ` +As you can see, our Spider subclasses :class:`scrapy.Spider ` and defines some attributes and methods: -* :attr:`~scrapy.spiders.Spider.name`: identifies the Spider. It must be +* :attr:`~scrapy.Spider.name`: identifies the Spider. It must be unique within a project, that is, you can't set the same name for different Spiders. -* :meth:`~scrapy.spiders.Spider.start_requests`: must return an iterable of +* :meth:`~scrapy.Spider.start_requests`: must return an iterable of Requests (you can return a list of requests or write a generator function) which the Spider will begin to crawl from. Subsequent requests will be generated successively from these initial requests. -* :meth:`~scrapy.spiders.Spider.parse`: a method that will be called to handle +* :meth:`~scrapy.Spider.parse`: a method that will be called to handle the response downloaded for each of the requests made. The response parameter is an instance of :class:`~scrapy.http.TextResponse` that holds the page content and has further helpful methods to handle it. - The :meth:`~scrapy.spiders.Spider.parse` method usually parses the response, extracting + The :meth:`~scrapy.Spider.parse` method usually parses the response, extracting the scraped data as dicts and also finding new URLs to - follow and creating new requests (:class:`~scrapy.http.Request`) from them. + follow and creating new requests (:class:`~scrapy.Request`) from them. How to run our spider --------------------- @@ -162,7 +162,7 @@ for the respective URLs, as our ``parse`` method instructs. What just happened under the hood? ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -Scrapy schedules the :class:`scrapy.Request ` objects +Scrapy schedules the :class:`scrapy.Request ` objects returned by the ``start_requests`` method of the Spider. Upon receiving a response for each one, it instantiates :class:`~scrapy.http.Response` objects and calls the callback method associated with the request (in this case, the @@ -171,11 +171,11 @@ and calls the callback method associated with the request (in this case, the A shortcut to the start_requests method --------------------------------------- -Instead of implementing a :meth:`~scrapy.spiders.Spider.start_requests` method -that generates :class:`scrapy.Request ` objects from URLs, -you can just define a :attr:`~scrapy.spiders.Spider.start_urls` class attribute +Instead of implementing a :meth:`~scrapy.Spider.start_requests` method +that generates :class:`scrapy.Request ` objects from URLs, +you can just define a :attr:`~scrapy.Spider.start_urls` class attribute with a list of URLs. This list will then be used by the default implementation -of :meth:`~scrapy.spiders.Spider.start_requests` to create the initial requests +of :meth:`~scrapy.Spider.start_requests` to create the initial requests for your spider:: import scrapy @@ -190,13 +190,13 @@ for your spider:: def parse(self, response): page = response.url.split("/")[-2] - filename = 'quotes-%s.html' % page + filename = f'quotes-{page}.html' with open(filename, 'wb') as f: f.write(response.body) -The :meth:`~scrapy.spiders.Spider.parse` method will be called to handle each +The :meth:`~scrapy.Spider.parse` method will be called to handle each of the requests for those URLs, even though we haven't explicitly told Scrapy -to do so. This happens because :meth:`~scrapy.spiders.Spider.parse` is Scrapy's +to do so. This happens because :meth:`~scrapy.Spider.parse` is Scrapy's default callback method, which is called for requests without an explicitly assigned callback. @@ -248,7 +248,7 @@ object: The result of running ``response.css('title')`` is a list-like object called :class:`~scrapy.selector.SelectorList`, which represents a list of -:class:`~scrapy.selector.Selector` objects that wrap around XML/HTML elements +:class:`~scrapy.Selector` objects that wrap around XML/HTML elements and allow you to run further queries to fine-grain the selection or extract the data. @@ -405,8 +405,6 @@ to get all of them: from sys import version_info -.. skip: next if(version_info < (3, 6), reason="Only Python 3.6+ dictionaries match the output") - Having figured out how to extract each bit, we can now iterate over all the quotes elements and put them together into a Python dictionary: @@ -464,16 +462,15 @@ Storing the scraped data The simplest way to store the scraped data is by using :ref:`Feed exports `, with the following command:: - scrapy crawl quotes -o quotes.json + scrapy crawl quotes -O quotes.json -That will generate an ``quotes.json`` file containing all scraped items, +That will generate a ``quotes.json`` file containing all scraped items, serialized in `JSON`_. -For historic reasons, Scrapy appends to a given file instead of overwriting -its contents. If you run this command twice without removing the file -before the second time, you'll end up with a broken JSON file. - -You can also use other formats, like `JSON Lines`_:: +The ``-O`` command-line switch overwrites any existing file; use ``-o`` instead +to append new content to any existing file. However, appending to a JSON file +makes the file contents invalid JSON. When appending to a file, consider +using a different serialization format, such as `JSON Lines`_:: scrapy crawl quotes -o quotes.jl @@ -673,7 +670,7 @@ the pagination links with the ``parse`` callback as we saw before. Here we're passing callbacks to :meth:`response.follow_all ` as positional arguments to make the code shorter; it also works for -:class:`~scrapy.http.Request`. +:class:`~scrapy.Request`. The ``parse_author`` callback defines a helper function to extract and cleanup the data from a CSS query and yields the Python dict with the author data. @@ -704,7 +701,7 @@ Using spider arguments You can provide command line arguments to your spiders by using the ``-a`` option when running them:: - scrapy crawl quotes -o quotes-humor.json -a tag=humor + scrapy crawl quotes -O quotes-humor.json -a tag=humor These arguments are passed to the Spider's ``__init__`` method and become spider attributes by default. diff --git a/docs/news.rst b/docs/news.rst index a158246eb..0ea412e75 100644 --- a/docs/news.rst +++ b/docs/news.rst @@ -3,6 +3,847 @@ Release notes ============= +.. _release-2.5.0: + +Scrapy 2.5.0 (2021-04-06) +------------------------- + +Highlights: + +- Official Python 3.9 support + +- Experimental :ref:`HTTP/2 support ` + +- New :func:`~scrapy.downloadermiddlewares.retry.get_retry_request` function + to retry requests from spider callbacks + +- New :class:`~scrapy.signals.headers_received` signal that allows stopping + downloads early + +- New :class:`Response.protocol ` attribute + +Deprecation removals +~~~~~~~~~~~~~~~~~~~~ + +- Removed all code that :ref:`was deprecated in 1.7.0 <1.7-deprecations>` and + had not :ref:`already been removed in 2.4.0 <2.4-deprecation-removals>`. + (:issue:`4901`) + +- Removed support for the ``SCRAPY_PICKLED_SETTINGS_TO_OVERRIDE`` environment + variable, :ref:`deprecated in 1.8.0 <1.8-deprecations>`. (:issue:`4912`) + + +Deprecations +~~~~~~~~~~~~ + +- The :mod:`scrapy.utils.py36` module is now deprecated in favor of + :mod:`scrapy.utils.asyncgen`. (:issue:`4900`) + + +New features +~~~~~~~~~~~~ + +- Experimental :ref:`HTTP/2 support ` through a new download handler + that can be assigned to the ``https`` protocol in the + :setting:`DOWNLOAD_HANDLERS` setting. + (:issue:`1854`, :issue:`4769`, :issue:`5058`, :issue:`5059`, :issue:`5066`) + +- The new :func:`scrapy.downloadermiddlewares.retry.get_retry_request` + function may be used from spider callbacks or middlewares to handle the + retrying of a request beyond the scenarios that + :class:`~scrapy.downloadermiddlewares.retry.RetryMiddleware` supports. + (:issue:`3590`, :issue:`3685`, :issue:`4902`) + +- The new :class:`~scrapy.signals.headers_received` signal gives early access + to response headers and allows :ref:`stopping downloads + `. + (:issue:`1772`, :issue:`4897`) + +- The new :attr:`Response.protocol ` + attribute gives access to the string that identifies the protocol used to + download a response. (:issue:`4878`) + +- :ref:`Stats ` now include the following entries that indicate + the number of successes and failures in storing + :ref:`feeds `:: + + feedexport/success_count/ + feedexport/failed_count/ + + Where ```` is the feed storage backend class name, such as + :class:`~scrapy.extensions.feedexport.FileFeedStorage` or + :class:`~scrapy.extensions.feedexport.FTPFeedStorage`. + + (:issue:`3947`, :issue:`4850`) + +- The :class:`~scrapy.spidermiddlewares.urllength.UrlLengthMiddleware` spider + middleware now logs ignored URLs with ``INFO`` :ref:`logging level + ` instead of ``DEBUG``, and it now includes the following entry + into :ref:`stats ` to keep track of the number of ignored + URLs:: + + urllength/request_ignored_count + + (:issue:`5036`) + +- The + :class:`~scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware` + downloader middleware now logs the number of decompressed responses and the + total count of resulting bytes:: + + httpcompression/response_bytes + httpcompression/response_count + + (:issue:`4797`, :issue:`4799`) + + +Bug fixes +~~~~~~~~~ + +- Fixed installation on PyPy installing PyDispatcher in addition to + PyPyDispatcher, which could prevent Scrapy from working depending on which + package got imported. (:issue:`4710`, :issue:`4814`) + +- When inspecting a callback to check if it is a generator that also returns + a value, an exception is no longer raised if the callback has a docstring + with lower indentation than the following code. + (:issue:`4477`, :issue:`4935`) + +- The `Content-Length `_ + header is no longer omitted from responses when using the default, HTTP/1.1 + download handler (see :setting:`DOWNLOAD_HANDLERS`). + (:issue:`5009`, :issue:`5034`, :issue:`5045`, :issue:`5057`, :issue:`5062`) + +- Setting the :reqmeta:`handle_httpstatus_all` request meta key to ``False`` + now has the same effect as not setting it at all, instead of having the + same effect as setting it to ``True``. + (:issue:`3851`, :issue:`4694`) + + +Documentation +~~~~~~~~~~~~~ + +- Added instructions to :ref:`install Scrapy in Windows using pip + `. + (:issue:`4715`, :issue:`4736`) + +- Logging documentation now includes :ref:`additional ways to filter logs + `. + (:issue:`4216`, :issue:`4257`, :issue:`4965`) + +- Covered how to deal with long lists of allowed domains in the :ref:`FAQ + `. (:issue:`2263`, :issue:`3667`) + +- Covered scrapy-bench_ in :ref:`benchmarking`. + (:issue:`4996`, :issue:`5016`) + +- Clarified that one :ref:`extension ` instance is created + per crawler. + (:issue:`5014`) + +- Fixed some errors in examples. + (:issue:`4829`, :issue:`4830`, :issue:`4907`, :issue:`4909`, + :issue:`5008`) + +- Fixed some external links, typos, and so on. + (:issue:`4892`, :issue:`4899`, :issue:`4936`, :issue:`4942`, :issue:`5005`, + :issue:`5063`) + +- The :ref:`list of Request.meta keys ` is now sorted + alphabetically. + (:issue:`5061`, :issue:`5065`) + +- Updated references to Scrapinghub, which is now called Zyte. + (:issue:`4973`, :issue:`5072`) + +- Added a mention to contributors in the README. (:issue:`4956`) + +- Reduced the top margin of lists. (:issue:`4974`) + + +Quality Assurance +~~~~~~~~~~~~~~~~~ + +- Made Python 3.9 support official (:issue:`4757`, :issue:`4759`) + +- Extended typing hints (:issue:`4895`) + +- Fixed deprecated uses of the Twisted API. + (:issue:`4940`, :issue:`4950`, :issue:`5073`) + +- Made our tests run with the new pip resolver. + (:issue:`4710`, :issue:`4814`) + +- Added tests to ensure that :ref:`coroutine support ` + is tested. (:issue:`4987`) + +- Migrated from Travis CI to GitHub Actions. (:issue:`4924`) + +- Fixed CI issues. + (:issue:`4986`, :issue:`5020`, :issue:`5022`, :issue:`5027`, :issue:`5052`, + :issue:`5053`) + +- Implemented code refactorings, style fixes and cleanups. + (:issue:`4911`, :issue:`4982`, :issue:`5001`, :issue:`5002`, :issue:`5076`) + + +.. _release-2.4.1: + +Scrapy 2.4.1 (2020-11-17) +------------------------- + +- Fixed :ref:`feed exports ` overwrite support (:issue:`4845`, :issue:`4857`, :issue:`4859`) + +- Fixed the AsyncIO event loop handling, which could make code hang + (:issue:`4855`, :issue:`4872`) + +- Fixed the IPv6-capable DNS resolver + :class:`~scrapy.resolver.CachingHostnameResolver` for download handlers + that call + :meth:`reactor.resolve ` + (:issue:`4802`, :issue:`4803`) + +- Fixed the output of the :command:`genspider` command showing placeholders + instead of the import path of the generated spider module (:issue:`4874`) + +- Migrated Windows CI from Azure Pipelines to GitHub Actions (:issue:`4869`, + :issue:`4876`) + + +.. _release-2.4.0: + +Scrapy 2.4.0 (2020-10-11) +------------------------- + +Highlights: + +* Python 3.5 support has been dropped. + +* The ``file_path`` method of :ref:`media pipelines ` + can now access the source :ref:`item `. + + This allows you to set a download file path based on item data. + +* The new ``item_export_kwargs`` key of the :setting:`FEEDS` setting allows + to define keyword parameters to pass to :ref:`item exporter classes + ` + +* You can now choose whether :ref:`feed exports ` + overwrite or append to the output file. + + For example, when using the :command:`crawl` or :command:`runspider` + commands, you can use the ``-O`` option instead of ``-o`` to overwrite the + output file. + +* Zstd-compressed responses are now supported if zstandard_ is installed. + +* In settings, where the import path of a class is required, it is now + possible to pass a class object instead. + +Modified requirements +~~~~~~~~~~~~~~~~~~~~~ + +* Python 3.6 or greater is now required; support for Python 3.5 has been + dropped + + As a result: + + - When using PyPy, PyPy 7.2.0 or greater :ref:`is now required + ` + + - For Amazon S3 storage support in :ref:`feed exports + ` or :ref:`media pipelines + `, botocore_ 1.4.87 or greater is now required + + - To use the :ref:`images pipeline `, Pillow_ 4.0.0 or + greater is now required + + (:issue:`4718`, :issue:`4732`, :issue:`4733`, :issue:`4742`, :issue:`4743`, + :issue:`4764`) + + +Backward-incompatible changes +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +* :class:`~scrapy.downloadermiddlewares.cookies.CookiesMiddleware` once again + discards cookies defined in :attr:`Request.headers + `. + + We decided to revert this bug fix, introduced in Scrapy 2.2.0, because it + was reported that the current implementation could break existing code. + + If you need to set cookies for a request, use the :class:`Request.cookies + ` parameter. + + A future version of Scrapy will include a new, better implementation of the + reverted bug fix. + + (:issue:`4717`, :issue:`4823`) + + +.. _2.4-deprecation-removals: + +Deprecation removals +~~~~~~~~~~~~~~~~~~~~ + +* :class:`scrapy.extensions.feedexport.S3FeedStorage` no longer reads the + values of ``access_key`` and ``secret_key`` from the running project + settings when they are not passed to its ``__init__`` method; you must + either pass those parameters to its ``__init__`` method or use + :class:`S3FeedStorage.from_crawler + ` + (:issue:`4356`, :issue:`4411`, :issue:`4688`) + +* :attr:`Rule.process_request ` + no longer admits callables which expect a single ``request`` parameter, + rather than both ``request`` and ``response`` (:issue:`4818`) + + +Deprecations +~~~~~~~~~~~~ + +* In custom :ref:`media pipelines `, signatures that + do not accept a keyword-only ``item`` parameter in any of the methods that + :ref:`now support this parameter ` are now + deprecated (:issue:`4628`, :issue:`4686`) + +* In custom :ref:`feed storage backend classes `, + ``__init__`` method signatures that do not accept a keyword-only + ``feed_options`` parameter are now deprecated (:issue:`547`, :issue:`716`, + :issue:`4512`) + +* The :class:`scrapy.utils.python.WeakKeyCache` class is now deprecated + (:issue:`4684`, :issue:`4701`) + +* The :func:`scrapy.utils.boto.is_botocore` function is now deprecated, use + :func:`scrapy.utils.boto.is_botocore_available` instead (:issue:`4734`, + :issue:`4776`) + + +New features +~~~~~~~~~~~~ + +.. _media-pipeline-item-parameter: + +* The following methods of :ref:`media pipelines ` now + accept an ``item`` keyword-only parameter containing the source + :ref:`item `: + + - In :class:`scrapy.pipelines.files.FilesPipeline`: + + - :meth:`~scrapy.pipelines.files.FilesPipeline.file_downloaded` + + - :meth:`~scrapy.pipelines.files.FilesPipeline.file_path` + + - :meth:`~scrapy.pipelines.files.FilesPipeline.media_downloaded` + + - :meth:`~scrapy.pipelines.files.FilesPipeline.media_to_download` + + - In :class:`scrapy.pipelines.images.ImagesPipeline`: + + - :meth:`~scrapy.pipelines.images.ImagesPipeline.file_downloaded` + + - :meth:`~scrapy.pipelines.images.ImagesPipeline.file_path` + + - :meth:`~scrapy.pipelines.images.ImagesPipeline.get_images` + + - :meth:`~scrapy.pipelines.images.ImagesPipeline.image_downloaded` + + - :meth:`~scrapy.pipelines.images.ImagesPipeline.media_downloaded` + + - :meth:`~scrapy.pipelines.images.ImagesPipeline.media_to_download` + + (:issue:`4628`, :issue:`4686`) + +* The new ``item_export_kwargs`` key of the :setting:`FEEDS` setting allows + to define keyword parameters to pass to :ref:`item exporter classes + ` (:issue:`4606`, :issue:`4768`) + +* :ref:`Feed exports ` gained overwrite support: + + * When using the :command:`crawl` or :command:`runspider` commands, you + can use the ``-O`` option instead of ``-o`` to overwrite the output + file + + * You can use the ``overwrite`` key in the :setting:`FEEDS` setting to + configure whether to overwrite the output file (``True``) or append to + its content (``False``) + + * The ``__init__`` and ``from_crawler`` methods of :ref:`feed storage + backend classes ` now receive a new keyword-only + parameter, ``feed_options``, which is a dictionary of :ref:`feed + options ` + + (:issue:`547`, :issue:`716`, :issue:`4512`) + +* Zstd-compressed responses are now supported if zstandard_ is installed + (:issue:`4831`) + +* In settings, where the import path of a class is required, it is now + possible to pass a class object instead (:issue:`3870`, :issue:`3873`). + + This includes also settings where only part of its value is made of an + import path, such as :setting:`DOWNLOADER_MIDDLEWARES` or + :setting:`DOWNLOAD_HANDLERS`. + +* :ref:`Downloader middlewares ` can now + override :class:`response.request `. + + If a :ref:`downloader middleware ` returns + a :class:`~scrapy.http.Response` object from + :meth:`~scrapy.downloadermiddlewares.DownloaderMiddleware.process_response` + or + :meth:`~scrapy.downloadermiddlewares.DownloaderMiddleware.process_exception` + with a custom :class:`~scrapy.http.Request` object assigned to + :class:`response.request `: + + - The response is handled by the callback of that custom + :class:`~scrapy.http.Request` object, instead of being handled by the + callback of the original :class:`~scrapy.http.Request` object + + - That custom :class:`~scrapy.http.Request` object is now sent as the + ``request`` argument to the :signal:`response_received` signal, instead + of the original :class:`~scrapy.http.Request` object + + (:issue:`4529`, :issue:`4632`) + +* When using the :ref:`FTP feed storage backend `: + + - It is now possible to set the new ``overwrite`` :ref:`feed option + ` to ``False`` to append to an existing file instead of + overwriting it + + - The FTP password can now be omitted if it is not necessary + + (:issue:`547`, :issue:`716`, :issue:`4512`) + +* The ``__init__`` method of :class:`~scrapy.exporters.CsvItemExporter` now + supports an ``errors`` parameter to indicate how to handle encoding errors + (:issue:`4755`) + +* When :ref:`using asyncio `, it is now possible to + :ref:`set a custom asyncio loop ` (:issue:`4306`, + :issue:`4414`) + +* Serialized requests (see :ref:`topics-jobs`) now support callbacks that are + spider methods that delegate on other callable (:issue:`4756`) + +* When a response is larger than :setting:`DOWNLOAD_MAXSIZE`, the logged + message is now a warning, instead of an error (:issue:`3874`, + :issue:`3886`, :issue:`4752`) + + +Bug fixes +~~~~~~~~~ + +* The :command:`genspider` command no longer overwrites existing files + unless the ``--force`` option is used (:issue:`4561`, :issue:`4616`, + :issue:`4623`) + +* Cookies with an empty value are no longer considered invalid cookies + (:issue:`4772`) + +* The :command:`runspider` command now supports files with the ``.pyw`` file + extension (:issue:`4643`, :issue:`4646`) + +* The :class:`~scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware` + middleware now simply ignores unsupported proxy values (:issue:`3331`, + :issue:`4778`) + +* Checks for generator callbacks with a ``return`` statement no longer warn + about ``return`` statements in nested functions (:issue:`4720`, + :issue:`4721`) + +* The system file mode creation mask no longer affects the permissions of + files generated using the :command:`startproject` command (:issue:`4722`) + +* :func:`scrapy.utils.iterators.xmliter` now supports namespaced node names + (:issue:`861`, :issue:`4746`) + +* :class:`~scrapy.Request` objects can now have ``about:`` URLs, which can + work when using a headless browser (:issue:`4835`) + + +Documentation +~~~~~~~~~~~~~ + +* The :setting:`FEED_URI_PARAMS` setting is now documented (:issue:`4671`, + :issue:`4724`) + +* Improved the documentation of + :ref:`link extractors ` with an usage example from + a spider callback and reference documentation for the + :class:`~scrapy.link.Link` class (:issue:`4751`, :issue:`4775`) + +* Clarified the impact of :setting:`CONCURRENT_REQUESTS` when using the + :class:`~scrapy.extensions.closespider.CloseSpider` extension + (:issue:`4836`) + +* Removed references to Python 2’s ``unicode`` type (:issue:`4547`, + :issue:`4703`) + +* We now have an :ref:`official deprecation policy ` + (:issue:`4705`) + +* Our :ref:`documentation policies ` now cover usage + of Sphinx’s :rst:dir:`versionadded` and :rst:dir:`versionchanged` + directives, and we have removed usages referencing Scrapy 1.4.0 and earlier + versions (:issue:`3971`, :issue:`4310`) + +* Other documentation cleanups (:issue:`4090`, :issue:`4782`, :issue:`4800`, + :issue:`4801`, :issue:`4809`, :issue:`4816`, :issue:`4825`) + + +Quality assurance +~~~~~~~~~~~~~~~~~ + +* Extended typing hints (:issue:`4243`, :issue:`4691`) + +* Added tests for the :command:`check` command (:issue:`4663`) + +* Fixed test failures on Debian (:issue:`4726`, :issue:`4727`, :issue:`4735`) + +* Improved Windows test coverage (:issue:`4723`) + +* Switched to :ref:`formatted string literals ` where possible + (:issue:`4307`, :issue:`4324`, :issue:`4672`) + +* Modernized :func:`super` usage (:issue:`4707`) + +* Other code and test cleanups (:issue:`1790`, :issue:`3288`, :issue:`4165`, + :issue:`4564`, :issue:`4651`, :issue:`4714`, :issue:`4738`, :issue:`4745`, + :issue:`4747`, :issue:`4761`, :issue:`4765`, :issue:`4804`, :issue:`4817`, + :issue:`4820`, :issue:`4822`, :issue:`4839`) + + +.. _release-2.3.0: + +Scrapy 2.3.0 (2020-08-04) +------------------------- + +Highlights: + +* :ref:`Feed exports ` now support :ref:`Google Cloud + Storage ` as a storage backend + +* The new :setting:`FEED_EXPORT_BATCH_ITEM_COUNT` setting allows to deliver + output items in batches of up to the specified number of items. + + It also serves as a workaround for :ref:`delayed file delivery + `, which causes Scrapy to only start item delivery + after the crawl has finished when using certain storage backends + (:ref:`S3 `, :ref:`FTP `, + and now :ref:`GCS `). + +* The base implementation of :ref:`item loaders ` has been + moved into a separate library, :doc:`itemloaders `, + allowing usage from outside Scrapy and a separate release schedule + +Deprecation removals +~~~~~~~~~~~~~~~~~~~~ + +* Removed the following classes and their parent modules from + ``scrapy.linkextractors``: + + * ``htmlparser.HtmlParserLinkExtractor`` + * ``regex.RegexLinkExtractor`` + * ``sgml.BaseSgmlLinkExtractor`` + * ``sgml.SgmlLinkExtractor`` + + Use + :class:`LinkExtractor ` + instead (:issue:`4356`, :issue:`4679`) + + +Deprecations +~~~~~~~~~~~~ + +* The ``scrapy.utils.python.retry_on_eintr`` function is now deprecated + (:issue:`4683`) + + +New features +~~~~~~~~~~~~ + +* :ref:`Feed exports ` support :ref:`Google Cloud + Storage ` (:issue:`685`, :issue:`3608`) + +* New :setting:`FEED_EXPORT_BATCH_ITEM_COUNT` setting for batch deliveries + (:issue:`4250`, :issue:`4434`) + +* The :command:`parse` command now allows specifying an output file + (:issue:`4317`, :issue:`4377`) + +* :meth:`Request.from_curl ` and + :func:`~scrapy.utils.curl.curl_to_request_kwargs` now also support + ``--data-raw`` (:issue:`4612`) + +* A ``parse`` callback may now be used in built-in spider subclasses, such + as :class:`~scrapy.spiders.CrawlSpider` (:issue:`712`, :issue:`732`, + :issue:`781`, :issue:`4254` ) + + +Bug fixes +~~~~~~~~~ + +* Fixed the :ref:`CSV exporting ` of + :ref:`dataclass items ` and :ref:`attr.s items + ` (:issue:`4667`, :issue:`4668`) + +* :meth:`Request.from_curl ` and + :func:`~scrapy.utils.curl.curl_to_request_kwargs` now set the request + method to ``POST`` when a request body is specified and no request method + is specified (:issue:`4612`) + +* The processing of ANSI escape sequences in enabled in Windows 10.0.14393 + and later, where it is required for colored output (:issue:`4393`, + :issue:`4403`) + + +Documentation +~~~~~~~~~~~~~ + +* Updated the `OpenSSL cipher list format`_ link in the documentation about + the :setting:`DOWNLOADER_CLIENT_TLS_CIPHERS` setting (:issue:`4653`) + +* Simplified the code example in :ref:`topics-loaders-dataclass` + (:issue:`4652`) + +.. _OpenSSL cipher list format: https://www.openssl.org/docs/manmaster/man1/openssl-ciphers.html#CIPHER-LIST-FORMAT + + +Quality assurance +~~~~~~~~~~~~~~~~~ + +* The base implementation of :ref:`item loaders ` has been + moved into :doc:`itemloaders ` (:issue:`4005`, + :issue:`4516`) + +* Fixed a silenced error in some scheduler tests (:issue:`4644`, + :issue:`4645`) + +* Renewed the localhost certificate used for SSL tests (:issue:`4650`) + +* Removed cookie-handling code specific to Python 2 (:issue:`4682`) + +* Stopped using Python 2 unicode literal syntax (:issue:`4704`) + +* Stopped using a backlash for line continuation (:issue:`4673`) + +* Removed unneeded entries from the MyPy exception list (:issue:`4690`) + +* Automated tests now pass on Windows as part of our continuous integration + system (:issue:`4458`) + +* Automated tests now pass on the latest PyPy version for supported Python + versions in our continuous integration system (:issue:`4504`) + + +.. _release-2.2.1: + +Scrapy 2.2.1 (2020-07-17) +------------------------- + +* The :command:`startproject` command no longer makes unintended changes to + the permissions of files in the destination folder, such as removing + execution permissions (:issue:`4662`, :issue:`4666`) + + +.. _release-2.2.0: + +Scrapy 2.2.0 (2020-06-24) +------------------------- + +Highlights: + +* Python 3.5.2+ is required now +* :ref:`dataclass objects ` and + :ref:`attrs objects ` are now valid :ref:`item types + ` +* New :meth:`TextResponse.json ` method +* New :signal:`bytes_received` signal that allows canceling response download +* :class:`~scrapy.downloadermiddlewares.cookies.CookiesMiddleware` fixes + +Backward-incompatible changes +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +* Support for Python 3.5.0 and 3.5.1 has been dropped; Scrapy now refuses to + run with a Python version lower than 3.5.2, which introduced + :class:`typing.Type` (:issue:`4615`) + + +Deprecations +~~~~~~~~~~~~ + +* :meth:`TextResponse.body_as_unicode + ` is now deprecated, use + :attr:`TextResponse.text ` instead + (:issue:`4546`, :issue:`4555`, :issue:`4579`) + +* :class:`scrapy.item.BaseItem` is now deprecated, use + :class:`scrapy.item.Item` instead (:issue:`4534`) + + +New features +~~~~~~~~~~~~ + +* :ref:`dataclass objects ` and + :ref:`attrs objects ` are now valid :ref:`item types + `, and a new itemadapter_ library makes it easy to + write code that :ref:`supports any item type ` + (:issue:`2749`, :issue:`2807`, :issue:`3761`, :issue:`3881`, :issue:`4642`) + +* A new :meth:`TextResponse.json ` method + allows to deserialize JSON responses (:issue:`2444`, :issue:`4460`, + :issue:`4574`) + +* A new :signal:`bytes_received` signal allows monitoring response download + progress and :ref:`stopping downloads ` + (:issue:`4205`, :issue:`4559`) + +* The dictionaries in the result list of a :ref:`media pipeline + ` now include a new key, ``status``, which indicates + if the file was downloaded or, if the file was not downloaded, why it was + not downloaded; see :meth:`FilesPipeline.get_media_requests + ` for more + information (:issue:`2893`, :issue:`4486`) + +* When using :ref:`Google Cloud Storage ` for + a :ref:`media pipeline `, a warning is now logged if + the configured credentials do not grant the required permissions + (:issue:`4346`, :issue:`4508`) + +* :ref:`Link extractors ` are now serializable, + as long as you do not use :ref:`lambdas ` for parameters; for + example, you can now pass link extractors in :attr:`Request.cb_kwargs + ` or + :attr:`Request.meta ` when :ref:`persisting + scheduled requests ` (:issue:`4554`) + +* Upgraded the :ref:`pickle protocol ` that Scrapy uses + from protocol 2 to protocol 4, improving serialization capabilities and + performance (:issue:`4135`, :issue:`4541`) + +* :func:`scrapy.utils.misc.create_instance` now raises a :exc:`TypeError` + exception if the resulting instance is ``None`` (:issue:`4528`, + :issue:`4532`) + +.. _itemadapter: https://github.com/scrapy/itemadapter + + +Bug fixes +~~~~~~~~~ + +* :class:`~scrapy.downloadermiddlewares.cookies.CookiesMiddleware` no longer + discards cookies defined in :attr:`Request.headers + ` (:issue:`1992`, :issue:`2400`) + +* :class:`~scrapy.downloadermiddlewares.cookies.CookiesMiddleware` no longer + re-encodes cookies defined as :class:`bytes` in the ``cookies`` parameter + of the ``__init__`` method of :class:`~scrapy.http.Request` + (:issue:`2400`, :issue:`3575`) + +* When :setting:`FEEDS` defines multiple URIs, :setting:`FEED_STORE_EMPTY` is + ``False`` and the crawl yields no items, Scrapy no longer stops feed + exports after the first URI (:issue:`4621`, :issue:`4626`) + +* :class:`~scrapy.spiders.Spider` callbacks defined using :doc:`coroutine + syntax ` no longer need to return an iterable, and may + instead return a :class:`~scrapy.http.Request` object, an + :ref:`item `, or ``None`` (:issue:`4609`) + +* The :command:`startproject` command now ensures that the generated project + folders and files have the right permissions (:issue:`4604`) + +* Fix a :exc:`KeyError` exception being sometimes raised from + :class:`scrapy.utils.datatypes.LocalWeakReferencedCache` (:issue:`4597`, + :issue:`4599`) + +* When :setting:`FEEDS` defines multiple URIs, log messages about items being + stored now contain information from the corresponding feed, instead of + always containing information about only one of the feeds (:issue:`4619`, + :issue:`4629`) + + +Documentation +~~~~~~~~~~~~~ + +* Added a new section about :ref:`accessing cb_kwargs from errbacks + ` (:issue:`4598`, :issue:`4634`) + +* Covered chompjs_ in :ref:`topics-parsing-javascript` (:issue:`4556`, + :issue:`4562`) + +* Removed from :doc:`topics/coroutines` the warning about the API being + experimental (:issue:`4511`, :issue:`4513`) + +* Removed references to unsupported versions of :doc:`Twisted + ` (:issue:`4533`) + +* Updated the description of the :ref:`screenshot pipeline example + `, which now uses :doc:`coroutine syntax + ` instead of returning a + :class:`~twisted.internet.defer.Deferred` (:issue:`4514`, :issue:`4593`) + +* Removed a misleading import line from the + :func:`scrapy.utils.log.configure_logging` code example (:issue:`4510`, + :issue:`4587`) + +* The display-on-hover behavior of internal documentation references now also + covers links to :ref:`commands `, :attr:`Request.meta + ` keys, :ref:`settings ` and + :ref:`signals ` (:issue:`4495`, :issue:`4563`) + +* It is again possible to download the documentation for offline reading + (:issue:`4578`, :issue:`4585`) + +* Removed backslashes preceding ``*args`` and ``**kwargs`` in some function + and method signatures (:issue:`4592`, :issue:`4596`) + +.. _chompjs: https://github.com/Nykakin/chompjs + + +Quality assurance +~~~~~~~~~~~~~~~~~ + +* Adjusted the code base further to our :ref:`style guidelines + ` (:issue:`4237`, :issue:`4525`, :issue:`4538`, + :issue:`4539`, :issue:`4540`, :issue:`4542`, :issue:`4543`, :issue:`4544`, + :issue:`4545`, :issue:`4557`, :issue:`4558`, :issue:`4566`, :issue:`4568`, + :issue:`4572`) + +* Removed remnants of Python 2 support (:issue:`4550`, :issue:`4553`, + :issue:`4568`) + +* Improved code sharing between the :command:`crawl` and :command:`runspider` + commands (:issue:`4548`, :issue:`4552`) + +* Replaced ``chain(*iterable)`` with ``chain.from_iterable(iterable)`` + (:issue:`4635`) + +* You may now run the :mod:`asyncio` tests with Tox on any Python version + (:issue:`4521`) + +* Updated test requirements to reflect an incompatibility with pytest 5.4 and + 5.4.1 (:issue:`4588`) + +* Improved :class:`~scrapy.spiderloader.SpiderLoader` test coverage for + scenarios involving duplicate spider names (:issue:`4549`, :issue:`4560`) + +* Configured Travis CI to also run the tests with Python 3.5.2 + (:issue:`4518`, :issue:`4615`) + +* Added a `Pylint `_ job to Travis CI + (:issue:`3727`) + +* Added a `Mypy `_ job to Travis CI (:issue:`4637`) + +* Made use of set literals in tests (:issue:`4573`) + +* Cleaned up the Travis CI configuration (:issue:`4517`, :issue:`4519`, + :issue:`4522`, :issue:`4537`) + + .. _release-2.1.0: Scrapy 2.1.0 (2020-04-24) @@ -778,6 +1619,8 @@ Deprecation removals * ``scrapy.xlib`` has been removed (:issue:`4015`) +.. _1.8-deprecations: + Deprecations ~~~~~~~~~~~~ @@ -1134,6 +1977,8 @@ The following deprecated settings have also been removed (:issue:`3578`): * ``SPIDER_MANAGER_CLASS`` (use :setting:`SPIDER_LOADER_CLASS`) +.. _1.7-deprecations: + Deprecations ~~~~~~~~~~~~ @@ -1773,7 +2618,7 @@ Bug fixes - Fix compatibility with Twisted 17+ (:issue:`2496`, :issue:`2528`). - Fix ``scrapy.Item`` inheritance on Python 3.6 (:issue:`2511`). - Enforce numeric values for components order in ``SPIDER_MIDDLEWARES``, - ``DOWNLOADER_MIDDLEWARES``, ``EXTENIONS`` and ``SPIDER_CONTRACTS`` (:issue:`2420`). + ``DOWNLOADER_MIDDLEWARES``, ``EXTENSIONS`` and ``SPIDER_CONTRACTS`` (:issue:`2420`). Documentation ~~~~~~~~~~~~~ @@ -3529,7 +4374,7 @@ API changes - ``url`` and ``body`` attributes of Request objects are now read-only (#230) - ``Request.copy()`` and ``Request.replace()`` now also copies their ``callback`` and ``errback`` attributes (#231) - Removed ``UrlFilterMiddleware`` from ``scrapy.contrib`` (already disabled by default) -- Offsite middelware doesn't filter out any request coming from a spider that doesn't have a allowed_domains attribute (#225) +- Offsite middleware doesn't filter out any request coming from a spider that doesn't have a allowed_domains attribute (#225) - Removed Spider Manager ``load()`` method. Now spiders are loaded in the ``__init__`` method itself. - Changes to Scrapy Manager (now called "Crawler"): - ``scrapy.core.manager.ScrapyManager`` class renamed to ``scrapy.crawler.Crawler`` @@ -3676,13 +4521,14 @@ First release of Scrapy. .. _resource: https://docs.python.org/2/library/resource.html .. _robots.txt: https://www.robotstxt.org/ .. _scrapely: https://github.com/scrapy/scrapely +.. _scrapy-bench: https://github.com/scrapy/scrapy-bench .. _service_identity: https://service-identity.readthedocs.io/en/stable/ .. _six: https://six.readthedocs.io/ .. _tox: https://pypi.org/project/tox/ .. _Twisted: https://twistedmatrix.com/trac/ -.. _Twisted - hello, asynchronous programming: http://jessenoller.com/blog/2009/02/11/twisted-hello-asynchronous-programming/ .. _w3lib: https://github.com/scrapy/w3lib .. _w3lib.encoding: https://github.com/scrapy/w3lib/blob/master/w3lib/encoding.py .. _What is cacheable: https://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.9.1 .. _zope.interface: https://zopeinterface.readthedocs.io/en/latest/ .. _Zsh: https://www.zsh.org/ +.. _zstandard: https://pypi.org/project/zstandard/ diff --git a/docs/requirements.txt b/docs/requirements.txt index 3d34b47da..a0930ba1e 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1,4 +1,4 @@ Sphinx>=3.0 sphinx-hoverxref>=0.2b1 sphinx-notfound-page>=0.4 -sphinx_rtd_theme>=0.4 +sphinx-rtd-theme>=0.5.2 \ No newline at end of file diff --git a/docs/topics/api.rst b/docs/topics/api.rst index 52509ffdf..900b19c7a 100644 --- a/docs/topics/api.rst +++ b/docs/topics/api.rst @@ -4,8 +4,6 @@ Core API ======== -.. versionadded:: 0.15 - This section documents the Scrapy core API, and it's intended for developers of extensions and middlewares. @@ -31,7 +29,7 @@ how you :ref:`configure the downloader middlewares .. class:: Crawler(spidercls, settings) The Crawler object must be instantiated with a - :class:`scrapy.spiders.Spider` subclass and a + :class:`scrapy.Spider` subclass and a :class:`scrapy.settings.Settings` object. .. attribute:: settings @@ -198,7 +196,7 @@ SpiderLoader API match the request's url against the domains of the spiders. :param request: queried request - :type request: :class:`~scrapy.http.Request` instance + :type request: :class:`~scrapy.Request` instance .. _topics-api-signals: diff --git a/docs/topics/architecture.rst b/docs/topics/architecture.rst index ae25dfa2f..71d027c86 100644 --- a/docs/topics/architecture.rst +++ b/docs/topics/architecture.rst @@ -87,8 +87,9 @@ of the system, and triggering events when certain actions occur. See the Scheduler --------- -The Scheduler receives requests from the engine and enqueues them for feeding -them later (also to the engine) when the engine requests them. +The :ref:`scheduler ` receives requests from the engine and +enqueues them for feeding them later (also to the engine) when the engine +requests them. .. _component-downloader: @@ -104,7 +105,7 @@ Spiders ------- Spiders are custom classes written by Scrapy users to parse responses and -extract items (aka scraped items) from them or additional requests to +extract :ref:`items ` from them or additional requests to follow. For more information see :ref:`topics-spiders`. .. _component-pipelines: diff --git a/docs/topics/asyncio.rst b/docs/topics/asyncio.rst index 038a459fd..82c5f271f 100644 --- a/docs/topics/asyncio.rst +++ b/docs/topics/asyncio.rst @@ -1,16 +1,19 @@ +.. _using-asyncio: + ======= asyncio ======= .. versionadded:: 2.0 -Scrapy has partial support :mod:`asyncio`. After you :ref:`install the asyncio -reactor `, you may use :mod:`asyncio` and +Scrapy has partial support for :mod:`asyncio`. After you :ref:`install the +asyncio reactor `, you may use :mod:`asyncio` and :mod:`asyncio`-powered libraries in any :doc:`coroutine `. -.. warning:: :mod:`asyncio` support in Scrapy is experimental. Future Scrapy - versions may introduce related changes without a deprecation - period or warning. +.. warning:: :mod:`asyncio` support in Scrapy is experimental, and not yet + recommended for production environments. Future Scrapy versions + may introduce related changes without a deprecation period or + warning. .. _install-asyncio: @@ -26,3 +29,15 @@ reactor manually. You can do that using :func:`~scrapy.utils.reactor.install_reactor`:: install_reactor('twisted.internet.asyncioreactor.AsyncioSelectorReactor') + +.. _using-custom-loops: + +Using custom asyncio loops +========================== + +You can also use custom asyncio event loops with the asyncio reactor. Set the +:setting:`ASYNCIO_EVENT_LOOP` setting to the import path of the desired event loop class to +use it instead of the default asyncio event loop. + + + diff --git a/docs/topics/autothrottle.rst b/docs/topics/autothrottle.rst index 4317019fc..8e6aae65c 100644 --- a/docs/topics/autothrottle.rst +++ b/docs/topics/autothrottle.rst @@ -128,8 +128,6 @@ The maximum download delay (in seconds) to be set in case of high latencies. AUTOTHROTTLE_TARGET_CONCURRENCY ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -.. versionadded:: 1.1 - Default: ``1.0`` Average number of requests Scrapy should be sending in parallel to remote diff --git a/docs/topics/benchmarking.rst b/docs/topics/benchmarking.rst index 99469ebf1..0643df6a6 100644 --- a/docs/topics/benchmarking.rst +++ b/docs/topics/benchmarking.rst @@ -4,8 +4,6 @@ Benchmarking ============ -.. versionadded:: 0.17 - Scrapy comes with a simple benchmarking suite that spawns a local HTTP server and crawls it at the maximum possible speed. The goal of this benchmarking is to get an idea of how Scrapy performs in your hardware, in order to have a @@ -83,5 +81,6 @@ follow links, any custom spider you write will probably do more stuff which results in slower crawl rates. How slower depends on how much your spider does and how well it's written. -In the future, more cases will be added to the benchmarking suite to cover -other common scenarios. +Use scrapy-bench_ for more complex benchmarking. + +.. _scrapy-bench: https://github.com/scrapy/scrapy-bench \ No newline at end of file diff --git a/docs/topics/commands.rst b/docs/topics/commands.rst index a0dcba90d..eef6b36ff 100644 --- a/docs/topics/commands.rst +++ b/docs/topics/commands.rst @@ -6,8 +6,6 @@ Command line tool ================= -.. versionadded:: 0.10 - Scrapy is controlled through the ``scrapy`` command-line tool, to be referred here as the "Scrapy tool" to differentiate it from the sub-commands, which we just call "commands" or "Scrapy commands". @@ -468,7 +466,7 @@ Supported options: * ``--callback`` or ``-c``: spider method to use as callback for parsing the response -* ``--meta`` or ``-m``: additional request meta that will be passed to the callback +* ``--meta`` or ``-m``: additional request meta that will be passed to the callback request. This must be a valid json string. Example: --meta='{"foo" : "bar"}' * ``--cbkwargs``: additional keyword arguments that will be passed to the callback. @@ -491,6 +489,10 @@ Supported options: * ``--verbose`` or ``-v``: display information for each depth level +* ``--output`` or ``-o``: dump scraped items to a file + + .. versionadded:: 2.3 + .. skip: start Usage example:: @@ -562,8 +564,6 @@ and Platform info, which is useful for bug reports. bench ----- -.. versionadded:: 0.17 - * Syntax: ``scrapy bench`` * Requires project: *no* @@ -598,8 +598,6 @@ Example: Register commands via setup.py entry points ------------------------------------------- -.. note:: This is an experimental feature, use with caution. - You can also add Scrapy commands from an external library by adding a ``scrapy.commands`` section in the entry points of the library ``setup.py`` file. diff --git a/docs/topics/contracts.rst b/docs/topics/contracts.rst index b8b3078c4..ef296dc9e 100644 --- a/docs/topics/contracts.rst +++ b/docs/topics/contracts.rst @@ -4,8 +4,6 @@ Spiders Contracts ================= -.. versionadded:: 0.15 - Testing spiders can get particularly annoying and while nothing prevents you from writing unit tests the task gets cumbersome quickly. Scrapy offers an integrated way of testing your spiders by the means of contracts. @@ -39,7 +37,7 @@ This callback is tested using three built-in contracts: .. class:: CallbackKeywordArgumentsContract - This contract (``@cb_kwargs``) sets the :attr:`cb_kwargs ` + This contract (``@cb_kwargs``) sets the :attr:`cb_kwargs ` attribute for the sample request. It must be a valid JSON dictionary. :: @@ -81,7 +79,7 @@ override three methods: .. class:: Contract(method, *args) :param method: callback function to which the contract is associated - :type method: function + :type method: collections.abc.Callable :param args: list of arguments passed into the docstring (whitespace separated) @@ -90,7 +88,7 @@ override three methods: .. method:: Contract.adjust_request_args(args) This receives a ``dict`` as an argument containing default arguments - for request object. :class:`~scrapy.http.Request` is used by default, + for request object. :class:`~scrapy.Request` is used by default, but this can be changed with the ``request_cls`` attribute. If multiple contracts in chain have this attribute defined, the last one is used. diff --git a/docs/topics/coroutines.rst b/docs/topics/coroutines.rst index 7a9ecd4d5..0904637b0 100644 --- a/docs/topics/coroutines.rst +++ b/docs/topics/coroutines.rst @@ -15,21 +15,16 @@ Supported callables The following callables may be defined as coroutines using ``async def``, and hence use coroutine syntax (e.g. ``await``, ``async for``, ``async with``): -- :class:`~scrapy.http.Request` callbacks. +- :class:`~scrapy.Request` callbacks. - The following are known caveats of the current implementation that we aim - to address in future versions of Scrapy: - - - The callback output is not processed until the whole callback finishes. + .. note:: The callback output is not processed until the whole callback + finishes. As a side effect, if the callback raises an exception, none of its output is processed. - - Because `asynchronous generators were introduced in Python 3.6`_, you - can only use ``yield`` if you are using Python 3.6 or later. - - If you need to output multiple items or requests and you are using - Python 3.5, return an iterable (e.g. a list) instead. + This is a known caveat of the current implementation that we aim to + address in a future version of Scrapy. - The :meth:`process_item` method of :ref:`item pipelines `. @@ -44,8 +39,6 @@ hence use coroutine syntax (e.g. ``await``, ``async for``, ``async with``): - :ref:`Signal handlers that support deferreds `. -.. _asynchronous generators were introduced in Python 3.6: https://www.python.org/dev/peps/pep-0525/ - Usage ===== @@ -53,21 +46,28 @@ There are several use cases for coroutines in Scrapy. Code that would return Deferreds when written for previous Scrapy versions, such as downloader middlewares and signal handlers, can be rewritten to be shorter and cleaner:: + from itemadapter import ItemAdapter + class DbPipeline: def _update_item(self, data, item): - item['field'] = data + adapter = ItemAdapter(item) + adapter['field'] = data return item def process_item(self, item, spider): - dfd = db.get_some_data(item['id']) + adapter = ItemAdapter(item) + dfd = db.get_some_data(adapter['id']) dfd.addCallback(self._update_item, item) return dfd becomes:: + from itemadapter import ItemAdapter + class DbPipeline: async def process_item(self, item, spider): - item['field'] = await db.get_some_data(item['id']) + adapter = ItemAdapter(item) + adapter['field'] = await db.get_some_data(adapter['id']) return item Coroutines may be used to call asynchronous code. This includes other diff --git a/docs/topics/debug.rst b/docs/topics/debug.rst index d75f17301..4d452b4df 100644 --- a/docs/topics/debug.rst +++ b/docs/topics/debug.rst @@ -36,7 +36,7 @@ Consider the following Scrapy spider below:: Basically this is a simple spider which parses two pages of items (the start_urls). Items also have a details page with additional information, so we -use the ``cb_kwargs`` functionality of :class:`~scrapy.http.Request` to pass a +use the ``cb_kwargs`` functionality of :class:`~scrapy.Request` to pass a partially populated item. diff --git a/docs/topics/deploy.rst b/docs/topics/deploy.rst index 361914a29..961d6dc01 100644 --- a/docs/topics/deploy.rst +++ b/docs/topics/deploy.rst @@ -14,7 +14,7 @@ spiders come in. Popular choices for deploying Scrapy spiders are: * :ref:`Scrapyd ` (open source) -* :ref:`Scrapy Cloud ` (cloud-based) +* :ref:`Zyte Scrapy Cloud ` (cloud-based) .. _deploy-scrapyd: @@ -32,28 +32,28 @@ Scrapyd is maintained by some of the Scrapy developers. .. _deploy-scrapy-cloud: -Deploying to Scrapy Cloud -========================= +Deploying to Zyte Scrapy Cloud +============================== -`Scrapy Cloud`_ is a hosted, cloud-based service by `Scrapinghub`_, -the company behind Scrapy. +`Zyte Scrapy Cloud`_ is a hosted, cloud-based service by Zyte_, the company +behind Scrapy. -Scrapy Cloud removes the need to setup and monitor servers -and provides a nice UI to manage spiders and review scraped items, -logs and stats. +Zyte Scrapy Cloud removes the need to setup and monitor servers and provides a +nice UI to manage spiders and review scraped items, logs and stats. -To deploy spiders to Scrapy Cloud you can use the `shub`_ command line tool. -Please refer to the `Scrapy Cloud documentation`_ for more information. +To deploy spiders to Zyte Scrapy Cloud you can use the `shub`_ command line +tool. +Please refer to the `Zyte Scrapy Cloud documentation`_ for more information. -Scrapy Cloud is compatible with Scrapyd and one can switch between +Zyte Scrapy Cloud is compatible with Scrapyd and one can switch between them as needed - the configuration is read from the ``scrapy.cfg`` file just like ``scrapyd-deploy``. -.. _Scrapyd: https://github.com/scrapy/scrapyd .. _Deploying your project: https://scrapyd.readthedocs.io/en/latest/deploy.html -.. _Scrapy Cloud: https://scrapinghub.com/scrapy-cloud +.. _Scrapyd: https://github.com/scrapy/scrapyd .. _scrapyd-client: https://github.com/scrapy/scrapyd-client -.. _shub: https://doc.scrapinghub.com/shub.html .. _scrapyd-deploy documentation: https://scrapyd.readthedocs.io/en/latest/deploy.html -.. _Scrapy Cloud documentation: https://doc.scrapinghub.com/scrapy-cloud.html -.. _Scrapinghub: https://scrapinghub.com/ +.. _shub: https://shub.readthedocs.io/en/latest/ +.. _Zyte: https://zyte.com/ +.. _Zyte Scrapy Cloud: https://www.zyte.com/scrapy-cloud/ +.. _Zyte Scrapy Cloud documentation: https://docs.zyte.com/scrapy-cloud.html diff --git a/docs/topics/developer-tools.rst b/docs/topics/developer-tools.rst index 4e87a00f2..057b1ec62 100644 --- a/docs/topics/developer-tools.rst +++ b/docs/topics/developer-tools.rst @@ -5,9 +5,9 @@ Using your browser's Developer Tools for scraping ================================================= Here is a general guide on how to use your browser's Developer Tools -to ease the scraping process. Today almost all browsers come with +to ease the scraping process. Today almost all browsers come with built in `Developer Tools`_ and although we will use Firefox in this -guide, the concepts are applicable to any other browser. +guide, the concepts are applicable to any other browser. In this guide we'll introduce the basic tools to use from a browser's Developer Tools by scraping `quotes.toscrape.com`_. @@ -41,16 +41,16 @@ Therefore, you should keep in mind the following things: Inspecting a website ==================== -By far the most handy feature of the Developer Tools is the `Inspector` -feature, which allows you to inspect the underlying HTML code of -any webpage. To demonstrate the Inspector, let's look at the +By far the most handy feature of the Developer Tools is the `Inspector` +feature, which allows you to inspect the underlying HTML code of +any webpage. To demonstrate the Inspector, let's look at the `quotes.toscrape.com`_-site. On the site we have a total of ten quotes from various authors with specific -tags, as well as the Top Ten Tags. Let's say we want to extract all the quotes -on this page, without any meta-information about authors, tags, etc. +tags, as well as the Top Ten Tags. Let's say we want to extract all the quotes +on this page, without any meta-information about authors, tags, etc. -Instead of viewing the whole source code for the page, we can simply right click +Instead of viewing the whole source code for the page, we can simply right click on a quote and select ``Inspect Element (Q)``, which opens up the `Inspector`. In it you should see something like this: @@ -97,16 +97,16 @@ Then, back to your web browser, right-click on the ``span`` tag, select >>> response.xpath('/html/body/div/div[2]/div[1]/div[1]/span[1]/text()').getall() ['“The world as we have created it is a process of our thinking. It cannot be changed without changing our thinking.”'] -Adding ``text()`` at the end we are able to extract the first quote with this +Adding ``text()`` at the end we are able to extract the first quote with this basic selector. But this XPath is not really that clever. All it does is -go down a desired path in the source code starting from ``html``. So let's -see if we can refine our XPath a bit: +go down a desired path in the source code starting from ``html``. So let's +see if we can refine our XPath a bit: -If we check the `Inspector` again we'll see that directly beneath our -expanded ``div`` tag we have nine identical ``div`` tags, each with the -same attributes as our first. If we expand any of them, we'll see the same +If we check the `Inspector` again we'll see that directly beneath our +expanded ``div`` tag we have nine identical ``div`` tags, each with the +same attributes as our first. If we expand any of them, we'll see the same structure as with our first quote: Two ``span`` tags and one ``div`` tag. We can -expand each ``span`` tag with the ``class="text"`` inside our ``div`` tags and +expand each ``span`` tag with the ``class="text"`` inside our ``div`` tags and see each quote: .. code-block:: html @@ -121,7 +121,7 @@ see each quote: With this knowledge we can refine our XPath: Instead of a path to follow, -we'll simply select all ``span`` tags with the ``class="text"`` by using +we'll simply select all ``span`` tags with the ``class="text"`` by using the `has-class-extension`_: >>> response.xpath('//span[has-class("text")]/text()').getall() @@ -130,45 +130,45 @@ the `has-class-extension`_: '“There are only two ways to live your life. One is as though nothing is a miracle. The other is as though everything is a miracle.”', ...] -And with one simple, cleverer XPath we are able to extract all quotes from -the page. We could have constructed a loop over our first XPath to increase -the number of the last ``div``, but this would have been unnecessarily +And with one simple, cleverer XPath we are able to extract all quotes from +the page. We could have constructed a loop over our first XPath to increase +the number of the last ``div``, but this would have been unnecessarily complex and by simply constructing an XPath with ``has-class("text")`` -we were able to extract all quotes in one line. +we were able to extract all quotes in one line. -The `Inspector` has a lot of other helpful features, such as searching in the +The `Inspector` has a lot of other helpful features, such as searching in the source code or directly scrolling to an element you selected. Let's demonstrate -a use case: +a use case: -Say you want to find the ``Next`` button on the page. Type ``Next`` into the -search bar on the top right of the `Inspector`. You should get two results. -The first is a ``li`` tag with the ``class="next"``, the second the text +Say you want to find the ``Next`` button on the page. Type ``Next`` into the +search bar on the top right of the `Inspector`. You should get two results. +The first is a ``li`` tag with the ``class="next"``, the second the text of an ``a`` tag. Right click on the ``a`` tag and select ``Scroll into View``. If you hover over the tag, you'll see the button highlighted. From here -we could easily create a :ref:`Link Extractor ` to -follow the pagination. On a simple site such as this, there may not be +we could easily create a :ref:`Link Extractor ` to +follow the pagination. On a simple site such as this, there may not be the need to find an element visually but the ``Scroll into View`` function -can be quite useful on complex sites. +can be quite useful on complex sites. Note that the search bar can also be used to search for and test CSS -selectors. For example, you could search for ``span.text`` to find -all quote texts. Instead of a full text search, this searches for -exactly the ``span`` tag with the ``class="text"`` in the page. +selectors. For example, you could search for ``span.text`` to find +all quote texts. Instead of a full text search, this searches for +exactly the ``span`` tag with the ``class="text"`` in the page. .. _topics-network-tool: The Network-tool ================ While scraping you may come across dynamic webpages where some parts -of the page are loaded dynamically through multiple requests. While -this can be quite tricky, the `Network`-tool in the Developer Tools +of the page are loaded dynamically through multiple requests. While +this can be quite tricky, the `Network`-tool in the Developer Tools greatly facilitates this task. To demonstrate the Network-tool, let's -take a look at the page `quotes.toscrape.com/scroll`_. +take a look at the page `quotes.toscrape.com/scroll`_. -The page is quite similar to the basic `quotes.toscrape.com`_-page, -but instead of the above-mentioned ``Next`` button, the page -automatically loads new quotes when you scroll to the bottom. We -could go ahead and try out different XPaths directly, but instead +The page is quite similar to the basic `quotes.toscrape.com`_-page, +but instead of the above-mentioned ``Next`` button, the page +automatically loads new quotes when you scroll to the bottom. We +could go ahead and try out different XPaths directly, but instead we'll check another quite useful command from the Scrapy shell: .. skip: next @@ -179,9 +179,9 @@ we'll check another quite useful command from the Scrapy shell: (...) >>> view(response) -A browser window should open with the webpage but with one -crucial difference: Instead of the quotes we just see a greenish -bar with the word ``Loading...``. +A browser window should open with the webpage but with one +crucial difference: Instead of the quotes we just see a greenish +bar with the word ``Loading...``. .. image:: _images/network_01.png :width: 777 @@ -189,21 +189,21 @@ bar with the word ``Loading...``. :alt: Response from quotes.toscrape.com/scroll The ``view(response)`` command let's us view the response our -shell or later our spider receives from the server. Here we see -that some basic template is loaded which includes the title, +shell or later our spider receives from the server. Here we see +that some basic template is loaded which includes the title, the login-button and the footer, but the quotes are missing. This tells us that the quotes are being loaded from a different request -than ``quotes.toscrape/scroll``. +than ``quotes.toscrape/scroll``. -If you click on the ``Network`` tab, you will probably only see -two entries. The first thing we do is enable persistent logs by -clicking on ``Persist Logs``. If this option is disabled, the +If you click on the ``Network`` tab, you will probably only see +two entries. The first thing we do is enable persistent logs by +clicking on ``Persist Logs``. If this option is disabled, the log is automatically cleared each time you navigate to a different -page. Enabling this option is a good default, since it gives us -control on when to clear the logs. +page. Enabling this option is a good default, since it gives us +control on when to clear the logs. If we reload the page now, you'll see the log get populated with six -new requests. +new requests. .. image:: _images/network_02.png :width: 777 @@ -212,31 +212,31 @@ new requests. Here we see every request that has been made when reloading the page and can inspect each request and its response. So let's find out -where our quotes are coming from: +where our quotes are coming from: -First click on the request with the name ``scroll``. On the right +First click on the request with the name ``scroll``. On the right you can now inspect the request. In ``Headers`` you'll find details about the request headers, such as the URL, the method, the IP-address, and so on. We'll ignore the other tabs and click directly on ``Response``. -What you should see in the ``Preview`` pane is the rendered HTML-code, -that is exactly what we saw when we called ``view(response)`` in the -shell. Accordingly the ``type`` of the request in the log is ``html``. -The other requests have types like ``css`` or ``js``, but what -interests us is the one request called ``quotes?page=1`` with the -type ``json``. +What you should see in the ``Preview`` pane is the rendered HTML-code, +that is exactly what we saw when we called ``view(response)`` in the +shell. Accordingly the ``type`` of the request in the log is ``html``. +The other requests have types like ``css`` or ``js``, but what +interests us is the one request called ``quotes?page=1`` with the +type ``json``. -If we click on this request, we see that the request URL is +If we click on this request, we see that the request URL is ``http://quotes.toscrape.com/api/quotes?page=1`` and the response is a JSON-object that contains our quotes. We can also right-click -on the request and open ``Open in new tab`` to get a better overview. +on the request and open ``Open in new tab`` to get a better overview. .. image:: _images/network_03.png :width: 777 :height: 375 :alt: JSON-object returned from the quotes.toscrape API -With this response we can now easily parse the JSON-object and +With this response we can now easily parse the JSON-object and also request each page to get every quote on the site:: import scrapy @@ -255,17 +255,17 @@ also request each page to get every quote on the site:: yield {"quote": quote["text"]} if data["has_next"]: self.page += 1 - url = "http://quotes.toscrape.com/api/quotes?page={}".format(self.page) + url = f"http://quotes.toscrape.com/api/quotes?page={self.page}" yield scrapy.Request(url=url, callback=self.parse) -This spider starts at the first page of the quotes-API. With each -response, we parse the ``response.text`` and assign it to ``data``. -This lets us operate on the JSON-object like on a Python dictionary. +This spider starts at the first page of the quotes-API. With each +response, we parse the ``response.text`` and assign it to ``data``. +This lets us operate on the JSON-object like on a Python dictionary. We iterate through the ``quotes`` and print out the ``quote["text"]``. -If the handy ``has_next`` element is ``true`` (try loading +If the handy ``has_next`` element is ``true`` (try loading `quotes.toscrape.com/api/quotes?page=10`_ in your browser or a -page-number greater than 10), we increment the ``page`` attribute -and ``yield`` a new request, inserting the incremented page-number +page-number greater than 10), we increment the ``page`` attribute +and ``yield`` a new request, inserting the incremented page-number into our ``url``. .. _requests-from-curl: @@ -274,7 +274,7 @@ In more complex websites, it could be difficult to easily reproduce the requests, as we could need to add ``headers`` or ``cookies`` to make it work. In those cases you can export the requests in `cURL `_ format, by right-clicking on each of them in the network tool and using the -:meth:`~scrapy.http.Request.from_curl()` method to generate an equivalent +:meth:`~scrapy.Request.from_curl()` method to generate an equivalent request:: from scrapy import Request @@ -289,14 +289,16 @@ request:: "://quotes.toscrape.com/scroll' -H 'Cache-Control: max-age=0'") Alternatively, if you want to know the arguments needed to recreate that -request you can use the :func:`scrapy.utils.curl.curl_to_request_kwargs` -function to get a dictionary with the equivalent arguments. +request you can use the :func:`~scrapy.utils.curl.curl_to_request_kwargs` +function to get a dictionary with the equivalent arguments: + +.. autofunction:: scrapy.utils.curl.curl_to_request_kwargs Note that to translate a cURL command into a Scrapy request, you may use `curl2scrapy `_. As you can see, with a few inspections in the `Network`-tool we -were able to easily replicate the dynamic requests of the scrolling +were able to easily replicate the dynamic requests of the scrolling functionality of the page. Crawling dynamic pages can be quite daunting and pages can be very complex, but it (mostly) boils down to identifying the correct request and replicating it in your spider. diff --git a/docs/topics/downloader-middleware.rst b/docs/topics/downloader-middleware.rst index 323e553e5..80c6c2c37 100644 --- a/docs/topics/downloader-middleware.rst +++ b/docs/topics/downloader-middleware.rst @@ -76,7 +76,7 @@ object gives you access, for example, to the :ref:`settings `. middleware. :meth:`process_request` should either: return ``None``, return a - :class:`~scrapy.http.Response` object, return a :class:`~scrapy.http.Request` + :class:`~scrapy.Response` object, return a :class:`~scrapy.http.Request` object, or raise :exc:`~scrapy.exceptions.IgnoreRequest`. If it returns ``None``, Scrapy will continue processing this request, executing all @@ -88,7 +88,7 @@ object gives you access, for example, to the :ref:`settings `. or the appropriate download function; it'll return that response. The :meth:`process_response` methods of installed middleware is always called on every response. - If it returns a :class:`~scrapy.http.Request` object, Scrapy will stop calling + If it returns a :class:`~scrapy.Request` object, Scrapy will stop calling process_request methods and reschedule the returned request. Once the newly returned request is performed, the appropriate middleware chain will be called on the downloaded response. @@ -100,22 +100,22 @@ object gives you access, for example, to the :ref:`settings `. ignored and not logged (unlike other exceptions). :param request: the request being processed - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param spider: the spider for which this request is intended - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: process_response(request, response, spider) :meth:`process_response` should either: return a :class:`~scrapy.http.Response` - object, return a :class:`~scrapy.http.Request` object or + object, return a :class:`~scrapy.Request` object or raise a :exc:`~scrapy.exceptions.IgnoreRequest` exception. If it returns a :class:`~scrapy.http.Response` (it could be the same given response, or a brand-new one), that response will continue to be processed with the :meth:`process_response` of the next middleware in the chain. - If it returns a :class:`~scrapy.http.Request` object, the middleware chain is + If it returns a :class:`~scrapy.Request` object, the middleware chain is halted and the returned request is rescheduled to be downloaded in the future. This is the same behavior as if a request is returned from :meth:`process_request`. @@ -124,13 +124,13 @@ object gives you access, for example, to the :ref:`settings `. exception, it is ignored and not logged (unlike other exceptions). :param request: the request that originated the response - :type request: is a :class:`~scrapy.http.Request` object + :type request: is a :class:`~scrapy.Request` object :param response: the response being processed :type response: :class:`~scrapy.http.Response` object :param spider: the spider for which this response is intended - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: process_exception(request, exception, spider) @@ -139,7 +139,7 @@ object gives you access, for example, to the :ref:`settings `. exception (including an :exc:`~scrapy.exceptions.IgnoreRequest` exception) :meth:`process_exception` should return: either ``None``, - a :class:`~scrapy.http.Response` object, or a :class:`~scrapy.http.Request` object. + a :class:`~scrapy.http.Response` object, or a :class:`~scrapy.Request` object. If it returns ``None``, Scrapy will continue processing this exception, executing any other :meth:`process_exception` methods of installed middleware, @@ -149,19 +149,19 @@ object gives you access, for example, to the :ref:`settings `. method chain of installed middleware is started, and Scrapy won't bother calling any other :meth:`process_exception` methods of middleware. - If it returns a :class:`~scrapy.http.Request` object, the returned request is + If it returns a :class:`~scrapy.Request` object, the returned request is rescheduled to be downloaded in the future. This stops the execution of :meth:`process_exception` methods of the middleware the same as returning a response would. :param request: the request that generated the exception - :type request: is a :class:`~scrapy.http.Request` object + :type request: is a :class:`~scrapy.Request` object :param exception: the raised exception :type exception: an ``Exception`` object :param spider: the spider for which this request is intended - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: from_crawler(cls, crawler) @@ -203,10 +203,15 @@ CookiesMiddleware browsers do. .. caution:: When non-UTF8 encoded byte sequences are passed to a - :class:`~scrapy.http.Request`, the ``CookiesMiddleware`` will log + :class:`~scrapy.Request`, the ``CookiesMiddleware`` will log a warning. Refer to :ref:`topics-logging-advanced-customization` to customize the logging behaviour. + .. caution:: Cookies set via the ``Cookie`` header are not considered by the + :ref:`cookies-mw`. If you need to set cookies for a request, use the + :class:`Request.cookies ` parameter. This is a known + current limitation that is being worked on. + The following settings can be used to configure the cookie middleware: * :setting:`COOKIES_ENABLED` @@ -217,8 +222,6 @@ The following settings can be used to configure the cookie middleware: Multiple cookie sessions per spider ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -.. versionadded:: 0.15 - There is support for keeping multiple cookie sessions per spider by using the :reqmeta:`cookiejar` Request meta key. By default it uses a single cookie jar (session), but you can pass an identifier to use different ones. @@ -255,7 +258,7 @@ web server and received cookies in :class:`~scrapy.http.Response` will **not** be merged with the existing cookies. For more detailed information see the ``cookies`` parameter in -:class:`~scrapy.http.Request`. +:class:`~scrapy.Request`. .. setting:: COOKIES_DEBUG @@ -475,8 +478,6 @@ DBM storage backend .. class:: DbmCacheStorage - .. versionadded:: 0.13 - A DBM_ storage backend is also available for the HTTP cache middleware. By default, it uses the :mod:`dbm`, but you can change it with the @@ -500,7 +501,7 @@ defines the methods described below. the :signal:`open_spider ` signal. :param spider: the spider which has been opened - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: close_spider(spider) @@ -508,27 +509,27 @@ defines the methods described below. the :signal:`close_spider ` signal. :param spider: the spider which has been closed - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: retrieve_response(spider, request) Return response if present in cache, or ``None`` otherwise. :param spider: the spider which generated the request - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object :param request: the request to find cached response for - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object .. method:: store_response(spider, request, response) Store the given response in the cache. :param spider: the spider for which the response is intended - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object :param request: the corresponding request the spider generated - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param response: the response to store in the cache :type response: :class:`~scrapy.http.Response` object @@ -549,15 +550,10 @@ settings: HTTPCACHE_ENABLED ^^^^^^^^^^^^^^^^^ -.. versionadded:: 0.11 - Default: ``False`` Whether the HTTP cache will be enabled. -.. versionchanged:: 0.11 - Before 0.11, :setting:`HTTPCACHE_DIR` was used to enable cache. - .. setting:: HTTPCACHE_EXPIRATION_SECS HTTPCACHE_EXPIRATION_SECS @@ -570,9 +566,6 @@ Expiration time for cached requests, in seconds. Cached requests older than this time will be re-downloaded. If zero, cached requests will never expire. -.. versionchanged:: 0.11 - Before 0.11, zero meant cached requests always expire. - .. setting:: HTTPCACHE_DIR HTTPCACHE_DIR @@ -589,8 +582,6 @@ project data dir. For more info see: :ref:`topics-project-structure`. HTTPCACHE_IGNORE_HTTP_CODES ^^^^^^^^^^^^^^^^^^^^^^^^^^^ -.. versionadded:: 0.10 - Default: ``[]`` Don't cache response with these HTTP codes. @@ -609,8 +600,6 @@ If enabled, requests not found in the cache will be ignored instead of downloade HTTPCACHE_IGNORE_SCHEMES ^^^^^^^^^^^^^^^^^^^^^^^^ -.. versionadded:: 0.10 - Default: ``['file']`` Don't cache responses with these URI schemes. @@ -629,8 +618,6 @@ The class which implements the cache storage backend. HTTPCACHE_DBM_MODULE ^^^^^^^^^^^^^^^^^^^^ -.. versionadded:: 0.13 - Default: ``'dbm'`` The database module to use in the :ref:`DBM storage backend @@ -641,8 +628,6 @@ The database module to use in the :ref:`DBM storage backend HTTPCACHE_POLICY ^^^^^^^^^^^^^^^^ -.. versionadded:: 0.18 - Default: ``'scrapy.extensions.httpcache.DummyPolicy'`` The class which implements the cache policy. @@ -652,8 +637,6 @@ The class which implements the cache policy. HTTPCACHE_GZIP ^^^^^^^^^^^^^^ -.. versionadded:: 1.0 - Default: ``False`` If enabled, will compress all cached data with gzip. @@ -664,8 +647,6 @@ This setting is specific to the Filesystem backend. HTTPCACHE_ALWAYS_STORE ^^^^^^^^^^^^^^^^^^^^^^ -.. versionadded:: 1.1 - Default: ``False`` If enabled, will cache pages unconditionally. @@ -684,8 +665,6 @@ responses you feed to the cache middleware. HTTPCACHE_IGNORE_RESPONSE_CACHE_CONTROLS ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -.. versionadded:: 1.1 - Default: ``[]`` List of Cache-Control directives in responses to be ignored. @@ -710,11 +689,14 @@ HttpCompressionMiddleware This middleware allows compressed (gzip, deflate) traffic to be sent/received from web sites. - This middleware also supports decoding `brotli-compressed`_ responses, - provided `brotlipy`_ is installed. + This middleware also supports decoding `brotli-compressed`_ as well as + `zstd-compressed`_ responses, provided that `brotlipy`_ or `zstandard`_ is + installed, respectively. .. _brotli-compressed: https://www.ietf.org/rfc/rfc7932.txt .. _brotlipy: https://pypi.org/project/brotlipy/ +.. _zstd-compressed: https://www.ietf.org/rfc/rfc8478.txt +.. _zstandard: https://pypi.org/project/zstandard/ HttpCompressionMiddleware Settings ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -735,14 +717,12 @@ HttpProxyMiddleware .. module:: scrapy.downloadermiddlewares.httpproxy :synopsis: Http Proxy Middleware -.. versionadded:: 0.8 - .. reqmeta:: proxy .. class:: HttpProxyMiddleware This middleware sets the HTTP proxy to use for requests, by setting the - ``proxy`` meta value for :class:`~scrapy.http.Request` objects. + ``proxy`` meta value for :class:`~scrapy.Request` objects. Like the Python standard library module :mod:`urllib.request`, it obeys the following environment variables: @@ -769,12 +749,12 @@ RedirectMiddleware .. reqmeta:: redirect_urls The urls which the request goes through (while being redirected) can be found -in the ``redirect_urls`` :attr:`Request.meta ` key. +in the ``redirect_urls`` :attr:`Request.meta ` key. .. reqmeta:: redirect_reasons The reason behind each redirect in :reqmeta:`redirect_urls` can be found in the -``redirect_reasons`` :attr:`Request.meta ` key. For +``redirect_reasons`` :attr:`Request.meta ` key. For example: ``[301, 302, 307, 'meta refresh']``. The format of a reason depends on the middleware that handled the corresponding @@ -790,7 +770,7 @@ settings (see the settings documentation for more info): .. reqmeta:: dont_redirect -If :attr:`Request.meta ` has ``dont_redirect`` +If :attr:`Request.meta ` has ``dont_redirect`` key set to True, the request will be ignored by this middleware. If you want to handle some redirect status codes in your spider, you can @@ -803,7 +783,7 @@ responses (and pass them through to your spider) you can do this:: handle_httpstatus_list = [301, 302] The ``handle_httpstatus_list`` key of :attr:`Request.meta -` can also be used to specify which response codes to +` can also be used to specify which response codes to allow on a per-request basis. You can also set the meta key ``handle_httpstatus_all`` to ``True`` if you want to allow any response code for a request. @@ -817,8 +797,6 @@ RedirectMiddleware settings REDIRECT_ENABLED ^^^^^^^^^^^^^^^^ -.. versionadded:: 0.13 - Default: ``True`` Whether the Redirect middleware will be enabled. @@ -860,8 +838,6 @@ MetaRefreshMiddleware settings METAREFRESH_ENABLED ^^^^^^^^^^^^^^^^^^^ -.. versionadded:: 0.17 - Default: ``True`` Whether the Meta Refresh middleware will be enabled. @@ -913,9 +889,14 @@ settings (see the settings documentation for more info): .. reqmeta:: dont_retry -If :attr:`Request.meta ` has ``dont_retry`` key +If :attr:`Request.meta ` has ``dont_retry`` key set to True, the request will be ignored by this middleware. +To retry requests from a spider callback, you can use the +:func:`get_retry_request` function: + +.. autofunction:: get_retry_request + RetryMiddleware Settings ~~~~~~~~~~~~~~~~~~~~~~~~ @@ -924,8 +905,6 @@ RetryMiddleware Settings RETRY_ENABLED ^^^^^^^^^^^^^ -.. versionadded:: 0.13 - Default: ``True`` Whether the Retry middleware will be enabled. @@ -940,7 +919,7 @@ Default: ``2`` Maximum number of times to retry, in addition to the first download. Maximum number of retries can also be specified per-request using -:reqmeta:`max_retry_times` attribute of :attr:`Request.meta `. +:reqmeta:`max_retry_times` attribute of :attr:`Request.meta `. When initialized, the :reqmeta:`max_retry_times` meta key takes higher precedence over the :setting:`RETRY_TIMES` setting. @@ -958,6 +937,18 @@ In some cases you may want to add 400 to :setting:`RETRY_HTTP_CODES` because it is a common code used to indicate server overload. It is not included by default because HTTP specs say so. +.. setting:: RETRY_PRIORITY_ADJUST + +RETRY_PRIORITY_ADJUST +--------------------- + +Default: ``-1`` + +Adjust retry request priority relative to original request: + +- a positive priority adjust means higher priority. +- **a negative priority adjust (default) means lower priority.** + .. _topics-dlmw-robots: @@ -995,7 +986,7 @@ RobotsTxtMiddleware .. reqmeta:: dont_obey_robotstxt -If :attr:`Request.meta ` has +If :attr:`Request.meta ` has ``dont_obey_robotstxt`` key set to True the request will be ignored by this middleware even if :setting:`ROBOTSTXT_OBEY` is enabled. @@ -1179,8 +1170,6 @@ AjaxCrawlMiddleware Settings AJAXCRAWL_ENABLED ^^^^^^^^^^^^^^^^^ -.. versionadded:: 0.21 - Default: ``False`` Whether the AjaxCrawlMiddleware will be enabled. You may want to diff --git a/docs/topics/dynamic-content.rst b/docs/topics/dynamic-content.rst index e918bc006..f96be0bbc 100644 --- a/docs/topics/dynamic-content.rst +++ b/docs/topics/dynamic-content.rst @@ -62,9 +62,9 @@ download the webpage with an HTTP client like curl_ or wget_ and see if the information can be found in the response they get. If they get a response with the desired data, modify your Scrapy -:class:`~scrapy.http.Request` to match that of the other HTTP client. For +:class:`~scrapy.Request` to match that of the other HTTP client. For example, try using the same user-agent string (:setting:`USER_AGENT`) or the -same :attr:`~scrapy.http.Request.headers`. +same :attr:`~scrapy.Request.headers`. If they also get a response without the desired data, you’ll need to take steps to make your request more similar to that of the web browser. See @@ -81,14 +81,14 @@ Use the :ref:`network tool ` of your web browser to see how your web browser performs the desired request, and try to reproduce that request with Scrapy. -It might be enough to yield a :class:`~scrapy.http.Request` with the same HTTP +It might be enough to yield a :class:`~scrapy.Request` with the same HTTP method and URL. However, you may also need to reproduce the body, headers and -form parameters (see :class:`~scrapy.http.FormRequest`) of that request. +form parameters (see :class:`~scrapy.FormRequest`) of that request. As all major browsers allow to export the requests in `cURL `_ format, Scrapy incorporates the method -:meth:`~scrapy.http.Request.from_curl()` to generate an equivalent -:class:`~scrapy.http.Request` from a cURL command. To get more information +:meth:`~scrapy.Request.from_curl()` to generate an equivalent +:class:`~scrapy.Request` from a cURL command. To get more information visit :ref:`request from curl ` inside the network tool section. @@ -125,7 +125,7 @@ data from it depends on the type of response: If the desired data is inside HTML or XML code embedded within JSON data, you can load that HTML or XML code into a - :class:`~scrapy.selector.Selector` and then + :class:`~scrapy.Selector` and then :ref:`use it ` as usual:: selector = Selector(data['html']) diff --git a/docs/topics/email.rst b/docs/topics/email.rst index e347c3a35..1a2bc6330 100644 --- a/docs/topics/email.rst +++ b/docs/topics/email.rst @@ -62,10 +62,10 @@ rest of the framework. :type smtpport: int :param smtptls: enforce using SMTP STARTTLS - :type smtptls: boolean + :type smtptls: bool :param smtpssl: enforce using a secure SSL connection - :type smtpssl: boolean + :type smtpssl: bool .. classmethod:: from_settings(settings) @@ -79,14 +79,14 @@ rest of the framework. Send email to the given recipients. - :param to: the e-mail recipients - :type to: str or list of str + :param to: the e-mail recipients as a string or as a list of strings + :type to: str or list :param subject: the subject of the e-mail :type subject: str - :param cc: the e-mails to CC - :type cc: str or list of str + :param cc: the e-mails to CC as a string or as a list of strings + :type cc: str or list :param body: the e-mail body :type body: str @@ -96,7 +96,7 @@ rest of the framework. appear on the e-mail's attachment, ``mimetype`` is the mimetype of the attachment and ``file_object`` is a readable file object with the contents of the attachment - :type attachs: iterable + :type attachs: collections.abc.Iterable :param mimetype: the MIME type of the e-mail :type mimetype: str diff --git a/docs/topics/exceptions.rst b/docs/topics/exceptions.rst index 583a50ab8..9150ca7d9 100644 --- a/docs/topics/exceptions.rst +++ b/docs/topics/exceptions.rst @@ -64,10 +64,10 @@ NotConfigured This exception can be raised by some components to indicate that they will remain disabled. Those components include: - * Extensions - * Item pipelines - * Downloader middlewares - * Spider middlewares +- Extensions +- Item pipelines +- Downloader middlewares +- Spider middlewares The exception must be raised in the component's ``__init__`` method. @@ -85,8 +85,8 @@ StopDownload .. exception:: StopDownload(fail=True) -Raised from a :class:`~scrapy.signals.bytes_received` signal handler to -indicate that no further bytes should be downloaded for a response. +Raised from a :class:`~scrapy.signals.bytes_received` or :class:`~scrapy.signals.headers_received` +signal handler to indicate that no further bytes should be downloaded for a response. The ``fail`` boolean parameter controls which method will handle the resulting response: @@ -110,5 +110,6 @@ attribute. ``StopDownload(False)`` or ``StopDownload(True)`` will raise a :class:`TypeError`. -See the documentation for the :class:`~scrapy.signals.bytes_received` signal +See the documentation for the :class:`~scrapy.signals.bytes_received` and +:class:`~scrapy.signals.headers_received` signals and the :ref:`topics-stop-response-download` topic for additional information and examples. diff --git a/docs/topics/exporters.rst b/docs/topics/exporters.rst index 7daf25ab3..8c30122b6 100644 --- a/docs/topics/exporters.rst +++ b/docs/topics/exporters.rst @@ -40,6 +40,7 @@ Here you can see an :doc:`Item Pipeline ` which uses multiple Item Exporters to group scraped items to different files according to the value of one of their fields:: + from itemadapter import ItemAdapter from scrapy.exporters import XmlItemExporter class PerYearXmlExportPipeline: @@ -49,17 +50,19 @@ value of one of their fields:: self.year_to_exporter = {} def close_spider(self, spider): - for exporter in self.year_to_exporter.values(): + for exporter, xml_file in self.year_to_exporter.values(): exporter.finish_exporting() + xml_file.close() def _exporter_for_item(self, item): - year = item['year'] + adapter = ItemAdapter(item) + year = adapter['year'] if year not in self.year_to_exporter: - f = open('{}.xml'.format(year), 'wb') - exporter = XmlItemExporter(f) + xml_file = open(f'{year}.xml', 'wb') + exporter = XmlItemExporter(xml_file) exporter.start_exporting() - self.year_to_exporter[year] = exporter - return self.year_to_exporter[year] + self.year_to_exporter[year] = (exporter, xml_file) + return self.year_to_exporter[year][0] def process_item(self, item, spider): exporter = self._exporter_for_item(item) @@ -87,7 +90,7 @@ described next. 1. Declaring a serializer in the field -------------------------------------- -If you use :class:`~.Item` you can declare a serializer in the +If you use :class:`~scrapy.Item` you can declare a serializer in the :ref:`field metadata `. The serializer must be a callable which receives a value and returns its serialized form. @@ -96,7 +99,7 @@ Example:: import scrapy def serialize_price(value): - return '$ %s' % str(value) + return f'$ {str(value)}' class Product(scrapy.Item): name = scrapy.Field() @@ -120,8 +123,8 @@ Example:: def serialize_field(self, field, name, value): if field == 'price': - return '$ %s' % str(value) - return super(Product, self).serialize_field(field, name, value) + return f'$ {str(value)}' + return super().serialize_field(field, name, value) .. _topics-exporters-reference: @@ -164,12 +167,12 @@ BaseItemExporter By default, this method looks for a serializer :ref:`declared in the item field ` and returns the result of applying that serializer to the value. If no serializer is found, it returns the - value unchanged except for ``unicode`` values which are encoded to - ``str`` using the encoding declared in the :attr:`encoding` attribute. + value unchanged. - :param field: the field being serialized. If a raw dict is being - exported (not :class:`~.Item`) *field* value is an empty dict. - :type field: :class:`~scrapy.item.Field` object or an empty dict + :param field: the field being serialized. If the source :ref:`item object + ` does not define field metadata, *field* is an empty + :class:`dict`. + :type field: :class:`~scrapy.Field` object or a :class:`dict` instance :param name: the name of the field being serialized :type name: str @@ -192,14 +195,17 @@ BaseItemExporter .. attribute:: fields_to_export - A list with the name of the fields that will be exported, or None if you - want to export all fields. Defaults to None. + A list with the name of the fields that will be exported, or ``None`` if + you want to export all fields. Defaults to ``None``. Some exporters (like :class:`CsvItemExporter`) respect the order of the fields defined in this attribute. - Some exporters may require fields_to_export list in order to export the - data properly when spiders return dicts (not :class:`~Item` instances). + When using :ref:`item objects ` that do not expose all their + possible fields, exporters that do not support exporting a different + subset of fields per item will only export the fields found in the first + item exported. Use ``fields_to_export`` to define all the fields to be + exported. .. attribute:: export_empty_fields @@ -211,10 +217,7 @@ BaseItemExporter .. attribute:: encoding - The encoding that will be used to encode unicode values. This only - affects unicode values (which are always serialized to str using this - encoding). Other value types are passed unchanged to the specific - serialization library. + The output character encoding. .. attribute:: indent @@ -238,7 +241,7 @@ XmlItemExporter .. class:: XmlItemExporter(file, item_element='item', root_element='items', **kwargs) - Exports Items in XML format to the specified file object. + Exports items in XML format to the specified file object. :param file: the file-like object to use for exporting the data. Its ``write`` method should accept ``bytes`` (a disk file opened in binary mode, a ``io.BytesIO`` object, etc) @@ -290,9 +293,9 @@ XmlItemExporter CsvItemExporter --------------- -.. class:: CsvItemExporter(file, include_headers_line=True, join_multivalued=',', **kwargs) +.. class:: CsvItemExporter(file, include_headers_line=True, join_multivalued=',', errors=None, **kwargs) - Exports Items in CSV format to the given file-like object. If the + Exports items in CSV format to the given file-like object. If the :attr:`fields_to_export` attribute is set, it will be used to define the CSV columns and their order. The :attr:`export_empty_fields` attribute has no effect on this exporter. @@ -303,12 +306,17 @@ CsvItemExporter :param include_headers_line: If enabled, makes the exporter output a header line with the field names taken from :attr:`BaseItemExporter.fields_to_export` or the first exported item fields. - :type include_headers_line: boolean + :type include_headers_line: bool :param join_multivalued: The char (or chars) that will be used for joining multi-valued fields, if found. :type include_headers_line: str + :param errors: The optional string that specifies how encoding and decoding + errors are to be handled. For more information see + :class:`io.TextIOWrapper`. + :type errors: str + The additional keyword arguments of this ``__init__`` method are passed to the :class:`BaseItemExporter` ``__init__`` method, and the leftover arguments to the :func:`csv.writer` function, so you can use any :func:`csv.writer` function @@ -325,7 +333,7 @@ PickleItemExporter .. class:: PickleItemExporter(file, protocol=0, **kwargs) - Exports Items in pickle format to the given file-like object. + Exports items in pickle format to the given file-like object. :param file: the file-like object to use for exporting the data. Its ``write`` method should accept ``bytes`` (a disk file opened in binary mode, a ``io.BytesIO`` object, etc) @@ -345,7 +353,7 @@ PprintItemExporter .. class:: PprintItemExporter(file, **kwargs) - Exports Items in pretty print format to the specified file object. + Exports items in pretty print format to the specified file object. :param file: the file-like object to use for exporting the data. Its ``write`` method should accept ``bytes`` (a disk file opened in binary mode, a ``io.BytesIO`` object, etc) @@ -365,7 +373,7 @@ JsonItemExporter .. class:: JsonItemExporter(file, **kwargs) - Exports Items in JSON format to the specified file-like object, writing all + Exports items in JSON format to the specified file-like object, writing all objects as a list of objects. The additional ``__init__`` method arguments are passed to the :class:`BaseItemExporter` ``__init__`` method, and the leftover arguments to the :class:`~json.JSONEncoder` ``__init__`` method, so you can use any @@ -394,7 +402,7 @@ JsonLinesItemExporter .. class:: JsonLinesItemExporter(file, **kwargs) - Exports Items in JSON format to the specified file-like object, writing one + Exports items in JSON format to the specified file-like object, writing one JSON-encoded item per line. The additional ``__init__`` method arguments are passed to the :class:`BaseItemExporter` ``__init__`` method, and the leftover arguments to the :class:`~json.JSONEncoder` ``__init__`` method, so you can use any diff --git a/docs/topics/extensions.rst b/docs/topics/extensions.rst index 0fc83e645..9e86fd0fe 100644 --- a/docs/topics/extensions.rst +++ b/docs/topics/extensions.rst @@ -7,8 +7,7 @@ Extensions The extensions framework provides a mechanism for inserting your own custom functionality into Scrapy. -Extensions are just regular classes that are instantiated at Scrapy startup, -when extensions are initialized. +Extensions are just regular classes. Extension settings ================== @@ -27,8 +26,8 @@ Loading & activating extensions =============================== Extensions are loaded and activated at startup by instantiating a single -instance of the extension class. Therefore, all the extension initialization -code must be performed in the class ``__init__`` method. +instance of the extension class per spider being run. All the extension +initialization code must be performed in the class ``__init__`` method. To make an extension available, add it to the :setting:`EXTENSIONS` setting in your Scrapy settings. In :setting:`EXTENSIONS`, each extension is represented @@ -257,6 +256,12 @@ settings: * :setting:`CLOSESPIDER_PAGECOUNT` * :setting:`CLOSESPIDER_ERRORCOUNT` +.. note:: + + When a certain closing condition is met, requests which are + currently in the downloader queue (up to :setting:`CONCURRENT_REQUESTS` + requests) are still processed. + .. setting:: CLOSESPIDER_TIMEOUT CLOSESPIDER_TIMEOUT @@ -279,8 +284,6 @@ Default: ``0`` An integer which specifies a number of items. If the spider scrapes more than that amount and those items are passed by the item pipeline, the spider will be closed with the reason ``closespider_itemcount``. -Requests which are currently in the downloader queue (up to -:setting:`CONCURRENT_REQUESTS` requests) are still processed. If zero (or non set), spiders won't be closed by number of passed items. .. setting:: CLOSESPIDER_PAGECOUNT @@ -288,8 +291,6 @@ If zero (or non set), spiders won't be closed by number of passed items. CLOSESPIDER_PAGECOUNT """"""""""""""""""""" -.. versionadded:: 0.11 - Default: ``0`` An integer which specifies the maximum number of responses to crawl. If the spider @@ -302,8 +303,6 @@ number of crawled responses. CLOSESPIDER_ERRORCOUNT """""""""""""""""""""" -.. versionadded:: 0.11 - Default: ``0`` An integer which specifies the maximum number of errors to receive before diff --git a/docs/topics/feed-exports.rst b/docs/topics/feed-exports.rst index 9e5968a29..216a8bc52 100644 --- a/docs/topics/feed-exports.rst +++ b/docs/topics/feed-exports.rst @@ -4,8 +4,6 @@ Feed exports ============ -.. versionadded:: 0.10 - One of the most frequently required features when implementing scrapers is being able to store the scraped data properly and, quite often, that means generating an "export file" with the scraped data (commonly called "export @@ -23,10 +21,10 @@ Serialization formats For serializing the scraped data, the feed exports use the :ref:`Item exporters `. These formats are supported out of the box: - * :ref:`topics-feed-format-json` - * :ref:`topics-feed-format-jsonlines` - * :ref:`topics-feed-format-csv` - * :ref:`topics-feed-format-xml` +- :ref:`topics-feed-format-json` +- :ref:`topics-feed-format-jsonlines` +- :ref:`topics-feed-format-csv` +- :ref:`topics-feed-format-xml` But you can also extend the supported format through the :setting:`FEED_EXPORTERS` setting. @@ -36,54 +34,58 @@ But you can also extend the supported format through the JSON ---- - * Value for the ``format`` key in the :setting:`FEEDS` setting: ``json`` - * Exporter used: :class:`~scrapy.exporters.JsonItemExporter` - * See :ref:`this warning ` if you're using JSON with - large feeds. +- Value for the ``format`` key in the :setting:`FEEDS` setting: ``json`` + +- Exporter used: :class:`~scrapy.exporters.JsonItemExporter` + +- See :ref:`this warning ` if you're using JSON with + large feeds. .. _topics-feed-format-jsonlines: JSON lines ---------- - * Value for the ``format`` key in the :setting:`FEEDS` setting: ``jsonlines`` - * Exporter used: :class:`~scrapy.exporters.JsonLinesItemExporter` +- Value for the ``format`` key in the :setting:`FEEDS` setting: ``jsonlines`` +- Exporter used: :class:`~scrapy.exporters.JsonLinesItemExporter` .. _topics-feed-format-csv: CSV --- - * Value for the ``format`` key in the :setting:`FEEDS` setting: ``csv`` - * Exporter used: :class:`~scrapy.exporters.CsvItemExporter` - * To specify columns to export and their order use - :setting:`FEED_EXPORT_FIELDS`. Other feed exporters can also use this - option, but it is important for CSV because unlike many other export - formats CSV uses a fixed header. +- Value for the ``format`` key in the :setting:`FEEDS` setting: ``csv`` + +- Exporter used: :class:`~scrapy.exporters.CsvItemExporter` + +- To specify columns to export and their order use + :setting:`FEED_EXPORT_FIELDS`. Other feed exporters can also use this + option, but it is important for CSV because unlike many other export + formats CSV uses a fixed header. .. _topics-feed-format-xml: XML --- - * Value for the ``format`` key in the :setting:`FEEDS` setting: ``xml`` - * Exporter used: :class:`~scrapy.exporters.XmlItemExporter` +- Value for the ``format`` key in the :setting:`FEEDS` setting: ``xml`` +- Exporter used: :class:`~scrapy.exporters.XmlItemExporter` .. _topics-feed-format-pickle: Pickle ------ - * Value for the ``format`` key in the :setting:`FEEDS` setting: ``pickle`` - * Exporter used: :class:`~scrapy.exporters.PickleItemExporter` +- Value for the ``format`` key in the :setting:`FEEDS` setting: ``pickle`` +- Exporter used: :class:`~scrapy.exporters.PickleItemExporter` .. _topics-feed-format-marshal: Marshal ------- - * Value for the ``format`` key in the :setting:`FEEDS` setting: ``marshal`` - * Exporter used: :class:`~scrapy.exporters.MarshalItemExporter` +- Value for the ``format`` key in the :setting:`FEEDS` setting: ``marshal`` +- Exporter used: :class:`~scrapy.exporters.MarshalItemExporter` .. _topics-feed-storage: @@ -97,10 +99,11 @@ storage backend types which are defined by the URI scheme. The storages backends supported out of the box are: - * :ref:`topics-feed-storage-fs` - * :ref:`topics-feed-storage-ftp` - * :ref:`topics-feed-storage-s3` (requires botocore_) - * :ref:`topics-feed-storage-stdout` +- :ref:`topics-feed-storage-fs` +- :ref:`topics-feed-storage-ftp` +- :ref:`topics-feed-storage-s3` (requires botocore_) +- :ref:`topics-feed-storage-gcs` (requires `google-cloud-storage`_) +- :ref:`topics-feed-storage-stdout` Some storage backends may be unavailable if the required external libraries are not available. For example, the S3 backend is only available if the botocore_ @@ -115,8 +118,8 @@ Storage URI parameters The storage URI can also contain parameters that get replaced when the feed is being created. These parameters are: - * ``%(time)s`` - gets replaced by a timestamp when the feed is being created - * ``%(name)s`` - gets replaced by the spider name +- ``%(time)s`` - gets replaced by a timestamp when the feed is being created +- ``%(name)s`` - gets replaced by the spider name Any other named parameter gets replaced by the spider attribute of the same name. For example, ``%(site_id)s`` would get replaced by the ``spider.site_id`` @@ -124,13 +127,16 @@ attribute the moment the feed is being created. Here are some examples to illustrate: - * Store in FTP using one directory per spider: +- Store in FTP using one directory per spider: - * ``ftp://user:password@ftp.example.com/scraping/feeds/%(name)s/%(time)s.json`` + - ``ftp://user:password@ftp.example.com/scraping/feeds/%(name)s/%(time)s.json`` - * Store in S3 using one directory per spider: +- Store in S3 using one directory per spider: - * ``s3://mybucket/scraping/feeds/%(name)s/%(time)s.json`` + - ``s3://mybucket/scraping/feeds/%(name)s/%(time)s.json`` + +.. note:: :ref:`Spider arguments ` become spider attributes, hence + they can also be used as storage URI parameters. .. _topics-feed-storage-backends: @@ -145,9 +151,9 @@ Local filesystem The feeds are stored in the local filesystem. - * URI scheme: ``file`` - * Example URI: ``file:///tmp/export.csv`` - * Required external libraries: none +- URI scheme: ``file`` +- Example URI: ``file:///tmp/export.csv`` +- Required external libraries: none Note that for the local filesystem storage (only) you can omit the scheme if you specify an absolute path like ``/tmp/export.csv``. This only works on Unix @@ -160,15 +166,18 @@ FTP The feeds are stored in a FTP server. - * URI scheme: ``ftp`` - * Example URI: ``ftp://user:pass@ftp.example.com/path/to/export.csv`` - * Required external libraries: none +- URI scheme: ``ftp`` +- Example URI: ``ftp://user:pass@ftp.example.com/path/to/export.csv`` +- Required external libraries: none FTP supports two different connection modes: `active or passive `_. Scrapy uses the passive connection mode by default. To use the active connection mode instead, set the :setting:`FEED_STORAGE_FTP_ACTIVE` setting to ``True``. +This storage backend uses :ref:`delayed file delivery `. + + .. _topics-feed-storage-s3: S3 @@ -176,23 +185,58 @@ S3 The feeds are stored on `Amazon S3`_. - * URI scheme: ``s3`` - * Example URIs: +- URI scheme: ``s3`` - * ``s3://mybucket/path/to/export.csv`` - * ``s3://aws_key:aws_secret@mybucket/path/to/export.csv`` +- Example URIs: - * Required external libraries: `botocore`_ + - ``s3://mybucket/path/to/export.csv`` + + - ``s3://aws_key:aws_secret@mybucket/path/to/export.csv`` + +- Required external libraries: `botocore`_ >= 1.4.87 The AWS credentials can be passed as user/password in the URI, or they can be passed through the following settings: - * :setting:`AWS_ACCESS_KEY_ID` - * :setting:`AWS_SECRET_ACCESS_KEY` +- :setting:`AWS_ACCESS_KEY_ID` +- :setting:`AWS_SECRET_ACCESS_KEY` -You can also define a custom ACL for exported feeds using this setting: +You can also define a custom ACL and custom endpoint for exported feeds using this setting: + +- :setting:`FEED_STORAGE_S3_ACL` +- :setting:`AWS_ENDPOINT_URL` + +This storage backend uses :ref:`delayed file delivery `. + + +.. _topics-feed-storage-gcs: + +Google Cloud Storage (GCS) +-------------------------- + +.. versionadded:: 2.3 + +The feeds are stored on `Google Cloud Storage`_. + +- URI scheme: ``gs`` + +- Example URIs: + + - ``gs://mybucket/path/to/export.csv`` + +- Required external libraries: `google-cloud-storage`_. + +For more information about authentication, please refer to `Google Cloud documentation `_. + +You can set a *Project ID* and *Access Control List (ACL)* through the following settings: + +- :setting:`FEED_STORAGE_GCS_ACL` +- :setting:`GCS_PROJECT_ID` + +This storage backend uses :ref:`delayed file delivery `. + +.. _google-cloud-storage: https://cloud.google.com/storage/docs/reference/libraries#client-libraries-install-python - * :setting:`FEED_STORAGE_S3_ACL` .. _topics-feed-storage-stdout: @@ -201,9 +245,68 @@ Standard output The feeds are written to the standard output of the Scrapy process. - * URI scheme: ``stdout`` - * Example URI: ``stdout:`` - * Required external libraries: none +- URI scheme: ``stdout`` +- Example URI: ``stdout:`` +- Required external libraries: none + + +.. _delayed-file-delivery: + +Delayed file delivery +--------------------- + +As indicated above, some of the described storage backends use delayed file +delivery. + +These storage backends do not upload items to the feed URI as those items are +scraped. Instead, Scrapy writes items into a temporary local file, and only +once all the file contents have been written (i.e. at the end of the crawl) is +that file uploaded to the feed URI. + +If you want item delivery to start earlier when using one of these storage +backends, use :setting:`FEED_EXPORT_BATCH_ITEM_COUNT` to split the output items +in multiple files, with the specified maximum item count per file. That way, as +soon as a file reaches the maximum item count, that file is delivered to the +feed URI, allowing item delivery to start way before the end of the crawl. + +.. _item-filter: + +Item filtering +============== + +.. versionadded:: VERSION + +You can filter items that you want to allow for a particular feed by using the +``item_classes`` option in :ref:`feeds options `. Only items of +the specified types will be added to the feed. + +The ``item_classes`` option is implemented by the :class:`~scrapy.extensions.feedexport.ItemFilter` +class, which is the default value of the ``item_filter`` :ref:`feed option `. + +You can create your own custom filtering class by implementing :class:`~scrapy.extensions.feedexport.ItemFilter`'s +method ``accepts`` and taking ``feed_options`` as an argument. + +For instance:: + + class MyCustomFilter: + + def __init__(self, feed_options): + self.feed_options = feed_options + + def accepts(self, item): + if "field1" in item and item["field1"] == "expected_data": + return True + return False + + +You can assign your custom filtering class to the ``item_filter`` :ref:`option of a feed `. +See :setting:`FEEDS` for examples. + +ItemFilter +---------- + +.. autoclass:: scrapy.extensions.feedexport.ItemFilter + :members: Settings @@ -211,15 +314,16 @@ Settings These are the settings used for configuring the feed exports: - * :setting:`FEEDS` (mandatory) - * :setting:`FEED_EXPORT_ENCODING` - * :setting:`FEED_STORE_EMPTY` - * :setting:`FEED_EXPORT_FIELDS` - * :setting:`FEED_EXPORT_INDENT` - * :setting:`FEED_STORAGES` - * :setting:`FEED_STORAGE_FTP_ACTIVE` - * :setting:`FEED_STORAGE_S3_ACL` - * :setting:`FEED_EXPORTERS` +- :setting:`FEEDS` (mandatory) +- :setting:`FEED_EXPORT_ENCODING` +- :setting:`FEED_STORE_EMPTY` +- :setting:`FEED_EXPORT_FIELDS` +- :setting:`FEED_EXPORT_INDENT` +- :setting:`FEED_STORAGES` +- :setting:`FEED_STORAGE_FTP_ACTIVE` +- :setting:`FEED_STORAGE_S3_ACL` +- :setting:`FEED_EXPORTERS` +- :setting:`FEED_EXPORT_BATCH_ITEM_COUNT` .. currentmodule:: scrapy.extensions.feedexport @@ -235,6 +339,7 @@ Default: ``{}`` A dictionary in which every key is a feed URI (or a :class:`pathlib.Path` object) and each value is a nested dictionary containing configuration parameters for the specific feed. + This setting is required for enabling the feed export feature. See :ref:`topics-feed-storage-backends` for supported URI schemes. @@ -246,31 +351,87 @@ For instance:: 'format': 'json', 'encoding': 'utf8', 'store_empty': False, + 'item_classes': [MyItemClass1, 'myproject.items.MyItemClass2'], 'fields': None, 'indent': 4, + 'item_export_kwargs': { + 'export_empty_fields': True, + }, }, '/home/user/documents/items.xml': { 'format': 'xml', 'fields': ['name', 'price'], + 'item_filter': MyCustomFilter1, 'encoding': 'latin1', 'indent': 8, }, pathlib.Path('items.csv'): { 'format': 'csv', 'fields': ['price', 'name'], + 'item_filter': 'myproject.filters.MyCustomFilter2', }, } -The following is a list of the accepted keys and the setting that is used -as a fallback value if that key is not provided for a specific feed definition. +.. _feed-options: + +The following is a list of the accepted keys and the setting that is used +as a fallback value if that key is not provided for a specific feed definition: + +- ``format``: the :ref:`serialization format `. + + This setting is mandatory, there is no fallback value. + +- ``batch_item_count``: falls back to + :setting:`FEED_EXPORT_BATCH_ITEM_COUNT`. + + .. versionadded:: 2.3.0 + +- ``encoding``: falls back to :setting:`FEED_EXPORT_ENCODING`. + +- ``fields``: falls back to :setting:`FEED_EXPORT_FIELDS`. + +- ``item_classes``: list of :ref:`item classes ` to export. + + If undefined or empty, all items are exported. + + .. versionadded:: VERSION + +- ``item_filter``: a :ref:`filter class ` to filter items to export. + + :class:`~scrapy.extensions.feedexport.ItemFilter` is used be default. + + .. versionadded:: VERSION + +- ``indent``: falls back to :setting:`FEED_EXPORT_INDENT`. + +- ``item_export_kwargs``: :class:`dict` with keyword arguments for the corresponding :ref:`item exporter class `. + + .. versionadded:: 2.4.0 + +- ``overwrite``: whether to overwrite the file if it already exists + (``True``) or append to its content (``False``). + + The default value depends on the :ref:`storage backend + `: + + - :ref:`topics-feed-storage-fs`: ``False`` + + - :ref:`topics-feed-storage-ftp`: ``True`` + + .. note:: Some FTP servers may not support appending to files (the + ``APPE`` FTP command). + + - :ref:`topics-feed-storage-s3`: ``True`` (appending `is not supported + `_) + + - :ref:`topics-feed-storage-stdout`: ``False`` (overwriting is not supported) + + .. versionadded:: 2.4.0 + +- ``store_empty``: falls back to :setting:`FEED_STORE_EMPTY`. + +- ``uri_params``: falls back to :setting:`FEED_URI_PARAMS`. -* ``format``: the serialization format to be used for the feed. - See :ref:`topics-feed-format` for possible values. - Mandatory, no fallback setting -* ``encoding``: falls back to :setting:`FEED_EXPORT_ENCODING` -* ``fields``: falls back to :setting:`FEED_EXPORT_FIELDS` -* ``indent``: falls back to :setting:`FEED_EXPORT_INDENT` -* ``store_empty``: falls back to :setting:`FEED_STORE_EMPTY` .. setting:: FEED_EXPORT_ENCODING @@ -298,8 +459,8 @@ Example: ``FEED_EXPORT_FIELDS = ["foo", "bar", "baz"]``. Use FEED_EXPORT_FIELDS option to define fields to export and their order. -When FEED_EXPORT_FIELDS is empty or None (default), Scrapy uses fields -defined in dicts or :class:`~.Item` subclasses a spider is yielding. +When FEED_EXPORT_FIELDS is empty or None (default), Scrapy uses the fields +defined in :ref:`item objects ` yielded by your spider. If an exporter requires a fixed set of fields (this is the case for :ref:`CSV ` export format) and FEED_EXPORT_FIELDS @@ -425,7 +586,117 @@ format in :setting:`FEED_EXPORTERS`. E.g., to disable the built-in CSV exporter 'csv': None, } + +.. setting:: FEED_EXPORT_BATCH_ITEM_COUNT + +FEED_EXPORT_BATCH_ITEM_COUNT +---------------------------- + +.. versionadded:: 2.3.0 + +Default: ``0`` + +If assigned an integer number higher than ``0``, Scrapy generates multiple output files +storing up to the specified number of items in each output file. + +When generating multiple output files, you must use at least one of the following +placeholders in the feed URI to indicate how the different output file names are +generated: + +* ``%(batch_time)s`` - gets replaced by a timestamp when the feed is being created + (e.g. ``2020-03-28T14-45-08.237134``) + +* ``%(batch_id)d`` - gets replaced by the 1-based sequence number of the batch. + + Use :ref:`printf-style string formatting ` to + alter the number format. For example, to make the batch ID a 5-digit + number by introducing leading zeroes as needed, use ``%(batch_id)05d`` + (e.g. ``3`` becomes ``00003``, ``123`` becomes ``00123``). + +For instance, if your settings include:: + + FEED_EXPORT_BATCH_ITEM_COUNT = 100 + +And your :command:`crawl` command line is:: + + scrapy crawl spidername -o "dirname/%(batch_id)d-filename%(batch_time)s.json" + +The command line above can generate a directory tree like:: + + ->projectname + -->dirname + --->1-filename2020-03-28T14-45-08.237134.json + --->2-filename2020-03-28T14-45-09.148903.json + --->3-filename2020-03-28T14-45-10.046092.json + +Where the first and second files contain exactly 100 items. The last one contains +100 items or fewer. + + +.. setting:: FEED_URI_PARAMS + +FEED_URI_PARAMS +--------------- + +Default: ``None`` + +A string with the import path of a function to set the parameters to apply with +:ref:`printf-style string formatting ` to the +feed URI. + +The function signature should be as follows: + +.. function:: uri_params(params, spider) + + Return a :class:`dict` of key-value pairs to apply to the feed URI using + :ref:`printf-style string formatting `. + + :param params: default key-value pairs + + Specifically: + + - ``batch_id``: ID of the file batch. See + :setting:`FEED_EXPORT_BATCH_ITEM_COUNT`. + + If :setting:`FEED_EXPORT_BATCH_ITEM_COUNT` is ``0``, ``batch_id`` + is always ``1``. + + .. versionadded:: 2.3.0 + + - ``batch_time``: UTC date and time, in ISO format with ``:`` + replaced with ``-``. + + See :setting:`FEED_EXPORT_BATCH_ITEM_COUNT`. + + .. versionadded:: 2.3.0 + + - ``time``: ``batch_time``, with microseconds set to ``0``. + :type params: dict + + :param spider: source spider of the feed items + :type spider: scrapy.Spider + +For example, to include the :attr:`name ` of the +source spider in the feed URI: + +#. Define the following function somewhere in your project:: + + # myproject/utils.py + def uri_params(params, spider): + return {**params, 'spider_name': spider.name} + +#. Point :setting:`FEED_URI_PARAMS` to that function in your settings:: + + # myproject/settings.py + FEED_URI_PARAMS = 'myproject.utils.uri_params' + +#. Use ``%(spider_name)s`` in your feed URI:: + + scrapy crawl -o "%(spider_name)s.jl" + + .. _URIs: https://en.wikipedia.org/wiki/Uniform_Resource_Identifier .. _Amazon S3: https://aws.amazon.com/s3/ .. _botocore: https://github.com/boto/botocore .. _Canned ACL: https://docs.aws.amazon.com/AmazonS3/latest/dev/acl-overview.html#canned-acl +.. _Google Cloud Storage: https://cloud.google.com/storage/ diff --git a/docs/topics/item-pipeline.rst b/docs/topics/item-pipeline.rst index c9194caa1..5351a2293 100644 --- a/docs/topics/item-pipeline.rst +++ b/docs/topics/item-pipeline.rst @@ -27,18 +27,22 @@ Each item pipeline component is a Python class that must implement the following .. method:: process_item(self, item, spider) - This method is called for every item pipeline component. :meth:`process_item` - must either: return a dict with data, return an :class:`~scrapy.item.Item` - (or any descendant class) object, return a - :class:`~twisted.internet.defer.Deferred` or raise - :exc:`~scrapy.exceptions.DropItem` exception. Dropped items are no longer - processed by further pipeline components. + This method is called for every item pipeline component. - :param item: the item scraped - :type item: :class:`~scrapy.item.Item` object or a dict + `item` is an :ref:`item object `, see + :ref:`supporting-item-types`. + + :meth:`process_item` must either: return an :ref:`item object `, + return a :class:`~twisted.internet.defer.Deferred` or raise a + :exc:`~scrapy.exceptions.DropItem` exception. + + Dropped items are no longer processed by further pipeline components. + + :param item: the scraped item + :type item: :ref:`item object ` :param spider: the spider which scraped the item - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object Additionally, they may also implement the following methods: @@ -47,14 +51,14 @@ Additionally, they may also implement the following methods: This method is called when the spider is opened. :param spider: the spider which was opened - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: close_spider(self, spider) This method is called when the spider is closed. :param spider: the spider which was closed - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: from_crawler(cls, crawler) @@ -79,19 +83,20 @@ Let's take a look at the following hypothetical pipeline that adjusts the (``price_excludes_vat`` attribute), and drops those items which don't contain a price:: + from itemadapter import ItemAdapter from scrapy.exceptions import DropItem - class PricePipeline: vat_factor = 1.15 def process_item(self, item, spider): - if item.get('price'): - if item.get('price_excludes_vat'): - item['price'] = item['price'] * self.vat_factor + adapter = ItemAdapter(item) + if adapter.get('price'): + if adapter.get('price_excludes_vat'): + adapter['price'] = adapter['price'] * self.vat_factor return item else: - raise DropItem("Missing price in %s" % item) + raise DropItem(f"Missing price in {item}") Write items to a JSON file @@ -103,6 +108,8 @@ format:: import json + from itemadapter import ItemAdapter + class JsonWriterPipeline: def open_spider(self, spider): @@ -112,7 +119,7 @@ format:: self.file.close() def process_item(self, item, spider): - line = json.dumps(dict(item)) + "\n" + line = json.dumps(ItemAdapter(item).asdict()) + "\n" self.file.write(line) return item @@ -131,6 +138,7 @@ The main point of this example is to show how to use :meth:`from_crawler` method and how to clean up the resources properly.:: import pymongo + from itemadapter import ItemAdapter class MongoPipeline: @@ -155,7 +163,7 @@ method and how to clean up the resources properly.:: self.client.close() def process_item(self, item, spider): - self.db[self.collection_name].insert_one(dict(item)) + self.db[self.collection_name].insert_one(ItemAdapter(item).asdict()) return item .. _MongoDB: https://www.mongodb.com/ @@ -177,10 +185,11 @@ item. :: - import scrapy import hashlib from urllib.parse import quote + import scrapy + from itemadapter import ItemAdapter class ScreenshotPipeline: """Pipeline that uses Splash to render screenshot of @@ -189,7 +198,8 @@ item. SPLASH_URL = "http://localhost:8050/render.png?url={}" async def process_item(self, item, spider): - encoded_item_url = quote(item["url"]) + adapter = ItemAdapter(item) + encoded_item_url = quote(adapter["url"]) screenshot_url = self.SPLASH_URL.format(encoded_item_url) request = scrapy.Request(screenshot_url) response = await spider.crawler.engine.download(request, spider) @@ -199,14 +209,14 @@ item. return item # Save screenshot to file, filename will be hash of url. - url = item["url"] + url = adapter["url"] url_hash = hashlib.md5(url.encode("utf8")).hexdigest() - filename = "{}.png".format(url_hash) + filename = f"{url_hash}.png" with open(filename, "wb") as f: f.write(response.body) # Store filename in item. - item["screenshot_filename"] = filename + adapter["screenshot_filename"] = filename return item .. _Splash: https://splash.readthedocs.io/en/stable/ @@ -219,6 +229,7 @@ already processed. Let's say that our items have a unique id, but our spider returns multiples items with the same id:: + from itemadapter import ItemAdapter from scrapy.exceptions import DropItem class DuplicatesPipeline: @@ -227,10 +238,11 @@ returns multiples items with the same id:: self.ids_seen = set() def process_item(self, item, spider): - if item['id'] in self.ids_seen: - raise DropItem("Duplicate item found: %s" % item) + adapter = ItemAdapter(item) + if adapter['id'] in self.ids_seen: + raise DropItem(f"Duplicate item found: {item!r}") else: - self.ids_seen.add(item['id']) + self.ids_seen.add(adapter['id']) return item diff --git a/docs/topics/items.rst b/docs/topics/items.rst index 0941a8a1b..7cd482d07 100644 --- a/docs/topics/items.rst +++ b/docs/topics/items.rst @@ -8,29 +8,156 @@ Items :synopsis: Item and Field classes The main goal in scraping is to extract structured data from unstructured -sources, typically, web pages. Scrapy spiders can return the extracted data -as Python dicts. While convenient and familiar, Python dicts lack structure: -it is easy to make a typo in a field name or return inconsistent data, -especially in a larger project with many spiders. +sources, typically, web pages. :ref:`Spiders ` may return the +extracted data as `items`, Python objects that define key-value pairs. -To define common output data format Scrapy provides the :class:`Item` class. -:class:`Item` objects are simple containers used to collect the scraped data. -They provide an API similar to :class:`dict` API with a convenient syntax -for declaring their available fields. +Scrapy supports :ref:`multiple types of items `. When you create an +item, you may use whichever type of item you want. When you write code that +receives an item, your code should :ref:`work for any item type +`. -Various Scrapy components use extra information provided by Items: -exporters look at declared fields to figure out columns to export, -serialization can be customized using Item fields metadata, :mod:`trackref` -tracks Item instances to help find memory leaks -(see :ref:`topics-leaks-trackrefs`), etc. +.. _item-types: + +Item Types +========== + +Scrapy supports the following types of items, via the `itemadapter`_ library: +:ref:`dictionaries `, :ref:`Item objects `, +:ref:`dataclass objects `, and :ref:`attrs objects `. + +.. _itemadapter: https://github.com/scrapy/itemadapter + +.. _dict-items: + +Dictionaries +------------ + +As an item type, :class:`dict` is convenient and familiar. + +.. _item-objects: + +Item objects +------------ + +:class:`Item` provides a :class:`dict`-like API plus additional features that +make it the most feature-complete item type: + +.. class:: scrapy.item.Item([arg]) +.. class:: scrapy.Item([arg]) + + :class:`Item` objects replicate the standard :class:`dict` API, including + its ``__init__`` method. + + :class:`Item` allows defining field names, so that: + + - :class:`KeyError` is raised when using undefined field names (i.e. + prevents typos going unnoticed) + + - :ref:`Item exporters ` can export all fields by + default even if the first scraped object does not have values for all + of them + + :class:`Item` also allows defining field metadata, which can be used to + :ref:`customize serialization `. + + :mod:`trackref` tracks :class:`Item` objects to help find memory leaks + (see :ref:`topics-leaks-trackrefs`). + + :class:`Item` objects also provide the following additional API members: + + .. automethod:: copy + + .. automethod:: deepcopy + + .. attribute:: fields + + A dictionary containing *all declared fields* for this Item, not only + those populated. The keys are the field names and the values are the + :class:`Field` objects used in the :ref:`Item declaration + `. + +Example:: + + from scrapy.item import Item, Field + + class CustomItem(Item): + one_field = Field() + another_field = Field() + +.. _dataclass-items: + +Dataclass objects +----------------- + +.. versionadded:: 2.2 + +:func:`~dataclasses.dataclass` allows defining item classes with field names, +so that :ref:`item exporters ` can export all fields by +default even if the first scraped object does not have values for all of them. + +Additionally, ``dataclass`` items also allow to: + +* define the type and default value of each defined field. + +* define custom field metadata through :func:`dataclasses.field`, which can be used to + :ref:`customize serialization `. + +They work natively in Python 3.7 or later, or using the `dataclasses +backport`_ in Python 3.6. + +.. _dataclasses backport: https://pypi.org/project/dataclasses/ + +Example:: + + from dataclasses import dataclass + + @dataclass + class CustomItem: + one_field: str + another_field: int + +.. note:: Field types are not enforced at run time. + +.. _attrs-items: + +attr.s objects +-------------- + +.. versionadded:: 2.2 + +:func:`attr.s` allows defining item classes with field names, +so that :ref:`item exporters ` can export all fields by +default even if the first scraped object does not have values for all of them. + +Additionally, ``attr.s`` items also allow to: + +* define the type and default value of each defined field. + +* define custom field :ref:`metadata `, which can be used to + :ref:`customize serialization `. + +In order to use this type, the :doc:`attrs package ` needs to be installed. + +Example:: + + import attr + + @attr.s + class CustomItem: + one_field = attr.ib() + another_field = attr.ib() + + +Working with Item objects +========================= .. _topics-items-declaring: -Declaring Items -=============== +Declaring Item subclasses +------------------------- -Items are declared using a simple class definition syntax and :class:`Field` -objects. Here is an example:: +Item subclasses are declared using a simple class definition syntax and +:class:`Field` objects. Here is an example:: import scrapy @@ -48,10 +175,11 @@ objects. Here is an example:: .. _Django: https://www.djangoproject.com/ .. _Django Models: https://docs.djangoproject.com/en/dev/topics/db/models/ + .. _topics-items-fields: -Item Fields -=========== +Declaring fields +---------------- :class:`Field` objects are used to specify metadata for each field. For example, the serializer function for the ``last_updated`` field illustrated in @@ -72,15 +200,32 @@ It's important to note that the :class:`Field` objects used to declare the item do not stay assigned as class attributes. Instead, they can be accessed through the :attr:`Item.fields` attribute. -Working with Items -================== +.. class:: scrapy.item.Field([arg]) +.. class:: scrapy.Field([arg]) + + The :class:`Field` class is just an alias to the built-in :class:`dict` class and + doesn't provide any extra functionality or attributes. In other words, + :class:`Field` objects are plain-old Python dicts. A separate class is used + to support the :ref:`item declaration syntax ` + based on class attributes. + +.. note:: Field metadata can also be declared for ``dataclass`` and ``attrs`` + items. Please refer to the documentation for `dataclasses.field`_ and + `attr.ib`_ for additional information. + + .. _dataclasses.field: https://docs.python.org/3/library/dataclasses.html#dataclasses.field + .. _attr.ib: https://www.attrs.org/en/stable/api.html#attr.ib + + +Working with Item objects +------------------------- Here are some examples of common tasks performed with items, using the ``Product`` item :ref:`declared above `. You will notice the API is very similar to the :class:`dict` API. Creating items --------------- +'''''''''''''' >>> product = Product(name='Desktop PC', price=1000) >>> print(product) @@ -88,7 +233,7 @@ Product(name='Desktop PC', price=1000) Getting field values --------------------- +'''''''''''''''''''' >>> product['name'] Desktop PC @@ -128,7 +273,7 @@ False Setting field values --------------------- +'''''''''''''''''''' >>> product['last_updated'] = 'today' >>> product['last_updated'] @@ -141,7 +286,7 @@ KeyError: 'Product does not support field: lala' Accessing all populated values ------------------------------- +'''''''''''''''''''''''''''''' To access all populated values, just use the typical :class:`dict` API: @@ -155,7 +300,7 @@ To access all populated values, just use the typical :class:`dict` API: .. _copying-items: Copying items -------------- +''''''''''''' To copy an item, you must first decide whether you want a shallow copy or a deep copy. @@ -174,16 +319,16 @@ If that is not the desired behavior, use a deep copy instead. See :mod:`copy` for more information. To create a shallow copy of an item, you can either call -:meth:`~scrapy.item.Item.copy` on an existing item +:meth:`~scrapy.Item.copy` on an existing item (``product2 = product.copy()``) or instantiate your item class from an existing item (``product2 = Product(product)``). -To create a deep copy, call :meth:`~scrapy.item.Item.deepcopy` instead +To create a deep copy, call :meth:`~scrapy.Item.deepcopy` instead (``product2 = product.deepcopy()``). Other common tasks ------------------- +'''''''''''''''''' Creating dicts from items: @@ -201,8 +346,8 @@ Traceback (most recent call last): KeyError: 'Product does not support field: lala' -Extending Items -=============== +Extending Item subclasses +------------------------- You can extend Items (to add more fields or to change some metadata for some fields) by declaring a subclass of your original Item. @@ -222,39 +367,25 @@ appending more values, or changing existing values, like this:: That adds (or replaces) the ``serializer`` metadata key for the ``name`` field, keeping all the previously existing metadata values. -Item objects -============ -.. class:: Item([arg]) +.. _supporting-item-types: - Return a new Item optionally initialized from the given argument. +Supporting All Item Types +========================= - Items replicate the standard :class:`dict` API, including its ``__init__`` - method, and also provide the following additional API members: +In code that receives an item, such as methods of :ref:`item pipelines +` or :ref:`spider middlewares +`, it is a good practice to use the +:class:`~itemadapter.ItemAdapter` class and the +:func:`~itemadapter.is_item` function to write code that works for +any :ref:`supported item type `: - .. automethod:: copy +.. autoclass:: itemadapter.ItemAdapter - .. automethod:: deepcopy +.. autofunction:: itemadapter.is_item - .. attribute:: fields - A dictionary containing *all declared fields* for this Item, not only - those populated. The keys are the field names and the values are the - :class:`Field` objects used in the :ref:`Item declaration - `. - -Field objects -============= - -.. class:: Field([arg]) - - The :class:`Field` class is just an alias to the built-in :class:`dict` class and - doesn't provide any extra functionality or attributes. In other words, - :class:`Field` objects are plain-old Python dicts. A separate class is used - to support the :ref:`item declaration syntax ` - based on class attributes. - -Other classes related to Item -============================= +Other classes related to items +============================== .. autoclass:: ItemMeta diff --git a/docs/topics/jobs.rst b/docs/topics/jobs.rst index 58601824a..e49f37a2f 100644 --- a/docs/topics/jobs.rst +++ b/docs/topics/jobs.rst @@ -65,7 +65,7 @@ Cookies expiration ------------------ Cookies may expire. So, if you don't resume your spider quickly the requests -scheduled may no longer work. This won't be an issue if you spider doesn't rely +scheduled may no longer work. This won't be an issue if your spider doesn't rely on cookies. @@ -74,10 +74,10 @@ on cookies. Request serialization --------------------- -For persistence to work, :class:`~scrapy.http.Request` objects must be +For persistence to work, :class:`~scrapy.Request` objects must be serializable with :mod:`pickle`, except for the ``callback`` and ``errback`` values passed to their ``__init__`` method, which must be methods of the -running :class:`~scrapy.spiders.Spider` class. +running :class:`~scrapy.Spider` class. If you wish to log the requests that couldn't be serialized, you can set the :setting:`SCHEDULER_DEBUG` setting to ``True`` in the project's settings page. diff --git a/docs/topics/leaks.rst b/docs/topics/leaks.rst index ceb708c7e..477652704 100644 --- a/docs/topics/leaks.rst +++ b/docs/topics/leaks.rst @@ -4,7 +4,7 @@ Debugging memory leaks ====================== -In Scrapy, objects such as Requests, Responses and Items have a finite +In Scrapy, objects such as requests, responses and items have a finite lifetime: they are created, used for a while, and finally destroyed. From all those objects, the Request is probably the one with the longest @@ -27,7 +27,7 @@ Common causes of memory leaks It happens quite often (sometimes by accident, sometimes on purpose) that the Scrapy developer passes objects referenced in Requests (for example, using the -:attr:`~scrapy.http.Request.cb_kwargs` or :attr:`~scrapy.http.Request.meta` +:attr:`~scrapy.Request.cb_kwargs` or :attr:`~scrapy.Request.meta` attributes or the request callback function) and that effectively bounds the lifetime of those referenced objects to the lifetime of the Request. This is, by far, the most common cause of memory leaks in Scrapy projects, and a quite @@ -48,9 +48,9 @@ Too Many Requests? ------------------ By default Scrapy keeps the request queue in memory; it includes -:class:`~scrapy.http.Request` objects and all objects -referenced in Request attributes (e.g. in :attr:`~scrapy.http.Request.cb_kwargs` -and :attr:`~scrapy.http.Request.meta`). +:class:`~scrapy.Request` objects and all objects +referenced in Request attributes (e.g. in :attr:`~scrapy.Request.cb_kwargs` +and :attr:`~scrapy.Request.meta`). While not necessarily a leak, this can take a lot of memory. Enabling :ref:`persistent job queue ` could help keeping memory usage in control. @@ -61,8 +61,8 @@ Debugging memory leaks with ``trackref`` ======================================== :mod:`trackref` is a module provided by Scrapy to debug the most common cases of -memory leaks. It basically tracks the references to all live Requests, -Responses, Item and Selector objects. +memory leaks. It basically tracks the references to all live Request, +Response, Item, Spider and Selector objects. You can enter the telnet console and inspect how many objects (of the classes mentioned above) are currently alive using the ``prefs()`` function which is an @@ -90,11 +90,11 @@ Which objects are tracked? The objects tracked by ``trackrefs`` are all from these classes (and all its subclasses): -* :class:`scrapy.http.Request` +* :class:`scrapy.Request` * :class:`scrapy.http.Response` -* :class:`scrapy.item.Item` -* :class:`scrapy.selector.Selector` -* :class:`scrapy.spiders.Spider` +* :class:`scrapy.Item` +* :class:`scrapy.Selector` +* :class:`scrapy.Spider` A real example -------------- @@ -102,7 +102,7 @@ A real example Let's see a concrete example of a hypothetical case of memory leaks. Suppose we have some spider with a line similar to this one:: - return Request("http://www.somenastyspider.com/product.php?pid=%d" % product_id, + return Request(f"http://www.somenastyspider.com/product.php?pid={product_id}", callback=self.parse, cb_kwargs={'referer': response}) That line is passing a response reference inside a request which effectively @@ -179,7 +179,7 @@ Here are the functions available in the :mod:`~scrapy.utils.trackref` module. :param ignore: if given, all objects from the specified class (or tuple of classes) will be ignored. - :type ignore: class or classes tuple + :type ignore: type or tuple .. function:: get_oldest(class_name) @@ -200,11 +200,10 @@ Debugging memory leaks with muppy ``trackref`` provides a very convenient mechanism for tracking down memory leaks, but it only keeps track of the objects that are more likely to cause -memory leaks (Requests, Responses, Items, and Selectors). However, there are -other cases where the memory leaks could come from other (more or less obscure) -objects. If this is your case, and you can't find your leaks using ``trackref``, -you still have another resource: the muppy library. - +memory leaks. However, there are other cases where the memory leaks could come +from other (more or less obscure) objects. If this is your case, and you can't +find your leaks using ``trackref``, you still have another resource: the muppy +library. You can use muppy from `Pympler`_. diff --git a/docs/topics/link-extractors.rst b/docs/topics/link-extractors.rst index 0162a331a..e12ad45e0 100644 --- a/docs/topics/link-extractors.rst +++ b/docs/topics/link-extractors.rst @@ -10,12 +10,19 @@ The ``__init__`` method of :class:`~scrapy.linkextractors.lxmlhtml.LxmlLinkExtractor` takes settings that determine which links may be extracted. :class:`LxmlLinkExtractor.extract_links ` returns a -list of matching :class:`scrapy.link.Link` objects from a +list of matching :class:`~scrapy.link.Link` objects from a :class:`~scrapy.http.Response` object. Link extractors are used in :class:`~scrapy.spiders.CrawlSpider` spiders -through a set of :class:`~scrapy.spiders.Rule` objects. You can also use link -extractors in regular spiders. +through a set of :class:`~scrapy.spiders.Rule` objects. + +You can also use link extractors in regular spiders. For example, you can instantiate +:class:`LinkExtractor ` into a class +variable in your spider, and use it from your spider callbacks:: + + def parse(self, response): + for link in self.link_extractor.extract_links(response): + yield Request(link.url, callback=self.parse) .. _topics-link-extractors-ref: @@ -46,13 +53,13 @@ LxmlLinkExtractor :param allow: a single regular expression (or list of regular expressions) that the (absolute) urls must match in order to be extracted. If not given (or empty), it will match all links. - :type allow: a regular expression (or list of) + :type allow: str or list :param deny: a single regular expression (or list of regular expressions) that the (absolute) urls must match in order to be excluded (i.e. not extracted). It has precedence over the ``allow`` parameter. If not given (or empty) it won't exclude any links. - :type deny: a regular expression (or list of) + :type deny: str or list :param allow_domains: a single value or a list of string containing domains which will be considered for extracting the links @@ -88,7 +95,7 @@ LxmlLinkExtractor that the link's text must match in order to be extracted. If not given (or empty), it will match all links. If a list of regular expressions is given, the link will be extracted if it matches at least one. - :type restrict_text: a regular expression (or list of) + :type restrict_text: str or list :param tags: a tag or a list of tags to consider when extracting links. Defaults to ``('a', 'area')``. @@ -106,11 +113,11 @@ LxmlLinkExtractor different for requests with canonicalized and raw URLs. If you're using LinkExtractor to follow links it is more robust to keep the default ``canonicalize=False``. - :type canonicalize: boolean + :type canonicalize: bool :param unique: whether duplicate filtering should be applied to extracted links. - :type unique: boolean + :type unique: bool :param process_value: a function which receives each value extracted from the tag and attributes scanned and can modify the value and return a @@ -132,7 +139,7 @@ LxmlLinkExtractor if m: return m.group(1) - :type process_value: callable + :type process_value: collections.abc.Callable :param strip: whether to strip whitespaces from extracted attributes. According to HTML5 standard, leading and trailing whitespaces @@ -141,8 +148,16 @@ LxmlLinkExtractor elements, etc., so LinkExtractor strips space chars by default. Set ``strip=False`` to turn it off (e.g. if you're extracting urls from elements or attributes which allow leading/trailing whitespaces). - :type strip: boolean + :type strip: bool .. automethod:: extract_links +Link +---- + +.. module:: scrapy.link + :synopsis: Link from link extractors + +.. autoclass:: Link + .. _scrapy.linkextractors: https://github.com/scrapy/scrapy/blob/master/scrapy/linkextractors/__init__.py diff --git a/docs/topics/loaders.rst b/docs/topics/loaders.rst index eb804f1db..c0f534493 100644 --- a/docs/topics/loaders.rst +++ b/docs/topics/loaders.rst @@ -7,13 +7,12 @@ Item Loaders .. module:: scrapy.loader :synopsis: Item Loader class -Item Loaders provide a convenient mechanism for populating scraped :ref:`Items -`. Even though Items can be populated using their own -dictionary-like API, Item Loaders provide a much more convenient API for -populating them from a scraping process, by automating some common tasks like -parsing the raw extracted data before assigning it. +Item Loaders provide a convenient mechanism for populating scraped :ref:`items +`. Even though items can be populated directly, Item Loaders provide a +much more convenient API for populating them from a scraping process, by automating +some common tasks like parsing the raw extracted data before assigning it. -In other words, :ref:`Items ` provide the *container* of +In other words, :ref:`items ` provide the *container* of scraped data, while Item Loaders provide the mechanism for *populating* that container. @@ -21,14 +20,18 @@ Item Loaders are designed to provide a flexible, efficient and easy mechanism for extending and overriding different field parsing rules, either by spider, or by source format (HTML, XML, etc) without becoming a nightmare to maintain. +.. note:: Item Loaders are an extension of the itemloaders_ library that make it + easier to work with Scrapy by adding support for + :ref:`responses `. + Using Item Loaders to populate items ==================================== To use an Item Loader, you must first instantiate it. You can either -instantiate it with a dict-like object (e.g. Item or dict) or without one, in -which case an Item is automatically instantiated in the Item Loader ``__init__`` method -using the Item class specified in the :attr:`ItemLoader.default_item_class` -attribute. +instantiate it with an :ref:`item object ` or without one, in which +case an :ref:`item object ` is automatically created in the +Item Loader ``__init__`` method using the :ref:`item ` class +specified in the :attr:`ItemLoader.default_item_class` attribute. Then, you start collecting values into the Item Loader, typically using :ref:`Selectors `. You can add more than one value to @@ -77,6 +80,31 @@ called which actually returns the item populated with the data previously extracted and collected with the :meth:`~ItemLoader.add_xpath`, :meth:`~ItemLoader.add_css`, and :meth:`~ItemLoader.add_value` calls. + +.. _topics-loaders-dataclass: + +Working with dataclass items +============================ + +By default, :ref:`dataclass items ` require all fields to be +passed when created. This could be an issue when using dataclass items with +item loaders: unless a pre-populated item is passed to the loader, fields +will be populated incrementally using the loader's :meth:`~ItemLoader.add_xpath`, +:meth:`~ItemLoader.add_css` and :meth:`~ItemLoader.add_value` methods. + +One approach to overcome this is to define items using the +:func:`~dataclasses.field` function, with a ``default`` argument:: + + from dataclasses import dataclass, field + from typing import Optional + + @dataclass + class InventoryItem: + name: Optional[str] = field(default=None) + price: Optional[float] = field(default=None) + stock: Optional[int] = field(default=None) + + .. _topics-loaders-processors: Input and Output processors @@ -88,7 +116,7 @@ received (through the :meth:`~ItemLoader.add_xpath`, :meth:`~ItemLoader.add_css` :meth:`~ItemLoader.add_value` methods) and the result of the input processor is collected and kept inside the ItemLoader. After collecting all data, the :meth:`ItemLoader.load_item` method is called to populate and get the populated -:class:`~scrapy.item.Item` object. That's when the output processor is +:ref:`item object `. That's when the output processor is called with the data previously collected (and processed using the input processor). The result of the output processor is the final value that gets assigned to the item. @@ -149,28 +177,26 @@ The other thing you need to keep in mind is that the values returned by input processors are collected internally (in lists) and then passed to output processors to populate the fields. -Last, but not least, Scrapy comes with some :ref:`commonly used processors -` built-in for convenience. - +Last, but not least, itemloaders_ comes with some :ref:`commonly used +processors ` built-in for convenience. Declaring Item Loaders ====================== -Item Loaders are declared like Items, by using a class definition syntax. Here -is an example:: +Item Loaders are declared using a class definition syntax. Here is an example:: + from itemloaders.processors import TakeFirst, MapCompose, Join from scrapy.loader import ItemLoader - from scrapy.loader.processors import TakeFirst, MapCompose, Join class ProductLoader(ItemLoader): default_output_processor = TakeFirst() - name_in = MapCompose(unicode.title) + name_in = MapCompose(str.title) name_out = Join() - price_in = MapCompose(unicode.strip) + price_in = MapCompose(str.strip) # ... @@ -192,7 +218,7 @@ output processors to use: in the :ref:`Item Field ` metadata. Here is an example:: import scrapy - from scrapy.loader.processors import Join, MapCompose, TakeFirst + from itemloaders.processors import Join, MapCompose, TakeFirst from w3lib.html import remove_tags def filter_price(value): @@ -211,10 +237,10 @@ metadata. Here is an example:: >>> from scrapy.loader import ItemLoader >>> il = ItemLoader(item=Product()) ->>> il.add_value('name', [u'Welcome to my', u'website']) ->>> il.add_value('price', [u'€', u'1000']) +>>> il.add_value('name', ['Welcome to my', 'website']) +>>> il.add_value('price', ['€', '1000']) >>> il.load_item() -{'name': u'Welcome to my website', 'price': u'1000'} +{'name': 'Welcome to my website', 'price': '1000'} The precedence order, for both input and output processors, is as follows: @@ -273,248 +299,9 @@ There are several ways to modify Item Loader context values: ItemLoader objects ================== -.. class:: ItemLoader([item, selector, response], **kwargs) - - Return a new Item Loader for populating the given Item. If no item is - given, one is instantiated automatically using the class in - :attr:`default_item_class`. - - When instantiated with a ``selector`` or a ``response`` parameters - the :class:`ItemLoader` class provides convenient mechanisms for extracting - data from web pages using :ref:`selectors `. - - :param item: The item instance to populate using subsequent calls to - :meth:`~ItemLoader.add_xpath`, :meth:`~ItemLoader.add_css`, - or :meth:`~ItemLoader.add_value`. - :type item: :class:`~scrapy.item.Item` object - - :param selector: The selector to extract data from, when using the - :meth:`add_xpath` (resp. :meth:`add_css`) or :meth:`replace_xpath` - (resp. :meth:`replace_css`) method. - :type selector: :class:`~scrapy.selector.Selector` object - - :param response: The response used to construct the selector using the - :attr:`default_selector_class`, unless the selector argument is given, - in which case this argument is ignored. - :type response: :class:`~scrapy.http.Response` object - - The item, selector, response and the remaining keyword arguments are - assigned to the Loader context (accessible through the :attr:`context` attribute). - - :class:`ItemLoader` instances have the following methods: - - .. method:: get_value(value, *processors, **kwargs) - - Process the given ``value`` by the given ``processors`` and keyword - arguments. - - Available keyword arguments: - - :param re: a regular expression to use for extracting data from the - given value using :meth:`~scrapy.utils.misc.extract_regex` method, - applied before processors - :type re: str or compiled regex - - Examples: - - >>> from scrapy.loader.processors import TakeFirst - >>> loader.get_value(u'name: foo', TakeFirst(), unicode.upper, re='name: (.+)') - 'FOO` - - .. method:: add_value(field_name, value, *processors, **kwargs) - - Process and then add the given ``value`` for the given field. - - The value is first passed through :meth:`get_value` by giving the - ``processors`` and ``kwargs``, and then passed through the - :ref:`field input processor ` and its result - appended to the data collected for that field. If the field already - contains collected data, the new data is added. - - The given ``field_name`` can be ``None``, in which case values for - multiple fields may be added. And the processed value should be a dict - with field_name mapped to values. - - Examples:: - - loader.add_value('name', u'Color TV') - loader.add_value('colours', [u'white', u'blue']) - loader.add_value('length', u'100') - loader.add_value('name', u'name: foo', TakeFirst(), re='name: (.+)') - loader.add_value(None, {'name': u'foo', 'sex': u'male'}) - - .. method:: replace_value(field_name, value, *processors, **kwargs) - - Similar to :meth:`add_value` but replaces the collected data with the - new value instead of adding it. - .. method:: get_xpath(xpath, *processors, **kwargs) - - Similar to :meth:`ItemLoader.get_value` but receives an XPath instead of a - value, which is used to extract a list of unicode strings from the - selector associated with this :class:`ItemLoader`. - - :param xpath: the XPath to extract data from - :type xpath: str - - :param re: a regular expression to use for extracting data from the - selected XPath region - :type re: str or compiled regex - - Examples:: - - # HTML snippet:

Color TV

- loader.get_xpath('//p[@class="product-name"]') - # HTML snippet:

the price is $1200

- loader.get_xpath('//p[@id="price"]', TakeFirst(), re='the price is (.*)') - - .. method:: add_xpath(field_name, xpath, *processors, **kwargs) - - Similar to :meth:`ItemLoader.add_value` but receives an XPath instead of a - value, which is used to extract a list of unicode strings from the - selector associated with this :class:`ItemLoader`. - - See :meth:`get_xpath` for ``kwargs``. - - :param xpath: the XPath to extract data from - :type xpath: str - - Examples:: - - # HTML snippet:

Color TV

- loader.add_xpath('name', '//p[@class="product-name"]') - # HTML snippet:

the price is $1200

- loader.add_xpath('price', '//p[@id="price"]', re='the price is (.*)') - - .. method:: replace_xpath(field_name, xpath, *processors, **kwargs) - - Similar to :meth:`add_xpath` but replaces collected data instead of - adding it. - - .. method:: get_css(css, *processors, **kwargs) - - Similar to :meth:`ItemLoader.get_value` but receives a CSS selector - instead of a value, which is used to extract a list of unicode strings - from the selector associated with this :class:`ItemLoader`. - - :param css: the CSS selector to extract data from - :type css: str - - :param re: a regular expression to use for extracting data from the - selected CSS region - :type re: str or compiled regex - - Examples:: - - # HTML snippet:

Color TV

- loader.get_css('p.product-name') - # HTML snippet:

the price is $1200

- loader.get_css('p#price', TakeFirst(), re='the price is (.*)') - - .. method:: add_css(field_name, css, *processors, **kwargs) - - Similar to :meth:`ItemLoader.add_value` but receives a CSS selector - instead of a value, which is used to extract a list of unicode strings - from the selector associated with this :class:`ItemLoader`. - - See :meth:`get_css` for ``kwargs``. - - :param css: the CSS selector to extract data from - :type css: str - - Examples:: - - # HTML snippet:

Color TV

- loader.add_css('name', 'p.product-name') - # HTML snippet:

the price is $1200

- loader.add_css('price', 'p#price', re='the price is (.*)') - - .. method:: replace_css(field_name, css, *processors, **kwargs) - - Similar to :meth:`add_css` but replaces collected data instead of - adding it. - - .. method:: load_item() - - Populate the item with the data collected so far, and return it. The - data collected is first passed through the :ref:`output processors - ` to get the final value to assign to each - item field. - - .. method:: nested_xpath(xpath) - - Create a nested loader with an xpath selector. - The supplied selector is applied relative to selector associated - with this :class:`ItemLoader`. The nested loader shares the :class:`Item` - with the parent :class:`ItemLoader` so calls to :meth:`add_xpath`, - :meth:`add_value`, :meth:`replace_value`, etc. will behave as expected. - - .. method:: nested_css(css) - - Create a nested loader with a css selector. - The supplied selector is applied relative to selector associated - with this :class:`ItemLoader`. The nested loader shares the :class:`Item` - with the parent :class:`ItemLoader` so calls to :meth:`add_xpath`, - :meth:`add_value`, :meth:`replace_value`, etc. will behave as expected. - - .. method:: get_collected_values(field_name) - - Return the collected values for the given field. - - .. method:: get_output_value(field_name) - - Return the collected values parsed using the output processor, for the - given field. This method doesn't populate or modify the item at all. - - .. method:: get_input_processor(field_name) - - Return the input processor for the given field. - - .. method:: get_output_processor(field_name) - - Return the output processor for the given field. - - :class:`ItemLoader` instances have the following attributes: - - .. attribute:: item - - The :class:`~scrapy.item.Item` object being parsed by this Item Loader. - This is mostly used as a property so when attempting to override this - value, you may want to check out :attr:`default_item_class` first. - - .. attribute:: context - - The currently active :ref:`Context ` of this - Item Loader. - - .. attribute:: default_item_class - - An Item class (or factory), used to instantiate items when not given in - the ``__init__`` method. - - .. attribute:: default_input_processor - - The default input processor to use for those fields which don't specify - one. - - .. attribute:: default_output_processor - - The default output processor to use for those fields which don't specify - one. - - .. attribute:: default_selector_class - - The class used to construct the :attr:`selector` of this - :class:`ItemLoader`, if only a response is given in the ``__init__`` method. - If a selector is given in the ``__init__`` method this attribute is ignored. - This attribute is sometimes overridden in subclasses. - - .. attribute:: selector - - The :class:`~scrapy.selector.Selector` object to extract data from. - It's either the selector given in the ``__init__`` method or one created from - the response given in the ``__init__`` method using the - :attr:`default_selector_class`. This attribute is meant to be - read-only. +.. autoclass:: scrapy.loader.ItemLoader + :members: + :inherited-members: .. _topics-loaders-nested: @@ -585,7 +372,7 @@ those dashes in the final product names. Here's how you can remove those dashes by reusing and extending the default Product Item Loader (``ProductLoader``):: - from scrapy.loader.processors import MapCompose + from itemloaders.processors import MapCompose from myproject.ItemLoaders import ProductLoader def strip_dashes(x): @@ -598,7 +385,7 @@ Another case where extending Item Loaders can be very helpful is when you have multiple source formats, for example XML and HTML. In the XML version you may want to remove ``CDATA`` occurrences. Here's an example of how to do it:: - from scrapy.loader.processors import MapCompose + from itemloaders.processors import MapCompose from myproject.ItemLoaders import ProductLoader from myproject.utils.xml import remove_cdata @@ -618,156 +405,5 @@ projects. Scrapy only provides the mechanism; it doesn't impose any specific organization of your Loaders collection - that's up to you and your project's needs. -.. _topics-loaders-available-processors: - -Available built-in processors -============================= - -.. module:: scrapy.loader.processors - :synopsis: A collection of processors to use with Item Loaders - -Even though you can use any callable function as input and output processors, -Scrapy provides some commonly used processors, which are described below. Some -of them, like the :class:`MapCompose` (which is typically used as input -processor) compose the output of several functions executed in order, to -produce the final parsed value. - -Here is a list of all built-in processors: - -.. class:: Identity - - The simplest processor, which doesn't do anything. It returns the original - values unchanged. It doesn't receive any ``__init__`` method arguments, nor does it - accept Loader contexts. - - Example: - - >>> from scrapy.loader.processors import Identity - >>> proc = Identity() - >>> proc(['one', 'two', 'three']) - ['one', 'two', 'three'] - -.. class:: TakeFirst - - Returns the first non-null/non-empty value from the values received, - so it's typically used as an output processor to single-valued fields. - It doesn't receive any ``__init__`` method arguments, nor does it accept Loader contexts. - - Example: - - >>> from scrapy.loader.processors import TakeFirst - >>> proc = TakeFirst() - >>> proc(['', 'one', 'two', 'three']) - 'one' - -.. class:: Join(separator=u' ') - - Returns the values joined with the separator given in the ``__init__`` method, which - defaults to ``u' '``. It doesn't accept Loader contexts. - - When using the default separator, this processor is equivalent to the - function: ``u' '.join`` - - Examples: - - >>> from scrapy.loader.processors import Join - >>> proc = Join() - >>> proc(['one', 'two', 'three']) - 'one two three' - >>> proc = Join('
') - >>> proc(['one', 'two', 'three']) - 'one
two
three' - -.. class:: Compose(*functions, **default_loader_context) - - A processor which is constructed from the composition of the given - functions. This means that each input value of this processor is passed to - the first function, and the result of that function is passed to the second - function, and so on, until the last function returns the output value of - this processor. - - By default, stop process on ``None`` value. This behaviour can be changed by - passing keyword argument ``stop_on_none=False``. - - Example: - - >>> from scrapy.loader.processors import Compose - >>> proc = Compose(lambda v: v[0], str.upper) - >>> proc(['hello', 'world']) - 'HELLO' - - Each function can optionally receive a ``loader_context`` parameter. For - those which do, this processor will pass the currently active :ref:`Loader - context ` through that parameter. - - The keyword arguments passed in the ``__init__`` method are used as the default - Loader context values passed to each function call. However, the final - Loader context values passed to functions are overridden with the currently - active Loader context accessible through the :meth:`ItemLoader.context` - attribute. - -.. class:: MapCompose(*functions, **default_loader_context) - - A processor which is constructed from the composition of the given - functions, similar to the :class:`Compose` processor. The difference with - this processor is the way internal results are passed among functions, - which is as follows: - - The input value of this processor is *iterated* and the first function is - applied to each element. The results of these function calls (one for each element) - are concatenated to construct a new iterable, which is then used to apply the - second function, and so on, until the last function is applied to each - value of the list of values collected so far. The output values of the last - function are concatenated together to produce the output of this processor. - - Each particular function can return a value or a list of values, which is - flattened with the list of values returned by the same function applied to - the other input values. The functions can also return ``None`` in which - case the output of that function is ignored for further processing over the - chain. - - This processor provides a convenient way to compose functions that only - work with single values (instead of iterables). For this reason the - :class:`MapCompose` processor is typically used as input processor, since - data is often extracted using the - :meth:`~scrapy.selector.Selector.extract` method of :ref:`selectors - `, which returns a list of unicode strings. - - The example below should clarify how it works: - - >>> def filter_world(x): - ... return None if x == 'world' else x - ... - >>> from scrapy.loader.processors import MapCompose - >>> proc = MapCompose(filter_world, str.upper) - >>> proc(['hello', 'world', 'this', 'is', 'scrapy']) - ['HELLO, 'THIS', 'IS', 'SCRAPY'] - - As with the Compose processor, functions can receive Loader contexts, and - ``__init__`` method keyword arguments are used as default context values. See - :class:`Compose` processor for more info. - -.. class:: SelectJmes(json_path) - - Queries the value using the json path provided to the ``__init__`` method and returns the output. - Requires jmespath (https://github.com/jmespath/jmespath.py) to run. - This processor takes only one input at a time. - - Example: - - >>> from scrapy.loader.processors import SelectJmes, Compose, MapCompose - >>> proc = SelectJmes("foo") #for direct use on lists and dictionaries - >>> proc({'foo': 'bar'}) - 'bar' - >>> proc({'foo': {'bar': 'baz'}}) - {'bar': 'baz'} - - Working with Json: - - >>> import json - >>> proc_single_json_str = Compose(json.loads, SelectJmes("foo")) - >>> proc_single_json_str('{"foo": "bar"}') - 'bar' - >>> proc_json_list = Compose(json.loads, MapCompose(SelectJmes('foo'))) - >>> proc_json_list('[{"foo":"bar"}, {"baz":"tar"}]') - ['bar'] +.. _itemloaders: https://itemloaders.readthedocs.io/en/latest/ +.. _processors: https://itemloaders.readthedocs.io/en/latest/built-in-processors.html diff --git a/docs/topics/logging.rst b/docs/topics/logging.rst index 55065a1a3..dda04dc4d 100644 --- a/docs/topics/logging.rst +++ b/docs/topics/logging.rst @@ -93,7 +93,7 @@ path:: Logging from Spiders ==================== -Scrapy provides a :data:`~scrapy.spiders.Spider.logger` within each Spider +Scrapy provides a :data:`~scrapy.Spider.logger` within each Spider instance, which can be accessed and used like this:: import scrapy @@ -101,7 +101,7 @@ instance, which can be accessed and used like this:: class MySpider(scrapy.Spider): name = 'myspider' - start_urls = ['https://scrapinghub.com'] + start_urls = ['https://scrapy.org'] def parse(self, response): self.logger.info('Parse function called on %s', response.url) @@ -117,7 +117,7 @@ Python logger you want. For example:: class MySpider(scrapy.Spider): name = 'myspider' - start_urls = ['https://scrapinghub.com'] + start_urls = ['https://scrapy.org'] def parse(self, response): logger.info('Parse function called on %s', response.url) @@ -242,6 +242,47 @@ e.g. in the spider's ``__init__`` method:: If you run this spider again then INFO messages from ``scrapy.spidermiddlewares.httperror`` logger will be gone. +You can also filter log records by :class:`~logging.LogRecord` data. For +example, you can filter log records by message content using a substring or +a regular expression. Create a :class:`logging.Filter` subclass +and equip it with a regular expression pattern to +filter out unwanted messages:: + + import logging + import re + + class ContentFilter(logging.Filter): + def filter(self, record): + match = re.search(r'\d{3} [Ee]rror, retrying', record.message) + if match: + return False + +A project-level filter may be attached to the root +handler created by Scrapy, this is a wieldy way to +filter all loggers in different parts of the project +(middlewares, spider, etc.):: + + import logging + import scrapy + + class MySpider(scrapy.Spider): + # ... + def __init__(self, *args, **kwargs): + for handler in logging.root.handlers: + handler.addFilter(ContentFilter()) + +Alternatively, you may choose a specific logger +and hide it without affecting other loggers:: + + import logging + import scrapy + + class MySpider(scrapy.Spider): + # ... + def __init__(self, *args, **kwargs): + logger = logging.getLogger('my_logger') + logger.addFilter(ContentFilter()) + scrapy.utils.log module ======================= diff --git a/docs/topics/media-pipeline.rst b/docs/topics/media-pipeline.rst index 86550d7a4..46bd2859b 100644 --- a/docs/topics/media-pipeline.rst +++ b/docs/topics/media-pipeline.rst @@ -15,7 +15,7 @@ typically you'll either use the Files Pipeline or the Images Pipeline. Both pipelines implement these features: * Avoid re-downloading media that was downloaded recently -* Specifying where to store the media (filesystem directory, Amazon S3 bucket, +* Specifying where to store the media (filesystem directory, FTP server, Amazon S3 bucket, Google Cloud Storage bucket) The Images Pipeline has a few extra functions for processing images: @@ -56,6 +56,8 @@ this: error will be logged and the file won't be present in the ``files`` field. +.. _images-pipeline: + Using the Images Pipeline ========================= @@ -68,14 +70,10 @@ The advantage of using the :class:`ImagesPipeline` for image files is that you can configure some extra functions like generating thumbnails and filtering the images based on their size. -The Images Pipeline uses `Pillow`_ for thumbnailing and normalizing images to -JPEG/RGB format, so you need to install this library in order to use it. -`Python Imaging Library`_ (PIL) should also work in most cases, but it is known -to cause troubles in some setups, so we recommend to use `Pillow`_ instead of -PIL. +The Images Pipeline requires Pillow_ 4.0.0 or greater. It is used for +thumbnailing and normalizing images to JPEG/RGB format. .. _Pillow: https://github.com/python-pillow/Pillow -.. _Python Imaging Library: http://www.pythonware.com/products/pil/ .. _topics-media-pipeline-enabling: @@ -113,25 +111,82 @@ For the Images Pipeline, set the :setting:`IMAGES_STORE` setting:: IMAGES_STORE = '/path/to/valid/dir' +.. _topics-file-naming: + +File Naming +=========== + +Default File Naming +------------------- + +By default, files are stored using an `SHA-1 hash`_ of their URLs for the file names. + +For example, the following image URL:: + + http://www.example.com/image.jpg + +Whose ``SHA-1 hash`` is:: + + 3afec3b4765f8f0a07b78f98c07b83f013567a0a + +Will be downloaded and stored using your chosen :ref:`storage method ` and the following file name:: + + 3afec3b4765f8f0a07b78f98c07b83f013567a0a.jpg + +Custom File Naming +------------------- + +You may wish to use a different calculated file name for saved files. +For example, classifying an image by including meta in the file name. + +Customize file names by overriding the ``file_path`` method of your +media pipeline. + +For example, an image pipeline with image URL:: + + http://www.example.com/product/images/large/front/0000000004166 + +Can be processed into a file name with a condensed hash and the perspective +``front``:: + + 00b08510e4_front.jpg + +By overriding ``file_path`` like this: + +.. code-block:: python + + import hashlib + from os.path import splitext + + def file_path(self, request, response=None, info=None, *, item=None): + image_url_hash = hashlib.shake_256(request.url.encode()).hexdigest(5) + image_perspective = request.url.split('/')[-2] + image_filename = f'{image_url_hash}_{image_perspective}.jpg' + + return image_filename + +.. warning:: + If your custom file name scheme relies on meta data that can vary between + scrapes it may lead to unexpected re-downloading of existing media using + new file names. + + For example, if your custom file name scheme uses a product title and the + site changes an item's product title between scrapes, Scrapy will re-download + the same media using updated file names. + +For more information about the ``file_path`` method, see :ref:`topics-media-pipeline-override`. + +.. _topics-supported-storage: + Supported Storage ================= File system storage ------------------- -The files are stored using a `SHA1 hash`_ of their URLs for the file names. +File system storage will save files to the following path:: -For example, the following image URL:: - - http://www.example.com/image.jpg - -Whose ``SHA1 hash`` is:: - - 3afec3b4765f8f0a07b78f98c07b83f013567a0a - -Will be downloaded and stored in the following file:: - - /full/3afec3b4765f8f0a07b78f98c07b83f013567a0a.jpg + /full/ Where: @@ -141,6 +196,9 @@ Where: * ``full`` is a sub-directory to separate full images from thumbnails (if used). For more info see :ref:`topics-images-thumbnails`. +* ```` is the file name assigned to the file. For more info see :ref:`topics-file-naming`. + + .. _media-pipeline-ftp: FTP server storage @@ -156,7 +214,7 @@ following forms:: ftp://username:password@address:port/path ftp://address:port/path - + If ``username`` and ``password`` are not provided, they are taken from the :setting:`FTP_USER` and :setting:`FTP_PASSWORD` settings respectively. @@ -164,14 +222,17 @@ FTP supports two different connection modes: active or passive. Scrapy uses the passive connection mode by default. To use the active connection mode instead, set the :setting:`FEED_STORAGE_FTP_ACTIVE` setting to ``True``. +.. _media-pipelines-s3: + Amazon S3 storage ----------------- .. setting:: FILES_STORE_S3_ACL .. setting:: IMAGES_STORE_S3_ACL -:setting:`FILES_STORE` and :setting:`IMAGES_STORE` can represent an Amazon S3 -bucket. Scrapy will automatically upload the files to the bucket. +If botocore_ >= 1.4.87 is installed, :setting:`FILES_STORE` and +:setting:`IMAGES_STORE` can represent an Amazon S3 bucket. Scrapy will +automatically upload the files to the bucket. For example, this is a valid :setting:`IMAGES_STORE` value:: @@ -187,8 +248,9 @@ policy:: For more information, see `canned ACLs`_ in the Amazon S3 Developer Guide. -Because Scrapy uses ``botocore`` internally you can also use other S3-like storages. Storages like -self-hosted `Minio`_ or `s3.scality`_. All you need to do is set endpoint option in you Scrapy settings:: +You can also use other S3-like storages. Storages like self-hosted `Minio`_ or +`s3.scality`_. All you need to do is set endpoint option in you Scrapy +settings:: AWS_ENDPOINT_URL = 'http://minio.example.com:9000' @@ -197,14 +259,17 @@ For self-hosting you also might feel the need not to use SSL and not to verify S AWS_USE_SSL = False # or True (None by default) AWS_VERIFY = False # or True (None by default) +.. _botocore: https://github.com/boto/botocore +.. _canned ACLs: https://docs.aws.amazon.com/AmazonS3/latest/dev/acl-overview.html#canned-acl .. _Minio: https://github.com/minio/minio .. _s3.scality: https://s3.scality.com/ -.. _canned ACLs: https://docs.aws.amazon.com/AmazonS3/latest/dev/acl-overview.html#canned-acl + + +.. _media-pipeline-gcs: Google Cloud Storage --------------------- -.. setting:: GCS_PROJECT_ID .. setting:: FILES_STORE_GCS_ACL .. setting:: IMAGES_STORE_GCS_ACL @@ -243,20 +308,22 @@ Usage example .. setting:: IMAGES_URLS_FIELD .. setting:: IMAGES_RESULT_FIELD -In order to use a media pipeline first, :ref:`enable it +In order to use a media pipeline, first :ref:`enable it `. -Then, if a spider returns a dict with the URLs key (``file_urls`` or -``image_urls``, for the Files or Images Pipeline respectively), the pipeline will -put the results under respective key (``files`` or ``images``). +Then, if a spider returns an :ref:`item object ` with the URLs +field (``file_urls`` or ``image_urls``, for the Files or Images Pipeline +respectively), the pipeline will put the results under the respective field +(``files`` or ``images``). -If you prefer to use :class:`~.Item`, then define a custom item with the -necessary fields, like in this example for Images Pipeline:: +When using :ref:`item types ` for which fields are defined beforehand, +you must define both the URLs field and the results field. For example, when +using the images pipeline, items must define both the ``image_urls`` and the +``images`` field. For instance, using the :class:`~scrapy.Item` class:: import scrapy class MyItem(scrapy.Item): - # ... other item fields ... image_urls = scrapy.Field() images = scrapy.Field() @@ -346,9 +413,9 @@ Where: * ```` is the one specified in the :setting:`IMAGES_THUMBS` dictionary keys (``small``, ``big``, etc) -* ```` is the `SHA1 hash`_ of the image url +* ```` is the `SHA-1 hash`_ of the image url -.. _SHA1 hash: https://en.wikipedia.org/wiki/SHA_hash_functions +.. _SHA-1 hash: https://en.wikipedia.org/wiki/SHA_hash_functions Example of image files stored using ``small`` and ``big`` thumbnail names:: @@ -408,15 +475,16 @@ See here the methods that you can override in your custom Files Pipeline: .. class:: FilesPipeline - .. method:: file_path(self, request, response=None, info=None) + .. method:: file_path(self, request, response=None, info=None, *, item=None) This method is called once per downloaded item. It returns the download path of the file originating from the specified :class:`response `. In addition to ``response``, this method receives the original - :class:`request ` and - :class:`info `. + :class:`request `, + :class:`info ` and + :class:`item ` You can override this method to customize the download path of each file. @@ -432,12 +500,18 @@ See here the methods that you can override in your custom Files Pipeline: class MyFilesPipeline(FilesPipeline): - def file_path(self, request, response=None, info=None): + def file_path(self, request, response=None, info=None, *, item=None): return 'files/' + os.path.basename(urlparse(request.url).path) + Similarly, you can use the ``item`` to determine the file path based on some item + property. + By default the :meth:`file_path` method returns ``full/.``. + .. versionadded:: 2.4 + The *item* parameter. + .. method:: FilesPipeline.get_media_requests(item, info) As seen on the workflow, the pipeline will get the URLs of the images to @@ -445,8 +519,11 @@ See here the methods that you can override in your custom Files Pipeline: :meth:`~get_media_requests` method and return a Request for each file URL:: + from itemadapter import ItemAdapter + def get_media_requests(self, item, info): - for file_url in item['file_urls']: + adapter = ItemAdapter(item) + for file_url in adapter['file_urls']: yield scrapy.Request(file_url) Those requests will be processed by the pipeline and, when they have finished @@ -470,7 +547,11 @@ See here the methods that you can override in your custom Files Pipeline: * ``checksum`` - a `MD5 hash`_ of the image contents - * ``status`` - the file status indication. It can be one of the following: + * ``status`` - the file status indication. + + .. versionadded:: 2.2 + + It can be one of the following: * ``downloaded`` - file was downloaded. * ``uptodate`` - file was not downloaded, as it was downloaded recently, @@ -509,13 +590,15 @@ See here the methods that you can override in your custom Files Pipeline: store the downloaded file paths (passed in results) in the ``file_paths`` item field, and we drop the item if it doesn't contain any files:: + from itemadapter import ItemAdapter from scrapy.exceptions import DropItem def item_completed(self, results, item, info): file_paths = [x['path'] for ok, x in results if ok] if not file_paths: raise DropItem("Item contains no files") - item['file_paths'] = file_paths + adapter = ItemAdapter(item) + adapter['file_paths'] = file_paths return item By default, the :meth:`item_completed` method returns the item. @@ -531,15 +614,16 @@ See here the methods that you can override in your custom Images Pipeline: The :class:`ImagesPipeline` is an extension of the :class:`FilesPipeline`, customizing the field names and adding custom behavior for images. - .. method:: file_path(self, request, response=None, info=None) + .. method:: file_path(self, request, response=None, info=None, *, item=None) This method is called once per downloaded item. It returns the download path of the file originating from the specified :class:`response `. In addition to ``response``, this method receives the original - :class:`request ` and - :class:`info `. + :class:`request `, + :class:`info ` and + :class:`item ` You can override this method to customize the download path of each file. @@ -555,12 +639,18 @@ See here the methods that you can override in your custom Images Pipeline: class MyImagesPipeline(ImagesPipeline): - def file_path(self, request, response=None, info=None): + def file_path(self, request, response=None, info=None, *, item=None): return 'files/' + os.path.basename(urlparse(request.url).path) + Similarly, you can use the ``item`` to determine the file path based on some item + property. + By default the :meth:`file_path` method returns ``full/.``. + .. versionadded:: 2.4 + The *item* parameter. + .. method:: ImagesPipeline.get_media_requests(item, info) Works the same way as :meth:`FilesPipeline.get_media_requests` method, @@ -589,8 +679,9 @@ Here is a full example of the Images Pipeline whose methods are exemplified above:: import scrapy - from scrapy.pipelines.images import ImagesPipeline + from itemadapter import ItemAdapter from scrapy.exceptions import DropItem + from scrapy.pipelines.images import ImagesPipeline class MyImagesPipeline(ImagesPipeline): @@ -602,7 +693,8 @@ above:: image_paths = [x['path'] for ok, x in results if ok] if not image_paths: raise DropItem("Item contains no images") - item['image_paths'] = image_paths + adapter = ItemAdapter(item) + adapter['image_paths'] = image_paths return item diff --git a/docs/topics/practices.rst b/docs/topics/practices.rst index cf1de1bd1..732eba587 100644 --- a/docs/topics/practices.rst +++ b/docs/topics/practices.rst @@ -63,7 +63,7 @@ project as example. process = CrawlerProcess(get_project_settings()) # 'followall' is the name of one of the spiders of the project. - process.crawl('followall', domain='scrapinghub.com') + process.crawl('followall', domain='scrapy.org') process.start() # the script will block here until the crawling is finished There's another Scrapy utility that provides more control over the crawling @@ -119,6 +119,7 @@ Here is an example that runs multiple spiders simultaneously: import scrapy from scrapy.crawler import CrawlerProcess + from scrapy.utils.project import get_project_settings class MySpider1(scrapy.Spider): # Your first spider definition @@ -128,7 +129,8 @@ Here is an example that runs multiple spiders simultaneously: # Your second spider definition ... - process = CrawlerProcess() + settings = get_project_settings() + process = CrawlerProcess(settings) process.crawl(MySpider1) process.crawl(MySpider2) process.start() # the script will block here until all crawling jobs are finished @@ -141,6 +143,7 @@ Same example using :class:`~scrapy.crawler.CrawlerRunner`: from twisted.internet import reactor from scrapy.crawler import CrawlerRunner from scrapy.utils.log import configure_logging + from scrapy.utils.project import get_project_settings class MySpider1(scrapy.Spider): # Your first spider definition @@ -151,7 +154,8 @@ Same example using :class:`~scrapy.crawler.CrawlerRunner`: ... configure_logging() - runner = CrawlerRunner() + settings = get_project_settings() + runner = CrawlerRunner(settings) runner.crawl(MySpider1) runner.crawl(MySpider2) d = runner.join() @@ -166,6 +170,7 @@ Same example but running the spiders sequentially by chaining the deferreds: from twisted.internet import reactor, defer from scrapy.crawler import CrawlerRunner from scrapy.utils.log import configure_logging + from scrapy.utils.project import get_project_settings class MySpider1(scrapy.Spider): # Your first spider definition @@ -176,7 +181,8 @@ Same example but running the spiders sequentially by chaining the deferreds: ... configure_logging() - runner = CrawlerRunner() + settings = get_project_settings() + runner = CrawlerRunner(settings) @defer.inlineCallbacks def crawl(): @@ -244,7 +250,7 @@ Here are some tips to keep in mind when dealing with these kinds of sites: super proxy that you can attach your own proxies to. * use a highly distributed downloader that circumvents bans internally, so you can just focus on parsing clean pages. One example of such downloaders is - `Crawlera`_ + `Zyte Smart Proxy Manager`_ If you are still unable to prevent your bot getting banned, consider contacting `commercial support`_. @@ -254,5 +260,5 @@ If you are still unable to prevent your bot getting banned, consider contacting .. _ProxyMesh: https://proxymesh.com/ .. _Google cache: http://www.googleguide.com/cached_pages.html .. _testspiders: https://github.com/scrapinghub/testspiders -.. _Crawlera: https://scrapinghub.com/crawlera .. _scrapoxy: https://scrapoxy.io/ +.. _Zyte Smart Proxy Manager: https://www.zyte.com/smart-proxy-manager/ diff --git a/docs/topics/request-response.rst b/docs/topics/request-response.rst index bbd715766..a6a3daf31 100644 --- a/docs/topics/request-response.rst +++ b/docs/topics/request-response.rst @@ -26,41 +26,43 @@ Request objects .. autoclass:: Request - A :class:`Request` object represents an HTTP request, which is usually - generated in the Spider and executed by the Downloader, and thus generating - a :class:`Response`. - :param url: the URL of this request If the URL is invalid, a :exc:`ValueError` exception is raised. - :type url: string + :type url: str :param callback: the function that will be called with the response of this request (once it's downloaded) as its first parameter. For more information see :ref:`topics-request-response-ref-request-callback-arguments` below. If a Request doesn't specify a callback, the spider's - :meth:`~scrapy.spiders.Spider.parse` method will be used. + :meth:`~scrapy.Spider.parse` method will be used. Note that if exceptions are raised during processing, errback is called instead. - :type callback: callable + :type callback: collections.abc.Callable :param method: the HTTP method of this request. Defaults to ``'GET'``. - :type method: string + :type method: str :param meta: the initial values for the :attr:`Request.meta` attribute. If given, the dict passed in this parameter will be shallow copied. :type meta: dict - :param body: the request body. If a ``unicode`` is passed, then it's encoded to - ``str`` using the ``encoding`` passed (which defaults to ``utf-8``). If - ``body`` is not given, an empty string is stored. Regardless of the - type of this argument, the final value stored will be a ``str`` (never - ``unicode`` or ``None``). - :type body: str or unicode + :param body: the request body. If a string is passed, then it's encoded as + bytes using the ``encoding`` passed (which defaults to ``utf-8``). If + ``body`` is not given, an empty bytes object is stored. Regardless of the + type of this argument, the final value stored will be a bytes object + (never a string or ``None``). + :type body: bytes or str :param headers: the headers of this request. The dict values can be strings (for single valued headers) or lists (for multi-valued headers). If ``None`` is passed as value, the HTTP header will not be sent at all. + + .. caution:: Cookies set via the ``Cookie`` header are not considered by the + :ref:`cookies-mw`. If you need to set cookies for a request, use the + :class:`Request.cookies ` parameter. This is a known + current limitation that is being worked on. + :type headers: dict :param cookies: the request cookies. These can be sent in two forms. @@ -90,7 +92,7 @@ Request objects To create a request that does not send stored cookies and does not store received cookies, set the ``dont_merge_cookies`` key to ``True`` - in :attr:`request.meta `. + in :attr:`request.meta `. Example of a request that sends manually-defined cookies and ignores cookie storage:: @@ -102,12 +104,18 @@ Request objects ) For more info see :ref:`cookies-mw`. + + .. caution:: Cookies set via the ``Cookie`` header are not considered by the + :ref:`cookies-mw`. If you need to set cookies for a request, use the + :class:`Request.cookies ` parameter. This is a known + current limitation that is being worked on. + :type cookies: dict or list :param encoding: the encoding of this request (defaults to ``'utf-8'``). This encoding will be used to percent-encode the URL and to convert the - body to ``str`` (if given as ``unicode``). - :type encoding: string + body to bytes (if given as a string). + :type encoding: str :param priority: the priority of this request (defaults to ``0``). The priority is used by the scheduler to define the order used to process @@ -119,7 +127,7 @@ Request objects the scheduler. This is used when you want to perform an identical request multiple times, to ignore the duplicates filter. Use it with care, or you will get into crawling loops. Default to ``False``. - :type dont_filter: boolean + :type dont_filter: bool :param errback: a function that will be called if any exception was raised while processing the request. This includes pages that failed @@ -131,7 +139,7 @@ Request objects .. versionchanged:: 2.0 The *callback* parameter is no longer required when the *errback* parameter is specified. - :type errback: callable + :type errback: collections.abc.Callable :param flags: Flags sent to the request, can be used for logging or similar purposes. :type flags: list @@ -159,7 +167,7 @@ Request objects .. attribute:: Request.body - A str that contains the request body. + The request body as bytes. This attribute is read-only. To change the body of a Request use :meth:`replace`. @@ -189,6 +197,12 @@ Request objects cloned using the ``copy()`` or ``replace()`` methods, and can also be accessed, in your spider, from the ``response.cb_kwargs`` attribute. + In case of a failure to process the request, this dict can be accessed as + ``failure.request.cb_kwargs`` in the request's errback. For more information, + see :ref:`errback-cb_kwargs`. + + .. autoattribute:: Request.attributes + .. method:: Request.copy() Return a new Request which is a copy of this Request. See also: @@ -204,6 +218,15 @@ Request objects .. automethod:: from_curl + .. automethod:: to_dict + + +Other functions related to requests +----------------------------------- + +.. autofunction:: scrapy.utils.request.request_from_dict + + .. _topics-request-response-ref-request-callback-arguments: Passing additional data to callback functions @@ -312,6 +335,31 @@ errors if needed:: request = failure.request self.logger.error('TimeoutError on %s', request.url) +.. _errback-cb_kwargs: + +Accessing additional data in errback functions +---------------------------------------------- + +In case of a failure to process the request, you may be interested in +accessing arguments to the callback functions so you can process further +based on the arguments in the errback. The following example shows how to +achieve this by using ``Failure.request.cb_kwargs``:: + + def parse(self, response): + request = scrapy.Request('http://www.example.com/index.html', + callback=self.parse_page2, + errback=self.errback_page2, + cb_kwargs=dict(main_url=response.url)) + yield request + + def parse_page2(self, response, main_url): + pass + + def errback_page2(self, failure): + yield dict( + main_url=failure.request.cb_kwargs['main_url'], + ) + .. _topics-request-meta: Request.meta special keys @@ -322,26 +370,26 @@ are some special keys recognized by Scrapy and its built-in extensions. Those are: -* :reqmeta:`dont_redirect` -* :reqmeta:`dont_retry` -* :reqmeta:`handle_httpstatus_list` -* :reqmeta:`handle_httpstatus_all` -* :reqmeta:`dont_merge_cookies` +* :reqmeta:`bindaddress` * :reqmeta:`cookiejar` * :reqmeta:`dont_cache` +* :reqmeta:`dont_merge_cookies` +* :reqmeta:`dont_obey_robotstxt` +* :reqmeta:`dont_redirect` +* :reqmeta:`dont_retry` +* :reqmeta:`download_fail_on_dataloss` +* :reqmeta:`download_latency` +* :reqmeta:`download_maxsize` +* :reqmeta:`download_timeout` +* ``ftp_password`` (See :setting:`FTP_PASSWORD` for more info) +* ``ftp_user`` (See :setting:`FTP_USER` for more info) +* :reqmeta:`handle_httpstatus_all` +* :reqmeta:`handle_httpstatus_list` +* :reqmeta:`max_retry_times` +* :reqmeta:`proxy` * :reqmeta:`redirect_reasons` * :reqmeta:`redirect_urls` -* :reqmeta:`bindaddress` -* :reqmeta:`dont_obey_robotstxt` -* :reqmeta:`download_timeout` -* :reqmeta:`download_maxsize` -* :reqmeta:`download_latency` -* :reqmeta:`download_fail_on_dataloss` -* :reqmeta:`proxy` -* ``ftp_user`` (See :setting:`FTP_USER` for more info) -* ``ftp_password`` (See :setting:`FTP_PASSWORD` for more info) * :reqmeta:`referrer_policy` -* :reqmeta:`max_retry_times` .. reqmeta:: bindaddress @@ -391,9 +439,9 @@ The meta key is used set retry times per request. When initialized, the Stopping the download of a Response =================================== -Raising a :exc:`~scrapy.exceptions.StopDownload` exception from a -:class:`~scrapy.signals.bytes_received` signal handler will stop the -download of a given response. See the following example:: +Raising a :exc:`~scrapy.exceptions.StopDownload` exception from a handler for the +:class:`~scrapy.signals.bytes_received` or :class:`~scrapy.signals.headers_received` +signals will stop the download of a given response. See the following example:: import scrapy @@ -447,7 +495,9 @@ fields with form data from :class:`Response` objects. .. _lxml.html forms: https://lxml.de/lxmlhtml.html#forms -.. class:: FormRequest(url, [formdata, ...]) +.. class:: scrapy.http.request.form.FormRequest +.. class:: scrapy.http.FormRequest +.. class:: scrapy.FormRequest(url, [formdata, ...]) The :class:`FormRequest` class adds a new keyword parameter to the ``__init__`` method. The remaining arguments are the same as for the :class:`Request` class and are @@ -456,7 +506,7 @@ fields with form data from :class:`Response` objects. :param formdata: is a dictionary (or iterable of (key, value) tuples) containing HTML Form data which will be url-encoded and assigned to the body of the request. - :type formdata: dict or iterable of tuples + :type formdata: dict or collections.abc.Iterable The :class:`FormRequest` objects support the following class method in addition to the standard :class:`Request` methods: @@ -488,20 +538,20 @@ fields with form data from :class:`Response` objects. :type response: :class:`Response` object :param formname: if given, the form with name attribute set to this value will be used. - :type formname: string + :type formname: str :param formid: if given, the form with id attribute set to this value will be used. - :type formid: string + :type formid: str :param formxpath: if given, the first form that matches the xpath will be used. - :type formxpath: string + :type formxpath: str :param formcss: if given, the first form that matches the css selector will be used. - :type formcss: string + :type formcss: str :param formnumber: the number of form to use, when the response contains multiple forms. The first one (and also the default) is ``0``. - :type formnumber: integer + :type formnumber: int :param formdata: fields to override in the form data. If a field was already present in the response ``
`` element, its value is @@ -519,23 +569,11 @@ fields with form data from :class:`Response` objects. :param dont_click: If True, the form data will be submitted without clicking in any element. - :type dont_click: boolean + :type dont_click: bool The other parameters of this class method are passed directly to the :class:`FormRequest` ``__init__`` method. - .. versionadded:: 0.10.3 - The ``formname`` parameter. - - .. versionadded:: 0.17 - The ``formxpath`` parameter. - - .. versionadded:: 1.1.0 - The ``formcss`` parameter. - - .. versionadded:: 1.1.0 - The ``formid`` parameter. - Request usage examples ---------------------- @@ -607,12 +645,14 @@ dealing with JSON requests. if :attr:`Request.body` argument is provided this parameter will be ignored. if :attr:`Request.body` argument is not provided and data argument is provided :attr:`Request.method` will be set to ``'POST'`` automatically. - :type data: JSON serializable object + :type data: object :param dumps_kwargs: Parameters that will be passed to underlying :func:`json.dumps` method which is used to serialize data into JSON format. :type dumps_kwargs: dict + .. autoattribute:: JsonRequest.attributes + JsonRequest usage example ------------------------- @@ -634,16 +674,16 @@ Response objects downloaded (by the Downloader) and fed to the Spiders for processing. :param url: the URL of this response - :type url: string + :type url: str :param status: the HTTP status of the response. Defaults to ``200``. - :type status: integer + :type status: int :param headers: the headers of this response. The dict values can be strings (for single valued headers) or lists (for multi-valued headers). :type headers: dict - :param body: the response body. To access the decoded text as str you can use + :param body: the response body. To access the decoded text as a string, use ``response.text`` from an encoding-aware :ref:`Response subclass `, such as :class:`TextResponse`. @@ -656,7 +696,7 @@ Response objects :param request: the initial value of the :attr:`Response.request` attribute. This represents the :class:`Request` that generated this response. - :type request: scrapy.http.Request + :type request: scrapy.Request :param certificate: an object representing the server's SSL certificate. :type certificate: twisted.internet.ssl.Certificate @@ -664,9 +704,19 @@ Response objects :param ip_address: The IP address of the server from which the Response originated. :type ip_address: :class:`ipaddress.IPv4Address` or :class:`ipaddress.IPv6Address` + :param protocol: The protocol that was used to download the response. + For instance: "HTTP/1.0", "HTTP/1.1", "h2" + :type protocol: :class:`str` + + .. versionadded:: 2.0.0 + The ``certificate`` parameter. + .. versionadded:: 2.1.0 The ``ip_address`` parameter. + .. versionadded:: 2.5.0 + The ``protocol`` parameter. + .. attribute:: Response.url A string containing the URL of the response. @@ -691,10 +741,10 @@ Response objects .. attribute:: Response.body - The body of this Response. Keep in mind that Response.body - is always a bytes object. If you want the unicode version use - :attr:`TextResponse.text` (only available in :class:`TextResponse` - and subclasses). + The response body as bytes. + + If you want the body as a string, use :attr:`TextResponse.text` (only + available in :class:`TextResponse` and subclasses). This attribute is read-only. To change the body of a Response use :meth:`replace`. @@ -751,6 +801,8 @@ Response objects .. attribute:: Response.certificate + .. versionadded:: 2.0.0 + A :class:`twisted.internet.ssl.Certificate` object representing the server's SSL certificate. @@ -766,6 +818,17 @@ Response objects handler, i.e. for ``http(s)`` responses. For other handlers, :attr:`ip_address` is always ``None``. + .. attribute:: Response.protocol + + .. versionadded:: 2.5.0 + + The protocol that was used to download the response. + For instance: "HTTP/1.0", "HTTP/1.1" + + This attribute is currently only populated by the HTTP download + handlers, i.e. for ``http(s)`` responses. For other handlers, + :attr:`protocol` is always ``None``. + .. method:: Response.copy() Returns a new Response which is a copy of this Response. @@ -813,18 +876,18 @@ TextResponse objects is the same as for the :class:`Response` class and is not documented here. :param encoding: is a string which contains the encoding to use for this - response. If you create a :class:`TextResponse` object with a unicode - body, it will be encoded using this encoding (remember the body attribute - is always a string). If ``encoding`` is ``None`` (default value), the - encoding will be looked up in the response headers and body instead. - :type encoding: string + response. If you create a :class:`TextResponse` object with a string as + body, it will be converted to bytes encoded using this encoding. If + *encoding* is ``None`` (default), the encoding will be looked up in the + response headers and body instead. + :type encoding: str :class:`TextResponse` objects support the following attributes in addition to the standard :class:`Response` ones: .. attribute:: TextResponse.text - Response body, as unicode. + Response body, as a string. The same as ``response.body.decode(response.encoding)``, but the result is cached after the first call, so you can access @@ -832,9 +895,11 @@ TextResponse objects .. note:: - ``unicode(response.body)`` is not a correct way to convert response - body to unicode: you would be using the system default encoding - (typically ``ascii``) instead of the response encoding. + ``str(response.body)`` is not a correct way to convert the response + body into a string: + + >>> str(b'body') + "b'body'" .. attribute:: TextResponse.encoding @@ -857,7 +922,7 @@ TextResponse objects .. attribute:: TextResponse.selector - A :class:`~scrapy.selector.Selector` instance using the response as + A :class:`~scrapy.Selector` instance using the response as target. The selector is lazily instantiated on first access. :class:`TextResponse` objects support the following methods in addition to diff --git a/docs/topics/scheduler.rst b/docs/topics/scheduler.rst new file mode 100644 index 000000000..57c24b76a --- /dev/null +++ b/docs/topics/scheduler.rst @@ -0,0 +1,34 @@ +.. _topics-scheduler: + +========= +Scheduler +========= + +.. module:: scrapy.core.scheduler + +The scheduler component receives requests from the :ref:`engine ` +and stores them into persistent and/or non-persistent data structures. +It also gets those requests and feeds them back to the engine when it +asks for a next request to be downloaded. + + +Overriding the default scheduler +================================ + +You can use your own custom scheduler class by supplying its full +Python path in the :setting:`SCHEDULER` setting. + + +Minimal scheduler interface +=========================== + +.. autoclass:: BaseScheduler + :members: + + +Default Scrapy scheduler +======================== + +.. autoclass:: Scheduler + :members: + :special-members: __len__ diff --git a/docs/topics/selectors.rst b/docs/topics/selectors.rst index bb46ea80f..574d4568c 100644 --- a/docs/topics/selectors.rst +++ b/docs/topics/selectors.rst @@ -8,14 +8,14 @@ When you're scraping web pages, the most common task you need to perform is to extract data from the HTML source. There are several libraries available to achieve this, such as: - * `BeautifulSoup`_ is a very popular web scraping library among Python - programmers which constructs a Python object based on the structure of the - HTML code and also deals with bad markup reasonably well, but it has one - drawback: it's slow. +- `BeautifulSoup`_ is a very popular web scraping library among Python + programmers which constructs a Python object based on the structure of the + HTML code and also deals with bad markup reasonably well, but it has one + drawback: it's slow. - * `lxml`_ is an XML parsing library (which also parses HTML) with a pythonic - API based on :mod:`~xml.etree.ElementTree`. (lxml is not part of the Python standard - library.) +- `lxml`_ is an XML parsing library (which also parses HTML) with a pythonic + API based on :mod:`~xml.etree.ElementTree`. (lxml is not part of the Python + standard library.) Scrapy comes with its own mechanism for extracting data. They're called selectors because they "select" certain parts of the HTML document specified @@ -48,7 +48,7 @@ Constructing selectors .. highlight:: python -Response objects expose a :class:`~scrapy.selector.Selector` instance +Response objects expose a :class:`~scrapy.Selector` instance on ``.selector`` attribute: >>> response.selector.xpath('//span/text()').get() @@ -62,9 +62,10 @@ more shortcuts: ``response.xpath()`` and ``response.css()``: >>> response.css('span::text').get() 'good' -Scrapy selectors are instances of :class:`~scrapy.selector.Selector` class +Scrapy selectors are instances of :class:`~scrapy.Selector` class constructed by passing either :class:`~scrapy.http.TextResponse` object or -markup as an unicode string (in ``text`` argument). +markup as a string (in ``text`` argument). + Usually there is no need to construct Scrapy selectors manually: ``response`` object is available in Spider callbacks, so in most cases it is more convenient to use ``response.css()`` and ``response.xpath()`` @@ -174,7 +175,7 @@ of ``None``: 'not-found' Instead of using e.g. ``'@src'`` XPath it is possible to query for attributes -using ``.attrib`` property of a :class:`~scrapy.selector.Selector`: +using ``.attrib`` property of a :class:`~scrapy.Selector`: >>> [img.attrib['src'] for img in response.css('img')] ['image1_thumb.jpg', @@ -327,8 +328,9 @@ too. Here's an example: 'Name: My image 5
'] >>> for index, link in enumerate(links): -... args = (index, link.xpath('@href').get(), link.xpath('img/@src').get()) -... print('Link number %d points to url %r and image %r' % args) +... href_xpath = link.xpath('@href').get() +... img_xpath = link.xpath('img/@src').get() +... print(f'Link number {index} points to url {href_xpath!r} and image {img_xpath!r}') Link number 0 points to url 'image1.html' and image 'image1_thumb.jpg' Link number 1 points to url 'image2.html' and image 'image2_thumb.jpg' Link number 2 points to url 'image3.html' and image 'image3_thumb.jpg' @@ -381,9 +383,9 @@ ID, or when selecting an unique element on a page): Using selectors with regular expressions ---------------------------------------- -:class:`~scrapy.selector.Selector` also has a ``.re()`` method for extracting +:class:`~scrapy.Selector` also has a ``.re()`` method for extracting data using regular expressions. However, unlike using ``.xpath()`` or -``.css()`` methods, ``.re()`` returns a list of unicode strings. So you +``.css()`` methods, ``.re()`` returns a list of strings. So you can't construct nested ``.re()`` calls. Here's an example used to extract image names from the :ref:`HTML code @@ -462,10 +464,10 @@ effectively. If you are not much familiar with XPath yet, you may want to take a look first at this `XPath tutorial`_. .. note:: - Some of the tips are based on `this post from ScrapingHub's blog`_. + Some of the tips are based on `this post from Zyte's blog`_. .. _`XPath tutorial`: http://www.zvon.org/comp/r/tut-XPath_1.html -.. _`this post from ScrapingHub's blog`: https://blog.scrapinghub.com/2014/07/17/xpath-tips-from-the-web-scraping-trenches/ +.. _this post from Zyte's blog: https://www.zyte.com/blog/xpath-tips-from-the-web-scraping-trenches/ .. _topics-selectors-relative-xpaths: @@ -734,7 +736,7 @@ The ``test()`` function, for example, can prove quite useful when XPath's Example selecting links in list item with a "class" attribute ending with a digit: >>> from scrapy import Selector ->>> doc = u""" +>>> doc = """ ...
...
    ...
  • first item
    • @@ -765,7 +767,7 @@ extracting text elements for example. Example extracting microdata (sample content taken from https://schema.org/Product) with groups of itemscopes and corresponding itemprops:: - >>> doc = u""" + >>> doc = """ ...
    ... Kenmore White 17" Microwave ... Kenmore 17" Microwave @@ -821,7 +823,7 @@ with groups of itemscopes and corresponding itemprops:: ... props = scope.xpath(''' ... set:difference(./descendant::*/@itemprop, ... .//*[@itemscope]/*/@itemprop)''') - ... print(" properties: %s" % (props.getall())) + ... print(f" properties: {props.getall()}") ... print("") current scope: ['http://schema.org/Product'] @@ -989,7 +991,7 @@ a :class:`~scrapy.http.HtmlResponse` object like this:: sel.xpath("//h1") 2. Extract the text of all ``

    `` elements from an HTML response body, - returning a list of unicode strings:: + returning a list of strings:: sel.xpath("//h1").getall() # this includes the h1 tag sel.xpath("//h1/text()").getall() # this excludes the h1 tag diff --git a/docs/topics/settings.rst b/docs/topics/settings.rst index f06d9db3c..1290b4a5e 100644 --- a/docs/topics/settings.rst +++ b/docs/topics/settings.rst @@ -67,7 +67,7 @@ Example:: Spiders (See the :ref:`topics-spiders` chapter for reference) can define their own settings that will take precedence and override the project ones. They can -do so by setting their :attr:`~scrapy.spiders.Spider.custom_settings` attribute:: +do so by setting their :attr:`~scrapy.Spider.custom_settings` attribute:: class MySpider(scrapy.Spider): name = 'myspider' @@ -98,6 +98,32 @@ class. The global defaults are located in the ``scrapy.settings.default_settings`` module and documented in the :ref:`topics-settings-ref` section. + +Import paths and classes +======================== + +.. versionadded:: 2.4.0 + +When a setting references a callable object to be imported by Scrapy, such as a +class or a function, there are two different ways you can specify that object: + +- As a string containing the import path of that object + +- As the object itself + +For example:: + + from mybot.pipelines.validate import ValidateMyItem + ITEM_PIPELINES = { + # passing the classname... + ValidateMyItem: 300, + # ...equals passing the class path + 'mybot.pipelines.validate.ValidateMyItem': 300, + } + +.. note:: Passing non-callable objects is not supported. + + How to access settings ====================== @@ -110,13 +136,13 @@ In a spider, the settings are available through ``self.settings``:: start_urls = ['http://example.com'] def parse(self, response): - print("Existing settings: %s" % self.settings.attributes.keys()) + print(f"Existing settings: {self.settings.attributes.keys()}") .. note:: The ``settings`` attribute is set in the base Spider class after the spider is initialized. If you want to use the settings before the initialization (e.g., in your spider's ``__init__()`` method), you'll need to override the - :meth:`~scrapy.spiders.Spider.from_crawler` method. + :meth:`~scrapy.Spider.from_crawler` method. Settings can be accessed through the :attr:`scrapy.crawler.Crawler.settings` attribute of the Crawler that is passed to ``from_crawler`` method in @@ -216,6 +242,32 @@ Default: ``None`` The name of the region associated with the AWS client. +.. setting:: ASYNCIO_EVENT_LOOP + +ASYNCIO_EVENT_LOOP +------------------ + +Default: ``None`` + +Import path of a given ``asyncio`` event loop class. + +If the asyncio reactor is enabled (see :setting:`TWISTED_REACTOR`) this setting can be used to specify the +asyncio event loop to be used with it. Set the setting to the import path of the +desired asyncio event loop class. If the setting is set to ``None`` the default asyncio +event loop will be used. + +If you are installing the asyncio reactor manually using the :func:`~scrapy.utils.reactor.install_reactor` +function, you can use the ``event_loop_path`` parameter to indicate the import path of the event loop +class to be used. + +Note that the event loop class must inherit from :class:`asyncio.AbstractEventLoop`. + +.. caution:: Please be aware that, when using a non-default event loop + (either defined via :setting:`ASYNCIO_EVENT_LOOP` or installed with + :func:`~scrapy.utils.reactor.install_reactor`), Scrapy will call + :func:`asyncio.set_event_loop`, which will set the specified event loop + as the current loop for the current OS thread. + .. setting:: BOT_NAME BOT_NAME @@ -236,8 +288,8 @@ CONCURRENT_ITEMS Default: ``100`` -Maximum number of concurrent items (per response) to process in parallel in the -Item Processor (also known as the :ref:`Item Pipeline `). +Maximum number of concurrent items (per response) to process in parallel in +:ref:`item pipelines `. .. setting:: CONCURRENT_REQUESTS @@ -286,7 +338,7 @@ is non-zero, download delay is enforced per IP, not per domain. DEFAULT_ITEM_CLASS ------------------ -Default: ``'scrapy.item.Item'`` +Default: ``'scrapy.Item'`` The default class that will be used for instantiating items in the :ref:`the Scrapy shell `. @@ -306,6 +358,11 @@ Default:: The default headers used for Scrapy HTTP Requests. They're populated in the :class:`~scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware`. +.. caution:: Cookies set via the ``Cookie`` header are not considered by the + :ref:`cookies-mw`. If you need to set cookies for a request, use the + :class:`Request.cookies ` parameter. This is a known + current limitation that is being worked on. + .. setting:: DEPTH_LIMIT DEPTH_LIMIT @@ -327,8 +384,8 @@ Default: ``0`` Scope: ``scrapy.spidermiddlewares.depth.DepthMiddleware`` -An integer that is used to adjust the :attr:`~scrapy.http.Request.priority` of -a :class:`~scrapy.http.Request` based on its depth. +An integer that is used to adjust the :attr:`~scrapy.Request.priority` of +a :class:`~scrapy.Request` based on its depth. The priority of a request is adjusted as follows:: @@ -469,7 +526,7 @@ necessary to access certain HTTPS websites: for example, you may need to use ``'DEFAULT:!DH'`` for a website with weak DH parameters or enable a specific cipher that is not included in ``DEFAULT`` if a website requires it. -.. _OpenSSL cipher list format: https://www.openssl.org/docs/manmaster/man1/ciphers.html#CIPHER-LIST-FORMAT +.. _OpenSSL cipher list format: https://www.openssl.org/docs/manmaster/man1/openssl-ciphers.html#CIPHER-LIST-FORMAT .. setting:: DOWNLOADER_CLIENT_TLS_METHOD @@ -600,6 +657,7 @@ DOWNLOAD_HANDLERS_BASE Default:: { + 'data': 'scrapy.core.downloader.handlers.datauri.DataURIDownloadHandler', 'file': 'scrapy.core.downloader.handlers.file.FileDownloadHandler', 'http': 'scrapy.core.downloader.handlers.http.HTTPDownloadHandler', 'https': 'scrapy.core.downloader.handlers.http.HTTPDownloadHandler', @@ -620,6 +678,45 @@ handler (without replacement), place this in your ``settings.py``:: 'ftp': None, } +.. _http2: + +The default HTTPS handler uses HTTP/1.1. To use HTTP/2: + +#. Install ``Twisted[http2]>=17.9.0`` to install the packages required to + enable HTTP/2 support in Twisted. + +#. Update :setting:`DOWNLOAD_HANDLERS` as follows:: + + DOWNLOAD_HANDLERS = { + 'https': 'scrapy.core.downloader.handlers.http2.H2DownloadHandler', + } + +.. warning:: + + HTTP/2 support in Scrapy is experimental, and not yet recommended for + production environments. Future Scrapy versions may introduce related + changes without a deprecation period or warning. + +.. note:: + + Known limitations of the current HTTP/2 implementation of Scrapy include: + + - No support for HTTP/2 Cleartext (h2c), since no major browser supports + HTTP/2 unencrypted (refer `http2 faq`_). + + - No setting to specify a maximum `frame size`_ larger than the default + value, 16384. Connections to servers that send a larger frame will + fail. + + - No support for `server pushes`_, which are ignored. + + - No support for the :signal:`bytes_received` and + :signal:`headers_received` signals. + +.. _frame size: https://tools.ietf.org/html/rfc7540#section-4.2 +.. _http2 faq: https://http2.github.io/faq/#does-http2-require-encryption +.. _server pushes: https://tools.ietf.org/html/rfc7540#section-8.2 + .. setting:: DOWNLOAD_TIMEOUT DOWNLOAD_TIMEOUT @@ -697,6 +794,15 @@ Optionally, this can be set per-request basis by using the If :setting:`RETRY_ENABLED` is ``True`` and this setting is set to ``True``, the ``ResponseFailed([_DataLoss])`` failure will be retried as usual. +.. warning:: + + This setting is ignored by the + :class:`~scrapy.core.downloader.handlers.http2.H2DownloadHandler` + download handler (see :setting:`DOWNLOAD_HANDLERS`). In case of a data loss + error, the corresponding HTTP/2 connection may be corrupted, affecting other + requests that use the same connection; hence, a ``ResponseFailed([InvalidBodyLengthError])`` + failure is always raised for every request that was using that connection. + .. setting:: DUPEFILTER_CLASS DUPEFILTER_CLASS @@ -710,14 +816,14 @@ The default (``RFPDupeFilter``) filters based on request fingerprint using the ``scrapy.utils.request.request_fingerprint`` function. In order to change the way duplicates are checked you could subclass ``RFPDupeFilter`` and override its ``request_fingerprint`` method. This method should accept -scrapy :class:`~scrapy.http.Request` object and return its fingerprint +scrapy :class:`~scrapy.Request` object and return its fingerprint (a string). You can disable filtering of duplicate requests by setting :setting:`DUPEFILTER_CLASS` to ``'scrapy.dupefilters.BaseDupeFilter'``. Be very careful about this however, because you can get into crawling loops. It's usually a better idea to set the ``dont_filter`` parameter to -``True`` on the specific :class:`~scrapy.http.Request` that should not be +``True`` on the specific :class:`~scrapy.Request` that should not be filtered. .. setting:: DUPEFILTER_DEBUG @@ -786,6 +892,14 @@ The Feed Temp dir allows you to set a custom folder to save crawler temporary files before uploading with :ref:`FTP feed storage ` and :ref:`Amazon S3 `. +.. setting:: FEED_STORAGE_GCS_ACL + +FEED_STORAGE_GCS_ACL +-------------------- + +The Access Control List (ACL) used when storing items to :ref:`Google Cloud Storage `. +For more information on how to set this value, please refer to the column *JSON API* in `Google Cloud documentation `_. + .. setting:: FTP_PASSIVE_MODE FTP_PASSIVE_MODE @@ -825,6 +939,15 @@ Default: ``"anonymous"`` The username to use for FTP connections when there is no ``"ftp_user"`` in ``Request`` meta. +.. setting:: GCS_PROJECT_ID + +GCS_PROJECT_ID +----------------- + +Default: ``None`` + +The Project ID that will be used when storing data on `Google Cloud Storage`_. + .. setting:: ITEM_PIPELINES ITEM_PIPELINES @@ -1013,8 +1136,6 @@ See :ref:`topics-extensions-ref-memusage`. MEMUSAGE_CHECK_INTERVAL_SECONDS ------------------------------- -.. versionadded:: 1.1 - Default: ``60.0`` Scope: ``scrapy.extensions.memusage`` @@ -1116,20 +1237,6 @@ Adjust redirect request priority relative to original request: - **a positive priority adjust (default) means higher priority.** - a negative priority adjust means lower priority. -.. setting:: RETRY_PRIORITY_ADJUST - -RETRY_PRIORITY_ADJUST ---------------------- - -Default: ``-1`` - -Scope: ``scrapy.downloadermiddlewares.retry.RetryMiddleware`` - -Adjust retry request priority relative to original request: - -- a positive priority adjust means higher priority. -- **a negative priority adjust (default) means lower priority.** - .. setting:: ROBOTSTXT_OBEY ROBOTSTXT_OBEY @@ -1177,7 +1284,8 @@ SCHEDULER Default: ``'scrapy.core.scheduler.Scheduler'`` -The scheduler to use for crawling. +The scheduler class to be used for crawling. +See the :ref:`topics-scheduler` topic for details. .. setting:: SCHEDULER_DEBUG @@ -1295,8 +1403,6 @@ The class that will be used for loading spiders, which must implement the SPIDER_LOADER_WARN_ONLY ----------------------- -.. versionadded:: 1.3.3 - Default: ``False`` By default, when Scrapy tries to import spider classes from :setting:`SPIDER_MODULES`, @@ -1517,7 +1623,7 @@ Default: ``2083`` Scope: ``spidermiddlewares.urllength`` The maximum URL length to allow for crawled URLs. For more information about -the default value for this setting see: https://boutell.com/newfaq/misc/urllength.html +the default value for this setting see: https://support.microsoft.com/en-us/topic/maximum-url-length-is-2-083-characters-in-internet-explorer-174e7c8a-6666-f4e0-6fd6-908b53c12246 .. setting:: USER_AGENT @@ -1540,7 +1646,7 @@ case to see how to enable and use them. .. settingslist:: - .. _Amazon web services: https://aws.amazon.com/ .. _breadth-first order: https://en.wikipedia.org/wiki/Breadth-first_search .. _depth-first order: https://en.wikipedia.org/wiki/Depth-first_search +.. _Google Cloud Storage: https://cloud.google.com/storage/ diff --git a/docs/topics/shell.rst b/docs/topics/shell.rst index 0f46f1c87..8c90a506c 100644 --- a/docs/topics/shell.rst +++ b/docs/topics/shell.rst @@ -95,20 +95,21 @@ convenience. Available Shortcuts ------------------- - * ``shelp()`` - print a help with the list of available objects and shortcuts +- ``shelp()`` - print a help with the list of available objects and + shortcuts - * ``fetch(url[, redirect=True])`` - fetch a new response from the given - URL and update all related objects accordingly. You can optionaly ask for - HTTP 3xx redirections to not be followed by passing ``redirect=False`` +- ``fetch(url[, redirect=True])`` - fetch a new response from the given URL + and update all related objects accordingly. You can optionaly ask for HTTP + 3xx redirections to not be followed by passing ``redirect=False`` - * ``fetch(request)`` - fetch a new response from the given request and - update all related objects accordingly. +- ``fetch(request)`` - fetch a new response from the given request and update + all related objects accordingly. - * ``view(response)`` - open the given response in your local web browser, for - inspection. This will add a `\ tag`_ to the response body in order - for external links (such as images and style sheets) to display properly. - Note, however, that this will create a temporary file in your computer, - which won't be removed automatically. +- ``view(response)`` - open the given response in your local web browser, for + inspection. This will add a `\ tag`_ to the response body in order + for external links (such as images and style sheets) to display properly. + Note, however, that this will create a temporary file in your computer, + which won't be removed automatically. .. _ tag: https://developer.mozilla.org/en-US/docs/Web/HTML/Element/base @@ -117,26 +118,26 @@ Available Scrapy objects The Scrapy shell automatically creates some convenient objects from the downloaded page, like the :class:`~scrapy.http.Response` object and the -:class:`~scrapy.selector.Selector` objects (for both HTML and XML +:class:`~scrapy.Selector` objects (for both HTML and XML content). Those objects are: - * ``crawler`` - the current :class:`~scrapy.crawler.Crawler` object. +- ``crawler`` - the current :class:`~scrapy.crawler.Crawler` object. - * ``spider`` - the Spider which is known to handle the URL, or a - :class:`~scrapy.spiders.Spider` object if there is no spider found for - the current URL +- ``spider`` - the Spider which is known to handle the URL, or a + :class:`~scrapy.Spider` object if there is no spider found for the + current URL - * ``request`` - a :class:`~scrapy.http.Request` object of the last fetched - page. You can modify this request using :meth:`~scrapy.http.Request.replace` - or fetch a new request (without leaving the shell) using the ``fetch`` - shortcut. +- ``request`` - a :class:`~scrapy.Request` object of the last fetched + page. You can modify this request using + :meth:`~scrapy.Request.replace` or fetch a new request (without + leaving the shell) using the ``fetch`` shortcut. - * ``response`` - a :class:`~scrapy.http.Response` object containing the last - fetched page +- ``response`` - a :class:`~scrapy.http.Response` object containing the last + fetched page - * ``settings`` - the current :ref:`Scrapy settings ` +- ``settings`` - the current :ref:`Scrapy settings ` Example of shell session ======================== diff --git a/docs/topics/signals.rst b/docs/topics/signals.rst index fe4fb0834..a67cc1879 100644 --- a/docs/topics/signals.rst +++ b/docs/topics/signals.rst @@ -151,11 +151,11 @@ item_scraped This signal supports returning deferreds from its handlers. - :param item: the item scraped - :type item: dict or :class:`~scrapy.item.Item` object + :param item: the scraped item + :type item: :ref:`item object ` :param spider: the spider which scraped the item - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object :param response: the response from where the item was scraped :type response: :class:`~scrapy.http.Response` object @@ -172,10 +172,10 @@ item_dropped This signal supports returning deferreds from its handlers. :param item: the item dropped from the :ref:`topics-item-pipeline` - :type item: dict or :class:`~scrapy.item.Item` object + :type item: :ref:`item object ` :param spider: the spider which scraped the item - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object :param response: the response from where the item was dropped :type response: :class:`~scrapy.http.Response` object @@ -196,14 +196,14 @@ item_error This signal supports returning deferreds from its handlers. - :param item: the item dropped from the :ref:`topics-item-pipeline` - :type item: dict or :class:`~scrapy.item.Item` object + :param item: the item that caused the error in the :ref:`topics-item-pipeline` + :type item: :ref:`item object ` :param response: the response being processed when the exception was raised :type response: :class:`~scrapy.http.Response` object :param spider: the spider which raised the exception - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object :param failure: the exception raised :type failure: twisted.python.failure.Failure @@ -223,7 +223,7 @@ spider_closed This signal supports returning deferreds from its handlers. :param spider: the spider which has been closed - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object :param reason: a string which describes the reason why the spider was closed. If it was closed because the spider has completed scraping, the reason @@ -247,7 +247,7 @@ spider_opened This signal supports returning deferreds from its handlers. :param spider: the spider which has been opened - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object spider_idle ~~~~~~~~~~~ @@ -268,10 +268,17 @@ spider_idle You may raise a :exc:`~scrapy.exceptions.DontCloseSpider` exception to prevent the spider from being closed. + Alternatively, you may raise a :exc:`~scrapy.exceptions.CloseSpider` + exception to provide a custom spider closing reason. An + idle handler is the perfect place to put some code that assesses + the final spider results and update the final closing reason + accordingly (e.g. setting it to 'too_few_results' instead of + 'finished'). + This signal does not support returning deferreds from its handlers. :param spider: the spider which has gone idle - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. note:: Scheduling some requests in your :signal:`spider_idle` handler does **not** guarantee that it can prevent the spider from being closed, @@ -296,7 +303,7 @@ spider_error :type response: :class:`~scrapy.http.Response` object :param spider: the spider which raised the exception - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object Request signals --------------- @@ -307,16 +314,16 @@ request_scheduled .. signal:: request_scheduled .. function:: request_scheduled(request, spider) - Sent when the engine schedules a :class:`~scrapy.http.Request`, to be + Sent when the engine schedules a :class:`~scrapy.Request`, to be downloaded later. This signal does not support returning deferreds from its handlers. :param request: the request that reached the scheduler - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param spider: the spider that yielded the request - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object request_dropped ~~~~~~~~~~~~~~~ @@ -324,16 +331,16 @@ request_dropped .. signal:: request_dropped .. function:: request_dropped(request, spider) - Sent when a :class:`~scrapy.http.Request`, scheduled by the engine to be + Sent when a :class:`~scrapy.Request`, scheduled by the engine to be downloaded later, is rejected by the scheduler. This signal does not support returning deferreds from its handlers. :param request: the request that reached the scheduler - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param spider: the spider that yielded the request - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object request_reached_downloader ~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -341,15 +348,15 @@ request_reached_downloader .. signal:: request_reached_downloader .. function:: request_reached_downloader(request, spider) - Sent when a :class:`~scrapy.http.Request` reached downloader. + Sent when a :class:`~scrapy.Request` reached downloader. This signal does not support returning deferreds from its handlers. :param request: the request that reached downloader - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param spider: the spider that yielded the request - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object request_left_downloader ~~~~~~~~~~~~~~~~~~~~~~~ @@ -359,16 +366,16 @@ request_left_downloader .. versionadded:: 2.0 - Sent when a :class:`~scrapy.http.Request` leaves the downloader, even in case of + Sent when a :class:`~scrapy.Request` leaves the downloader, even in case of failure. This signal does not support returning deferreds from its handlers. :param request: the request that reached the downloader - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param spider: the spider that yielded the request - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object bytes_received ~~~~~~~~~~~~~~ @@ -384,22 +391,52 @@ bytes_received a possible scenario for a 25 kb response would be two signals fired with 10 kb of data, and a final one with 5 kb of data. + Handlers for this signal can stop the download of a response while it + is in progress by raising the :exc:`~scrapy.exceptions.StopDownload` + exception. Please refer to the :ref:`topics-stop-response-download` topic + for additional information and examples. + This signal does not support returning deferreds from its handlers. :param data: the data received by the download handler :type data: :class:`bytes` object :param request: the request that generated the download - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param spider: the spider associated with the response - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object -.. note:: Handlers of this signal can stop the download of a response while it +headers_received +~~~~~~~~~~~~~~~~ + +.. versionadded:: 2.5 + +.. signal:: headers_received +.. function:: headers_received(headers, request, spider) + + Sent by the HTTP 1.1 and S3 download handlers when the response headers are + available for a given request, before downloading any additional content. + + Handlers for this signal can stop the download of a response while it is in progress by raising the :exc:`~scrapy.exceptions.StopDownload` exception. Please refer to the :ref:`topics-stop-response-download` topic for additional information and examples. + This signal does not support returning deferreds from its handlers. + + :param headers: the headers received by the download handler + :type headers: :class:`scrapy.http.headers.Headers` object + + :param body_length: expected size of the response body, in bytes + :type body_length: `int` + + :param request: the request that generated the download + :type request: :class:`~scrapy.Request` object + + :param spider: the spider associated with the response + :type spider: :class:`~scrapy.Spider` object + Response signals ---------------- @@ -418,10 +455,15 @@ response_received :type response: :class:`~scrapy.http.Response` object :param request: the request that generated the response - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param spider: the spider for which the response is intended - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object + +.. note:: The ``request`` argument might not contain the original request that + reached the downloader, if a :ref:`topics-downloader-middleware` modifies + the :class:`~scrapy.http.Response` object and sets a specific ``request`` + attribute. response_downloaded ~~~~~~~~~~~~~~~~~~~ @@ -437,7 +479,7 @@ response_downloaded :type response: :class:`~scrapy.http.Response` object :param request: the request that generated the response - :type request: :class:`~scrapy.http.Request` object + :type request: :class:`~scrapy.Request` object :param spider: the spider for which the response is intended - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object diff --git a/docs/topics/spider-middleware.rst b/docs/topics/spider-middleware.rst index d49a2209d..f0158dc41 100644 --- a/docs/topics/spider-middleware.rst +++ b/docs/topics/spider-middleware.rst @@ -93,7 +93,7 @@ object gives you access, for example, to the :ref:`settings `. :type response: :class:`~scrapy.http.Response` object :param spider: the spider for which this response is intended - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: process_spider_output(response, result, spider) @@ -102,20 +102,19 @@ object gives you access, for example, to the :ref:`settings `. it has processed the response. :meth:`process_spider_output` must return an iterable of - :class:`~scrapy.http.Request`, dict or :class:`~scrapy.item.Item` - objects. + :class:`~scrapy.Request` objects and :ref:`item object + `. :param response: the response which generated this output from the spider :type response: :class:`~scrapy.http.Response` object :param result: the result returned by the spider - :type result: an iterable of :class:`~scrapy.http.Request`, dict - or :class:`~scrapy.item.Item` objects + :type result: an iterable of :class:`~scrapy.Request` objects and + :ref:`item object ` :param spider: the spider whose result is being processed - :type spider: :class:`~scrapy.spiders.Spider` object - + :type spider: :class:`~scrapy.Spider` object .. method:: process_spider_exception(response, exception, spider) @@ -123,8 +122,8 @@ object gives you access, for example, to the :ref:`settings `. method (from a previous spider middleware) raises an exception. :meth:`process_spider_exception` should return either ``None`` or an - iterable of :class:`~scrapy.http.Request`, dict or - :class:`~scrapy.item.Item` objects. + iterable of :class:`~scrapy.Request` objects and :ref:`item object + `. If it returns ``None``, Scrapy will continue processing this exception, executing any other :meth:`process_spider_exception` in the following @@ -143,19 +142,17 @@ object gives you access, for example, to the :ref:`settings `. :type exception: :exc:`Exception` object :param spider: the spider which raised the exception - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: process_start_requests(start_requests, spider) - .. versionadded:: 0.15 - This method is called with the start requests of the spider, and works similarly to the :meth:`process_spider_output` method, except that it doesn't have a response associated and must return only requests (not items). It receives an iterable (in the ``start_requests`` parameter) and must - return another iterable of :class:`~scrapy.http.Request` objects. + return another iterable of :class:`~scrapy.Request` objects. .. note:: When implementing this method in your spider middleware, you should always return an iterable (that follows the input one) and @@ -167,10 +164,10 @@ object gives you access, for example, to the :ref:`settings `. (like a time limit or item/page count). :param start_requests: the start requests - :type start_requests: an iterable of :class:`~scrapy.http.Request` + :type start_requests: an iterable of :class:`~scrapy.Request` :param spider: the spider to whom the start requests belong - :type spider: :class:`~scrapy.spiders.Spider` object + :type spider: :class:`~scrapy.Spider` object .. method:: from_crawler(cls, crawler) @@ -254,9 +251,10 @@ this:: .. reqmeta:: handle_httpstatus_all The ``handle_httpstatus_list`` key of :attr:`Request.meta -` can also be used to specify which response codes to +` can also be used to specify which response codes to allow on a per-request basis. You can also set the meta key ``handle_httpstatus_all`` -to ``True`` if you want to allow any response code for a request. +to ``True`` if you want to allow any response code for a request, and ``False`` to +disable the effects of the ``handle_httpstatus_all`` key. Keep in mind, however, that it's usually a bad idea to handle non-200 responses, unless you really know what you're doing. @@ -297,7 +295,7 @@ OffsiteMiddleware Filters out Requests for URLs outside the domains covered by the spider. This middleware filters out every request whose host names aren't in the - spider's :attr:`~scrapy.spiders.Spider.allowed_domains` attribute. + spider's :attr:`~scrapy.Spider.allowed_domains` attribute. All subdomains of any domain in the list are also allowed. E.g. the rule ``www.example.org`` will also allow ``bob.www.example.org`` but not ``www2.example.com`` nor ``example.com``. @@ -315,10 +313,10 @@ OffsiteMiddleware will be printed (but only for the first request filtered). If the spider doesn't define an - :attr:`~scrapy.spiders.Spider.allowed_domains` attribute, or the + :attr:`~scrapy.Spider.allowed_domains` attribute, or the attribute is empty, the offsite middleware will allow all requests. - If the request has the :attr:`~scrapy.http.Request.dont_filter` attribute + If the request has the :attr:`~scrapy.Request.dont_filter` attribute set, the offsite middleware will allow the request even if its domain is not listed in allowed domains. @@ -342,8 +340,6 @@ RefererMiddleware settings REFERER_ENABLED ^^^^^^^^^^^^^^^ -.. versionadded:: 0.15 - Default: ``True`` Whether to enable referer middleware. @@ -353,8 +349,6 @@ Whether to enable referer middleware. REFERRER_POLICY ^^^^^^^^^^^^^^^ -.. versionadded:: 1.4 - Default: ``'scrapy.spidermiddlewares.referer.DefaultReferrerPolicy'`` .. reqmeta:: referrer_policy diff --git a/docs/topics/spiders.rst b/docs/topics/spiders.rst index 8ff5e7292..67b9e2e0e 100644 --- a/docs/topics/spiders.rst +++ b/docs/topics/spiders.rst @@ -17,15 +17,15 @@ For spiders, the scraping cycle goes through something like this: those requests. The first requests to perform are obtained by calling the - :meth:`~scrapy.spiders.Spider.start_requests` method which (by default) - generates :class:`~scrapy.http.Request` for the URLs specified in the - :attr:`~scrapy.spiders.Spider.start_urls` and the - :attr:`~scrapy.spiders.Spider.parse` method as callback function for the + :meth:`~scrapy.Spider.start_requests` method which (by default) + generates :class:`~scrapy.Request` for the URLs specified in the + :attr:`~scrapy.Spider.start_urls` and the + :attr:`~scrapy.Spider.parse` method as callback function for the Requests. -2. In the callback function, you parse the response (web page) and return either - dicts with extracted data, :class:`~scrapy.item.Item` objects, - :class:`~scrapy.http.Request` objects, or an iterable of these objects. +2. In the callback function, you parse the response (web page) and return + :ref:`item objects `, + :class:`~scrapy.Request` objects, or an iterable of these objects. Those Requests will also contain a callback (maybe the same) and will then be downloaded by Scrapy and then their response handled by the specified callback. @@ -50,7 +50,8 @@ We will talk about those types here. scrapy.Spider ============= -.. class:: Spider() +.. class:: scrapy.spiders.Spider() +.. class:: scrapy.Spider() This is the simplest spider, and the one from which every other spider must inherit (including spiders that come bundled with Scrapy, as well as spiders @@ -86,7 +87,7 @@ scrapy.Spider A list of URLs where the spider will begin to crawl from, when no particular URLs are specified. So, the first pages downloaded will be those - listed here. The subsequent :class:`~scrapy.http.Request` will be generated successively from data + listed here. The subsequent :class:`~scrapy.Request` will be generated successively from data contained in the start URLs. .. attribute:: custom_settings @@ -179,8 +180,8 @@ scrapy.Spider the same requirements as the :class:`Spider` class. This method, as well as any other Request callback, must return an - iterable of :class:`~scrapy.http.Request` and/or - dicts or :class:`~scrapy.item.Item` objects. + iterable of :class:`~scrapy.Request` and/or :ref:`item objects + `. :param response: the response to parse :type response: :class:`~scrapy.http.Response` @@ -234,7 +235,7 @@ Return multiple Requests and items from a single callback:: yield scrapy.Request(response.urljoin(href), self.parse) Instead of :attr:`~.start_urls` you can use :meth:`~.start_requests` directly; -to give data more structure you can use :ref:`topics-items`:: +to give data more structure you can use :class:`~scrapy.Item` objects:: import scrapy from myproject.items import MyItem @@ -279,7 +280,7 @@ Spiders can access arguments in their `__init__` methods:: def __init__(self, category=None, *args, **kwargs): super(MySpider, self).__init__(*args, **kwargs) - self.start_urls = ['http://www.example.com/categories/%s' % category] + self.start_urls = [f'http://www.example.com/categories/{category}'] # ... The default `__init__` method will take any spider arguments @@ -292,7 +293,15 @@ The above example can also be written as follows:: name = 'myspider' def start_requests(self): - yield scrapy.Request('http://www.example.com/categories/%s' % self.category) + yield scrapy.Request(f'http://www.example.com/categories/{self.category}') + +If you are :ref:`running Scrapy from a script `, you can +specify spider arguments when calling +:class:`CrawlerProcess.crawl ` or +:class:`CrawlerRunner.crawl `:: + + process = CrawlerProcess() + process.crawl(MySpider, category="electronics") Keep in mind that spider arguments are only strings. The spider will not do any parsing on its own. @@ -360,11 +369,12 @@ CrawlSpider This spider also exposes an overrideable method: - .. method:: parse_start_url(response) + .. method:: parse_start_url(response, **kwargs) - This method is called for the start_urls responses. It allows to parse + This method is called for each response produced for the URLs in + the spider's ``start_urls`` attribute. It allows to parse the initial responses and must return either an - :class:`~scrapy.item.Item` object, a :class:`~scrapy.http.Request` + :ref:`item object `, a :class:`~scrapy.Request` object, or an iterable containing any of them. Crawling rules @@ -374,7 +384,7 @@ Crawling rules ``link_extractor`` is a :ref:`Link Extractor ` object which defines how links will be extracted from each crawled page. Each produced link will - be used to generate a :class:`~scrapy.http.Request` object, which will contain the + be used to generate a :class:`~scrapy.Request` object, which will contain the link's text in its ``meta`` dictionary (under the ``link_text`` key). If omitted, a default link extractor created with no arguments will be used, resulting in all links being extracted. @@ -383,16 +393,11 @@ Crawling rules object with that name will be used) to be called for each link extracted with the specified link extractor. This callback receives a :class:`~scrapy.http.Response` as its first argument and must return either a single instance or an iterable of - :class:`~scrapy.item.Item`, ``dict`` and/or :class:`~scrapy.http.Request` objects + :ref:`item objects ` and/or :class:`~scrapy.Request` objects (or any subclass of them). As mentioned above, the received :class:`~scrapy.http.Response` - object will contain the text of the link that produced the :class:`~scrapy.http.Request` + object will contain the text of the link that produced the :class:`~scrapy.Request` in its ``meta`` dictionary (under the ``link_text`` key) - .. warning:: When writing crawl spider rules, avoid using ``parse`` as - callback, since the :class:`CrawlSpider` uses the ``parse`` method - itself to implement its logic. So if you override the ``parse`` method, - the crawl spider will no longer work. - ``cb_kwargs`` is a dict containing the keyword arguments to be passed to the callback function. @@ -407,7 +412,7 @@ Crawling rules ``process_request`` is a callable (or a string, in which case a method from the spider object with that name will be used) which will be called for every - :class:`~scrapy.http.Request` extracted by this rule. This callable should + :class:`~scrapy.Request` extracted by this rule. This callable should take said request as first argument and the :class:`~scrapy.http.Response` from which the request originated as second argument. It must return a ``Request`` object or ``None`` (to filter out the request). @@ -418,6 +423,10 @@ Crawling rules It receives a :class:`Twisted Failure ` instance as first parameter. + .. warning:: Because of its internal implementation, you must explicitly set + callbacks for new requests when writing :class:`CrawlSpider`-based spiders; + unexpected behaviour can occur otherwise. + .. versionadded:: 2.0 The *errback* parameter. @@ -451,13 +460,18 @@ Let's now take a look at an example CrawlSpider with rules:: item['name'] = response.xpath('//td[@id="item_name"]/text()').get() item['description'] = response.xpath('//td[@id="item_description"]/text()').get() item['link_text'] = response.meta['link_text'] + url = response.xpath('//td[@id="additional_data"]/@href').get() + return response.follow(url, self.parse_additional_page, cb_kwargs=dict(item=item)) + + def parse_additional_page(self, response, item): + item['additional_data'] = response.xpath('//p[@id="additional_data"]/text()').get() return item This spider would start crawling example.com's home page, collecting category links, and item links, parsing the latter with the ``parse_item`` method. For each item response, some data will be extracted from the HTML using XPath, and -an :class:`~scrapy.item.Item` will be filled with it. +an :class:`~scrapy.Item` will be filled with it. XMLFeedSpider ------------- @@ -480,11 +494,11 @@ XMLFeedSpider - ``'iternodes'`` - a fast iterator based on regular expressions - - ``'html'`` - an iterator which uses :class:`~scrapy.selector.Selector`. + - ``'html'`` - an iterator which uses :class:`~scrapy.Selector`. Keep in mind this uses DOM parsing and must load all DOM in memory which could be a problem for big feeds - - ``'xml'`` - an iterator which uses :class:`~scrapy.selector.Selector`. + - ``'xml'`` - an iterator which uses :class:`~scrapy.Selector`. Keep in mind this uses DOM parsing and must load all DOM in memory which could be a problem for big feeds @@ -502,7 +516,7 @@ XMLFeedSpider available in that document that will be processed with this spider. The ``prefix`` and ``uri`` will be used to automatically register namespaces using the - :meth:`~scrapy.selector.Selector.register_namespace` method. + :meth:`~scrapy.Selector.register_namespace` method. You can then specify nodes with namespaces in the :attr:`itertag` attribute. @@ -529,10 +543,10 @@ XMLFeedSpider This method is called for the nodes matching the provided tag name (``itertag``). Receives the response and an - :class:`~scrapy.selector.Selector` for each node. Overriding this + :class:`~scrapy.Selector` for each node. Overriding this method is mandatory. Otherwise, you spider won't work. This method - must return either a :class:`~scrapy.item.Item` object, a - :class:`~scrapy.http.Request` object, or an iterable containing any of + must return an :ref:`item object `, a + :class:`~scrapy.Request` object, or an iterable containing any of them. .. method:: process_results(response, results) @@ -541,7 +555,11 @@ XMLFeedSpider spider, and it's intended to perform any last time processing required before returning the results to the framework core, for example setting the item IDs. It receives a list of results and the response which originated - those results. It must return a list of results (Items or Requests). + those results. It must return a list of results (items or requests). + + .. warning:: Because of its internal implementation, you must explicitly set + callbacks for new requests when writing :class:`XMLFeedSpider`-based spiders; + unexpected behaviour can occur otherwise. XMLFeedSpider example @@ -570,7 +588,7 @@ These spiders are pretty easy to use, let's have a look at one example:: Basically what we did up there was to create a spider that downloads a feed from the given ``start_urls``, and then iterates through each of its ``item`` tags, -prints them out, and stores some random data in an :class:`~scrapy.item.Item`. +prints them out, and stores some random data in an :class:`~scrapy.Item`. CSVFeedSpider ------------- diff --git a/docs/topics/telnetconsole.rst b/docs/topics/telnetconsole.rst index 9802a34a2..832829b75 100644 --- a/docs/topics/telnetconsole.rst +++ b/docs/topics/telnetconsole.rst @@ -110,11 +110,10 @@ using the telnet console:: Execution engine status time()-engine.start_time : 8.62972998619 - engine.has_capacity() : False len(engine.downloader.active) : 16 engine.scraper.is_idle() : False engine.spider.name : followall - engine.spider_is_idle(engine.spider) : False + engine.spider_is_idle() : False engine.slot.closing : False len(engine.slot.inprogress) : 16 len(engine.slot.scheduler.dqs or []) : 0 diff --git a/docs/utils/linkfix.py b/docs/utils/linkfix.py index 9acfc3b23..95a3f17d5 100755 --- a/docs/utils/linkfix.py +++ b/docs/utils/linkfix.py @@ -23,7 +23,7 @@ def main(): _contents = None # A regex that matches standard linkcheck output lines - line_re = re.compile(u'(.*)\:\d+\:\s\[(.*)\]\s(?:(.*)\sto\s(.*)|(.*))') + line_re = re.compile(r'(.*)\:\d+\:\s\[(.*)\]\s(?:(.*)\sto\s(.*)|(.*))') # Read lines from the linkcheck output file try: diff --git a/docs/versioning.rst b/docs/versioning.rst index 227085f02..57643ea9a 100644 --- a/docs/versioning.rst +++ b/docs/versioning.rst @@ -1,7 +1,7 @@ .. _versioning: ============================ -Versioning and API Stability +Versioning and API stability ============================ Versioning @@ -34,7 +34,7 @@ For example: production) -API Stability +API stability ============= API stability was one of the major goals for the *1.0* release. @@ -47,5 +47,23 @@ new methods or functionality but the existing methods should keep working the same way. +.. _deprecation-policy: + +Deprecation policy +================== + +We aim to maintain support for deprecated Scrapy features for at least 1 year. + +For example, if a feature is deprecated in a Scrapy version released on +June 15th 2020, that feature should continue to work in versions released on +June 14th 2021 or before that. + +Any new Scrapy release after a year *may* remove support for that deprecated +feature. + +All deprecated features removed in a Scrapy release are explicitly mentioned in +the :ref:`release notes `. + + .. _odd-numbered versions for development releases: https://en.wikipedia.org/wiki/Software_versioning#Odd-numbered_versions_for_development_releases diff --git a/extras/qps-bench-server.py b/extras/qps-bench-server.py index da7a0022b..a6472b1ba 100755 --- a/extras/qps-bench-server.py +++ b/extras/qps-bench-server.py @@ -37,7 +37,7 @@ class Root(Resource): if now - self.lastmark >= 3: self.lastmark = now qps = len(self.tail) / sum(self.tail) - print('samplesize={0} concurrent={1} qps={2:0.2f}'.format(len(self.tail), self.concurrent, qps)) + print(f'samplesize={len(self.tail)} concurrent={self.concurrent} qps={qps:0.2f}') if 'latency' in request.args: latency = float(request.args['latency'][0]) diff --git a/extras/qpsclient.py b/extras/qpsclient.py index 7554f7eec..f9fb70342 100644 --- a/extras/qpsclient.py +++ b/extras/qpsclient.py @@ -27,7 +27,7 @@ class QPSSpider(Spider): slots = 1 def __init__(self, *a, **kw): - super(QPSSpider, self).__init__(*a, **kw) + super().__init__(*a, **kw) if self.qps is not None: self.qps = float(self.qps) self.download_delay = 1 / self.qps @@ -37,11 +37,11 @@ class QPSSpider(Spider): def start_requests(self): url = self.benchurl if self.latency is not None: - url += '?latency={0}'.format(self.latency) + url += f'?latency={self.latency}' slots = int(self.slots) if slots > 1: - urls = [url.replace('localhost', '127.0.0.%d' % (x + 1)) for x in range(slots)] + urls = [url.replace('localhost', f'127.0.0.{x + 1}') for x in range(slots)] else: urls = [url] diff --git a/pylintrc b/pylintrc index 129c7bf7d..a44712507 100644 --- a/pylintrc +++ b/pylintrc @@ -6,6 +6,7 @@ jobs=1 # >1 hides results disable=abstract-method, anomalous-backslash-in-string, arguments-differ, + arguments-renamed, attribute-defined-outside-init, bad-classmethod-argument, bad-continuation, @@ -21,9 +22,12 @@ disable=abstract-method, cell-var-from-loop, comparison-with-callable, consider-iterating-dictionary, + consider-using-dict-items, + consider-using-from-import, consider-using-in, consider-using-set-comprehension, consider-using-sys-exit, + consider-using-with, cyclic-import, dangerous-default-value, deprecated-method, @@ -68,6 +72,7 @@ disable=abstract-method, pointless-statement, pointless-string-statement, protected-access, + raise-missing-from, redefined-argument-from-local, redefined-builtin, redefined-outer-name, @@ -75,6 +80,7 @@ disable=abstract-method, signature-differs, singleton-comparison, super-init-not-called, + super-with-arguments, superfluous-parens, too-few-public-methods, too-many-ancestors, @@ -102,6 +108,7 @@ disable=abstract-method, unsubscriptable-object, unused-argument, unused-import, + unused-private-member, unused-variable, unused-wildcard-import, used-before-assignment, diff --git a/pytest.ini b/pytest.ini index 663c5cc78..6de08c78d 100644 --- a/pytest.ini +++ b/pytest.ini @@ -1,4 +1,5 @@ [pytest] +xfail_strict = true usefixtures = chdir python_files=test_*.py __init__.py python_classes= @@ -17,26 +18,7 @@ addopts = --ignore=docs/topics/stats.rst --ignore=docs/topics/telnetconsole.rst --ignore=docs/utils -twisted = 1 markers = only_asyncio: marks tests as only enabled when --reactor=asyncio is passed -flake8-max-line-length = 119 -flake8-ignore = - W503 - - # Exclude files that are meant to provide top-level imports - # E402: Module level import not at top of file - # F401: Module imported but unused - scrapy/__init__.py E402 - scrapy/core/downloader/handlers/http.py F401 - scrapy/http/__init__.py F401 - scrapy/linkextractors/__init__.py E402 F401 - scrapy/selector/__init__.py F401 - scrapy/spiders/__init__.py E402 F401 - - # Issues pending a review: - scrapy/utils/http.py F403 - scrapy/utils/markup.py F403 - scrapy/utils/multipart.py F403 - scrapy/utils/url.py F403 F405 - tests/test_loader.py E741 +filterwarnings= + ignore::DeprecationWarning:twisted.web.test.test_webclient diff --git a/scrapy/VERSION b/scrapy/VERSION index 7ec1d6db4..437459cd9 100644 --- a/scrapy/VERSION +++ b/scrapy/VERSION @@ -1 +1 @@ -2.1.0 +2.5.0 diff --git a/scrapy/__init__.py b/scrapy/__init__.py index e791deaa6..8a8065bf2 100644 --- a/scrapy/__init__.py +++ b/scrapy/__init__.py @@ -22,14 +22,14 @@ __all__ = [ # Scrapy and Twisted versions -__version__ = pkgutil.get_data(__package__, 'VERSION').decode('ascii').strip() +__version__ = (pkgutil.get_data(__package__, "VERSION") or b"").decode("ascii").strip() version_info = tuple(int(v) if v.isdigit() else v for v in __version__.split('.')) twisted_version = (_txv.major, _txv.minor, _txv.micro) # Check minimum required Python version -if sys.version_info < (3, 5): - print("Scrapy %s requires Python 3.5" % __version__) +if sys.version_info < (3, 6): + print("Scrapy %s requires Python 3.6+" % __version__) sys.exit(1) diff --git a/scrapy/cmdline.py b/scrapy/cmdline.py index b189e016b..91482ce01 100644 --- a/scrapy/cmdline.py +++ b/scrapy/cmdline.py @@ -19,10 +19,12 @@ def _iter_command_classes(module_name): # scrapy.utils.spider.iter_spider_classes for module in walk_modules(module_name): for obj in vars(module).values(): - if inspect.isclass(obj) and \ - issubclass(obj, ScrapyCommand) and \ - obj.__module__ == module.__name__ and \ - not obj == ScrapyCommand: + if ( + inspect.isclass(obj) + and issubclass(obj, ScrapyCommand) + and obj.__module__ == module.__name__ + and not obj == ScrapyCommand + ): yield obj @@ -42,7 +44,7 @@ def _get_commands_from_entry_points(inproject, group='scrapy.commands'): if inspect.isclass(obj): cmds[entry_point.name] = obj() else: - raise Exception("Invalid entry point %s" % entry_point.name) + raise Exception(f"Invalid entry point {entry_point.name}") return cmds @@ -65,11 +67,11 @@ def _pop_command_name(argv): def _print_header(settings, inproject): + version = scrapy.__version__ if inproject: - print("Scrapy %s - project: %s\n" % (scrapy.__version__, - settings['BOT_NAME'])) + print(f"Scrapy {version} - project: {settings['BOT_NAME']}\n") else: - print("Scrapy %s - no active project\n" % scrapy.__version__) + print(f"Scrapy {version} - no active project\n") def _print_commands(settings, inproject): @@ -79,7 +81,7 @@ def _print_commands(settings, inproject): print("Available commands:") cmds = _get_commands_dict(settings, inproject) for cmdname, cmdclass in sorted(cmds.items()): - print(" %-13s %s" % (cmdname, cmdclass.short_desc())) + print(f" {cmdname:<13} {cmdclass.short_desc()}") if not inproject: print() print(" [ more ] More commands available when run from project directory") @@ -89,7 +91,7 @@ def _print_commands(settings, inproject): def _print_unknown_command(settings, cmdname, inproject): _print_header(settings, inproject) - print("Unknown command: %s\n" % cmdname) + print(f"Unknown command: {cmdname}\n") print('Use "scrapy" to see available commands') @@ -131,7 +133,7 @@ def execute(argv=None, settings=None): sys.exit(2) cmd = cmds[cmdname] - parser.usage = "scrapy %s %s" % (cmdname, cmd.syntax()) + parser.usage = f"scrapy {cmdname} {cmd.syntax()}" parser.description = cmd.long_desc() settings.setdict(cmd.default_settings, priority='command') cmd.settings = settings @@ -153,7 +155,7 @@ def _run_command(cmd, args, opts): def _run_command_profiled(cmd, args, opts): if opts.profile: - sys.stderr.write("scrapy: writing cProfile stats to %r\n" % opts.profile) + sys.stderr.write(f"scrapy: writing cProfile stats to {opts.profile!r}\n") loc = locals() p = cProfile.Profile() p.runctx('cmd.run(args, opts)', globals(), loc) diff --git a/scrapy/commands/__init__.py b/scrapy/commands/__init__.py index ab850dcb3..6e77551c6 100644 --- a/scrapy/commands/__init__.py +++ b/scrapy/commands/__init__.py @@ -3,6 +3,8 @@ Base class for Scrapy commands """ import os from optparse import OptionGroup +from typing import Any, Dict + from twisted.python import failure from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli @@ -15,7 +17,7 @@ class ScrapyCommand: crawler_process = None # default settings to be used for this command instead of global defaults - default_settings = {} + default_settings: Dict[str, Any] = {} exitcode = 0 @@ -61,7 +63,7 @@ class ScrapyCommand: group.add_option("--logfile", metavar="FILE", help="log file. if omitted stderr will be used") group.add_option("-L", "--loglevel", metavar="LEVEL", default=None, - help="log level (default: %s)" % self.settings['LOG_LEVEL']) + help=f"log level (default: {self.settings['LOG_LEVEL']})") group.add_option("--nolog", action="store_true", help="disable logging completely") group.add_option("--profile", metavar="FILE", default=None, @@ -108,16 +110,18 @@ class ScrapyCommand: class BaseRunSpiderCommand(ScrapyCommand): """ - Common class used to share functionality between the crawl and runspider commands + Common class used to share functionality between the crawl, parse and runspider commands """ def add_options(self, parser): ScrapyCommand.add_options(self, parser) parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE", help="set spider argument (may be repeated)") parser.add_option("-o", "--output", metavar="FILE", action="append", - help="dump scraped items into FILE (use - for stdout)") + help="append scraped items to the end of FILE (use - for stdout)") + parser.add_option("-O", "--overwrite-output", metavar="FILE", action="append", + help="dump scraped items into FILE, overwriting any existing file") parser.add_option("-t", "--output-format", metavar="FORMAT", - help="format to use for dumping items with -o") + help="format to use for dumping items") def process_options(self, args, opts): ScrapyCommand.process_options(self, args, opts) @@ -125,6 +129,11 @@ class BaseRunSpiderCommand(ScrapyCommand): opts.spargs = arglist_to_dict(opts.spargs) except ValueError: raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False) - if opts.output: - feeds = feed_process_params_from_cli(self.settings, opts.output, opts.output_format) + if opts.output or opts.overwrite_output: + feeds = feed_process_params_from_cli( + self.settings, + opts.output, + opts.output_format, + opts.overwrite_output, + ) self.settings.set('FEEDS', feeds, priority='cmdline') diff --git a/scrapy/commands/bench.py b/scrapy/commands/bench.py index c9f3b38e0..6bdf9eae0 100644 --- a/scrapy/commands/bench.py +++ b/scrapy/commands/bench.py @@ -50,7 +50,7 @@ class _BenchSpider(scrapy.Spider): def start_requests(self): qargs = {'total': self.total, 'show': self.show} - url = '{}?{}'.format(self.baseurl, urlencode(qargs, doseq=1)) + url = f'{self.baseurl}?{urlencode(qargs, doseq=True)}' return [scrapy.Request(url, dont_filter=True)] def parse(self, response): diff --git a/scrapy/commands/check.py b/scrapy/commands/check.py index 9d4437a47..ae21d86e6 100644 --- a/scrapy/commands/check.py +++ b/scrapy/commands/check.py @@ -17,7 +17,7 @@ class TextTestResult(_TextTestResult): plural = "s" if run != 1 else "" writeln(self.separator2) - writeln("Ran %d contract%s in %.3fs" % (run, plural, stop - start)) + writeln(f"Ran {run} contract{plural} in {stop - start:.3f}s") writeln() infos = [] @@ -25,14 +25,14 @@ class TextTestResult(_TextTestResult): write("FAILED") failed, errored = map(len, (self.failures, self.errors)) if failed: - infos.append("failures=%d" % failed) + infos.append(f"failures={failed}") if errored: - infos.append("errors=%d" % errored) + infos.append(f"errors={errored}") else: write("OK") if infos: - writeln(" (%s)" % (", ".join(infos),)) + writeln(f" ({', '.join(infos)})") else: write("\n") @@ -78,19 +78,19 @@ class Command(ScrapyCommand): elif tested_methods: self.crawler_process.crawl(spidercls) - # start checks - if opts.list: - for spider, methods in sorted(contract_reqs.items()): - if not methods and not opts.verbose: - continue - print(spider) - for method in sorted(methods): - print(' * %s' % method) - else: - start = time.time() - self.crawler_process.start() - stop = time.time() + # start checks + if opts.list: + for spider, methods in sorted(contract_reqs.items()): + if not methods and not opts.verbose: + continue + print(spider) + for method in sorted(methods): + print(f' * {method}') + else: + start = time.time() + self.crawler_process.start() + stop = time.time() - result.printErrors() - result.printSummary(start, stop) - self.exitcode = int(not result.wasSuccessful()) + result.printErrors() + result.printSummary(start, stop) + self.exitcode = int(not result.wasSuccessful()) diff --git a/scrapy/commands/crawl.py b/scrapy/commands/crawl.py index e1724c1e6..0f2a21b85 100644 --- a/scrapy/commands/crawl.py +++ b/scrapy/commands/crawl.py @@ -16,7 +16,7 @@ class Command(BaseRunSpiderCommand): if len(args) < 1: raise UsageError() elif len(args) > 1: - raise UsageError("running 'scrapy crawl' with more than one spider is no longer supported") + raise UsageError("running 'scrapy crawl' with more than one spider is not supported") spname = args[0] crawl_defer = self.crawler_process.crawl(spname, **opts.spargs) @@ -26,6 +26,8 @@ class Command(BaseRunSpiderCommand): else: self.crawler_process.start() - if self.crawler_process.bootstrap_failed or \ - (hasattr(self.crawler_process, 'has_exception') and self.crawler_process.has_exception): + if ( + self.crawler_process.bootstrap_failed + or hasattr(self.crawler_process, 'has_exception') and self.crawler_process.has_exception + ): self.exitcode = 1 diff --git a/scrapy/commands/edit.py b/scrapy/commands/edit.py index 25d843a53..177b20143 100644 --- a/scrapy/commands/edit.py +++ b/scrapy/commands/edit.py @@ -32,8 +32,8 @@ class Command(ScrapyCommand): try: spidercls = self.crawler_process.spider_loader.load(args[0]) except KeyError: - return self._err("Spider not found: %s" % args[0]) + return self._err(f"Spider not found: {args[0]}") sfile = sys.modules[spidercls.__module__].__file__ sfile = sfile.replace('.pyc', '.py') - self.exitcode = os.system('%s "%s"' % (editor, sfile)) + self.exitcode = os.system(f'{editor} "{sfile}"') diff --git a/scrapy/commands/fetch.py b/scrapy/commands/fetch.py index 063195f50..95f87e8c3 100644 --- a/scrapy/commands/fetch.py +++ b/scrapy/commands/fetch.py @@ -19,8 +19,10 @@ class Command(ScrapyCommand): return "Fetch a URL using the Scrapy downloader" def long_desc(self): - return "Fetch a URL using the Scrapy downloader and print its content " \ - "to stdout. You may want to use --nolog to disable logging" + return ( + "Fetch a URL using the Scrapy downloader and print its content" + " to stdout. You may want to use --nolog to disable logging" + ) def add_options(self, parser): ScrapyCommand.add_options(self, parser) diff --git a/scrapy/commands/genspider.py b/scrapy/commands/genspider.py index abf3b7a5c..5f44daa70 100644 --- a/scrapy/commands/genspider.py +++ b/scrapy/commands/genspider.py @@ -66,31 +66,25 @@ class Command(ScrapyCommand): print("Cannot create a spider with the same name as your project") return - try: - spidercls = self.crawler_process.spider_loader.load(name) - except KeyError: - pass - else: - # if spider already exists and not --force then halt - if not opts.force: - print("Spider %r already exists in module:" % name) - print(" %s" % spidercls.__module__) - return + if not opts.force and self._spider_exists(name): + return + template_file = self._find_template(opts.template) if template_file: self._genspider(module, name, domain, opts.template, template_file) if opts.edit: - self.exitcode = os.system('scrapy edit "%s"' % name) + self.exitcode = os.system(f'scrapy edit "{name}"') def _genspider(self, module, name, domain, template_name, template_file): """Generate the spider module, based on the given template""" + capitalized_module = ''.join(s.capitalize() for s in module.split('_')) tvars = { 'project_name': self.settings.get('BOT_NAME'), 'ProjectName': string_camelcase(self.settings.get('BOT_NAME')), 'module': module, 'name': name, 'domain': domain, - 'classname': '%sSpider' % ''.join(s.capitalize() for s in module.split('_')) + 'classname': f'{capitalized_module}Spider' } if self.settings.get('NEWSPIDER_MODULE'): spiders_module = import_module(self.settings['NEWSPIDER_MODULE']) @@ -98,29 +92,58 @@ class Command(ScrapyCommand): else: spiders_module = None spiders_dir = "." - spider_file = "%s.py" % join(spiders_dir, module) + spider_file = f"{join(spiders_dir, module)}.py" shutil.copyfile(template_file, spider_file) render_templatefile(spider_file, **tvars) - print("Created spider %r using template %r " - % (name, template_name), end=('' if spiders_module else '\n')) + print(f"Created spider {name!r} using template {template_name!r} ", + end=('' if spiders_module else '\n')) if spiders_module: - print("in module:\n %s.%s" % (spiders_module.__name__, module)) + print(f"in module:\n {spiders_module.__name__}.{module}") def _find_template(self, template): - template_file = join(self.templates_dir, '%s.tmpl' % template) + template_file = join(self.templates_dir, f'{template}.tmpl') if exists(template_file): return template_file - print("Unable to find template: %s\n" % template) + print(f"Unable to find template: {template}\n") print('Use "scrapy genspider --list" to see all available templates.') def _list_templates(self): print("Available templates:") for filename in sorted(os.listdir(self.templates_dir)): if filename.endswith('.tmpl'): - print(" %s" % splitext(filename)[0]) + print(f" {splitext(filename)[0]}") + + def _spider_exists(self, name): + if not self.settings.get('NEWSPIDER_MODULE'): + # if run as a standalone command and file with same filename already exists + if exists(name + ".py"): + print(f"{abspath(name + '.py')} already exists") + return True + return False + + try: + spidercls = self.crawler_process.spider_loader.load(name) + except KeyError: + pass + else: + # if spider with same name exists + print(f"Spider {name!r} already exists in module:") + print(f" {spidercls.__module__}") + return True + + # a file with the same name exists in the target directory + spiders_module = import_module(self.settings['NEWSPIDER_MODULE']) + spiders_dir = dirname(spiders_module.__file__) + spiders_dir_abs = abspath(spiders_dir) + if exists(join(spiders_dir_abs, name + ".py")): + print(f"{join(spiders_dir_abs, (name + '.py'))} already exists") + return True + + return False @property def templates_dir(self): - _templates_base_dir = self.settings['TEMPLATES_DIR'] or \ - join(scrapy.__path__[0], 'templates') - return join(_templates_base_dir, 'spiders') + return join( + self.settings['TEMPLATES_DIR'] or join(scrapy.__path__[0], 'templates'), + 'spiders' + ) diff --git a/scrapy/commands/parse.py b/scrapy/commands/parse.py index 580fd2828..52118db1b 100644 --- a/scrapy/commands/parse.py +++ b/scrapy/commands/parse.py @@ -1,26 +1,26 @@ import json import logging +from typing import Dict +from itemadapter import is_item, ItemAdapter from w3lib.url import is_url -from scrapy.commands import ScrapyCommand +from scrapy.commands import BaseRunSpiderCommand from scrapy.http import Request -from scrapy.item import _BaseItem from scrapy.utils import display -from scrapy.utils.conf import arglist_to_dict from scrapy.utils.spider import iterate_spider_output, spidercls_for_request from scrapy.exceptions import UsageError + logger = logging.getLogger(__name__) -class Command(ScrapyCommand): - +class Command(BaseRunSpiderCommand): requires_project = True spider = None - items = {} - requests = {} + items: Dict[int, list] = {} + requests: Dict[int, list] = {} first_response = None @@ -31,11 +31,9 @@ class Command(ScrapyCommand): return "Parse URL (using its spider) and print the results" def add_options(self, parser): - ScrapyCommand.add_options(self, parser) + BaseRunSpiderCommand.add_options(self, parser) parser.add_option("--spider", dest="spider", default=None, help="use this spider without looking for one") - parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE", - help="set spider argument (may be repeated)") parser.add_option("--pipelines", action="store_true", help="process items through pipelines") parser.add_option("--nolinks", dest="nolinks", action="store_true", @@ -81,7 +79,7 @@ class Command(ScrapyCommand): items = self.items.get(lvl, []) print("# Scraped Items ", "-" * 60) - display.pprint([dict(x) for x in items], colorize=colour) + display.pprint([ItemAdapter(x).asdict() for x in items], colorize=colour) def print_requests(self, lvl=None, colour=True): if lvl is None: @@ -100,13 +98,13 @@ class Command(ScrapyCommand): if opts.verbose: for level in range(1, self.max_level + 1): - print('\n>>> DEPTH LEVEL: %s <<<' % level) + print(f'\n>>> DEPTH LEVEL: {level} <<<') if not opts.noitems: self.print_items(level, colour) if not opts.nolinks: self.print_requests(level, colour) else: - print('\n>>> STATUS DEPTH LEVEL %s <<<' % self.max_level) + print(f'\n>>> STATUS DEPTH LEVEL {self.max_level} <<<') if not opts.noitems: self.print_items(colour=colour) if not opts.nolinks: @@ -117,7 +115,7 @@ class Command(ScrapyCommand): items, requests = [], [] for x in iterate_spider_output(callback(response, **cb_kwargs)): - if isinstance(x, (_BaseItem, dict)): + if is_item(x): items.append(x) elif isinstance(x, Request): requests.append(x) @@ -200,12 +198,15 @@ class Command(ScrapyCommand): self.add_items(depth, items) self.add_requests(depth, requests) + scraped_data = items if opts.output else [] if depth < opts.depth: for req in requests: req.meta['_depth'] = depth + 1 req.meta['_callback'] = req.callback req.callback = callback - return requests + scraped_data += requests + + return scraped_data # update request meta if any extra meta was passed through the --meta/-m opts. if opts.meta: @@ -221,18 +222,11 @@ class Command(ScrapyCommand): return request def process_options(self, args, opts): - ScrapyCommand.process_options(self, args, opts) + BaseRunSpiderCommand.process_options(self, args, opts) - self.process_spider_arguments(opts) self.process_request_meta(opts) self.process_request_cb_kwargs(opts) - def process_spider_arguments(self, opts): - try: - opts.spargs = arglist_to_dict(opts.spargs) - except ValueError: - raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False) - def process_request_meta(self, opts): if opts.meta: try: diff --git a/scrapy/commands/runspider.py b/scrapy/commands/runspider.py index befee021b..b957c29fb 100644 --- a/scrapy/commands/runspider.py +++ b/scrapy/commands/runspider.py @@ -11,8 +11,8 @@ def _import_file(filepath): abspath = os.path.abspath(filepath) dirname, file = os.path.split(abspath) fname, fext = os.path.splitext(file) - if fext != '.py': - raise ValueError("Not a Python source file: %s" % abspath) + if fext not in ('.py', '.pyw'): + raise ValueError(f"Not a Python source file: {abspath}") if dirname: sys.path = [dirname] + sys.path try: @@ -42,14 +42,14 @@ class Command(BaseRunSpiderCommand): raise UsageError() filename = args[0] if not os.path.exists(filename): - raise UsageError("File not found: %s\n" % filename) + raise UsageError(f"File not found: {filename}\n") try: module = _import_file(filename) except (ImportError, ValueError) as e: - raise UsageError("Unable to load %r: %s\n" % (filename, e)) + raise UsageError(f"Unable to load {filename!r}: {e}\n") spclasses = list(iter_spider_classes(module)) if not spclasses: - raise UsageError("No spider found in file: %s\n" % filename) + raise UsageError(f"No spider found in file: {filename}\n") spidercls = spclasses.pop() self.crawler_process.crawl(spidercls, **opts.spargs) diff --git a/scrapy/commands/startproject.py b/scrapy/commands/startproject.py index ebe3a9c2c..1d73fa0cb 100644 --- a/scrapy/commands/startproject.py +++ b/scrapy/commands/startproject.py @@ -4,6 +4,7 @@ import string from importlib import import_module from os.path import join, exists, abspath from shutil import ignore_patterns, move, copy2, copystat +from stat import S_IWUSR as OWNER_WRITE_PERMISSION import scrapy from scrapy.commands import ScrapyCommand @@ -19,7 +20,12 @@ TEMPLATES_TO_RENDER = ( ('${project_name}', 'middlewares.py.tmpl'), ) -IGNORE = ignore_patterns('*.pyc', '.svn') +IGNORE = ignore_patterns('*.pyc', '__pycache__', '.svn') + + +def _make_writable(path): + current_permissions = os.stat(path).st_mode + os.chmod(path, current_permissions | OWNER_WRITE_PERMISSION) class Command(ScrapyCommand): @@ -46,7 +52,7 @@ class Command(ScrapyCommand): print('Error: Project names must begin with a letter and contain' ' only\nletters, numbers and underscores') elif _module_exists(project_name): - print('Error: Module %r already exists' % project_name) + print(f'Error: Module {project_name!r} already exists') else: return True return False @@ -77,7 +83,10 @@ class Command(ScrapyCommand): self._copytree(srcname, dstname) else: copy2(srcname, dstname) + _make_writable(dstname) + copystat(src, dst) + _make_writable(dst) def run(self, args, opts): if len(args) not in (1, 2): @@ -91,7 +100,7 @@ class Command(ScrapyCommand): if exists(join(project_dir, 'scrapy.cfg')): self.exitcode = 1 - print('Error: scrapy.cfg already exists in %s' % abspath(project_dir)) + print(f'Error: scrapy.cfg already exists in {abspath(project_dir)}') return if not self._is_valid_name(project_name): @@ -104,15 +113,16 @@ class Command(ScrapyCommand): path = join(*paths) tplfile = join(project_dir, string.Template(path).substitute(project_name=project_name)) render_templatefile(tplfile, project_name=project_name, ProjectName=string_camelcase(project_name)) - print("New Scrapy project '%s', using template directory '%s', " - "created in:" % (project_name, self.templates_dir)) - print(" %s\n" % abspath(project_dir)) + print(f"New Scrapy project '{project_name}', using template directory " + f"'{self.templates_dir}', created in:") + print(f" {abspath(project_dir)}\n") print("You can start your first spider with:") - print(" cd %s" % project_dir) + print(f" cd {project_dir}") print(" scrapy genspider example example.com") @property def templates_dir(self): - _templates_base_dir = self.settings['TEMPLATES_DIR'] or \ - join(scrapy.__path__[0], 'templates') - return join(_templates_base_dir, 'project') + return join( + self.settings['TEMPLATES_DIR'] or join(scrapy.__path__[0], 'templates'), + 'project' + ) diff --git a/scrapy/commands/version.py b/scrapy/commands/version.py index d0ea72a67..1237610cb 100644 --- a/scrapy/commands/version.py +++ b/scrapy/commands/version.py @@ -23,8 +23,7 @@ class Command(ScrapyCommand): if opts.verbose: versions = scrapy_components_versions() width = max(len(n) for (n, _) in versions) - patt = "%-{}s : %s".format(width) for name, version in versions: - print(patt % (name, version)) + print(f"{name:<{width}} : {version}") else: - print("Scrapy %s" % scrapy.__version__) + print(f"Scrapy {scrapy.__version__}") diff --git a/scrapy/commands/view.py b/scrapy/commands/view.py index 41e77ba3b..c8f873334 100644 --- a/scrapy/commands/view.py +++ b/scrapy/commands/view.py @@ -8,11 +8,10 @@ class Command(fetch.Command): return "Open URL in browser, as seen by Scrapy" def long_desc(self): - return "Fetch a URL using the Scrapy downloader and show its " \ - "contents in a browser" + return "Fetch a URL using the Scrapy downloader and show its contents in a browser" def add_options(self, parser): - super(Command, self).add_options(parser) + super().add_options(parser) parser.remove_option("--headers") def _print_response(self, response, opts): diff --git a/scrapy/contracts/__init__.py b/scrapy/contracts/__init__.py index 5af3831a2..b47e55092 100644 --- a/scrapy/contracts/__init__.py +++ b/scrapy/contracts/__init__.py @@ -1,16 +1,77 @@ -import sys import re +import sys from functools import wraps from inspect import getmembers +from typing import Dict from unittest import TestCase from scrapy.http import Request -from scrapy.utils.spider import iterate_spider_output from scrapy.utils.python import get_spec +from scrapy.utils.spider import iterate_spider_output + + +class Contract: + """ Abstract class for contracts """ + request_cls = None + + def __init__(self, method, *args): + self.testcase_pre = _create_testcase(method, f'@{self.name} pre-hook') + self.testcase_post = _create_testcase(method, f'@{self.name} post-hook') + self.args = args + + def add_pre_hook(self, request, results): + if hasattr(self, 'pre_process'): + cb = request.callback + + @wraps(cb) + def wrapper(response, **cb_kwargs): + try: + results.startTest(self.testcase_pre) + self.pre_process(response) + results.stopTest(self.testcase_pre) + except AssertionError: + results.addFailure(self.testcase_pre, sys.exc_info()) + except Exception: + results.addError(self.testcase_pre, sys.exc_info()) + else: + results.addSuccess(self.testcase_pre) + finally: + return list(iterate_spider_output(cb(response, **cb_kwargs))) + + request.callback = wrapper + + return request + + def add_post_hook(self, request, results): + if hasattr(self, 'post_process'): + cb = request.callback + + @wraps(cb) + def wrapper(response, **cb_kwargs): + output = list(iterate_spider_output(cb(response, **cb_kwargs))) + try: + results.startTest(self.testcase_post) + self.post_process(output) + results.stopTest(self.testcase_post) + except AssertionError: + results.addFailure(self.testcase_post, sys.exc_info()) + except Exception: + results.addError(self.testcase_post, sys.exc_info()) + else: + results.addSuccess(self.testcase_post) + finally: + return output + + request.callback = wrapper + + return request + + def adjust_request_args(self, args): + return args class ContractsManager: - contracts = {} + contracts: Dict[str, Contract] = {} def __init__(self, contracts): for contract in contracts: @@ -107,73 +168,13 @@ class ContractsManager: request.errback = eb_wrapper -class Contract: - """ Abstract class for contracts """ - request_cls = None - - def __init__(self, method, *args): - self.testcase_pre = _create_testcase(method, '@%s pre-hook' % self.name) - self.testcase_post = _create_testcase(method, '@%s post-hook' % self.name) - self.args = args - - def add_pre_hook(self, request, results): - if hasattr(self, 'pre_process'): - cb = request.callback - - @wraps(cb) - def wrapper(response, **cb_kwargs): - try: - results.startTest(self.testcase_pre) - self.pre_process(response) - results.stopTest(self.testcase_pre) - except AssertionError: - results.addFailure(self.testcase_pre, sys.exc_info()) - except Exception: - results.addError(self.testcase_pre, sys.exc_info()) - else: - results.addSuccess(self.testcase_pre) - finally: - return list(iterate_spider_output(cb(response, **cb_kwargs))) - - request.callback = wrapper - - return request - - def add_post_hook(self, request, results): - if hasattr(self, 'post_process'): - cb = request.callback - - @wraps(cb) - def wrapper(response, **cb_kwargs): - output = list(iterate_spider_output(cb(response, **cb_kwargs))) - try: - results.startTest(self.testcase_post) - self.post_process(output) - results.stopTest(self.testcase_post) - except AssertionError: - results.addFailure(self.testcase_post, sys.exc_info()) - except Exception: - results.addError(self.testcase_post, sys.exc_info()) - else: - results.addSuccess(self.testcase_post) - finally: - return output - - request.callback = wrapper - - return request - - def adjust_request_args(self, args): - return args - - def _create_testcase(method, desc): spider = method.__self__.name class ContractTestCase(TestCase): def __str__(_self): - return "[%s] %s (%s)" % (spider, method.__name__, desc) + return f"[{spider}] {method.__name__} ({desc})" - name = '%s_%s' % (spider, method.__name__) + name = f'{spider}_{method.__name__}' setattr(ContractTestCase, name, lambda x: x) return ContractTestCase(name) diff --git a/scrapy/contracts/default.py b/scrapy/contracts/default.py index cdc2bac15..9704f5253 100644 --- a/scrapy/contracts/default.py +++ b/scrapy/contracts/default.py @@ -1,10 +1,10 @@ import json -from scrapy.item import _BaseItem -from scrapy.http import Request -from scrapy.exceptions import ContractFail +from itemadapter import is_item, ItemAdapter from scrapy.contracts import Contract +from scrapy.exceptions import ContractFail +from scrapy.http import Request # contracts @@ -48,23 +48,22 @@ class ReturnsContract(Contract): """ name = 'returns' - objects = { - 'request': Request, - 'requests': Request, - 'item': (_BaseItem, dict), - 'items': (_BaseItem, dict), + object_type_verifiers = { + 'request': lambda x: isinstance(x, Request), + 'requests': lambda x: isinstance(x, Request), + 'item': is_item, + 'items': is_item, } def __init__(self, *args, **kwargs): - super(ReturnsContract, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) if len(self.args) not in [1, 2, 3]: raise ValueError( - "Incorrect argument quantity: expected 1, 2 or 3, got %i" - % len(self.args) + f"Incorrect argument quantity: expected 1, 2 or 3, got {len(self.args)}" ) self.obj_name = self.args[0] or None - self.obj_type = self.objects[self.obj_name] + self.obj_type_verifier = self.object_type_verifiers[self.obj_name] try: self.min_bound = int(self.args[1]) @@ -79,7 +78,7 @@ class ReturnsContract(Contract): def post_process(self, output): occurrences = 0 for x in output: - if isinstance(x, self.obj_type): + if self.obj_type_verifier(x): occurrences += 1 assertion = (self.min_bound <= occurrences <= self.max_bound) @@ -88,10 +87,9 @@ class ReturnsContract(Contract): if self.min_bound == self.max_bound: expected = self.min_bound else: - expected = '%s..%s' % (self.min_bound, self.max_bound) + expected = f'{self.min_bound}..{self.max_bound}' - raise ContractFail("Returned %s %s, expected %s" % - (occurrences, self.obj_name, expected)) + raise ContractFail(f"Returned {occurrences} {self.obj_name}, expected {expected}") class ScrapesContract(Contract): @@ -103,8 +101,8 @@ class ScrapesContract(Contract): def post_process(self, output): for x in output: - if isinstance(x, (_BaseItem, dict)): - missing = [arg for arg in self.args if arg not in x] + if is_item(x): + missing = [arg for arg in self.args if arg not in ItemAdapter(x)] if missing: - raise ContractFail( - "Missing fields: %s" % ", ".join(missing)) + missing_fields = ", ".join(missing) + raise ContractFail(f"Missing fields: {missing_fields}") diff --git a/scrapy/core/downloader/__init__.py b/scrapy/core/downloader/__init__.py index dc5cf1ab8..4f7ab594f 100644 --- a/scrapy/core/downloader/__init__.py +++ b/scrapy/core/downloader/__init__.py @@ -41,17 +41,17 @@ class Slot: def __repr__(self): cls_name = self.__class__.__name__ - return "%s(concurrency=%r, delay=%0.2f, randomize_delay=%r)" % ( - cls_name, self.concurrency, self.delay, self.randomize_delay) + return (f"{cls_name}(concurrency={self.concurrency!r}, " + f"delay={self.delay:.2f}, " + f"randomize_delay={self.randomize_delay!r})") def __str__(self): return ( - "" % ( - self.concurrency, self.delay, self.randomize_delay, - len(self.active), len(self.queue), len(self.transferring), - datetime.fromtimestamp(self.lastseen).isoformat() - ) + f"" ) diff --git a/scrapy/core/downloader/contextfactory.py b/scrapy/core/downloader/contextfactory.py index 452242d47..073ef16bf 100644 --- a/scrapy/core/downloader/contextfactory.py +++ b/scrapy/core/downloader/contextfactory.py @@ -1,10 +1,15 @@ +import warnings + from OpenSSL import SSL +from twisted.internet._sslverify import _setAcceptableProtocols from twisted.internet.ssl import optionsForClientTLS, CertificateOptions, platformTrust, AcceptableCiphers from twisted.web.client import BrowserLikePolicyForHTTPS from twisted.web.iweb import IPolicyForHTTPS from zope.interface.declarations import implementer +from zope.interface.verify import verifyObject -from scrapy.core.downloader.tls import ScrapyClientTLSOptions, DEFAULT_CIPHERS +from scrapy.core.downloader.tls import DEFAULT_CIPHERS, openssl_methods, ScrapyClientTLSOptions +from scrapy.utils.misc import create_instance, load_object @implementer(IPolicyForHTTPS) @@ -20,7 +25,7 @@ class ScrapyClientContextFactory(BrowserLikePolicyForHTTPS): """ def __init__(self, method=SSL.SSLv23_METHOD, tls_verbose_logging=False, tls_ciphers=None, *args, **kwargs): - super(ScrapyClientContextFactory, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self._ssl_method = method self.tls_verbose_logging = tls_verbose_logging if tls_ciphers: @@ -45,7 +50,7 @@ class ScrapyClientContextFactory(BrowserLikePolicyForHTTPS): # (https://github.com/scrapy/scrapy/issues/1429#issuecomment-131782133) # # * getattr() for `_ssl_method` attribute for context factories - # not calling super(..., self).__init__ + # not calling super().__init__ return CertificateOptions( verify=False, method=getattr(self, 'method', getattr(self, '_ssl_method', None)), @@ -81,8 +86,8 @@ class BrowserLikeContextFactory(ScrapyClientContextFactory): The default OpenSSL method is ``TLS_METHOD`` (also called ``SSLv23_METHOD``) which allows TLS protocol negotiation. """ - def creatorForNetloc(self, hostname, port): + def creatorForNetloc(self, hostname, port): # trustRoot set to platformTrust() will use the platform's root CAs. # # This means that a website like https://www.cacert.org will be rejected @@ -92,3 +97,49 @@ class BrowserLikeContextFactory(ScrapyClientContextFactory): trustRoot=platformTrust(), extraCertificateOptions={'method': self._ssl_method}, ) + + +@implementer(IPolicyForHTTPS) +class AcceptableProtocolsContextFactory: + """Context factory to used to override the acceptable protocols + to set up the [OpenSSL.SSL.Context] for doing NPN and/or ALPN + negotiation. + """ + + def __init__(self, context_factory, acceptable_protocols): + verifyObject(IPolicyForHTTPS, context_factory) + self._wrapped_context_factory = context_factory + self._acceptable_protocols = acceptable_protocols + + def creatorForNetloc(self, hostname, port): + options = self._wrapped_context_factory.creatorForNetloc(hostname, port) + _setAcceptableProtocols(options._ctx, self._acceptable_protocols) + return options + + +def load_context_factory_from_settings(settings, crawler): + ssl_method = openssl_methods[settings.get('DOWNLOADER_CLIENT_TLS_METHOD')] + context_factory_cls = load_object(settings['DOWNLOADER_CLIENTCONTEXTFACTORY']) + # try method-aware context factory + try: + context_factory = create_instance( + objcls=context_factory_cls, + settings=settings, + crawler=crawler, + method=ssl_method, + ) + except TypeError: + # use context factory defaults + context_factory = create_instance( + objcls=context_factory_cls, + settings=settings, + crawler=crawler, + ) + msg = """ + '%s' does not accept `method` argument (type OpenSSL.SSL method,\ + e.g. OpenSSL.SSL.SSLv23_METHOD) and/or `tls_verbose_logging` argument and/or `tls_ciphers` argument.\ + Please upgrade your context factory class to handle them or ignore them.""" % ( + settings['DOWNLOADER_CLIENTCONTEXTFACTORY'],) + warnings.warn(msg) + + return context_factory diff --git a/scrapy/core/downloader/handlers/__init__.py b/scrapy/core/downloader/handlers/__init__.py index e86680978..73aeb2352 100644 --- a/scrapy/core/downloader/handlers/__init__.py +++ b/scrapy/core/downloader/handlers/__init__.py @@ -71,8 +71,7 @@ class DownloadHandlers: scheme = urlparse_cached(request).scheme handler = self._get_handler(scheme) if not handler: - raise NotSupported("Unsupported URL scheme '%s': %s" % - (scheme, self._notconfigured[scheme])) + raise NotSupported(f"Unsupported URL scheme '{scheme}': {self._notconfigured[scheme]}") return handler.download_request(request, spider) @defer.inlineCallbacks diff --git a/scrapy/core/downloader/handlers/http11.py b/scrapy/core/downloader/handlers/http11.py index 22c9ac520..8a91d4c5e 100644 --- a/scrapy/core/downloader/handlers/http11.py +++ b/scrapy/core/downloader/handlers/http11.py @@ -7,7 +7,7 @@ import warnings from contextlib import suppress from io import BytesIO from time import time -from urllib.parse import urldefrag +from urllib.parse import urldefrag, urlunparse from twisted.internet import defer, protocol, ssl from twisted.internet.endpoints import TCP4ClientEndpoint @@ -20,12 +20,11 @@ from twisted.web.iweb import IBodyProducer, UNKNOWN_LENGTH from zope.interface import implementer from scrapy import signals -from scrapy.core.downloader.tls import openssl_methods +from scrapy.core.downloader.contextfactory import load_context_factory_from_settings from scrapy.core.downloader.webclient import _parse from scrapy.exceptions import ScrapyDeprecationWarning, StopDownload from scrapy.http import Headers from scrapy.responsetypes import responsetypes -from scrapy.utils.misc import create_instance, load_object from scrapy.utils.python import to_bytes, to_unicode @@ -43,29 +42,7 @@ class HTTP11DownloadHandler: self._pool.maxPersistentPerHost = settings.getint('CONCURRENT_REQUESTS_PER_DOMAIN') self._pool._factory.noisy = False - self._sslMethod = openssl_methods[settings.get('DOWNLOADER_CLIENT_TLS_METHOD')] - self._contextFactoryClass = load_object(settings['DOWNLOADER_CLIENTCONTEXTFACTORY']) - # try method-aware context factory - try: - self._contextFactory = create_instance( - objcls=self._contextFactoryClass, - settings=settings, - crawler=crawler, - method=self._sslMethod, - ) - except TypeError: - # use context factory defaults - self._contextFactory = create_instance( - objcls=self._contextFactoryClass, - settings=settings, - crawler=crawler, - ) - msg = """ - '%s' does not accept `method` argument (type OpenSSL.SSL method,\ - e.g. OpenSSL.SSL.SSLv23_METHOD) and/or `tls_verbose_logging` argument and/or `tls_ciphers` argument.\ - Please upgrade your context factory class to handle them or ignore them.""" % ( - settings['DOWNLOADER_CLIENTCONTEXTFACTORY'],) - warnings.warn(msg) + self._contextFactory = load_context_factory_from_settings(settings, crawler) self._default_maxsize = settings.getint('DOWNLOAD_MAXSIZE') self._default_warnsize = settings.getint('DOWNLOAD_WARNSIZE') self._fail_on_dataloss = settings.getbool('DOWNLOAD_FAIL_ON_DATALOSS') @@ -121,12 +98,13 @@ class TunnelingTCP4ClientEndpoint(TCP4ClientEndpoint): with this endpoint comes from the pool and a CONNECT has already been issued for it. """ - - _responseMatcher = re.compile(br'HTTP/1\.. (?P\d{3})(?P.{,32})') + _truncatedLength = 1000 + _responseAnswer = r'HTTP/1\.. (?P\d{3})(?P.{,' + str(_truncatedLength) + r'})' + _responseMatcher = re.compile(_responseAnswer.encode()) def __init__(self, reactor, host, port, proxyConf, contextFactory, timeout=30, bindAddress=None): proxyHost, proxyPort, self._proxyAuthHeader = proxyConf - super(TunnelingTCP4ClientEndpoint, self).__init__(reactor, proxyHost, proxyPort, timeout, bindAddress) + super().__init__(reactor, proxyHost, proxyPort, timeout, bindAddress) self._tunnelReadyDeferred = defer.Deferred() self._tunneledHost = host self._tunneledPort = port @@ -167,10 +145,11 @@ class TunnelingTCP4ClientEndpoint(TCP4ClientEndpoint): extra = {'status': int(respm.group('status')), 'reason': respm.group('reason').strip()} else: - extra = rcvd_bytes[:32] + extra = rcvd_bytes[:self._truncatedLength] self._tunnelReadyDeferred.errback( - TunnelError('Could not open CONNECT tunnel with proxy %s:%s [%r]' % ( - self._host, self._port, extra))) + TunnelError('Could not open CONNECT tunnel with proxy ' + f'{self._host}:{self._port} [{extra!r}]') + ) def connectFailed(self, reason): """Propagates the errback to the appropriate deferred.""" @@ -178,7 +157,7 @@ class TunnelingTCP4ClientEndpoint(TCP4ClientEndpoint): def connect(self, protocolFactory): self._protocolFactory = protocolFactory - connectDeferred = super(TunnelingTCP4ClientEndpoint, self).connect(protocolFactory) + connectDeferred = super().connect(protocolFactory) connectDeferred.addCallback(self.requestTunnel) connectDeferred.addErrback(self.connectFailed) return self._tunnelReadyDeferred @@ -215,7 +194,7 @@ class TunnelingAgent(Agent): def __init__(self, reactor, proxyConf, contextFactory=None, connectTimeout=None, bindAddress=None, pool=None): - super(TunnelingAgent, self).__init__(reactor, contextFactory, connectTimeout, bindAddress, pool) + super().__init__(reactor, contextFactory, connectTimeout, bindAddress, pool) self._proxyConf = proxyConf self._contextFactory = contextFactory @@ -235,7 +214,7 @@ class TunnelingAgent(Agent): # otherwise, same remote host connection request could reuse # a cached tunneled connection to a different proxy key = key + self._proxyConf - return super(TunnelingAgent, self)._requestWithEndpoint( + return super()._requestWithEndpoint( key=key, endpoint=endpoint, method=method, @@ -249,7 +228,7 @@ class TunnelingAgent(Agent): class ScrapyProxyAgent(Agent): def __init__(self, reactor, proxyURI, connectTimeout=None, bindAddress=None, pool=None): - super(ScrapyProxyAgent, self).__init__( + super().__init__( reactor=reactor, connectTimeout=connectTimeout, bindAddress=bindAddress, @@ -297,16 +276,19 @@ class ScrapyAgent: bindaddress = request.meta.get('bindaddress') or self._bindAddress proxy = request.meta.get('proxy') if proxy: - _, _, proxyHost, proxyPort, proxyParams = _parse(proxy) + proxyScheme, proxyNetloc, proxyHost, proxyPort, proxyParams = _parse(proxy) scheme = _parse(request.url)[0] proxyHost = to_unicode(proxyHost) omitConnectTunnel = b'noconnect' in proxyParams if omitConnectTunnel: - warnings.warn("Using HTTPS proxies in the noconnect mode is deprecated. " - "If you use Crawlera, it doesn't require this mode anymore, " - "so you should update scrapy-crawlera to 1.3.0+ " - "and remove '?noconnect' from the Crawlera URL.", - ScrapyDeprecationWarning) + warnings.warn( + "Using HTTPS proxies in the noconnect mode is deprecated. " + "If you use Zyte Smart Proxy Manager, it doesn't require " + "this mode anymore, so you should update scrapy-crawlera " + "to scrapy-zyte-smartproxy and remove '?noconnect' " + "from the Zyte Smart Proxy Manager URL.", + ScrapyDeprecationWarning, + ) if scheme == b'https' and not omitConnectTunnel: proxyAuth = request.headers.get(b'Proxy-Authorization', None) proxyConf = (proxyHost, proxyPort, proxyAuth) @@ -319,9 +301,13 @@ class ScrapyAgent: pool=self._pool, ) else: + proxyScheme = proxyScheme or b'http' + proxyHost = to_bytes(proxyHost, encoding='ascii') + proxyPort = to_bytes(str(proxyPort), encoding='ascii') + proxyURI = urlunparse((proxyScheme, proxyNetloc, proxyParams, '', '', '')) return self._ProxyAgent( reactor=reactor, - proxyURI=to_bytes(proxy, encoding='ascii'), + proxyURI=to_bytes(proxyURI, encoding='ascii'), connectTimeout=timeout, bindAddress=bindaddress, pool=self._pool, @@ -371,13 +357,44 @@ class ScrapyAgent: if self._txresponse: self._txresponse._transport.stopProducing() - raise TimeoutError("Getting %s took longer than %s seconds." % (url, timeout)) + raise TimeoutError(f"Getting {url} took longer than {timeout} seconds.") def _cb_latency(self, result, request, start_time): request.meta['download_latency'] = time() - start_time return result + @staticmethod + def _headers_from_twisted_response(response): + headers = Headers() + if response.length != UNKNOWN_LENGTH: + headers[b'Content-Length'] = str(response.length).encode() + headers.update(response.headers.getAllRawHeaders()) + return headers + def _cb_bodyready(self, txresponse, request): + headers_received_result = self._crawler.signals.send_catch_log( + signal=signals.headers_received, + headers=self._headers_from_twisted_response(txresponse), + body_length=txresponse.length, + request=request, + spider=self._crawler.spider, + ) + for handler, result in headers_received_result: + if isinstance(result, Failure) and isinstance(result.value, StopDownload): + logger.debug("Download stopped for %(request)s from signal handler %(handler)s", + {"request": request, "handler": handler.__qualname__}) + txresponse._transport.stopProducing() + with suppress(AttributeError): + txresponse._transport._producer.loseConnection() + return { + "txresponse": txresponse, + "body": b"", + "flags": ["download_stopped"], + "certificate": None, + "ip_address": None, + "failure": result if result.value.fail else None, + } + # deliverBody hangs for responses without body if txresponse.length == 0: return { @@ -394,13 +411,14 @@ class ScrapyAgent: fail_on_dataloss = request.meta.get('download_fail_on_dataloss', self._fail_on_dataloss) if maxsize and expected_size > maxsize: - error_msg = ("Cancelling download of %(url)s: expected response " - "size (%(size)s) larger than download max size (%(maxsize)s).") - error_args = {'url': request.url, 'size': expected_size, 'maxsize': maxsize} + warning_msg = ("Cancelling download of %(url)s: expected response " + "size (%(size)s) larger than download max size (%(maxsize)s).") + warning_args = {'url': request.url, 'size': expected_size, 'maxsize': maxsize} + + logger.warning(warning_msg, warning_args) - logger.error(error_msg, error_args) txresponse._transport._producer.loseConnection() - raise defer.CancelledError(error_msg % error_args) + raise defer.CancelledError(warning_msg % warning_args) if warnsize and expected_size > warnsize: logger.warning("Expected response size (%(size)s) larger than " @@ -430,8 +448,13 @@ class ScrapyAgent: return d def _cb_bodydone(self, result, request, url): - headers = Headers(result["txresponse"].headers.getAllRawHeaders()) + headers = self._headers_from_twisted_response(result["txresponse"]) respcls = responsetypes.from_args(headers=headers, url=url, body=result["body"]) + try: + version = result["txresponse"].version + protocol = f"{to_unicode(version[0])}/{version[1]}.{version[2]}" + except (AttributeError, TypeError, IndexError): + protocol = None response = respcls( url=url, status=int(result["txresponse"].code), @@ -440,6 +463,7 @@ class ScrapyAgent: flags=result["flags"], certificate=result["certificate"], ip_address=result["ip_address"], + protocol=protocol, ) if result.get("failure"): result["failure"].value.response = response @@ -518,16 +542,17 @@ class _ResponseReader(protocol.Protocol): if isinstance(result, Failure) and isinstance(result.value, StopDownload): logger.debug("Download stopped for %(request)s from signal handler %(handler)s", {"request": self._request, "handler": handler.__qualname__}) + self.transport.stopProducing() self.transport._producer.loseConnection() failure = result if result.value.fail else None self._finish_response(flags=["download_stopped"], failure=failure) if self._maxsize and self._bytes_received > self._maxsize: - logger.error("Received (%(bytes)s) bytes larger than download " - "max size (%(maxsize)s) in request %(request)s.", - {'bytes': self._bytes_received, - 'maxsize': self._maxsize, - 'request': self._request}) + logger.warning("Received (%(bytes)s) bytes larger than download " + "max size (%(maxsize)s) in request %(request)s.", + {'bytes': self._bytes_received, + 'maxsize': self._maxsize, + 'request': self._request}) # Clear buffer earlier to avoid keeping data in memory for a long time. self._bodybuf.truncate(0) self._finished.cancel() diff --git a/scrapy/core/downloader/handlers/http2.py b/scrapy/core/downloader/handlers/http2.py new file mode 100644 index 000000000..7bb88a193 --- /dev/null +++ b/scrapy/core/downloader/handlers/http2.py @@ -0,0 +1,129 @@ +import warnings +from time import time +from typing import Optional, Type, TypeVar +from urllib.parse import urldefrag + +from twisted.internet.base import DelayedCall +from twisted.internet.defer import Deferred +from twisted.internet.error import TimeoutError +from twisted.web.client import URI + +from scrapy.core.downloader.contextfactory import load_context_factory_from_settings +from scrapy.core.downloader.webclient import _parse +from scrapy.core.http2.agent import H2Agent, H2ConnectionPool, ScrapyProxyH2Agent +from scrapy.crawler import Crawler +from scrapy.http import Request, Response +from scrapy.settings import Settings +from scrapy.spiders import Spider +from scrapy.utils.python import to_bytes + + +H2DownloadHandlerOrSubclass = TypeVar("H2DownloadHandlerOrSubclass", bound="H2DownloadHandler") + + +class H2DownloadHandler: + def __init__(self, settings: Settings, crawler: Optional[Crawler] = None): + self._crawler = crawler + + from twisted.internet import reactor + self._pool = H2ConnectionPool(reactor, settings) + self._context_factory = load_context_factory_from_settings(settings, crawler) + + @classmethod + def from_crawler(cls: Type[H2DownloadHandlerOrSubclass], crawler: Crawler) -> H2DownloadHandlerOrSubclass: + return cls(crawler.settings, crawler) + + def download_request(self, request: Request, spider: Spider) -> Deferred: + agent = ScrapyH2Agent( + context_factory=self._context_factory, + pool=self._pool, + crawler=self._crawler, + ) + return agent.download_request(request, spider) + + def close(self) -> None: + self._pool.close_connections() + + +class ScrapyH2Agent: + _Agent = H2Agent + _ProxyAgent = ScrapyProxyH2Agent + + def __init__( + self, context_factory, + pool: H2ConnectionPool, + connect_timeout: int = 10, + bind_address: Optional[bytes] = None, + crawler: Optional[Crawler] = None, + ) -> None: + self._context_factory = context_factory + self._connect_timeout = connect_timeout + self._bind_address = bind_address + self._pool = pool + self._crawler = crawler + + def _get_agent(self, request: Request, timeout: Optional[float]) -> H2Agent: + from twisted.internet import reactor + bind_address = request.meta.get('bindaddress') or self._bind_address + proxy = request.meta.get('proxy') + if proxy: + _, _, proxy_host, proxy_port, proxy_params = _parse(proxy) + scheme = _parse(request.url)[0] + proxy_host = proxy_host.decode() + omit_connect_tunnel = b'noconnect' in proxy_params + if omit_connect_tunnel: + warnings.warn( + "Using HTTPS proxies in the noconnect mode is not " + "supported by the downloader handler. If you use Zyte " + "Smart Proxy Manager, it doesn't require this mode " + "anymore, so you should update scrapy-crawlera to " + "scrapy-zyte-smartproxy and remove '?noconnect' from the " + "Zyte Smart Proxy Manager URL." + ) + + if scheme == b'https' and not omit_connect_tunnel: + # ToDo + raise NotImplementedError('Tunneling via CONNECT method using HTTP/2.0 is not yet supported') + return self._ProxyAgent( + reactor=reactor, + context_factory=self._context_factory, + proxy_uri=URI.fromBytes(to_bytes(proxy, encoding='ascii')), + connect_timeout=timeout, + bind_address=bind_address, + pool=self._pool, + ) + + return self._Agent( + reactor=reactor, + context_factory=self._context_factory, + connect_timeout=timeout, + bind_address=bind_address, + pool=self._pool, + ) + + def download_request(self, request: Request, spider: Spider) -> Deferred: + from twisted.internet import reactor + timeout = request.meta.get('download_timeout') or self._connect_timeout + agent = self._get_agent(request, timeout) + + start_time = time() + d = agent.request(request, spider) + d.addCallback(self._cb_latency, request, start_time) + + timeout_cl = reactor.callLater(timeout, d.cancel) + d.addBoth(self._cb_timeout, request, timeout, timeout_cl) + return d + + @staticmethod + def _cb_latency(response: Response, request: Request, start_time: float) -> Response: + request.meta['download_latency'] = time() - start_time + return response + + @staticmethod + def _cb_timeout(response: Response, request: Request, timeout: float, timeout_cl: DelayedCall) -> Response: + if timeout_cl.active(): + timeout_cl.cancel() + return response + + url = urldefrag(request.url)[0] + raise TimeoutError(f"Getting {url} took longer than {timeout} seconds.") diff --git a/scrapy/core/downloader/handlers/s3.py b/scrapy/core/downloader/handlers/s3.py index 8f63ad974..31f1be31a 100644 --- a/scrapy/core/downloader/handlers/s3.py +++ b/scrapy/core/downloader/handlers/s3.py @@ -1,42 +1,19 @@ -from urllib.parse import unquote - from scrapy.core.downloader.handlers.http import HTTPDownloadHandler from scrapy.exceptions import NotConfigured -from scrapy.utils.boto import is_botocore +from scrapy.utils.boto import is_botocore_available from scrapy.utils.httpobj import urlparse_cached from scrapy.utils.misc import create_instance -def _get_boto_connection(): - from boto.s3.connection import S3Connection - - class _v19_S3Connection(S3Connection): - """A dummy S3Connection wrapper that doesn't do any synchronous download""" - def _mexe(self, method, bucket, key, headers, *args, **kwargs): - return headers - - class _v20_S3Connection(S3Connection): - """A dummy S3Connection wrapper that doesn't do any synchronous download""" - def _mexe(self, http_request, *args, **kwargs): - http_request.authorize(connection=self) - return http_request.headers - - try: - import boto.auth # noqa: F401 - except ImportError: - _S3Connection = _v19_S3Connection - else: - _S3Connection = _v20_S3Connection - - return _S3Connection - - class S3DownloadHandler: def __init__(self, settings, *, crawler=None, aws_access_key_id=None, aws_secret_access_key=None, httpdownloadhandler=HTTPDownloadHandler, **kw): + if not is_botocore_available(): + raise NotConfigured('missing botocore library') + if not aws_access_key_id: aws_access_key_id = settings['AWS_ACCESS_KEY_ID'] if not aws_secret_access_key: @@ -51,23 +28,15 @@ class S3DownloadHandler: self.anon = kw.get('anon') self._signer = None - if is_botocore(): - import botocore.auth - import botocore.credentials - kw.pop('anon', None) - if kw: - raise TypeError('Unexpected keyword arguments: %s' % kw) - if not self.anon: - SignerCls = botocore.auth.AUTH_TYPE_MAPS['s3'] - self._signer = SignerCls(botocore.credentials.Credentials( - aws_access_key_id, aws_secret_access_key)) - else: - _S3Connection = _get_boto_connection() - try: - self.conn = _S3Connection( - aws_access_key_id, aws_secret_access_key, **kw) - except Exception as ex: - raise NotConfigured(str(ex)) + import botocore.auth + import botocore.credentials + kw.pop('anon', None) + if kw: + raise TypeError(f'Unexpected keyword arguments: {kw}') + if not self.anon: + SignerCls = botocore.auth.AUTH_TYPE_MAPS['s3'] + self._signer = SignerCls(botocore.credentials.Credentials( + aws_access_key_id, aws_secret_access_key)) _http_handler = create_instance( objcls=httpdownloadhandler, @@ -85,27 +54,17 @@ class S3DownloadHandler: scheme = 'https' if request.meta.get('is_secure') else 'http' bucket = p.hostname path = p.path + '?' + p.query if p.query else p.path - url = '%s://%s.s3.amazonaws.com%s' % (scheme, bucket, path) + url = f'{scheme}://{bucket}.s3.amazonaws.com{path}' if self.anon: request = request.replace(url=url) - elif self._signer is not None: + else: import botocore.awsrequest awsrequest = botocore.awsrequest.AWSRequest( method=request.method, - url='%s://s3.amazonaws.com/%s%s' % (scheme, bucket, path), + url=f'{scheme}://s3.amazonaws.com/{bucket}{path}', headers=request.headers.to_unicode_dict(), data=request.body) self._signer.add_auth(awsrequest) request = request.replace( url=url, headers=awsrequest.headers.items()) - else: - signed_headers = self.conn.make_request( - method=request.method, - bucket=bucket, - key=unquote(p.path), - query_args=unquote(p.query), - headers=request.headers, - data=request.body, - ) - request = request.replace(url=url, headers=signed_headers) return self._download_http(request, spider) diff --git a/scrapy/core/downloader/middleware.py b/scrapy/core/downloader/middleware.py index 4c2eea522..a5619d8a4 100644 --- a/scrapy/core/downloader/middleware.py +++ b/scrapy/core/downloader/middleware.py @@ -3,8 +3,12 @@ Downloader Middleware manager See documentation in docs/topics/downloader-middleware.rst """ -from twisted.internet import defer +from typing import Callable, Union +from twisted.internet import defer +from twisted.python.failure import Failure + +from scrapy import Spider from scrapy.exceptions import _InvalidOutput from scrapy.http import Request, Response from scrapy.middleware import MiddlewareManager @@ -29,22 +33,22 @@ class DownloaderMiddlewareManager(MiddlewareManager): if hasattr(mw, 'process_exception'): self.methods['process_exception'].appendleft(mw.process_exception) - def download(self, download_func, request, spider): + def download(self, download_func: Callable, request: Request, spider: Spider): @defer.inlineCallbacks - def process_request(request): + def process_request(request: Request): for method in self.methods['process_request']: response = yield deferred_from_coro(method(request=request, spider=spider)) if response is not None and not isinstance(response, (Response, Request)): raise _InvalidOutput( - "Middleware %s.process_request must return None, Response or Request, got %s" - % (method.__self__.__class__.__name__, response.__class__.__name__) + f"Middleware {method.__qualname__} must return None, Response or " + f"Request, got {response.__class__.__name__}" ) if response: return response return (yield download_func(request=request, spider=spider)) @defer.inlineCallbacks - def process_response(response): + def process_response(response: Union[Response, Request]): if response is None: raise TypeError("Received None in process_response") elif isinstance(response, Request): @@ -54,22 +58,22 @@ class DownloaderMiddlewareManager(MiddlewareManager): response = yield deferred_from_coro(method(request=request, response=response, spider=spider)) if not isinstance(response, (Response, Request)): raise _InvalidOutput( - "Middleware %s.process_response must return Response or Request, got %s" - % (method.__self__.__class__.__name__, type(response)) + f"Middleware {method.__qualname__} must return Response or Request, " + f"got {type(response)}" ) if isinstance(response, Request): return response return response @defer.inlineCallbacks - def process_exception(failure): + def process_exception(failure: Failure): exception = failure.value for method in self.methods['process_exception']: response = yield deferred_from_coro(method(request=request, exception=exception, spider=spider)) if response is not None and not isinstance(response, (Response, Request)): raise _InvalidOutput( - "Middleware %s.process_exception must return None, Response or Request, got %s" - % (method.__self__.__class__.__name__, type(response)) + f"Middleware {method.__qualname__} must return None, Response or " + f"Request, got {type(response)}" ) if response: return response diff --git a/scrapy/core/downloader/tls.py b/scrapy/core/downloader/tls.py index e43a3c83e..2b8990b75 100644 --- a/scrapy/core/downloader/tls.py +++ b/scrapy/core/downloader/tls.py @@ -5,7 +5,6 @@ from service_identity.exceptions import CertificateError from twisted.internet._sslverify import ClientTLSOptions, verifyHostname, VerificationError from twisted.internet.ssl import AcceptableCiphers -from scrapy import twisted_version from scrapy.utils.ssl import x509name_to_string, get_temp_key_info @@ -28,13 +27,6 @@ openssl_methods = { } -if twisted_version < (17, 0, 0): - from twisted.internet._sslverify import _maybeSetHostNameIndication as set_tlsext_host_name -else: - def set_tlsext_host_name(connection, hostNameBytes): - connection.set_tlsext_host_name(hostNameBytes) - - class ScrapyClientTLSOptions(ClientTLSOptions): """ SSL Client connection creator ignoring certificate verification errors @@ -47,26 +39,19 @@ class ScrapyClientTLSOptions(ClientTLSOptions): """ def __init__(self, hostname, ctx, verbose_logging=False): - super(ScrapyClientTLSOptions, self).__init__(hostname, ctx) + super().__init__(hostname, ctx) self.verbose_logging = verbose_logging def _identityVerifyingInfoCallback(self, connection, where, ret): if where & SSL.SSL_CB_HANDSHAKE_START: - set_tlsext_host_name(connection, self._hostnameBytes) + connection.set_tlsext_host_name(self._hostnameBytes) elif where & SSL.SSL_CB_HANDSHAKE_DONE: if self.verbose_logging: - if hasattr(connection, 'get_cipher_name'): # requires pyOPenSSL 0.15 - if hasattr(connection, 'get_protocol_version_name'): # requires pyOPenSSL 16.0.0 - logger.debug('SSL connection to %s using protocol %s, cipher %s', - self._hostnameASCII, - connection.get_protocol_version_name(), - connection.get_cipher_name(), - ) - else: - logger.debug('SSL connection to %s using cipher %s', - self._hostnameASCII, - connection.get_cipher_name(), - ) + logger.debug('SSL connection to %s using protocol %s, cipher %s', + self._hostnameASCII, + connection.get_protocol_version_name(), + connection.get_cipher_name(), + ) server_cert = connection.get_peer_certificate() logger.debug('SSL connection certificate: issuer "%s", subject "%s"', x509name_to_string(server_cert.get_issuer()), diff --git a/scrapy/core/downloader/webclient.py b/scrapy/core/downloader/webclient.py index 355045d74..915cb5fe3 100644 --- a/scrapy/core/downloader/webclient.py +++ b/scrapy/core/downloader/webclient.py @@ -1,13 +1,14 @@ +import re from time import time from urllib.parse import urlparse, urlunparse, urldefrag -from twisted.web.client import HTTPClientFactory from twisted.web.http import HTTPClient -from twisted.internet import defer +from twisted.internet import defer, reactor +from twisted.internet.protocol import ClientFactory from scrapy.http import Headers from scrapy.utils.httpobj import urlparse_cached -from scrapy.utils.python import to_bytes +from scrapy.utils.python import to_bytes, to_unicode from scrapy.responsetypes import responsetypes @@ -32,6 +33,8 @@ def _parse(url): and is ascii-only. """ url = url.strip() + if not re.match(r'^\w+://', url): + url = '//' + url parsed = urlparse(url) return _parsed_url_args(parsed) @@ -88,22 +91,38 @@ class ScrapyHTTPPageGetter(HTTPClient): self.transport.stopProducing() self.factory.noPage( - defer.TimeoutError("Getting %s took longer than %s seconds." - % (self.factory.url, self.factory.timeout))) + defer.TimeoutError(f"Getting {self.factory.url} took longer " + f"than {self.factory.timeout} seconds.")) -class ScrapyHTTPClientFactory(HTTPClientFactory): - """Scrapy implementation of the HTTPClientFactory overwriting the - setUrl method to make use of our Url object that cache the parse - result. - """ +# This class used to inherit from Twisted’s +# twisted.web.client.HTTPClientFactory. When that class was deprecated in +# Twisted (https://github.com/twisted/twisted/pull/643), we merged its +# non-overriden code into this class. +class ScrapyHTTPClientFactory(ClientFactory): protocol = ScrapyHTTPPageGetter + waiting = 1 noisy = False followRedirect = False afterFoundGet = False + def _build_response(self, body, request): + request.meta['download_latency'] = self.headers_time - self.start_time + status = int(self.status) + headers = Headers(self.response_headers) + respcls = responsetypes.from_args(headers=headers, url=self._url) + return respcls(url=self._url, status=status, headers=headers, body=body, protocol=to_unicode(self.version)) + + def _set_connection_attributes(self, request): + parsed = urlparse_cached(request) + self.scheme, self.netloc, self.host, self.port, self.path = _parsed_url_args(parsed) + proxy = request.meta.get('proxy') + if proxy: + self.scheme, _, self.host, self.port, _ = _parse(proxy) + self.path = self.url + def __init__(self, request, timeout=180): self._url = urldefrag(request.url)[0] # converting to bytes to comply to Twisted interface @@ -138,21 +157,59 @@ class ScrapyHTTPClientFactory(HTTPClientFactory): elif self.method == b'POST': self.headers['Content-Length'] = 0 - def _build_response(self, body, request): - request.meta['download_latency'] = self.headers_time - self.start_time - status = int(self.status) - headers = Headers(self.response_headers) - respcls = responsetypes.from_args(headers=headers, url=self._url) - return respcls(url=self._url, status=status, headers=headers, body=body) + def __repr__(self): + return f"<{self.__class__.__name__}: {self.url}>" - def _set_connection_attributes(self, request): - parsed = urlparse_cached(request) - self.scheme, self.netloc, self.host, self.port, self.path = _parsed_url_args(parsed) - proxy = request.meta.get('proxy') - if proxy: - self.scheme, _, self.host, self.port, _ = _parse(proxy) - self.path = self.url + def _cancelTimeout(self, result, timeoutCall): + if timeoutCall.active(): + timeoutCall.cancel() + return result + + def buildProtocol(self, addr): + p = ClientFactory.buildProtocol(self, addr) + p.followRedirect = self.followRedirect + p.afterFoundGet = self.afterFoundGet + if self.timeout: + timeoutCall = reactor.callLater(self.timeout, p.timeout) + self.deferred.addBoth(self._cancelTimeout, timeoutCall) + return p def gotHeaders(self, headers): self.headers_time = time() self.response_headers = headers + + def gotStatus(self, version, status, message): + """ + Set the status of the request on us. + @param version: The HTTP version. + @type version: L{bytes} + @param status: The HTTP status code, an integer represented as a + bytestring. + @type status: L{bytes} + @param message: The HTTP status message. + @type message: L{bytes} + """ + self.version, self.status, self.message = version, status, message + + def page(self, page): + if self.waiting: + self.waiting = 0 + self.deferred.callback(page) + + def noPage(self, reason): + if self.waiting: + self.waiting = 0 + self.deferred.errback(reason) + + def clientConnectionFailed(self, _, reason): + """ + When a connection attempt fails, the request cannot be issued. If no + result has yet been provided to the result Deferred, provide the + connection failure reason as an error result. + """ + if self.waiting: + self.waiting = 0 + # If the connection attempt failed, there is nothing more to + # disconnect, so just fire that Deferred now. + self._disconnectedDeferred.callback(None) + self.deferred.errback(reason) diff --git a/scrapy/core/engine.py b/scrapy/core/engine.py index de0da4b70..f9de7ee23 100644 --- a/scrapy/core/engine.py +++ b/scrapy/core/engine.py @@ -1,51 +1,66 @@ """ -This is the Scrapy engine which controls the Scheduler, Downloader and Spiders. +This is the Scrapy engine which controls the Scheduler, Downloader and Spider. For more information see docs/topics/architecture.rst """ import logging +import warnings from time import time +from typing import Callable, Iterable, Iterator, Optional, Set, Union -from twisted.internet import defer, task +from twisted.internet.defer import Deferred, inlineCallbacks, succeed +from twisted.internet.task import LoopingCall from twisted.python.failure import Failure from scrapy import signals from scrapy.core.scraper import Scraper -from scrapy.exceptions import DontCloseSpider +from scrapy.exceptions import ( + CloseSpider, + DontCloseSpider, + ScrapyDeprecationWarning, +) from scrapy.http import Response, Request -from scrapy.utils.misc import load_object -from scrapy.utils.reactor import CallLaterOnce +from scrapy.settings import BaseSettings +from scrapy.spiders import Spider from scrapy.utils.log import logformatter_adapter, failure_to_exc_info +from scrapy.utils.misc import create_instance, load_object +from scrapy.utils.reactor import CallLaterOnce + logger = logging.getLogger(__name__) class Slot: - - def __init__(self, start_requests, close_if_idle, nextcall, scheduler): - self.closing = False - self.inprogress = set() # requests in progress - self.start_requests = iter(start_requests) + def __init__( + self, + start_requests: Iterable, + close_if_idle: bool, + nextcall: CallLaterOnce, + scheduler, + ) -> None: + self.closing: Optional[Deferred] = None + self.inprogress: Set[Request] = set() + self.start_requests: Optional[Iterator] = iter(start_requests) self.close_if_idle = close_if_idle self.nextcall = nextcall self.scheduler = scheduler - self.heartbeat = task.LoopingCall(nextcall.schedule) + self.heartbeat = LoopingCall(nextcall.schedule) - def add_request(self, request): + def add_request(self, request: Request) -> None: self.inprogress.add(request) - def remove_request(self, request): + def remove_request(self, request: Request) -> None: self.inprogress.remove(request) self._maybe_fire_closing() - def close(self): - self.closing = defer.Deferred() + def close(self) -> Deferred: + self.closing = Deferred() self._maybe_fire_closing() return self.closing - def _maybe_fire_closing(self): - if self.closing and not self.inprogress: + def _maybe_fire_closing(self) -> None: + if self.closing is not None and not self.inprogress: if self.nextcall: self.nextcall.cancel() if self.heartbeat.running: @@ -54,203 +69,236 @@ class Slot: class ExecutionEngine: - - def __init__(self, crawler, spider_closed_callback): + def __init__(self, crawler, spider_closed_callback: Callable) -> None: self.crawler = crawler self.settings = crawler.settings self.signals = crawler.signals self.logformatter = crawler.logformatter - self.slot = None - self.spider = None + self.slot: Optional[Slot] = None + self.spider: Optional[Spider] = None self.running = False self.paused = False - self.scheduler_cls = load_object(self.settings['SCHEDULER']) + self.scheduler_cls = self._get_scheduler_class(crawler.settings) downloader_cls = load_object(self.settings['DOWNLOADER']) self.downloader = downloader_cls(crawler) self.scraper = Scraper(crawler) self._spider_closed_callback = spider_closed_callback - @defer.inlineCallbacks - def start(self): - """Start the execution engine""" + def _get_scheduler_class(self, settings: BaseSettings) -> type: + from scrapy.core.scheduler import BaseScheduler + scheduler_cls = load_object(settings["SCHEDULER"]) + if not issubclass(scheduler_cls, BaseScheduler): + raise TypeError( + f"The provided scheduler class ({settings['SCHEDULER']})" + " does not fully implement the scheduler interface" + ) + return scheduler_cls + + @inlineCallbacks + def start(self) -> Deferred: if self.running: raise RuntimeError("Engine already running") self.start_time = time() yield self.signals.send_catch_log_deferred(signal=signals.engine_started) self.running = True - self._closewait = defer.Deferred() + self._closewait = Deferred() yield self._closewait - def stop(self): - """Stop the execution engine gracefully""" + def stop(self) -> Deferred: + """Gracefully stop the execution engine""" + @inlineCallbacks + def _finish_stopping_engine(_) -> Deferred: + yield self.signals.send_catch_log_deferred(signal=signals.engine_stopped) + self._closewait.callback(None) + if not self.running: raise RuntimeError("Engine not running") + self.running = False - dfd = self._close_all_spiders() - return dfd.addBoth(lambda _: self._finish_stopping_engine()) + dfd = self.close_spider(self.spider, reason="shutdown") if self.spider is not None else succeed(None) + return dfd.addBoth(_finish_stopping_engine) - def close(self): - """Close the execution engine gracefully. - - If it has already been started, stop it. In all cases, close all spiders - and the downloader. + def close(self) -> Deferred: + """ + Gracefully close the execution engine. + If it has already been started, stop it. In all cases, close the spider and the downloader. """ if self.running: - # Will also close spiders and downloader - return self.stop() - elif self.open_spiders: - # Will also close downloader - return self._close_all_spiders() - else: - return defer.succeed(self.downloader.close()) + return self.stop() # will also close spider and downloader + if self.spider is not None: + return self.close_spider(self.spider, reason="shutdown") # will also close downloader + return succeed(self.downloader.close()) - def pause(self): - """Pause the execution engine""" + def pause(self) -> None: self.paused = True - def unpause(self): - """Resume the execution engine""" + def unpause(self) -> None: self.paused = False - def _next_request(self, spider): - slot = self.slot - if not slot: - return + def _next_request(self) -> None: + assert self.slot is not None # typing + assert self.spider is not None # typing if self.paused: - return + return None - while not self._needs_backout(spider): - if not self._next_request_from_scheduler(spider): - break + while not self._needs_backout() and self._next_request_from_scheduler() is not None: + pass - if slot.start_requests and not self._needs_backout(spider): + if self.slot.start_requests is not None and not self._needs_backout(): try: - request = next(slot.start_requests) + request = next(self.slot.start_requests) except StopIteration: - slot.start_requests = None + self.slot.start_requests = None except Exception: - slot.start_requests = None - logger.error('Error while obtaining start requests', - exc_info=True, extra={'spider': spider}) + self.slot.start_requests = None + logger.error('Error while obtaining start requests', exc_info=True, extra={'spider': self.spider}) else: - self.crawl(request, spider) + self.crawl(request) - if self.spider_is_idle(spider) and slot.close_if_idle: - self._spider_idle(spider) + if self.spider_is_idle() and self.slot.close_if_idle: + self._spider_idle() - def _needs_backout(self, spider): - slot = self.slot - return not self.running \ - or slot.closing \ - or self.downloader.needs_backout() \ - or self.scraper.slot.needs_backout() + def _needs_backout(self) -> bool: + return ( + not self.running + or self.slot.closing # type: ignore[union-attr] + or self.downloader.needs_backout() + or self.scraper.slot.needs_backout() # type: ignore[union-attr] + ) - def _next_request_from_scheduler(self, spider): - slot = self.slot - request = slot.scheduler.next_request() - if not request: - return - d = self._download(request, spider) - d.addBoth(self._handle_downloader_output, request, spider) + def _next_request_from_scheduler(self) -> Optional[Deferred]: + assert self.slot is not None # typing + assert self.spider is not None # typing + + request = self.slot.scheduler.next_request() + if request is None: + return None + + d = self._download(request, self.spider) + d.addBoth(self._handle_downloader_output, request) d.addErrback(lambda f: logger.info('Error while handling downloader output', exc_info=failure_to_exc_info(f), - extra={'spider': spider})) - d.addBoth(lambda _: slot.remove_request(request)) + extra={'spider': self.spider})) + d.addBoth(lambda _: self.slot.remove_request(request)) d.addErrback(lambda f: logger.info('Error while removing request from slot', exc_info=failure_to_exc_info(f), - extra={'spider': spider})) - d.addBoth(lambda _: slot.nextcall.schedule()) + extra={'spider': self.spider})) + d.addBoth(lambda _: self.slot.nextcall.schedule()) d.addErrback(lambda f: logger.info('Error while scheduling new request', exc_info=failure_to_exc_info(f), - extra={'spider': spider})) + extra={'spider': self.spider})) return d - def _handle_downloader_output(self, response, request, spider): - if not isinstance(response, (Request, Response, Failure)): - raise TypeError( - "Incorrect type: expected Request, Response or Failure, got %s: %r" - % (type(response), response) - ) + def _handle_downloader_output( + self, result: Union[Request, Response, Failure], request: Request + ) -> Optional[Deferred]: + assert self.spider is not None # typing + + if not isinstance(result, (Request, Response, Failure)): + raise TypeError(f"Incorrect type: expected Request, Response or Failure, got {type(result)}: {result!r}") + # downloader middleware can return requests (for example, redirects) - if isinstance(response, Request): - self.crawl(response, spider) - return - # response is a Response or Failure - d = self.scraper.enqueue_scrape(response, request, spider) - d.addErrback(lambda f: logger.error('Error while enqueuing downloader output', - exc_info=failure_to_exc_info(f), - extra={'spider': spider})) + if isinstance(result, Request): + self.crawl(result) + return None + + d = self.scraper.enqueue_scrape(result, request, self.spider) + d.addErrback( + lambda f: logger.error( + "Error while enqueuing downloader output", + exc_info=failure_to_exc_info(f), + extra={'spider': self.spider}, + ) + ) return d - def spider_is_idle(self, spider): - if not self.scraper.slot.is_idle(): - # scraper is not idle + def spider_is_idle(self, spider: Optional[Spider] = None) -> bool: + if spider is not None: + warnings.warn( + "Passing a 'spider' argument to ExecutionEngine.spider_is_idle is deprecated", + category=ScrapyDeprecationWarning, + stacklevel=2, + ) + if self.slot is None: + raise RuntimeError("Engine slot not assigned") + if not self.scraper.slot.is_idle(): # type: ignore[union-attr] return False - - if self.downloader.active: - # downloader has pending requests + if self.downloader.active: # downloader has pending requests return False - - if self.slot.start_requests is not None: - # not all start requests are handled + if self.slot.start_requests is not None: # not all start requests are handled return False - if self.slot.scheduler.has_pending_requests(): - # scheduler has pending requests return False - return True - @property - def open_spiders(self): - return [self.spider] if self.spider else [] + def crawl(self, request: Request, spider: Optional[Spider] = None) -> None: + """Inject the request into the spider <-> downloader pipeline""" + if spider is not None: + warnings.warn( + "Passing a 'spider' argument to ExecutionEngine.crawl is deprecated", + category=ScrapyDeprecationWarning, + stacklevel=2, + ) + if spider is not self.spider: + raise RuntimeError(f"The spider {spider.name!r} does not match the open spider") + if self.spider is None: + raise RuntimeError(f"No open spider to crawl: {request}") + self._schedule_request(request, self.spider) + self.slot.nextcall.schedule() # type: ignore[union-attr] - def has_capacity(self): - """Does the engine have capacity to handle more spiders""" - return not bool(self.slot) - - def crawl(self, request, spider): - if spider not in self.open_spiders: - raise RuntimeError("Spider %r not opened when crawling: %s" % (spider.name, request)) - self.schedule(request, spider) - self.slot.nextcall.schedule() - - def schedule(self, request, spider): + def _schedule_request(self, request: Request, spider: Spider) -> None: self.signals.send_catch_log(signals.request_scheduled, request=request, spider=spider) - if not self.slot.scheduler.enqueue_request(request): + if not self.slot.scheduler.enqueue_request(request): # type: ignore[union-attr] self.signals.send_catch_log(signals.request_dropped, request=request, spider=spider) - def download(self, request, spider): - d = self._download(request, spider) - d.addBoth(self._downloaded, self.slot, request, spider) - return d + def download(self, request: Request, spider: Optional[Spider] = None) -> Deferred: + """Return a Deferred which fires with a Response as result, only downloader middlewares are applied""" + if spider is None: + spider = self.spider + else: + warnings.warn( + "Passing a 'spider' argument to ExecutionEngine.download is deprecated", + category=ScrapyDeprecationWarning, + stacklevel=2, + ) + if spider is not self.spider: + logger.warning("The spider '%s' does not match the open spider", spider.name) + if spider is None: + raise RuntimeError(f"No open spider to crawl: {request}") + return self._download(request, spider).addBoth(self._downloaded, request, spider) - def _downloaded(self, response, slot, request, spider): - slot.remove_request(request) - return self.download(response, spider) if isinstance(response, Request) else response + def _downloaded( + self, result: Union[Response, Request], request: Request, spider: Spider + ) -> Union[Deferred, Response]: + assert self.slot is not None # typing + self.slot.remove_request(request) + return self.download(result, spider) if isinstance(result, Request) else result - def _download(self, request, spider): - slot = self.slot - slot.add_request(request) + def _download(self, request: Request, spider: Spider) -> Deferred: + assert self.slot is not None # typing - def _on_success(response): - if not isinstance(response, (Response, Request)): - raise TypeError( - "Incorrect type: expected Response or Request, got %s: %r" - % (type(response), response) - ) - if isinstance(response, Response): - response.request = request # tie request to response received - logkws = self.logformatter.crawled(request, response, spider) + self.slot.add_request(request) + + def _on_success(result: Union[Response, Request]) -> Union[Response, Request]: + if not isinstance(result, (Response, Request)): + raise TypeError(f"Incorrect type: expected Response or Request, got {type(result)}: {result!r}") + if isinstance(result, Response): + if result.request is None: + result.request = request + logkws = self.logformatter.crawled(result.request, result, spider) if logkws is not None: - logger.log(*logformatter_adapter(logkws), extra={'spider': spider}) - self.signals.send_catch_log(signals.response_received, - response=response, request=request, spider=spider) - return response + logger.log(*logformatter_adapter(logkws), extra={"spider": spider}) + self.signals.send_catch_log( + signal=signals.response_received, + response=result, + request=result.request, + spider=spider, + ) + return result def _on_complete(_): - slot.nextcall.schedule() + self.slot.nextcall.schedule() return _ dwld = self.downloader.fetch(request, spider) @@ -258,58 +306,62 @@ class ExecutionEngine: dwld.addBoth(_on_complete) return dwld - @defer.inlineCallbacks - def open_spider(self, spider, start_requests=(), close_if_idle=True): - if not self.has_capacity(): - raise RuntimeError("No free spider slot when opening %r" % spider.name) + @inlineCallbacks + def open_spider(self, spider: Spider, start_requests: Iterable = (), close_if_idle: bool = True): + if self.slot is not None: + raise RuntimeError(f"No free spider slot when opening {spider.name!r}") logger.info("Spider opened", extra={'spider': spider}) - nextcall = CallLaterOnce(self._next_request, spider) - scheduler = self.scheduler_cls.from_crawler(self.crawler) + nextcall = CallLaterOnce(self._next_request) + scheduler = create_instance(self.scheduler_cls, settings=None, crawler=self.crawler) start_requests = yield self.scraper.spidermw.process_start_requests(start_requests, spider) - slot = Slot(start_requests, close_if_idle, nextcall, scheduler) - self.slot = slot + self.slot = Slot(start_requests, close_if_idle, nextcall, scheduler) self.spider = spider - yield scheduler.open(spider) + if hasattr(scheduler, "open"): + yield scheduler.open(spider) yield self.scraper.open_spider(spider) self.crawler.stats.open_spider(spider) yield self.signals.send_catch_log_deferred(signals.spider_opened, spider=spider) - slot.nextcall.schedule() - slot.heartbeat.start(5) + self.slot.nextcall.schedule() + self.slot.heartbeat.start(5) - def _spider_idle(self, spider): - """Called when a spider gets idle. This function is called when there - are no remaining pages to download or schedule. It can be called - multiple times. If some extension raises a DontCloseSpider exception - (in the spider_idle signal handler) the spider is not closed until the - next loop and this function is guaranteed to be called (at least) once - again for this spider. + def _spider_idle(self) -> None: """ - res = self.signals.send_catch_log(signals.spider_idle, spider=spider, dont_log=DontCloseSpider) - if any(isinstance(x, Failure) and isinstance(x.value, DontCloseSpider) for _, x in res): - return + Called when a spider gets idle, i.e. when there are no remaining requests to download or schedule. + It can be called multiple times. If a handler for the spider_idle signal raises a DontCloseSpider + exception, the spider is not closed until the next loop and this function is guaranteed to be called + (at least) once again. A handler can raise CloseSpider to provide a custom closing reason. + """ + assert self.spider is not None # typing + expected_ex = (DontCloseSpider, CloseSpider) + res = self.signals.send_catch_log(signals.spider_idle, spider=self.spider, dont_log=expected_ex) + detected_ex = { + ex: x.value + for _, x in res + for ex in expected_ex + if isinstance(x, Failure) and isinstance(x.value, ex) + } + if DontCloseSpider in detected_ex: + return None + if self.spider_is_idle(): + ex = detected_ex.get(CloseSpider, CloseSpider(reason='finished')) + assert isinstance(ex, CloseSpider) # typing + self.close_spider(self.spider, reason=ex.reason) - if self.spider_is_idle(spider): - self.close_spider(spider, reason='finished') - - def close_spider(self, spider, reason='cancelled'): + def close_spider(self, spider: Spider, reason: str = "cancelled") -> Deferred: """Close (cancel) spider and clear all its outstanding requests""" + if self.slot is None: + raise RuntimeError("Engine slot not assigned") - slot = self.slot - if slot.closing: - return slot.closing - logger.info("Closing spider (%(reason)s)", - {'reason': reason}, - extra={'spider': spider}) + if self.slot.closing is not None: + return self.slot.closing - dfd = slot.close() + logger.info("Closing spider (%(reason)s)", {'reason': reason}, extra={'spider': spider}) - def log_failure(msg): - def errback(failure): - logger.error( - msg, - exc_info=failure_to_exc_info(failure), - extra={'spider': spider} - ) + dfd = self.slot.close() + + def log_failure(msg: str) -> Callable: + def errback(failure: Failure) -> None: + logger.error(msg, exc_info=failure_to_exc_info(failure), extra={'spider': spider}) return errback dfd.addBoth(lambda _: self.downloader.close()) @@ -318,19 +370,19 @@ class ExecutionEngine: dfd.addBoth(lambda _: self.scraper.close_spider(spider)) dfd.addErrback(log_failure('Scraper close failure')) - dfd.addBoth(lambda _: slot.scheduler.close(reason)) - dfd.addErrback(log_failure('Scheduler close failure')) + if hasattr(self.slot.scheduler, "close"): + dfd.addBoth(lambda _: self.slot.scheduler.close(reason)) + dfd.addErrback(log_failure("Scheduler close failure")) dfd.addBoth(lambda _: self.signals.send_catch_log_deferred( - signal=signals.spider_closed, spider=spider, reason=reason)) + signal=signals.spider_closed, spider=spider, reason=reason, + )) dfd.addErrback(log_failure('Error while sending spider_close signal')) dfd.addBoth(lambda _: self.crawler.stats.close_spider(spider, reason=reason)) dfd.addErrback(log_failure('Stats close failure')) - dfd.addBoth(lambda _: logger.info("Spider closed (%(reason)s)", - {'reason': reason}, - extra={'spider': spider})) + dfd.addBoth(lambda _: logger.info("Spider closed (%(reason)s)", {'reason': reason}, extra={'spider': spider})) dfd.addBoth(lambda _: setattr(self, 'slot', None)) dfd.addErrback(log_failure('Error while unassigning slot')) @@ -342,12 +394,26 @@ class ExecutionEngine: return dfd - def _close_all_spiders(self): - dfds = [self.close_spider(s, reason='shutdown') for s in self.open_spiders] - dlist = defer.DeferredList(dfds) - return dlist + @property + def open_spiders(self) -> list: + warnings.warn( + "ExecutionEngine.open_spiders is deprecated, please use ExecutionEngine.spider instead", + category=ScrapyDeprecationWarning, + stacklevel=2, + ) + return [self.spider] if self.spider is not None else [] - @defer.inlineCallbacks - def _finish_stopping_engine(self): - yield self.signals.send_catch_log_deferred(signal=signals.engine_stopped) - self._closewait.callback(None) + def has_capacity(self) -> bool: + warnings.warn("ExecutionEngine.has_capacity is deprecated", ScrapyDeprecationWarning, stacklevel=2) + return not bool(self.slot) + + def schedule(self, request: Request, spider: Spider) -> None: + warnings.warn( + "ExecutionEngine.schedule is deprecated, please use " + "ExecutionEngine.crawl or ExecutionEngine.download instead", + category=ScrapyDeprecationWarning, + stacklevel=2, + ) + if self.slot is None: + raise RuntimeError("Engine slot not assigned") + self._schedule_request(request, spider) diff --git a/scrapy/core/http2/__init__.py b/scrapy/core/http2/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/scrapy/core/http2/agent.py b/scrapy/core/http2/agent.py new file mode 100644 index 000000000..f7b0c3f99 --- /dev/null +++ b/scrapy/core/http2/agent.py @@ -0,0 +1,157 @@ +from collections import deque +from typing import Deque, Dict, List, Optional, Tuple + +from twisted.internet import defer +from twisted.internet.base import ReactorBase +from twisted.internet.defer import Deferred +from twisted.internet.endpoints import HostnameEndpoint +from twisted.python.failure import Failure +from twisted.web.client import URI, BrowserLikePolicyForHTTPS, _StandardEndpointFactory +from twisted.web.error import SchemeNotSupported + +from scrapy.core.downloader.contextfactory import AcceptableProtocolsContextFactory +from scrapy.core.http2.protocol import H2ClientProtocol, H2ClientFactory +from scrapy.http.request import Request +from scrapy.settings import Settings +from scrapy.spiders import Spider + + +class H2ConnectionPool: + def __init__(self, reactor: ReactorBase, settings: Settings) -> None: + self._reactor = reactor + self.settings = settings + + # Store a dictionary which is used to get the respective + # H2ClientProtocolInstance using the key as Tuple(scheme, hostname, port) + self._connections: Dict[Tuple, H2ClientProtocol] = {} + + # Save all requests that arrive before the connection is established + self._pending_requests: Dict[Tuple, Deque[Deferred]] = {} + + def get_connection(self, key: Tuple, uri: URI, endpoint: HostnameEndpoint) -> Deferred: + if key in self._pending_requests: + # Received a request while connecting to remote + # Create a deferred which will fire with the H2ClientProtocol + # instance + d = Deferred() + self._pending_requests[key].append(d) + return d + + # Check if we already have a connection to the remote + conn = self._connections.get(key, None) + if conn: + # Return this connection instance wrapped inside a deferred + return defer.succeed(conn) + + # No connection is established for the given URI + return self._new_connection(key, uri, endpoint) + + def _new_connection(self, key: Tuple, uri: URI, endpoint: HostnameEndpoint) -> Deferred: + self._pending_requests[key] = deque() + + conn_lost_deferred = Deferred() + conn_lost_deferred.addCallback(self._remove_connection, key) + + factory = H2ClientFactory(uri, self.settings, conn_lost_deferred) + conn_d = endpoint.connect(factory) + conn_d.addCallback(self.put_connection, key) + + d = Deferred() + self._pending_requests[key].append(d) + return d + + def put_connection(self, conn: H2ClientProtocol, key: Tuple) -> H2ClientProtocol: + self._connections[key] = conn + + # Now as we have established a proper HTTP/2 connection + # we fire all the deferred's with the connection instance + pending_requests = self._pending_requests.pop(key, None) + while pending_requests: + d = pending_requests.popleft() + d.callback(conn) + + return conn + + def _remove_connection(self, errors: List[BaseException], key: Tuple) -> None: + self._connections.pop(key) + + # Call the errback of all the pending requests for this connection + pending_requests = self._pending_requests.pop(key, None) + while pending_requests: + d = pending_requests.popleft() + d.errback(errors) + + def close_connections(self) -> None: + """Close all the HTTP/2 connections and remove them from pool + + Returns: + Deferred that fires when all connections have been closed + """ + for conn in self._connections.values(): + conn.transport.abortConnection() + + +class H2Agent: + def __init__( + self, + reactor: ReactorBase, + pool: H2ConnectionPool, + context_factory: BrowserLikePolicyForHTTPS = BrowserLikePolicyForHTTPS(), + connect_timeout: Optional[float] = None, + bind_address: Optional[bytes] = None, + ) -> None: + self._reactor = reactor + self._pool = pool + self._context_factory = AcceptableProtocolsContextFactory(context_factory, acceptable_protocols=[b'h2']) + self.endpoint_factory = _StandardEndpointFactory( + self._reactor, self._context_factory, connect_timeout, bind_address + ) + + def get_endpoint(self, uri: URI): + return self.endpoint_factory.endpointForURI(uri) + + def get_key(self, uri: URI) -> Tuple: + """ + Arguments: + uri - URI obtained directly from request URL + """ + return uri.scheme, uri.host, uri.port + + def request(self, request: Request, spider: Spider) -> Deferred: + uri = URI.fromBytes(bytes(request.url, encoding='utf-8')) + try: + endpoint = self.get_endpoint(uri) + except SchemeNotSupported: + return defer.fail(Failure()) + + key = self.get_key(uri) + d = self._pool.get_connection(key, uri, endpoint) + d.addCallback(lambda conn: conn.request(request, spider)) + return d + + +class ScrapyProxyH2Agent(H2Agent): + def __init__( + self, + reactor: ReactorBase, + proxy_uri: URI, + pool: H2ConnectionPool, + context_factory: BrowserLikePolicyForHTTPS = BrowserLikePolicyForHTTPS(), + connect_timeout: Optional[float] = None, + bind_address: Optional[bytes] = None, + ) -> None: + super(ScrapyProxyH2Agent, self).__init__( + reactor=reactor, + pool=pool, + context_factory=context_factory, + connect_timeout=connect_timeout, + bind_address=bind_address, + ) + self._proxy_uri = proxy_uri + + def get_endpoint(self, uri: URI): + return self.endpoint_factory.endpointForURI(self._proxy_uri) + + def get_key(self, uri: URI) -> Tuple: + """We use the proxy uri instead of uri obtained from request url""" + return "http-proxy", self._proxy_uri.host, self._proxy_uri.port diff --git a/scrapy/core/http2/protocol.py b/scrapy/core/http2/protocol.py new file mode 100644 index 000000000..1d150b7ce --- /dev/null +++ b/scrapy/core/http2/protocol.py @@ -0,0 +1,418 @@ +import ipaddress +import itertools +import logging +from collections import deque +from ipaddress import IPv4Address, IPv6Address +from typing import Dict, List, Optional, Union + +from h2.config import H2Configuration +from h2.connection import H2Connection +from h2.errors import ErrorCodes +from h2.events import ( + Event, ConnectionTerminated, DataReceived, ResponseReceived, + SettingsAcknowledged, StreamEnded, StreamReset, UnknownFrameReceived, + WindowUpdated +) +from h2.exceptions import FrameTooLargeError, H2Error +from twisted.internet.defer import Deferred +from twisted.internet.error import TimeoutError +from twisted.internet.interfaces import IHandshakeListener, IProtocolNegotiationFactory +from twisted.internet.protocol import connectionDone, Factory, Protocol +from twisted.internet.ssl import Certificate +from twisted.protocols.policies import TimeoutMixin +from twisted.python.failure import Failure +from twisted.web.client import URI +from zope.interface import implementer + +from scrapy.core.http2.stream import Stream, StreamCloseReason +from scrapy.http import Request +from scrapy.settings import Settings +from scrapy.spiders import Spider + + +logger = logging.getLogger(__name__) + + +PROTOCOL_NAME = b"h2" + + +class InvalidNegotiatedProtocol(H2Error): + + def __init__(self, negotiated_protocol: bytes) -> None: + self.negotiated_protocol = negotiated_protocol + + def __str__(self) -> str: + return (f"Expected {PROTOCOL_NAME!r}, received {self.negotiated_protocol!r}") + + +class RemoteTerminatedConnection(H2Error): + def __init__( + self, + remote_ip_address: Optional[Union[IPv4Address, IPv6Address]], + event: ConnectionTerminated, + ) -> None: + self.remote_ip_address = remote_ip_address + self.terminate_event = event + + def __str__(self) -> str: + return f'Received GOAWAY frame from {self.remote_ip_address!r}' + + +class MethodNotAllowed405(H2Error): + def __init__(self, remote_ip_address: Optional[Union[IPv4Address, IPv6Address]]) -> None: + self.remote_ip_address = remote_ip_address + + def __str__(self) -> str: + return f"Received 'HTTP/2.0 405 Method Not Allowed' from {self.remote_ip_address!r}" + + +@implementer(IHandshakeListener) +class H2ClientProtocol(Protocol, TimeoutMixin): + IDLE_TIMEOUT = 240 + + def __init__(self, uri: URI, settings: Settings, conn_lost_deferred: Deferred) -> None: + """ + Arguments: + uri -- URI of the base url to which HTTP/2 Connection will be made. + uri is used to verify that incoming client requests have correct + base URL. + settings -- Scrapy project settings + conn_lost_deferred -- Deferred fires with the reason: Failure to notify + that connection was lost + """ + self._conn_lost_deferred = conn_lost_deferred + + config = H2Configuration(client_side=True, header_encoding='utf-8') + self.conn = H2Connection(config=config) + + # ID of the next request stream + # Following the convention - 'Streams initiated by a client MUST + # use odd-numbered stream identifiers' (RFC 7540 - Section 5.1.1) + self._stream_id_generator = itertools.count(start=1, step=2) + + # Streams are stored in a dictionary keyed off their stream IDs + self.streams: Dict[int, Stream] = {} + + # If requests are received before connection is made we keep + # all requests in a pool and send them as the connection is made + self._pending_request_stream_pool: deque = deque() + + # Save an instance of errors raised which lead to losing the connection + # We pass these instances to the streams ResponseFailed() failure + self._conn_lost_errors: List[BaseException] = [] + + # Some meta data of this connection + # initialized when connection is successfully made + self.metadata: Dict = { + # Peer certificate instance + 'certificate': None, + + # Address of the server we are connected to which + # is updated when HTTP/2 connection is made successfully + 'ip_address': None, + + # URI of the peer HTTP/2 connection is made + 'uri': uri, + + # Both ip_address and uri are used by the Stream before + # initiating the request to verify that the base address + + # Variables taken from Project Settings + 'default_download_maxsize': settings.getint('DOWNLOAD_MAXSIZE'), + 'default_download_warnsize': settings.getint('DOWNLOAD_WARNSIZE'), + + # Counter to keep track of opened streams. This counter + # is used to make sure that not more than MAX_CONCURRENT_STREAMS + # streams are opened which leads to ProtocolError + # We use simple FIFO policy to handle pending requests + 'active_streams': 0, + + # Flag to keep track if settings were acknowledged by the remote + # This ensures that we have established a HTTP/2 connection + 'settings_acknowledged': False, + } + + @property + def h2_connected(self) -> bool: + """Boolean to keep track of the connection status. + This is used while initiating pending streams to make sure + that we initiate stream only during active HTTP/2 Connection + """ + return bool(self.transport.connected) and self.metadata['settings_acknowledged'] + + @property + def allowed_max_concurrent_streams(self) -> int: + """We keep total two streams for client (sending data) and + server side (receiving data) for a single request. To be safe + we choose the minimum. Since this value can change in event + RemoteSettingsChanged we make variable a property. + """ + return min( + self.conn.local_settings.max_concurrent_streams, + self.conn.remote_settings.max_concurrent_streams + ) + + def _send_pending_requests(self) -> None: + """Initiate all pending requests from the deque following FIFO + We make sure that at any time {allowed_max_concurrent_streams} + streams are active. + """ + while ( + self._pending_request_stream_pool + and self.metadata['active_streams'] < self.allowed_max_concurrent_streams + and self.h2_connected + ): + self.metadata['active_streams'] += 1 + stream = self._pending_request_stream_pool.popleft() + stream.initiate_request() + self._write_to_transport() + + def pop_stream(self, stream_id: int) -> Stream: + """Perform cleanup when a stream is closed + """ + stream = self.streams.pop(stream_id) + self.metadata['active_streams'] -= 1 + self._send_pending_requests() + return stream + + def _new_stream(self, request: Request, spider: Spider) -> Stream: + """Instantiates a new Stream object + """ + stream = Stream( + stream_id=next(self._stream_id_generator), + request=request, + protocol=self, + download_maxsize=getattr(spider, 'download_maxsize', self.metadata['default_download_maxsize']), + download_warnsize=getattr(spider, 'download_warnsize', self.metadata['default_download_warnsize']), + ) + self.streams[stream.stream_id] = stream + return stream + + def _write_to_transport(self) -> None: + """ Write data to the underlying transport connection + from the HTTP2 connection instance if any + """ + # Reset the idle timeout as connection is still actively sending data + self.resetTimeout() + + data = self.conn.data_to_send() + self.transport.write(data) + + def request(self, request: Request, spider: Spider) -> Deferred: + if not isinstance(request, Request): + raise TypeError(f'Expected scrapy.http.Request, received {request.__class__.__qualname__}') + + stream = self._new_stream(request, spider) + d = stream.get_response() + + # Add the stream to the request pool + self._pending_request_stream_pool.append(stream) + + # If we receive a request when connection is idle + # We need to initiate pending requests + self._send_pending_requests() + return d + + def connectionMade(self) -> None: + """Called by Twisted when the connection is established. We can start + sending some data now: we should open with the connection preamble. + """ + # Initialize the timeout + self.setTimeout(self.IDLE_TIMEOUT) + + destination = self.transport.getPeer() + self.metadata['ip_address'] = ipaddress.ip_address(destination.host) + + # Initiate H2 Connection + self.conn.initiate_connection() + self._write_to_transport() + + def _lose_connection_with_error(self, errors: List[BaseException]) -> None: + """Helper function to lose the connection with the error sent as a + reason""" + self._conn_lost_errors += errors + self.transport.loseConnection() + + def handshakeCompleted(self) -> None: + """ + Close the connection if it's not made via the expected protocol + """ + if self.transport.negotiatedProtocol is not None and self.transport.negotiatedProtocol != PROTOCOL_NAME: + # we have not initiated the connection yet, no need to send a GOAWAY frame to the remote peer + self._lose_connection_with_error([InvalidNegotiatedProtocol(self.transport.negotiatedProtocol)]) + + def _check_received_data(self, data: bytes) -> None: + """Checks for edge cases where the connection to remote fails + without raising an appropriate H2Error + + Arguments: + data -- Data received from the remote + """ + if data.startswith(b'HTTP/2.0 405 Method Not Allowed'): + raise MethodNotAllowed405(self.metadata['ip_address']) + + def dataReceived(self, data: bytes) -> None: + # Reset the idle timeout as connection is still actively receiving data + self.resetTimeout() + + try: + self._check_received_data(data) + events = self.conn.receive_data(data) + self._handle_events(events) + except H2Error as e: + if isinstance(e, FrameTooLargeError): + # hyper-h2 does not drop the connection in this scenario, we + # need to abort the connection manually. + self._conn_lost_errors += [e] + self.transport.abortConnection() + return + + # Save this error as ultimately the connection will be dropped + # internally by hyper-h2. Saved error will be passed to all the streams + # closed with the connection. + self._lose_connection_with_error([e]) + finally: + self._write_to_transport() + + def timeoutConnection(self) -> None: + """Called when the connection times out. + We lose the connection with TimeoutError""" + + # Check whether there are open streams. If there are, we're going to + # want to use the error code PROTOCOL_ERROR. If there aren't, use + # NO_ERROR. + if ( + self.conn.open_outbound_streams > 0 + or self.conn.open_inbound_streams > 0 + or self.metadata['active_streams'] > 0 + ): + error_code = ErrorCodes.PROTOCOL_ERROR + else: + error_code = ErrorCodes.NO_ERROR + self.conn.close_connection(error_code=error_code) + self._write_to_transport() + + self._lose_connection_with_error([ + TimeoutError(f"Connection was IDLE for more than {self.IDLE_TIMEOUT}s") + ]) + + def connectionLost(self, reason: Failure = connectionDone) -> None: + """Called by Twisted when the transport connection is lost. + No need to write anything to transport here. + """ + # Cancel the timeout if not done yet + self.setTimeout(None) + + # Notify the connection pool instance such that no new requests are + # sent over current connection + if not reason.check(connectionDone): + self._conn_lost_errors.append(reason) + + self._conn_lost_deferred.callback(self._conn_lost_errors) + + for stream in self.streams.values(): + if stream.metadata['request_sent']: + close_reason = StreamCloseReason.CONNECTION_LOST + else: + close_reason = StreamCloseReason.INACTIVE + stream.close(close_reason, self._conn_lost_errors, from_protocol=True) + + self.metadata['active_streams'] -= len(self.streams) + self.streams.clear() + self._pending_request_stream_pool.clear() + self.conn.close_connection() + + def _handle_events(self, events: List[Event]) -> None: + """Private method which acts as a bridge between the events + received from the HTTP/2 data and IH2EventsHandler + + Arguments: + events -- A list of events that the remote peer triggered by sending data + """ + for event in events: + if isinstance(event, ConnectionTerminated): + self.connection_terminated(event) + elif isinstance(event, DataReceived): + self.data_received(event) + elif isinstance(event, ResponseReceived): + self.response_received(event) + elif isinstance(event, StreamEnded): + self.stream_ended(event) + elif isinstance(event, StreamReset): + self.stream_reset(event) + elif isinstance(event, WindowUpdated): + self.window_updated(event) + elif isinstance(event, SettingsAcknowledged): + self.settings_acknowledged(event) + elif isinstance(event, UnknownFrameReceived): + logger.warning('Unknown frame received: %s', event.frame) + + # Event handler functions starts here + def connection_terminated(self, event: ConnectionTerminated) -> None: + self._lose_connection_with_error([ + RemoteTerminatedConnection(self.metadata['ip_address'], event) + ]) + + def data_received(self, event: DataReceived) -> None: + try: + stream = self.streams[event.stream_id] + except KeyError: + pass # We ignore server-initiated events + else: + stream.receive_data(event.data, event.flow_controlled_length) + + def response_received(self, event: ResponseReceived) -> None: + try: + stream = self.streams[event.stream_id] + except KeyError: + pass # We ignore server-initiated events + else: + stream.receive_headers(event.headers) + + def settings_acknowledged(self, event: SettingsAcknowledged) -> None: + self.metadata['settings_acknowledged'] = True + + # Send off all the pending requests as now we have + # established a proper HTTP/2 connection + self._send_pending_requests() + + # Update certificate when our HTTP/2 connection is established + self.metadata['certificate'] = Certificate(self.transport.getPeerCertificate()) + + def stream_ended(self, event: StreamEnded) -> None: + try: + stream = self.pop_stream(event.stream_id) + except KeyError: + pass # We ignore server-initiated events + else: + stream.close(StreamCloseReason.ENDED, from_protocol=True) + + def stream_reset(self, event: StreamReset) -> None: + try: + stream = self.pop_stream(event.stream_id) + except KeyError: + pass # We ignore server-initiated events + else: + stream.close(StreamCloseReason.RESET, from_protocol=True) + + def window_updated(self, event: WindowUpdated) -> None: + if event.stream_id != 0: + self.streams[event.stream_id].receive_window_update() + else: + # Send leftover data for all the streams + for stream in self.streams.values(): + stream.receive_window_update() + + +@implementer(IProtocolNegotiationFactory) +class H2ClientFactory(Factory): + def __init__(self, uri: URI, settings: Settings, conn_lost_deferred: Deferred) -> None: + self.uri = uri + self.settings = settings + self.conn_lost_deferred = conn_lost_deferred + + def buildProtocol(self, addr) -> H2ClientProtocol: + return H2ClientProtocol(self.uri, self.settings, self.conn_lost_deferred) + + def acceptableProtocols(self) -> List[bytes]: + return [PROTOCOL_NAME] diff --git a/scrapy/core/http2/stream.py b/scrapy/core/http2/stream.py new file mode 100644 index 000000000..c2a4b702f --- /dev/null +++ b/scrapy/core/http2/stream.py @@ -0,0 +1,470 @@ +import logging +from enum import Enum +from io import BytesIO +from urllib.parse import urlparse +from typing import Dict, List, Optional, Tuple, TYPE_CHECKING + +from h2.errors import ErrorCodes +from h2.exceptions import H2Error, ProtocolError, StreamClosedError +from hpack import HeaderTuple +from twisted.internet.defer import Deferred, CancelledError +from twisted.internet.error import ConnectionClosed +from twisted.python.failure import Failure +from twisted.web.client import ResponseFailed + +from scrapy.http import Request +from scrapy.http.headers import Headers +from scrapy.responsetypes import responsetypes + +if TYPE_CHECKING: + from scrapy.core.http2.protocol import H2ClientProtocol + + +logger = logging.getLogger(__name__) + + +class InactiveStreamClosed(ConnectionClosed): + """Connection was closed without sending request headers + of the stream. This happens when a stream is waiting for other + streams to close and connection is lost.""" + + def __init__(self, request: Request) -> None: + self.request = request + + def __str__(self) -> str: + return f'InactiveStreamClosed: Connection was closed without sending the request {self.request!r}' + + +class InvalidHostname(H2Error): + + def __init__(self, request: Request, expected_hostname: str, expected_netloc: str) -> None: + self.request = request + self.expected_hostname = expected_hostname + self.expected_netloc = expected_netloc + + def __str__(self) -> str: + return f'InvalidHostname: Expected {self.expected_hostname} or {self.expected_netloc} in {self.request}' + + +class StreamCloseReason(Enum): + # Received a StreamEnded event from the remote + ENDED = 1 + + # Received a StreamReset event -- ended abruptly + RESET = 2 + + # Transport connection was lost + CONNECTION_LOST = 3 + + # Expected response body size is more than allowed limit + MAXSIZE_EXCEEDED = 4 + + # Response deferred is cancelled by the client + # (happens when client called response_deferred.cancel()) + CANCELLED = 5 + + # Connection lost and the stream was not initiated + INACTIVE = 6 + + # The hostname of the request is not same as of connected peer hostname + # As a result sending this request will the end the connection + INVALID_HOSTNAME = 7 + + +class Stream: + """Represents a single HTTP/2 Stream. + + Stream is a bidirectional flow of bytes within an established connection, + which may carry one or more messages. Handles the transfer of HTTP Headers + and Data frames. + + Role of this class is to + 1. Combine all the data frames + """ + + def __init__( + self, + stream_id: int, + request: Request, + protocol: "H2ClientProtocol", + download_maxsize: int = 0, + download_warnsize: int = 0, + ) -> None: + """ + Arguments: + stream_id -- Unique identifier for the stream within a single HTTP/2 connection + request -- The HTTP request associated to the stream + protocol -- Parent H2ClientProtocol instance + """ + self.stream_id: int = stream_id + self._request: Request = request + self._protocol: "H2ClientProtocol" = protocol + + self._download_maxsize = self._request.meta.get('download_maxsize', download_maxsize) + self._download_warnsize = self._request.meta.get('download_warnsize', download_warnsize) + + # Metadata of an HTTP/2 connection stream + # initialized when stream is instantiated + self.metadata: Dict = { + 'request_content_length': 0 if self._request.body is None else len(self._request.body), + + # Flag to keep track whether the stream has initiated the request + 'request_sent': False, + + # Flag to track whether we have logged about exceeding download warnsize + 'reached_warnsize': False, + + # Each time we send a data frame, we will decrease value by the amount send. + 'remaining_content_length': 0 if self._request.body is None else len(self._request.body), + + # Flag to keep track whether client (self) have closed this stream + 'stream_closed_local': False, + + # Flag to keep track whether the server has closed the stream + 'stream_closed_server': False, + } + + # Private variable used to build the response + # this response is then converted to appropriate Response class + # passed to the response deferred callback + self._response: Dict = { + # Data received frame by frame from the server is appended + # and passed to the response Deferred when completely received. + 'body': BytesIO(), + + # The amount of data received that counts against the + # flow control window + 'flow_controlled_size': 0, + + # Headers received after sending the request + 'headers': Headers({}), + } + + def _cancel(_) -> None: + # Close this stream as gracefully as possible + # If the associated request is initiated we reset this stream + # else we directly call close() method + if self.metadata['request_sent']: + self.reset_stream(StreamCloseReason.CANCELLED) + else: + self.close(StreamCloseReason.CANCELLED) + + self._deferred_response = Deferred(_cancel) + + def __str__(self) -> str: + return f'Stream(id={self.stream_id!r})' + + __repr__ = __str__ + + @property + def _log_warnsize(self) -> bool: + """Checks if we have received data which exceeds the download warnsize + and whether we have not already logged about it. + + Returns: + True if both the above conditions hold true + False if any of the conditions is false + """ + content_length_header = int(self._response['headers'].get(b'Content-Length', -1)) + return ( + self._download_warnsize + and ( + self._response['flow_controlled_size'] > self._download_warnsize + or content_length_header > self._download_warnsize + ) + and not self.metadata['reached_warnsize'] + ) + + def get_response(self) -> Deferred: + """Simply return a Deferred which fires when response + from the asynchronous request is available + """ + return self._deferred_response + + def check_request_url(self) -> bool: + # Make sure that we are sending the request to the correct URL + url = urlparse(self._request.url) + return ( + url.netloc == str(self._protocol.metadata['uri'].host, 'utf-8') + or url.netloc == str(self._protocol.metadata['uri'].netloc, 'utf-8') + or url.netloc == f'{self._protocol.metadata["ip_address"]}:{self._protocol.metadata["uri"].port}' + ) + + def _get_request_headers(self) -> List[Tuple[str, str]]: + url = urlparse(self._request.url) + + path = url.path + if url.query: + path += '?' + url.query + + # This pseudo-header field MUST NOT be empty for "http" or "https" + # URIs; "http" or "https" URIs that do not contain a path component + # MUST include a value of '/'. The exception to this rule is an + # OPTIONS request for an "http" or "https" URI that does not include + # a path component; these MUST include a ":path" pseudo-header field + # with a value of '*' (refer RFC 7540 - Section 8.1.2.3) + if not path: + path = '*' if self._request.method == 'OPTIONS' else '/' + + # Make sure pseudo-headers comes before all the other headers + headers = [ + (':method', self._request.method), + (':authority', url.netloc), + ] + + # The ":scheme" and ":path" pseudo-header fields MUST + # be omitted for CONNECT method (refer RFC 7540 - Section 8.3) + if self._request.method != 'CONNECT': + headers += [ + (':scheme', self._protocol.metadata['uri'].scheme), + (':path', path), + ] + + content_length = str(len(self._request.body)) + headers.append(('Content-Length', content_length)) + + content_length_name = self._request.headers.normkey(b'Content-Length') + for name, values in self._request.headers.items(): + for value in values: + value = str(value, 'utf-8') + if name == content_length_name: + if value != content_length: + logger.warning( + 'Ignoring bad Content-Length header %r of request %r, ' + 'sending %r instead', + value, + self._request, + content_length, + ) + continue + headers.append((str(name, 'utf-8'), value)) + + return headers + + def initiate_request(self) -> None: + if self.check_request_url(): + headers = self._get_request_headers() + self._protocol.conn.send_headers(self.stream_id, headers, end_stream=False) + self.metadata['request_sent'] = True + self.send_data() + else: + # Close this stream calling the response errback + # Note that we have not sent any headers + self.close(StreamCloseReason.INVALID_HOSTNAME) + + def send_data(self) -> None: + """Called immediately after the headers are sent. Here we send all the + data as part of the request. + + If the content length is 0 initially then we end the stream immediately and + wait for response data. + + Warning: Only call this method when stream not closed from client side + and has initiated request already by sending HEADER frame. If not then + stream will raise ProtocolError (raise by h2 state machine). + """ + if self.metadata['stream_closed_local']: + raise StreamClosedError(self.stream_id) + + # Firstly, check what the flow control window is for current stream. + window_size = self._protocol.conn.local_flow_control_window(stream_id=self.stream_id) + + # Next, check what the maximum frame size is. + max_frame_size = self._protocol.conn.max_outbound_frame_size + + # We will send no more than the window size or the remaining file size + # of data in this call, whichever is smaller. + bytes_to_send_size = min(window_size, self.metadata['remaining_content_length']) + + # We now need to send a number of data frames. + while bytes_to_send_size > 0: + chunk_size = min(bytes_to_send_size, max_frame_size) + + data_chunk_start_id = self.metadata['request_content_length'] - self.metadata['remaining_content_length'] + data_chunk = self._request.body[data_chunk_start_id:data_chunk_start_id + chunk_size] + + self._protocol.conn.send_data(self.stream_id, data_chunk, end_stream=False) + + bytes_to_send_size = bytes_to_send_size - chunk_size + self.metadata['remaining_content_length'] = self.metadata['remaining_content_length'] - chunk_size + + self.metadata['remaining_content_length'] = max(0, self.metadata['remaining_content_length']) + + # End the stream if no more data needs to be send + if self.metadata['remaining_content_length'] == 0: + self._protocol.conn.end_stream(self.stream_id) + + # Q. What about the rest of the data? + # Ans: Remaining Data frames will be sent when we get a WindowUpdate frame + + def receive_window_update(self) -> None: + """Flow control window size was changed. + Send data that earlier could not be sent as we were + blocked behind the flow control. + """ + if ( + self.metadata['remaining_content_length'] + and not self.metadata['stream_closed_server'] + and self.metadata['request_sent'] + ): + self.send_data() + + def receive_data(self, data: bytes, flow_controlled_length: int) -> None: + self._response['body'].write(data) + self._response['flow_controlled_size'] += flow_controlled_length + + # We check maxsize here in case the Content-Length header was not received + if self._download_maxsize and self._response['flow_controlled_size'] > self._download_maxsize: + self.reset_stream(StreamCloseReason.MAXSIZE_EXCEEDED) + return + + if self._log_warnsize: + self.metadata['reached_warnsize'] = True + warning_msg = ( + f'Received more ({self._response["flow_controlled_size"]}) bytes than download ' + f'warn size ({self._download_warnsize}) in request {self._request}' + ) + logger.warning(warning_msg) + + # Acknowledge the data received + self._protocol.conn.acknowledge_received_data( + self._response['flow_controlled_size'], + self.stream_id + ) + + def receive_headers(self, headers: List[HeaderTuple]) -> None: + for name, value in headers: + self._response['headers'][name] = value + + # Check if we exceed the allowed max data size which can be received + expected_size = int(self._response['headers'].get(b'Content-Length', -1)) + if self._download_maxsize and expected_size > self._download_maxsize: + self.reset_stream(StreamCloseReason.MAXSIZE_EXCEEDED) + return + + if self._log_warnsize: + self.metadata['reached_warnsize'] = True + warning_msg = ( + f'Expected response size ({expected_size}) larger than ' + f'download warn size ({self._download_warnsize}) in request {self._request}' + ) + logger.warning(warning_msg) + + def reset_stream(self, reason: StreamCloseReason = StreamCloseReason.RESET) -> None: + """Close this stream by sending a RST_FRAME to the remote peer""" + if self.metadata['stream_closed_local']: + raise StreamClosedError(self.stream_id) + + # Clear buffer earlier to avoid keeping data in memory for a long time + self._response['body'].truncate(0) + + self.metadata['stream_closed_local'] = True + self._protocol.conn.reset_stream(self.stream_id, ErrorCodes.REFUSED_STREAM) + self.close(reason) + + def close( + self, + reason: StreamCloseReason, + errors: Optional[List[BaseException]] = None, + from_protocol: bool = False, + ) -> None: + """Based on the reason sent we will handle each case. + """ + if self.metadata['stream_closed_server']: + raise StreamClosedError(self.stream_id) + + if not isinstance(reason, StreamCloseReason): + raise TypeError(f'Expected StreamCloseReason, received {reason.__class__.__qualname__}') + + # Have default value of errors as an empty list as + # some cases can add a list of exceptions + errors = errors or [] + + if not from_protocol: + self._protocol.pop_stream(self.stream_id) + + self.metadata['stream_closed_server'] = True + + # We do not check for Content-Length or Transfer-Encoding in response headers + # and add `partial` flag as in HTTP/1.1 as 'A request or response that includes + # a payload body can include a content-length header field' (RFC 7540 - Section 8.1.2.6) + + # NOTE: Order of handling the events is important here + # As we immediately cancel the request when maxsize is exceeded while + # receiving DATA_FRAME's when we have received the headers (not + # having Content-Length) + if reason is StreamCloseReason.MAXSIZE_EXCEEDED: + expected_size = int(self._response['headers'].get( + b'Content-Length', + self._response['flow_controlled_size']) + ) + error_msg = ( + f'Cancelling download of {self._request.url}: received response ' + f'size ({expected_size}) larger than download max size ({self._download_maxsize})' + ) + logger.error(error_msg) + self._deferred_response.errback(CancelledError(error_msg)) + + elif reason is StreamCloseReason.ENDED: + self._fire_response_deferred() + + # Stream was abruptly ended here + elif reason is StreamCloseReason.CANCELLED: + # Client has cancelled the request. Remove all the data + # received and fire the response deferred with no flags set + + # NOTE: The data is already flushed in Stream.reset_stream() called + # immediately when the stream needs to be cancelled + + # There maybe no :status in headers, we make + # HTTP Status Code: 499 - Client Closed Request + self._response['headers'][':status'] = '499' + self._fire_response_deferred() + + elif reason is StreamCloseReason.RESET: + self._deferred_response.errback(ResponseFailed([ + Failure( + f'Remote peer {self._protocol.metadata["ip_address"]} sent RST_STREAM', + ProtocolError + ) + ])) + + elif reason is StreamCloseReason.CONNECTION_LOST: + self._deferred_response.errback(ResponseFailed(errors)) + + elif reason is StreamCloseReason.INACTIVE: + errors.insert(0, InactiveStreamClosed(self._request)) + self._deferred_response.errback(ResponseFailed(errors)) + + else: + assert reason is StreamCloseReason.INVALID_HOSTNAME + self._deferred_response.errback(InvalidHostname( + self._request, + str(self._protocol.metadata['uri'].host, 'utf-8'), + f'{self._protocol.metadata["ip_address"]}:{self._protocol.metadata["uri"].port}' + )) + + def _fire_response_deferred(self) -> None: + """Builds response from the self._response dict + and fires the response deferred callback with the + generated response instance""" + + body = self._response['body'].getvalue() + response_cls = responsetypes.from_args( + headers=self._response['headers'], + url=self._request.url, + body=body, + ) + + response = response_cls( + url=self._request.url, + status=int(self._response['headers'][':status']), + headers=self._response['headers'], + body=body, + request=self._request, + certificate=self._protocol.metadata['certificate'], + ip_address=self._protocol.metadata['ip_address'], + protocol='h2', + ) + + self._deferred_response.callback(response) diff --git a/scrapy/core/scheduler.py b/scrapy/core/scheduler.py index a18c26b17..5ba0fb63b 100644 --- a/scrapy/core/scheduler.py +++ b/scrapy/core/scheduler.py @@ -1,46 +1,179 @@ -import os import json import logging -import warnings -from os.path import join, exists +import os +from abc import abstractmethod +from os.path import exists, join +from typing import Optional, Type, TypeVar -from queuelib import PriorityQueue +from twisted.internet.defer import Deferred -from scrapy.utils.misc import load_object, create_instance +from scrapy.crawler import Crawler +from scrapy.http.request import Request +from scrapy.spiders import Spider from scrapy.utils.job import job_dir -from scrapy.utils.deprecate import ScrapyDeprecationWarning +from scrapy.utils.misc import create_instance, load_object logger = logging.getLogger(__name__) -class Scheduler: +class BaseSchedulerMeta(type): """ - Scrapy Scheduler. It allows to enqueue requests and then get - a next request to download. Scheduler is also handling duplication - filtering, via dupefilter. - - Prioritization and queueing is not performed by the Scheduler. - User sets ``priority`` field for each Request, and a PriorityQueue - (defined by :setting:`SCHEDULER_PRIORITY_QUEUE`) uses these priorities - to dequeue requests in a desired order. - - Scheduler uses two PriorityQueue instances, configured to work in-memory - and on-disk (optional). When on-disk queue is present, it is used by - default, and an in-memory queue is used as a fallback for cases where - a disk queue can't handle a request (can't serialize it). - - :setting:`SCHEDULER_MEMORY_QUEUE` and - :setting:`SCHEDULER_DISK_QUEUE` allow to specify lower-level queue classes - which PriorityQueue instances would be instantiated with, to keep requests - on disk and in memory respectively. - - Overall, Scheduler is an object which holds several PriorityQueue instances - (in-memory and on-disk) and implements fallback logic for them. - Also, it handles dupefilters. + Metaclass to check scheduler classes against the necessary interface """ - def __init__(self, dupefilter, jobdir=None, dqclass=None, mqclass=None, - logunser=False, stats=None, pqclass=None, crawler=None): + def __instancecheck__(cls, instance): + return cls.__subclasscheck__(type(instance)) + + def __subclasscheck__(cls, subclass): + return ( + hasattr(subclass, "has_pending_requests") and callable(subclass.has_pending_requests) + and hasattr(subclass, "enqueue_request") and callable(subclass.enqueue_request) + and hasattr(subclass, "next_request") and callable(subclass.next_request) + ) + + +class BaseScheduler(metaclass=BaseSchedulerMeta): + """ + The scheduler component is responsible for storing requests received from + the engine, and feeding them back upon request (also to the engine). + + The original sources of said requests are: + + * Spider: ``start_requests`` method, requests created for URLs in the ``start_urls`` attribute, request callbacks + * Spider middleware: ``process_spider_output`` and ``process_spider_exception`` methods + * Downloader middleware: ``process_request``, ``process_response`` and ``process_exception`` methods + + The order in which the scheduler returns its stored requests (via the ``next_request`` method) + plays a great part in determining the order in which those requests are downloaded. + + The methods defined in this class constitute the minimal interface that the Scrapy engine will interact with. + """ + + @classmethod + def from_crawler(cls, crawler: Crawler): + """ + Factory method which receives the current :class:`~scrapy.crawler.Crawler` object as argument. + """ + return cls() + + def open(self, spider: Spider) -> Optional[Deferred]: + """ + Called when the spider is opened by the engine. It receives the spider + instance as argument and it's useful to execute initialization code. + + :param spider: the spider object for the current crawl + :type spider: :class:`~scrapy.spiders.Spider` + """ + pass + + def close(self, reason: str) -> Optional[Deferred]: + """ + Called when the spider is closed by the engine. It receives the reason why the crawl + finished as argument and it's useful to execute cleaning code. + + :param reason: a string which describes the reason why the spider was closed + :type reason: :class:`str` + """ + pass + + @abstractmethod + def has_pending_requests(self) -> bool: + """ + ``True`` if the scheduler has enqueued requests, ``False`` otherwise + """ + raise NotImplementedError() + + @abstractmethod + def enqueue_request(self, request: Request) -> bool: + """ + Process a request received by the engine. + + Return ``True`` if the request is stored correctly, ``False`` otherwise. + + If ``False``, the engine will fire a ``request_dropped`` signal, and + will not make further attempts to schedule the request at a later time. + For reference, the default Scrapy scheduler returns ``False`` when the + request is rejected by the dupefilter. + """ + raise NotImplementedError() + + @abstractmethod + def next_request(self) -> Optional[Request]: + """ + Return the next :class:`~scrapy.http.Request` to be processed, or ``None`` + to indicate that there are no requests to be considered ready at the moment. + + Returning ``None`` implies that no request from the scheduler will be sent + to the downloader in the current reactor cycle. The engine will continue + calling ``next_request`` until ``has_pending_requests`` is ``False``. + """ + raise NotImplementedError() + + +SchedulerTV = TypeVar("SchedulerTV", bound="Scheduler") + + +class Scheduler(BaseScheduler): + """ + Default Scrapy scheduler. This implementation also handles duplication + filtering via the :setting:`dupefilter `. + + This scheduler stores requests into several priority queues (defined by the + :setting:`SCHEDULER_PRIORITY_QUEUE` setting). In turn, said priority queues + are backed by either memory or disk based queues (respectively defined by the + :setting:`SCHEDULER_MEMORY_QUEUE` and :setting:`SCHEDULER_DISK_QUEUE` settings). + + Request prioritization is almost entirely delegated to the priority queue. The only + prioritization performed by this scheduler is using the disk-based queue if present + (i.e. if the :setting:`JOBDIR` setting is defined) and falling back to the memory-based + queue if a serialization error occurs. If the disk queue is not present, the memory one + is used directly. + + :param dupefilter: An object responsible for checking and filtering duplicate requests. + The value for the :setting:`DUPEFILTER_CLASS` setting is used by default. + :type dupefilter: :class:`scrapy.dupefilters.BaseDupeFilter` instance or similar: + any class that implements the `BaseDupeFilter` interface + + :param jobdir: The path of a directory to be used for persisting the crawl's state. + The value for the :setting:`JOBDIR` setting is used by default. + See :ref:`topics-jobs`. + :type jobdir: :class:`str` or ``None`` + + :param dqclass: A class to be used as persistent request queue. + The value for the :setting:`SCHEDULER_DISK_QUEUE` setting is used by default. + :type dqclass: class + + :param mqclass: A class to be used as non-persistent request queue. + The value for the :setting:`SCHEDULER_MEMORY_QUEUE` setting is used by default. + :type mqclass: class + + :param logunser: A boolean that indicates whether or not unserializable requests should be logged. + The value for the :setting:`SCHEDULER_DEBUG` setting is used by default. + :type logunser: bool + + :param stats: A stats collector object to record stats about the request scheduling process. + The value for the :setting:`STATS_CLASS` setting is used by default. + :type stats: :class:`scrapy.statscollectors.StatsCollector` instance or similar: + any class that implements the `StatsCollector` interface + + :param pqclass: A class to be used as priority queue for requests. + The value for the :setting:`SCHEDULER_PRIORITY_QUEUE` setting is used by default. + :type pqclass: class + + :param crawler: The crawler object corresponding to the current crawl. + :type crawler: :class:`scrapy.crawler.Crawler` + """ + def __init__( + self, + dupefilter, + jobdir: Optional[str] = None, + dqclass=None, + mqclass=None, + logunser: bool = False, + stats=None, + pqclass=None, + crawler: Optional[Crawler] = None, + ): self.df = dupefilter self.dqdir = self._dqdir(jobdir) self.pqclass = pqclass @@ -51,42 +184,57 @@ class Scheduler: self.crawler = crawler @classmethod - def from_crawler(cls, crawler): - settings = crawler.settings - dupefilter_cls = load_object(settings['DUPEFILTER_CLASS']) - dupefilter = create_instance(dupefilter_cls, settings, crawler) - pqclass = load_object(settings['SCHEDULER_PRIORITY_QUEUE']) - if pqclass is PriorityQueue: - warnings.warn("SCHEDULER_PRIORITY_QUEUE='queuelib.PriorityQueue'" - " is no longer supported because of API changes; " - "please use 'scrapy.pqueues.ScrapyPriorityQueue'", - ScrapyDeprecationWarning) - from scrapy.pqueues import ScrapyPriorityQueue - pqclass = ScrapyPriorityQueue + def from_crawler(cls: Type[SchedulerTV], crawler) -> SchedulerTV: + """ + Factory method, initializes the scheduler with arguments taken from the crawl settings + """ + dupefilter_cls = load_object(crawler.settings['DUPEFILTER_CLASS']) + return cls( + dupefilter=create_instance(dupefilter_cls, crawler.settings, crawler), + jobdir=job_dir(crawler.settings), + dqclass=load_object(crawler.settings['SCHEDULER_DISK_QUEUE']), + mqclass=load_object(crawler.settings['SCHEDULER_MEMORY_QUEUE']), + logunser=crawler.settings.getbool('SCHEDULER_DEBUG'), + stats=crawler.stats, + pqclass=load_object(crawler.settings['SCHEDULER_PRIORITY_QUEUE']), + crawler=crawler, + ) - dqclass = load_object(settings['SCHEDULER_DISK_QUEUE']) - mqclass = load_object(settings['SCHEDULER_MEMORY_QUEUE']) - logunser = settings.getbool('SCHEDULER_DEBUG') - return cls(dupefilter, jobdir=job_dir(settings), logunser=logunser, - stats=crawler.stats, pqclass=pqclass, dqclass=dqclass, - mqclass=mqclass, crawler=crawler) - - def has_pending_requests(self): + def has_pending_requests(self) -> bool: return len(self) > 0 - def open(self, spider): + def open(self, spider: Spider) -> Optional[Deferred]: + """ + (1) initialize the memory queue + (2) initialize the disk queue if the ``jobdir`` attribute is a valid directory + (3) return the result of the dupefilter's ``open`` method + """ self.spider = spider self.mqs = self._mq() self.dqs = self._dq() if self.dqdir else None return self.df.open() - def close(self, reason): - if self.dqs: + def close(self, reason: str) -> Optional[Deferred]: + """ + (1) dump pending requests to disk if there is a disk queue + (2) return the result of the dupefilter's ``close`` method + """ + if self.dqs is not None: state = self.dqs.close() + assert isinstance(self.dqdir, str) self._write_dqs_state(self.dqdir, state) return self.df.close(reason) - def enqueue_request(self, request): + def enqueue_request(self, request: Request) -> bool: + """ + Unless the received request is filtered out by the Dupefilter, attempt to push + it into the disk queue, falling back to pushing it into the memory queue. + + Increment the appropriate stats, such as: ``scheduler/enqueued``, + ``scheduler/enqueued/disk``, ``scheduler/enqueued/memory``. + + Return ``True`` if the request was stored successfully, ``False`` otherwise. + """ if not request.dont_filter and self.df.request_seen(request): self.df.log(request, self.spider) return False @@ -99,24 +247,35 @@ class Scheduler: self.stats.inc_value('scheduler/enqueued', spider=self.spider) return True - def next_request(self): + def next_request(self) -> Optional[Request]: + """ + Return a :class:`~scrapy.http.Request` object from the memory queue, + falling back to the disk queue if the memory queue is empty. + Return ``None`` if there are no more enqueued requests. + + Increment the appropriate stats, such as: ``scheduler/dequeued``, + ``scheduler/dequeued/disk``, ``scheduler/dequeued/memory``. + """ request = self.mqs.pop() - if request: + if request is not None: self.stats.inc_value('scheduler/dequeued/memory', spider=self.spider) else: request = self._dqpop() - if request: + if request is not None: self.stats.inc_value('scheduler/dequeued/disk', spider=self.spider) - if request: + if request is not None: self.stats.inc_value('scheduler/dequeued', spider=self.spider) return request - def __len__(self): - return len(self.dqs) + len(self.mqs) if self.dqs else len(self.mqs) + def __len__(self) -> int: + """ + Return the total amount of enqueued requests + """ + return len(self.dqs) + len(self.mqs) if self.dqs is not None else len(self.mqs) - def _dqpush(self, request): + def _dqpush(self, request: Request) -> bool: if self.dqs is None: - return + return False try: self.dqs.push(request) except ValueError as e: # non serializable request @@ -127,18 +286,18 @@ class Scheduler: logger.warning(msg, {'request': request, 'reason': e}, exc_info=True, extra={'spider': self.spider}) self.logunser = False - self.stats.inc_value('scheduler/unserializable', - spider=self.spider) - return + self.stats.inc_value('scheduler/unserializable', spider=self.spider) + return False else: return True - def _mqpush(self, request): + def _mqpush(self, request: Request) -> None: self.mqs.push(request) - def _dqpop(self): - if self.dqs: + def _dqpop(self) -> Optional[Request]: + if self.dqs is not None: return self.dqs.pop() + return None def _mq(self): """ Create a new priority queue instance, with in-memory storage """ @@ -162,21 +321,22 @@ class Scheduler: {'queuesize': len(q)}, extra={'spider': self.spider}) return q - def _dqdir(self, jobdir): + def _dqdir(self, jobdir: Optional[str]) -> Optional[str]: """ Return a folder name to keep disk queue state at """ - if jobdir: + if jobdir is not None: dqdir = join(jobdir, 'requests.queue') if not exists(dqdir): os.makedirs(dqdir) return dqdir + return None - def _read_dqs_state(self, dqdir): + def _read_dqs_state(self, dqdir: str) -> list: path = join(dqdir, 'active.json') if not exists(path): - return () + return [] with open(path) as f: return json.load(f) - def _write_dqs_state(self, dqdir, state): + def _write_dqs_state(self, dqdir: str, state: list) -> None: with open(join(dqdir, 'active.json'), 'w') as f: json.dump(state, f) diff --git a/scrapy/core/scraper.py b/scrapy/core/scraper.py index 6785e103d..d6d6f64f9 100644 --- a/scrapy/core/scraper.py +++ b/scrapy/core/scraper.py @@ -3,19 +3,23 @@ extracts information from them""" import logging from collections import deque +from typing import Any, Deque, Iterable, Optional, Set, Tuple, Union +from itemadapter import is_item +from twisted.internet.defer import Deferred, inlineCallbacks from twisted.python.failure import Failure -from twisted.internet import defer -from scrapy.utils.defer import defer_result, defer_succeed, parallel, iter_errback -from scrapy.utils.spider import iterate_spider_output -from scrapy.utils.misc import load_object, warn_on_generator_with_return_value -from scrapy.utils.log import logformatter_adapter, failure_to_exc_info -from scrapy.exceptions import CloseSpider, DropItem, IgnoreRequest -from scrapy import signals -from scrapy.http import Request, Response -from scrapy.item import _BaseItem +from scrapy import signals, Spider from scrapy.core.spidermw import SpiderMiddlewareManager +from scrapy.exceptions import CloseSpider, DropItem, IgnoreRequest +from scrapy.http import Request, Response +from scrapy.utils.defer import defer_fail, defer_succeed, iter_errback, parallel +from scrapy.utils.log import failure_to_exc_info, logformatter_adapter +from scrapy.utils.misc import load_object, warn_on_generator_with_return_value +from scrapy.utils.spider import iterate_spider_output + + +QueueTuple = Tuple[Union[Response, Failure], Request, Deferred] logger = logging.getLogger(__name__) @@ -26,46 +30,46 @@ class Slot: MIN_RESPONSE_SIZE = 1024 - def __init__(self, max_active_size=5000000): + def __init__(self, max_active_size: int = 5000000): self.max_active_size = max_active_size - self.queue = deque() - self.active = set() - self.active_size = 0 - self.itemproc_size = 0 - self.closing = None + self.queue: Deque[QueueTuple] = deque() + self.active: Set[Request] = set() + self.active_size: int = 0 + self.itemproc_size: int = 0 + self.closing: Optional[Deferred] = None - def add_response_request(self, response, request): - deferred = defer.Deferred() - self.queue.append((response, request, deferred)) - if isinstance(response, Response): - self.active_size += max(len(response.body), self.MIN_RESPONSE_SIZE) + def add_response_request(self, result: Union[Response, Failure], request: Request) -> Deferred: + deferred = Deferred() + self.queue.append((result, request, deferred)) + if isinstance(result, Response): + self.active_size += max(len(result.body), self.MIN_RESPONSE_SIZE) else: self.active_size += self.MIN_RESPONSE_SIZE return deferred - def next_response_request_deferred(self): + def next_response_request_deferred(self) -> QueueTuple: response, request, deferred = self.queue.popleft() self.active.add(request) return response, request, deferred - def finish_response(self, response, request): + def finish_response(self, result: Union[Response, Failure], request: Request) -> None: self.active.remove(request) - if isinstance(response, Response): - self.active_size -= max(len(response.body), self.MIN_RESPONSE_SIZE) + if isinstance(result, Response): + self.active_size -= max(len(result.body), self.MIN_RESPONSE_SIZE) else: self.active_size -= self.MIN_RESPONSE_SIZE - def is_idle(self): + def is_idle(self) -> bool: return not (self.queue or self.active) - def needs_backout(self): + def needs_backout(self) -> bool: return self.active_size > self.max_active_size class Scraper: def __init__(self, crawler): - self.slot = None + self.slot: Optional[Slot] = None self.spidermw = SpiderMiddlewareManager.from_crawler(crawler) itemproc_cls = load_object(crawler.settings['ITEM_PROCESSOR']) self.itemproc = itemproc_cls.from_crawler(crawler) @@ -74,36 +78,39 @@ class Scraper: self.signals = crawler.signals self.logformatter = crawler.logformatter - @defer.inlineCallbacks - def open_spider(self, spider): + @inlineCallbacks + def open_spider(self, spider: Spider): """Open the given spider for scraping and allocate resources for it""" self.slot = Slot(self.crawler.settings.getint('SCRAPER_SLOT_MAX_ACTIVE_SIZE')) yield self.itemproc.open_spider(spider) - def close_spider(self, spider): + def close_spider(self, spider: Spider) -> Deferred: """Close a spider being scraped and release its resources""" - slot = self.slot - slot.closing = defer.Deferred() - slot.closing.addCallback(self.itemproc.close_spider) - self._check_if_closing(spider, slot) - return slot.closing + if self.slot is None: + raise RuntimeError("Scraper slot not assigned") + self.slot.closing = Deferred() + self.slot.closing.addCallback(self.itemproc.close_spider) + self._check_if_closing(spider) + return self.slot.closing - def is_idle(self): + def is_idle(self) -> bool: """Return True if there isn't any more spiders to process""" return not self.slot - def _check_if_closing(self, spider, slot): - if slot.closing and slot.is_idle(): - slot.closing.callback(spider) + def _check_if_closing(self, spider: Spider) -> None: + assert self.slot is not None # typing + if self.slot.closing and self.slot.is_idle(): + self.slot.closing.callback(spider) - def enqueue_scrape(self, response, request, spider): - slot = self.slot - dfd = slot.add_response_request(response, request) + def enqueue_scrape(self, result: Union[Response, Failure], request: Request, spider: Spider) -> Deferred: + if self.slot is None: + raise RuntimeError("Scraper slot not assigned") + dfd = self.slot.add_response_request(result, request) def finish_scraping(_): - slot.finish_response(response, request) - self._check_if_closing(spider, slot) - self._scrape_next(spider, slot) + self.slot.finish_response(result, request) + self._check_if_closing(spider) + self._scrape_next(spider) return _ dfd.addBoth(finish_scraping) @@ -112,51 +119,52 @@ class Scraper: {'request': request}, exc_info=failure_to_exc_info(f), extra={'spider': spider})) - self._scrape_next(spider, slot) + self._scrape_next(spider) return dfd - def _scrape_next(self, spider, slot): - while slot.queue: - response, request, deferred = slot.next_response_request_deferred() + def _scrape_next(self, spider: Spider) -> None: + assert self.slot is not None # typing + while self.slot.queue: + response, request, deferred = self.slot.next_response_request_deferred() self._scrape(response, request, spider).chainDeferred(deferred) - def _scrape(self, response, request, spider): - """Handle the downloaded response or failure through the spider - callback/errback""" - if not isinstance(response, (Response, Failure)): - raise TypeError( - "Incorrect type: expected Response or Failure, got %s: %r" - % (type(response), response) - ) - - dfd = self._scrape2(response, request, spider) # returns spider's processed output - dfd.addErrback(self.handle_spider_error, request, response, spider) - dfd.addCallback(self.handle_spider_output, request, response, spider) + def _scrape(self, result: Union[Response, Failure], request: Request, spider: Spider) -> Deferred: + """ + Handle the downloaded response or failure through the spider callback/errback + """ + if not isinstance(result, (Response, Failure)): + raise TypeError(f"Incorrect type: expected Response or Failure, got {type(result)}: {result!r}") + dfd = self._scrape2(result, request, spider) # returns spider's processed output + dfd.addErrback(self.handle_spider_error, request, result, spider) + dfd.addCallback(self.handle_spider_output, request, result, spider) return dfd - def _scrape2(self, request_result, request, spider): - """Handle the different cases of request's result been a Response or a - Failure""" - if not isinstance(request_result, Failure): - return self.spidermw.scrape_response( - self.call_spider, request_result, request, spider) - else: - dfd = self.call_spider(request_result, request, spider) - return dfd.addErrback( - self._log_download_errors, request_result, request, spider) + def _scrape2(self, result: Union[Response, Failure], request: Request, spider: Spider) -> Deferred: + """ + Handle the different cases of request's result been a Response or a Failure + """ + if isinstance(result, Response): + return self.spidermw.scrape_response(self.call_spider, result, request, spider) + else: # result is a Failure + dfd = self.call_spider(result, request, spider) + return dfd.addErrback(self._log_download_errors, result, request, spider) - def call_spider(self, result, request, spider): - result.request = request - dfd = defer_result(result) - callback = request.callback or spider.parse - warn_on_generator_with_return_value(spider, callback) - warn_on_generator_with_return_value(spider, request.errback) - dfd.addCallbacks(callback=callback, - errback=request.errback, - callbackKeywords=request.cb_kwargs) + def call_spider(self, result: Union[Response, Failure], request: Request, spider: Spider) -> Deferred: + if isinstance(result, Response): + if getattr(result, "request", None) is None: + result.request = request + callback = result.request.callback or spider._parse + warn_on_generator_with_return_value(spider, callback) + dfd = defer_succeed(result) + dfd.addCallback(callback, **result.request.cb_kwargs) + else: # result is a Failure + result.request = request + warn_on_generator_with_return_value(spider, request.errback) + dfd = defer_fail(result) + dfd.addErrback(request.errback) return dfd.addCallback(iterate_spider_output) - def handle_spider_error(self, _failure, request, response, spider): + def handle_spider_error(self, _failure: Failure, request: Request, response: Response, spider: Spider) -> None: exc = _failure.value if isinstance(exc, CloseSpider): self.crawler.engine.close_spider(spider, exc.reason or 'cancelled') @@ -173,11 +181,11 @@ class Scraper: spider=spider ) self.crawler.stats.inc_value( - "spider_exceptions/%s" % _failure.value.__class__.__name__, + f"spider_exceptions/{_failure.value.__class__.__name__}", spider=spider ) - def handle_spider_output(self, result, request, response, spider): + def handle_spider_output(self, result: Iterable, request: Request, response: Response, spider: Spider) -> Deferred: if not result: return defer_succeed(None) it = iter_errback(result, self.handle_spider_error, request, response, spider) @@ -185,13 +193,15 @@ class Scraper: request, response, spider) return dfd - def _process_spidermw_output(self, output, request, response, spider): + def _process_spidermw_output(self, output: Any, request: Request, response: Response, + spider: Spider) -> Optional[Deferred]: """Process each Request/Item (given in the output parameter) returned from the given spider """ + assert self.slot is not None # typing if isinstance(output, Request): - self.crawler.engine.crawl(request=output, spider=spider) - elif isinstance(output, (_BaseItem, dict)): + self.crawler.engine.crawl(request=output) + elif is_item(output): self.slot.itemproc_size += 1 dfd = self.itemproc.process_item(output, spider) dfd.addBoth(self._itemproc_finished, output, response, spider) @@ -200,16 +210,23 @@ class Scraper: pass else: typename = type(output).__name__ - logger.error('Spider must return Request, BaseItem, dict or None, ' - 'got %(typename)r in %(request)s', - {'request': request, 'typename': typename}, - extra={'spider': spider}) + logger.error( + 'Spider must return request, item, or None, got %(typename)r in %(request)s', + {'request': request, 'typename': typename}, + extra={'spider': spider}, + ) + return None - def _log_download_errors(self, spider_failure, download_failure, request, spider): + def _log_download_errors(self, spider_failure: Failure, download_failure: Failure, request: Request, + spider: Spider) -> Union[Failure, None]: """Log and silence errors that come from the engine (typically download - errors that got propagated thru here) + errors that got propagated thru here). + + spider_failure: the value passed into the errback of self.call_spider() + download_failure: the value passed into _scrape2() from + ExecutionEngine._handle_downloader_output() as "result" """ - if isinstance(download_failure, Failure) and not download_failure.check(IgnoreRequest): + if not download_failure.check(IgnoreRequest): if download_failure.frames: logkws = self.logformatter.download_error(download_failure, request, spider) logger.log( @@ -229,10 +246,12 @@ class Scraper: if spider_failure is not download_failure: return spider_failure + return None - def _itemproc_finished(self, output, item, response, spider): + def _itemproc_finished(self, output: Any, item: Any, response: Response, spider: Spider) -> None: """ItemProcessor finished for the given ``item`` and returned ``output`` """ + assert self.slot is not None # typing self.slot.itemproc_size -= 1 if isinstance(output, Failure): ex = output.value diff --git a/scrapy/core/spidermw.py b/scrapy/core/spidermw.py index 35264a92b..7e58521ac 100644 --- a/scrapy/core/spidermw.py +++ b/scrapy/core/spidermw.py @@ -4,25 +4,25 @@ Spider Middleware manager See documentation in docs/topics/spider-middleware.rst """ from itertools import islice +from typing import Any, Callable, Generator, Iterable, Union +from twisted.internet.defer import Deferred from twisted.python.failure import Failure +from scrapy import Request, Spider from scrapy.exceptions import _InvalidOutput +from scrapy.http import Response from scrapy.middleware import MiddlewareManager from scrapy.utils.conf import build_component_list from scrapy.utils.defer import mustbe_deferred from scrapy.utils.python import MutableChain -def _isiterable(possible_iterator): - return hasattr(possible_iterator, '__iter__') +ScrapeFunc = Callable[[Union[Response, Failure], Request, Spider], Any] -def _fname(f): - return "{}.{}".format( - f.__self__.__class__.__name__, - f.__func__.__name__ - ) +def _isiterable(o) -> bool: + return isinstance(o, Iterable) class SpiderMiddlewareManager(MiddlewareManager): @@ -34,7 +34,7 @@ class SpiderMiddlewareManager(MiddlewareManager): return build_component_list(settings.getwithbase('SPIDER_MIDDLEWARES')) def _add_middleware(self, mw): - super(SpiderMiddlewareManager, self)._add_middleware(mw) + super()._add_middleware(mw) if hasattr(mw, 'process_spider_input'): self.methods['process_spider_input'].append(mw.process_spider_input) if hasattr(mw, 'process_start_requests'): @@ -44,85 +44,99 @@ class SpiderMiddlewareManager(MiddlewareManager): process_spider_exception = getattr(mw, 'process_spider_exception', None) self.methods['process_spider_exception'].appendleft(process_spider_exception) - def scrape_response(self, scrape_func, response, request, spider): - - def process_spider_input(response): - for method in self.methods['process_spider_input']: - try: - result = method(response=response, spider=spider) - if result is not None: - msg = "Middleware {} must return None or raise an exception, got {}" - raise _InvalidOutput(msg.format(_fname(method), type(result))) - except _InvalidOutput: - raise - except Exception: - return scrape_func(Failure(), request, spider) - return scrape_func(response, request, spider) - - def _evaluate_iterable(iterable, exception_processor_index, recover_to): + def _process_spider_input(self, scrape_func: ScrapeFunc, response: Response, request: Request, + spider: Spider) -> Any: + for method in self.methods['process_spider_input']: try: - for r in iterable: - yield r + result = method(response=response, spider=spider) + if result is not None: + msg = (f"Middleware {method.__qualname__} must return None " + f"or raise an exception, got {type(result)}") + raise _InvalidOutput(msg) + except _InvalidOutput: + raise + except Exception: + return scrape_func(Failure(), request, spider) + return scrape_func(response, request, spider) + + def _evaluate_iterable(self, response: Response, spider: Spider, iterable: Iterable, + exception_processor_index: int, recover_to: MutableChain) -> Generator: + try: + for r in iterable: + yield r + except Exception as ex: + exception_result = self._process_spider_exception(response, spider, Failure(ex), + exception_processor_index) + if isinstance(exception_result, Failure): + raise + recover_to.extend(exception_result) + + def _process_spider_exception(self, response: Response, spider: Spider, _failure: Failure, + start_index: int = 0) -> Union[Failure, MutableChain]: + exception = _failure.value + # don't handle _InvalidOutput exception + if isinstance(exception, _InvalidOutput): + return _failure + method_list = islice(self.methods['process_spider_exception'], start_index, None) + for method_index, method in enumerate(method_list, start=start_index): + if method is None: + continue + result = method(response=response, exception=exception, spider=spider) + if _isiterable(result): + # stop exception handling by handing control over to the + # process_spider_output chain if an iterable has been returned + return self._process_spider_output(response, spider, result, method_index + 1) + elif result is None: + continue + else: + msg = (f"Middleware {method.__qualname__} must return None " + f"or an iterable, got {type(result)}") + raise _InvalidOutput(msg) + return _failure + + def _process_spider_output(self, response: Response, spider: Spider, + result: Iterable, start_index: int = 0) -> MutableChain: + # items in this iterable do not need to go through the process_spider_output + # chain, they went through it already from the process_spider_exception method + recovered = MutableChain() + + method_list = islice(self.methods['process_spider_output'], start_index, None) + for method_index, method in enumerate(method_list, start=start_index): + if method is None: + continue + try: + # might fail directly if the output value is not a generator + result = method(response=response, result=result, spider=spider) except Exception as ex: - exception_result = process_spider_exception(Failure(ex), exception_processor_index) + exception_result = self._process_spider_exception(response, spider, Failure(ex), method_index + 1) if isinstance(exception_result, Failure): raise - recover_to.extend(exception_result) + return exception_result + if _isiterable(result): + result = self._evaluate_iterable(response, spider, result, method_index + 1, recovered) + else: + msg = (f"Middleware {method.__qualname__} must return an " + f"iterable, got {type(result)}") + raise _InvalidOutput(msg) - def process_spider_exception(_failure, start_index=0): - exception = _failure.value - # don't handle _InvalidOutput exception - if isinstance(exception, _InvalidOutput): - return _failure - method_list = islice(self.methods['process_spider_exception'], start_index, None) - for method_index, method in enumerate(method_list, start=start_index): - if method is None: - continue - result = method(response=response, exception=exception, spider=spider) - if _isiterable(result): - # stop exception handling by handing control over to the - # process_spider_output chain if an iterable has been returned - return process_spider_output(result, method_index + 1) - elif result is None: - continue - else: - msg = "Middleware {} must return None or an iterable, got {}" - raise _InvalidOutput(msg.format(_fname(method), type(result))) - return _failure + return MutableChain(result, recovered) - def process_spider_output(result, start_index=0): - # items in this iterable do not need to go through the process_spider_output - # chain, they went through it already from the process_spider_exception method - recovered = MutableChain() + def _process_callback_output(self, response: Response, spider: Spider, result: Iterable) -> MutableChain: + recovered = MutableChain() + result = self._evaluate_iterable(response, spider, result, 0, recovered) + return MutableChain(self._process_spider_output(response, spider, result), recovered) - method_list = islice(self.methods['process_spider_output'], start_index, None) - for method_index, method in enumerate(method_list, start=start_index): - if method is None: - continue - try: - # might fail directly if the output value is not a generator - result = method(response=response, result=result, spider=spider) - except Exception as ex: - exception_result = process_spider_exception(Failure(ex), method_index + 1) - if isinstance(exception_result, Failure): - raise - return exception_result - if _isiterable(result): - result = _evaluate_iterable(result, method_index + 1, recovered) - else: - msg = "Middleware {} must return an iterable, got {}" - raise _InvalidOutput(msg.format(_fname(method), type(result))) + def scrape_response(self, scrape_func: ScrapeFunc, response: Response, request: Request, + spider: Spider) -> Deferred: + def process_callback_output(result: Iterable) -> MutableChain: + return self._process_callback_output(response, spider, result) - return MutableChain(result, recovered) + def process_spider_exception(_failure: Failure) -> Union[Failure, MutableChain]: + return self._process_spider_exception(response, spider, _failure) - def process_callback_output(result): - recovered = MutableChain() - result = _evaluate_iterable(result, 0, recovered) - return MutableChain(process_spider_output(result), recovered) - - dfd = mustbe_deferred(process_spider_input, response) + dfd = mustbe_deferred(self._process_spider_input, scrape_func, response, request, spider) dfd.addCallbacks(callback=process_callback_output, errback=process_spider_exception) return dfd - def process_start_requests(self, start_requests, spider): + def process_start_requests(self, start_requests, spider: Spider) -> Deferred: return self._process_chain('process_start_requests', start_requests, spider) diff --git a/scrapy/crawler.py b/scrapy/crawler.py index 6f43771e2..578016536 100644 --- a/scrapy/crawler.py +++ b/scrapy/crawler.py @@ -180,9 +180,9 @@ class CrawlerRunner: :type crawler_or_spidercls: :class:`~scrapy.crawler.Crawler` instance, :class:`~scrapy.spiders.Spider` subclass or string - :param list args: arguments to initialize the spider + :param args: arguments to initialize the spider - :param dict kwargs: keyword arguments to initialize the spider + :param kwargs: keyword arguments to initialize the spider """ if isinstance(crawler_or_spidercls, Spider): raise ValueError( @@ -277,7 +277,7 @@ class CrawlerProcess(CrawlerRunner): """ def __init__(self, settings=None, install_root_handler=True): - super(CrawlerProcess, self).__init__(settings) + super().__init__(settings) install_shutdown_handlers(self._signal_shutdown) configure_logging(self.settings, install_root_handler) log_scrapy_info(self.settings) @@ -307,7 +307,7 @@ class CrawlerProcess(CrawlerRunner): If ``stop_after_crawl`` is True, the reactor will be stopped after all crawlers have finished, using :meth:`join`. - :param boolean stop_after_crawl: stop or not the reactor when all + :param bool stop_after_crawl: stop or not the reactor when all crawlers have finished """ from twisted.internet import reactor @@ -340,5 +340,5 @@ class CrawlerProcess(CrawlerRunner): def _handle_twisted_reactor(self): if self.settings.get("TWISTED_REACTOR"): - install_reactor(self.settings["TWISTED_REACTOR"]) + install_reactor(self.settings["TWISTED_REACTOR"], self.settings["ASYNCIO_EVENT_LOOP"]) super()._handle_twisted_reactor() diff --git a/scrapy/downloadermiddlewares/cookies.py b/scrapy/downloadermiddlewares/cookies.py index 77048f389..d95ed3d38 100644 --- a/scrapy/downloadermiddlewares/cookies.py +++ b/scrapy/downloadermiddlewares/cookies.py @@ -54,8 +54,8 @@ class CookiesMiddleware: cl = [to_unicode(c, errors='replace') for c in request.headers.getlist('Cookie')] if cl: - cookies = "\n".join("Cookie: {}\n".format(c) for c in cl) - msg = "Sending cookies to: {}\n{}".format(request, cookies) + cookies = "\n".join(f"Cookie: {c}\n" for c in cl) + msg = f"Sending cookies to: {request}\n{cookies}" logger.debug(msg, extra={'spider': spider}) def _debug_set_cookie(self, response, spider): @@ -63,8 +63,8 @@ class CookiesMiddleware: cl = [to_unicode(c, errors='replace') for c in response.headers.getlist('Set-Cookie')] if cl: - cookies = "\n".join("Set-Cookie: {}\n".format(c) for c in cl) - msg = "Received cookies from: {}\n{}".format(response, cookies) + cookies = "\n".join(f"Set-Cookie: {c}\n" for c in cl) + msg = f"Received cookies from: {response}\n{cookies}" logger.debug(msg, extra={'spider': spider}) def _format_cookie(self, cookie, request): @@ -74,7 +74,7 @@ class CookiesMiddleware: """ decoded = {} for key in ("name", "value", "path", "domain"): - if not cookie.get(key): + if cookie.get(key) is None: if key in ("name", "value"): msg = "Invalid cookie found in request {}: {} ('{}' is missing)" logger.warning(msg.format(request, cookie, key)) @@ -90,42 +90,21 @@ class CookiesMiddleware: request, cookie) decoded[key] = cookie[key].decode("latin1", errors="replace") - cookie_str = "{}={}".format(decoded.pop("name"), decoded.pop("value")) + cookie_str = f"{decoded.pop('name')}={decoded.pop('value')}" for key, value in decoded.items(): # path, domain - cookie_str += "; {}={}".format(key.capitalize(), value) + cookie_str += f"; {key.capitalize()}={value}" return cookie_str def _get_request_cookies(self, jar, request): """ - Extract cookies from a Request. Values from the `Request.cookies` attribute - take precedence over values from the `Cookie` request header. + Extract cookies from the Request.cookies attribute """ - def get_cookies_from_header(jar, request): - cookie_header = request.headers.get("Cookie") - if not cookie_header: - return [] - cookie_gen_bytes = (s.strip() for s in cookie_header.split(b";")) - cookie_list_unicode = [] - for cookie_bytes in cookie_gen_bytes: - try: - cookie_unicode = cookie_bytes.decode("utf8") - except UnicodeDecodeError: - logger.warning("Non UTF-8 encoded cookie found in request %s: %s", - request, cookie_bytes) - cookie_unicode = cookie_bytes.decode("latin1", errors="replace") - cookie_list_unicode.append(cookie_unicode) - response = Response(request.url, headers={"Set-Cookie": cookie_list_unicode}) - return jar.make_cookies(response, request) - - def get_cookies_from_attribute(jar, request): - if not request.cookies: - return [] - elif isinstance(request.cookies, dict): - cookies = ({"name": k, "value": v} for k, v in request.cookies.items()) - else: - cookies = request.cookies - formatted = filter(None, (self._format_cookie(c, request) for c in cookies)) - response = Response(request.url, headers={"Set-Cookie": formatted}) - return jar.make_cookies(response, request) - - return get_cookies_from_header(jar, request) + get_cookies_from_attribute(jar, request) + if not request.cookies: + return [] + elif isinstance(request.cookies, dict): + cookies = ({"name": k, "value": v} for k, v in request.cookies.items()) + else: + cookies = request.cookies + formatted = filter(None, (self._format_cookie(c, request) for c in cookies)) + response = Response(request.url, headers={"Set-Cookie": formatted}) + return jar.make_cookies(response, request) diff --git a/scrapy/downloadermiddlewares/httpcache.py b/scrapy/downloadermiddlewares/httpcache.py index 6db57bd8b..62f1c3a29 100644 --- a/scrapy/downloadermiddlewares/httpcache.py +++ b/scrapy/downloadermiddlewares/httpcache.py @@ -1,4 +1,5 @@ from email.utils import formatdate +from typing import Optional, Type, TypeVar from twisted.internet import defer from twisted.internet.error import ( @@ -13,10 +14,19 @@ from twisted.internet.error import ( from twisted.web.client import ResponseFailed from scrapy import signals +from scrapy.crawler import Crawler from scrapy.exceptions import IgnoreRequest, NotConfigured +from scrapy.http.request import Request +from scrapy.http.response import Response +from scrapy.settings import Settings +from scrapy.spiders import Spider +from scrapy.statscollectors import StatsCollector from scrapy.utils.misc import load_object +HttpCacheMiddlewareTV = TypeVar("HttpCacheMiddlewareTV", bound="HttpCacheMiddleware") + + class HttpCacheMiddleware: DOWNLOAD_EXCEPTIONS = (defer.TimeoutError, TimeoutError, DNSLookupError, @@ -24,7 +34,7 @@ class HttpCacheMiddleware: ConnectionLost, TCPTimedOutError, ResponseFailed, IOError) - def __init__(self, settings, stats): + def __init__(self, settings: Settings, stats: StatsCollector) -> None: if not settings.getbool('HTTPCACHE_ENABLED'): raise NotConfigured self.policy = load_object(settings['HTTPCACHE_POLICY'])(settings) @@ -33,26 +43,26 @@ class HttpCacheMiddleware: self.stats = stats @classmethod - def from_crawler(cls, crawler): + def from_crawler(cls: Type[HttpCacheMiddlewareTV], crawler: Crawler) -> HttpCacheMiddlewareTV: o = cls(crawler.settings, crawler.stats) crawler.signals.connect(o.spider_opened, signal=signals.spider_opened) crawler.signals.connect(o.spider_closed, signal=signals.spider_closed) return o - def spider_opened(self, spider): + def spider_opened(self, spider: Spider) -> None: self.storage.open_spider(spider) - def spider_closed(self, spider): + def spider_closed(self, spider: Spider) -> None: self.storage.close_spider(spider) - def process_request(self, request, spider): + def process_request(self, request: Request, spider: Spider) -> Optional[Response]: if request.meta.get('dont_cache', False): - return + return None # Skip uncacheable requests if not self.policy.should_cache_request(request): request.meta['_dont_cache'] = True # flag as uncacheable - return + return None # Look for cached response and check if expired cachedresponse = self.storage.retrieve_response(spider, request) @@ -61,7 +71,7 @@ class HttpCacheMiddleware: if self.ignore_missing: self.stats.inc_value('httpcache/ignore', spider=spider) raise IgnoreRequest("Ignored request not in cache: %s" % request) - return # first time request + return None # first time request # Return cached response only if not expired cachedresponse.flags.append('cached') @@ -73,7 +83,9 @@ class HttpCacheMiddleware: # process_response hook request.meta['cached_response'] = cachedresponse - def process_response(self, request, response, spider): + return None + + def process_response(self, request: Request, response: Response, spider: Spider) -> Response: if request.meta.get('dont_cache', False): return response @@ -85,7 +97,7 @@ class HttpCacheMiddleware: # RFC2616 requires origin server to set Date header, # https://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.18 if 'Date' not in response.headers: - response.headers['Date'] = formatdate(usegmt=1) + response.headers['Date'] = formatdate(usegmt=True) # Do not validate first-hand responses cachedresponse = request.meta.pop('cached_response', None) @@ -102,13 +114,18 @@ class HttpCacheMiddleware: self._cache_response(spider, response, request, cachedresponse) return response - def process_exception(self, request, exception, spider): + def process_exception( + self, request: Request, exception: Exception, spider: Spider + ) -> Optional[Response]: cachedresponse = request.meta.pop('cached_response', None) if cachedresponse is not None and isinstance(exception, self.DOWNLOAD_EXCEPTIONS): self.stats.inc_value('httpcache/errorrecovery', spider=spider) return cachedresponse + return None - def _cache_response(self, spider, response, request, cachedresponse): + def _cache_response( + self, spider: Spider, response: Response, request: Request, cachedresponse: Optional[Response] + ) -> None: if self.policy.should_cache_response(response, request): self.stats.inc_value('httpcache/store', spider=spider) self.storage.store_response(spider, request, response) diff --git a/scrapy/downloadermiddlewares/httpcompression.py b/scrapy/downloadermiddlewares/httpcompression.py index 727c41466..4e7feeeaf 100644 --- a/scrapy/downloadermiddlewares/httpcompression.py +++ b/scrapy/downloadermiddlewares/httpcompression.py @@ -1,9 +1,12 @@ +import io +import warnings import zlib -from scrapy.utils.gz import gunzip +from scrapy.exceptions import NotConfigured from scrapy.http import Response, TextResponse from scrapy.responsetypes import responsetypes -from scrapy.exceptions import NotConfigured +from scrapy.utils.deprecate import ScrapyDeprecationWarning +from scrapy.utils.gz import gunzip ACCEPTED_ENCODINGS = [b'gzip', b'deflate'] @@ -14,15 +17,35 @@ try: except ImportError: pass +try: + import zstandard + ACCEPTED_ENCODINGS.append(b'zstd') +except ImportError: + pass + class HttpCompressionMiddleware: """This middleware allows compressed (gzip, deflate) traffic to be sent/received from web sites""" + def __init__(self, stats=None): + self.stats = stats + @classmethod def from_crawler(cls, crawler): if not crawler.settings.getbool('COMPRESSION_ENABLED'): raise NotConfigured - return cls() + try: + return cls(stats=crawler.stats) + except TypeError: + warnings.warn( + "HttpCompressionMiddleware subclasses must either modify " + "their '__init__' method to support a 'stats' parameter or " + "reimplement the 'from_crawler' method.", + ScrapyDeprecationWarning, + ) + result = cls() + result.stats = crawler.stats + return result def process_request(self, request, spider): request.headers.setdefault('Accept-Encoding', @@ -37,6 +60,9 @@ class HttpCompressionMiddleware: if content_encoding: encoding = content_encoding.pop() decoded_body = self._decode(response.body, encoding.lower()) + if self.stats: + self.stats.inc_value('httpcompression/response_bytes', len(decoded_body), spider=spider) + self.stats.inc_value('httpcompression/response_count', spider=spider) respcls = responsetypes.from_args( headers=response.headers, url=response.url, body=decoded_body ) @@ -67,4 +93,9 @@ class HttpCompressionMiddleware: body = zlib.decompress(body, -15) if encoding == b'br' and b'br' in ACCEPTED_ENCODINGS: body = brotli.decompress(body) + if encoding == b'zstd' and b'zstd' in ACCEPTED_ENCODINGS: + # Using its streaming API since its simple API could handle only cases + # where there is content size data embedded in the frame + reader = zstandard.ZstdDecompressor().stream_reader(io.BytesIO(body)) + body = reader.read() return body diff --git a/scrapy/downloadermiddlewares/httpproxy.py b/scrapy/downloadermiddlewares/httpproxy.py index da89d3e9b..d2665b655 100644 --- a/scrapy/downloadermiddlewares/httpproxy.py +++ b/scrapy/downloadermiddlewares/httpproxy.py @@ -13,7 +13,12 @@ class HttpProxyMiddleware: self.auth_encoding = auth_encoding self.proxies = {} for type_, url in getproxies().items(): - self.proxies[type_] = self._get_proxy(url, type_) + try: + self.proxies[type_] = self._get_proxy(url, type_) + # some values such as '/var/run/docker.sock' can't be parsed + # by _parse_proxy and as such should be skipped + except ValueError: + continue @classmethod def from_crawler(cls, crawler): @@ -24,7 +29,7 @@ class HttpProxyMiddleware: def _basic_auth_header(self, username, password): user_pass = to_bytes( - '%s:%s' % (unquote(username), unquote(password)), + f'{unquote(username)}:{unquote(password)}', encoding=self.auth_encoding) return base64.b64encode(user_pass) diff --git a/scrapy/downloadermiddlewares/redirect.py b/scrapy/downloadermiddlewares/redirect.py index b32afb8e4..4053fecc5 100644 --- a/scrapy/downloadermiddlewares/redirect.py +++ b/scrapy/downloadermiddlewares/redirect.py @@ -33,10 +33,8 @@ class BaseRedirectMiddleware: if ttl and redirects <= self.max_redirect_times: redirected.meta['redirect_times'] = redirects redirected.meta['redirect_ttl'] = ttl - 1 - redirected.meta['redirect_urls'] = request.meta.get('redirect_urls', []) + \ - [request.url] - redirected.meta['redirect_reasons'] = request.meta.get('redirect_reasons', []) + \ - [reason] + redirected.meta['redirect_urls'] = request.meta.get('redirect_urls', []) + [request.url] + redirected.meta['redirect_reasons'] = request.meta.get('redirect_reasons', []) + [reason] redirected.dont_filter = request.dont_filter redirected.priority = request.priority + self.priority_adjust logger.debug("Redirecting (%(reason)s) to %(redirected)s from %(request)s", @@ -94,13 +92,16 @@ class MetaRefreshMiddleware(BaseRedirectMiddleware): enabled_setting = 'METAREFRESH_ENABLED' def __init__(self, settings): - super(MetaRefreshMiddleware, self).__init__(settings) + super().__init__(settings) self._ignore_tags = settings.getlist('METAREFRESH_IGNORE_TAGS') self._maxdelay = settings.getint('METAREFRESH_MAXDELAY') def process_response(self, request, response, spider): - if request.meta.get('dont_redirect', False) or request.method == 'HEAD' or \ - not isinstance(response, HtmlResponse): + if ( + request.meta.get('dont_redirect', False) + or request.method == 'HEAD' + or not isinstance(response, HtmlResponse) + ): return response interval, url = get_meta_refresh(response, diff --git a/scrapy/downloadermiddlewares/retry.py b/scrapy/downloadermiddlewares/retry.py index 6d11af5b2..f1fdc3858 100644 --- a/scrapy/downloadermiddlewares/retry.py +++ b/scrapy/downloadermiddlewares/retry.py @@ -9,7 +9,8 @@ RETRY_HTTP_CODES - which HTTP response codes to retry Failed pages are collected on the scraping process and rescheduled at the end, once the spider has finished crawling all regular (non failed) pages. """ -import logging +from logging import getLogger, Logger +from typing import Optional, Union from twisted.internet import defer from twisted.internet.error import ( @@ -23,12 +24,104 @@ from twisted.internet.error import ( ) from twisted.web.client import ResponseFailed -from scrapy.exceptions import NotConfigured -from scrapy.utils.response import response_status_message from scrapy.core.downloader.handlers.http11 import TunnelError +from scrapy.exceptions import NotConfigured +from scrapy.http.request import Request +from scrapy.spiders import Spider from scrapy.utils.python import global_object_name +from scrapy.utils.response import response_status_message -logger = logging.getLogger(__name__) + +retry_logger = getLogger(__name__) + + +def get_retry_request( + request: Request, + *, + spider: Spider, + reason: Union[str, Exception] = 'unspecified', + max_retry_times: Optional[int] = None, + priority_adjust: Optional[int] = None, + logger: Logger = retry_logger, + stats_base_key: str = 'retry', +): + """ + Returns a new :class:`~scrapy.Request` object to retry the specified + request, or ``None`` if retries of the specified request have been + exhausted. + + For example, in a :class:`~scrapy.Spider` callback, you could use it as + follows:: + + def parse(self, response): + if not response.text: + new_request_or_none = get_retry_request( + response.request, + spider=self, + reason='empty', + ) + return new_request_or_none + + *spider* is the :class:`~scrapy.Spider` instance which is asking for the + retry request. It is used to access the :ref:`settings ` + and :ref:`stats `, and to provide extra logging context (see + :func:`logging.debug`). + + *reason* is a string or an :class:`Exception` object that indicates the + reason why the request needs to be retried. It is used to name retry stats. + + *max_retry_times* is a number that determines the maximum number of times + that *request* can be retried. If not specified or ``None``, the number is + read from the :reqmeta:`max_retry_times` meta key of the request. If the + :reqmeta:`max_retry_times` meta key is not defined or ``None``, the number + is read from the :setting:`RETRY_TIMES` setting. + + *priority_adjust* is a number that determines how the priority of the new + request changes in relation to *request*. If not specified, the number is + read from the :setting:`RETRY_PRIORITY_ADJUST` setting. + + *logger* is the logging.Logger object to be used when logging messages + + *stats_base_key* is a string to be used as the base key for the + retry-related job stats + """ + settings = spider.crawler.settings + stats = spider.crawler.stats + retry_times = request.meta.get('retry_times', 0) + 1 + if max_retry_times is None: + max_retry_times = request.meta.get('max_retry_times') + if max_retry_times is None: + max_retry_times = settings.getint('RETRY_TIMES') + if retry_times <= max_retry_times: + logger.debug( + "Retrying %(request)s (failed %(retry_times)d times): %(reason)s", + {'request': request, 'retry_times': retry_times, 'reason': reason}, + extra={'spider': spider} + ) + new_request: Request = request.copy() + new_request.meta['retry_times'] = retry_times + new_request.dont_filter = True + if priority_adjust is None: + priority_adjust = settings.getint('RETRY_PRIORITY_ADJUST') + new_request.priority = request.priority + priority_adjust + + if callable(reason): + reason = reason() + if isinstance(reason, Exception): + reason = global_object_name(reason.__class__) + + stats.inc_value(f'{stats_base_key}/count') + stats.inc_value(f'{stats_base_key}/reason_count/{reason}') + return new_request + else: + stats.inc_value(f'{stats_base_key}/max_reached') + logger.error( + "Gave up retrying %(request)s (failed %(retry_times)d times): " + "%(reason)s", + {'request': request, 'retry_times': retry_times, 'reason': reason}, + extra={'spider': spider}, + ) + return None class RetryMiddleware: @@ -60,36 +153,19 @@ class RetryMiddleware: return response def process_exception(self, request, exception, spider): - if isinstance(exception, self.EXCEPTIONS_TO_RETRY) \ - and not request.meta.get('dont_retry', False): + if ( + isinstance(exception, self.EXCEPTIONS_TO_RETRY) + and not request.meta.get('dont_retry', False) + ): return self._retry(request, exception, spider) def _retry(self, request, reason, spider): - retries = request.meta.get('retry_times', 0) + 1 - - retry_times = self.max_retry_times - - if 'max_retry_times' in request.meta: - retry_times = request.meta['max_retry_times'] - - stats = spider.crawler.stats - if retries <= retry_times: - logger.debug("Retrying %(request)s (failed %(retries)d times): %(reason)s", - {'request': request, 'retries': retries, 'reason': reason}, - extra={'spider': spider}) - retryreq = request.copy() - retryreq.meta['retry_times'] = retries - retryreq.dont_filter = True - retryreq.priority = request.priority + self.priority_adjust - - if isinstance(reason, Exception): - reason = global_object_name(reason.__class__) - - stats.inc_value('retry/count') - stats.inc_value('retry/reason_count/%s' % reason) - return retryreq - else: - stats.inc_value('retry/max_reached') - logger.error("Gave up retrying %(request)s (failed %(retries)d times): %(reason)s", - {'request': request, 'retries': retries, 'reason': reason}, - extra={'spider': spider}) + max_retry_times = request.meta.get('max_retry_times', self.max_retry_times) + priority_adjust = request.meta.get('priority_adjust', self.priority_adjust) + return get_retry_request( + request, + reason=reason, + spider=spider, + max_retry_times=max_retry_times, + priority_adjust=priority_adjust, + ) diff --git a/scrapy/downloadermiddlewares/robotstxt.py b/scrapy/downloadermiddlewares/robotstxt.py index 7f18b2bf2..e66bf177e 100644 --- a/scrapy/downloadermiddlewares/robotstxt.py +++ b/scrapy/downloadermiddlewares/robotstxt.py @@ -61,13 +61,13 @@ class RobotsTxtMiddleware: if netloc not in self._parsers: self._parsers[netloc] = Deferred() - robotsurl = "%s://%s/robots.txt" % (url.scheme, url.netloc) + robotsurl = f"{url.scheme}://{url.netloc}/robots.txt" robotsreq = Request( robotsurl, priority=self.DOWNLOAD_PRIORITY, meta={'dont_obey_robotstxt': True} ) - dfd = self.crawler.engine.download(robotsreq, spider) + dfd = self.crawler.engine.download(robotsreq) dfd.addCallback(self._parse_robots, netloc, spider) dfd.addErrback(self._logerror, robotsreq, spider) dfd.addErrback(self._robots_error, netloc) @@ -94,7 +94,7 @@ class RobotsTxtMiddleware: def _parse_robots(self, response, netloc, spider): self.crawler.stats.inc_value('robotstxt/response_count') - self.crawler.stats.inc_value('robotstxt/response_status_count/{}'.format(response.status)) + self.crawler.stats.inc_value(f'robotstxt/response_status_count/{response.status}') rp = self._parserimpl.from_crawler(self.crawler, response.body) rp_dfd = self._parsers[netloc] self._parsers[netloc] = rp @@ -102,7 +102,7 @@ class RobotsTxtMiddleware: def _robots_error(self, failure, netloc): if failure.type is not IgnoreRequest: - key = 'robotstxt/exception_count/{}'.format(failure.type) + key = f'robotstxt/exception_count/{failure.type}' self.crawler.stats.inc_value(key) rp_dfd = self._parsers[netloc] self._parsers[netloc] = None diff --git a/scrapy/downloadermiddlewares/stats.py b/scrapy/downloadermiddlewares/stats.py index 46a2ad397..5479cd0e2 100644 --- a/scrapy/downloadermiddlewares/stats.py +++ b/scrapy/downloadermiddlewares/stats.py @@ -17,13 +17,13 @@ class DownloaderStats: def process_request(self, request, spider): self.stats.inc_value('downloader/request_count', spider=spider) - self.stats.inc_value('downloader/request_method_count/%s' % request.method, spider=spider) + self.stats.inc_value(f'downloader/request_method_count/{request.method}', spider=spider) reqlen = len(request_httprepr(request)) self.stats.inc_value('downloader/request_bytes', reqlen, spider=spider) def process_response(self, request, response, spider): self.stats.inc_value('downloader/response_count', spider=spider) - self.stats.inc_value('downloader/response_status_count/%s' % response.status, spider=spider) + self.stats.inc_value(f'downloader/response_status_count/{response.status}', spider=spider) reslen = len(response_httprepr(response)) self.stats.inc_value('downloader/response_bytes', reslen, spider=spider) return response @@ -31,4 +31,4 @@ class DownloaderStats: def process_exception(self, request, exception, spider): ex_class = global_object_name(exception.__class__) self.stats.inc_value('downloader/exception_count', spider=spider) - self.stats.inc_value('downloader/exception_type_count/%s' % ex_class, spider=spider) + self.stats.inc_value(f'downloader/exception_type_count/{ex_class}', spider=spider) diff --git a/scrapy/dupefilters.py b/scrapy/dupefilters.py index ac5478e7c..292c68099 100644 --- a/scrapy/dupefilters.py +++ b/scrapy/dupefilters.py @@ -1,35 +1,47 @@ -import os import logging +import os +from typing import Optional, Set, Type, TypeVar +from twisted.internet.defer import Deferred + +from scrapy.http.request import Request +from scrapy.settings import BaseSettings +from scrapy.spiders import Spider from scrapy.utils.job import job_dir from scrapy.utils.request import referer_str, request_fingerprint -class BaseDupeFilter: +BaseDupeFilterTV = TypeVar("BaseDupeFilterTV", bound="BaseDupeFilter") + +class BaseDupeFilter: @classmethod - def from_settings(cls, settings): + def from_settings(cls: Type[BaseDupeFilterTV], settings: BaseSettings) -> BaseDupeFilterTV: return cls() - def request_seen(self, request): + def request_seen(self, request: Request) -> bool: return False - def open(self): # can return deferred + def open(self) -> Optional[Deferred]: pass - def close(self, reason): # can return a deferred + def close(self, reason: str) -> Optional[Deferred]: pass - def log(self, request, spider): # log that a request has been filtered + def log(self, request: Request, spider: Spider) -> None: + """Log that a request has been filtered""" pass +RFPDupeFilterTV = TypeVar("RFPDupeFilterTV", bound="RFPDupeFilter") + + class RFPDupeFilter(BaseDupeFilter): """Request Fingerprint duplicates filter""" - def __init__(self, path=None, debug=False): + def __init__(self, path: Optional[str] = None, debug: bool = False) -> None: self.file = None - self.fingerprints = set() + self.fingerprints: Set[str] = set() self.logdupes = True self.debug = debug self.logger = logging.getLogger(__name__) @@ -39,26 +51,27 @@ class RFPDupeFilter(BaseDupeFilter): self.fingerprints.update(x.rstrip() for x in self.file) @classmethod - def from_settings(cls, settings): + def from_settings(cls: Type[RFPDupeFilterTV], settings: BaseSettings) -> RFPDupeFilterTV: debug = settings.getbool('DUPEFILTER_DEBUG') return cls(job_dir(settings), debug) - def request_seen(self, request): + def request_seen(self, request: Request) -> bool: fp = self.request_fingerprint(request) if fp in self.fingerprints: return True self.fingerprints.add(fp) if self.file: self.file.write(fp + '\n') + return False - def request_fingerprint(self, request): + def request_fingerprint(self, request: Request) -> str: return request_fingerprint(request) - def close(self, reason): + def close(self, reason: str) -> None: if self.file: self.file.close() - def log(self, request, spider): + def log(self, request: Request, spider: Spider) -> None: if self.debug: msg = "Filtered duplicate request: %(request)s (referer: %(referer)s)" args = {'request': request, 'referer': referer_str(request)} diff --git a/scrapy/exceptions.py b/scrapy/exceptions.py index 45f152321..0c410f035 100644 --- a/scrapy/exceptions.py +++ b/scrapy/exceptions.py @@ -37,7 +37,7 @@ class CloseSpider(Exception): """Raise this from callbacks to request the spider to be closed""" def __init__(self, reason='cancelled'): - super(CloseSpider, self).__init__() + super().__init__() self.reason = reason @@ -74,7 +74,7 @@ class UsageError(Exception): def __init__(self, *a, **kw): self.print_help = kw.pop('print_help', True) - super(UsageError, self).__init__(*a, **kw) + super().__init__(*a, **kw) class ScrapyDeprecationWarning(Warning): diff --git a/scrapy/exporters.py b/scrapy/exporters.py index de009082a..fb4b565cf 100644 --- a/scrapy/exporters.py +++ b/scrapy/exporters.py @@ -4,16 +4,18 @@ Item Exporters are used to export/serialize items into different formats. import csv import io -import pprint import marshal -import warnings import pickle +import pprint +import warnings from xml.sax.saxutils import XMLGenerator -from scrapy.utils.serialize import ScrapyJSONEncoder -from scrapy.utils.python import to_bytes, to_unicode, is_listlike -from scrapy.item import _BaseItem +from itemadapter import is_item, ItemAdapter + from scrapy.exceptions import ScrapyDeprecationWarning +from scrapy.item import _BaseItem +from scrapy.utils.python import is_listlike, to_bytes, to_unicode +from scrapy.utils.serialize import ScrapyJSONEncoder __all__ = ['BaseItemExporter', 'PprintItemExporter', 'PickleItemExporter', @@ -37,7 +39,7 @@ class BaseItemExporter: self.export_empty_fields = options.pop('export_empty_fields', False) self.indent = options.pop('indent', None) if not dont_fail and options: - raise TypeError("Unexpected options: %s" % ', '.join(options.keys())) + raise TypeError(f"Unexpected options: {', '.join(options.keys())}") def export_item(self, item): raise NotImplementedError @@ -56,11 +58,14 @@ class BaseItemExporter: """Return the fields to export as an iterable of tuples (name, serialized_value) """ + item = ItemAdapter(item) + if include_empty is None: include_empty = self.export_empty_fields + if self.fields_to_export is None: - if include_empty and not isinstance(item, dict): - field_iter = item.fields.keys() + if include_empty: + field_iter = item.field_names() else: field_iter = item.keys() else: @@ -71,8 +76,8 @@ class BaseItemExporter: for field_name in field_iter: if field_name in item: - field = {} if isinstance(item, dict) else item.fields[field_name] - value = self.serialize_field(field, field_name, item[field_name]) + field_meta = item.get_field_meta(field_name) + value = self.serialize_field(field_meta, field_name, item[field_name]) else: value = default_value @@ -190,7 +195,7 @@ class XmlItemExporter(BaseItemExporter): class CsvItemExporter(BaseItemExporter): - def __init__(self, file, include_headers_line=True, join_multivalued=',', **kwargs): + def __init__(self, file, include_headers_line=True, join_multivalued=',', errors=None, **kwargs): super().__init__(dont_fail=True, **kwargs) if not self.encoding: self.encoding = 'utf-8' @@ -200,7 +205,8 @@ class CsvItemExporter(BaseItemExporter): line_buffering=False, write_through=True, encoding=self.encoding, - newline='' # Windows needs this https://github.com/scrapy/scrapy/issues/3034 + newline='', # Windows needs this https://github.com/scrapy/scrapy/issues/3034 + errors=errors, ) self.csv_writer = csv.writer(self.stream, **self._kwargs) self._headers_not_written = True @@ -238,12 +244,8 @@ class CsvItemExporter(BaseItemExporter): def _write_headers_and_set_fields_to_export(self, item): if self.include_headers_line: if not self.fields_to_export: - if isinstance(item, dict): - # for dicts try using fields of the first item - self.fields_to_export = list(item.keys()) - else: - # use fields declared in Item - self.fields_to_export = list(item.fields.keys()) + # use declared field names, or keys if the item is a dict + self.fields_to_export = ItemAdapter(item).field_names() row = list(self._build_row(self.fields_to_export)) self.csv_writer.writerow(row) @@ -297,9 +299,10 @@ class PythonItemExporter(BaseItemExporter): .. _msgpack: https://pypi.org/project/msgpack/ """ + def _configure(self, options, dont_fail=False): self.binary = options.pop('binary', True) - super(PythonItemExporter, self)._configure(options, dont_fail) + super()._configure(options, dont_fail) if self.binary: warnings.warn( "PythonItemExporter will drop support for binary export in the future", @@ -314,22 +317,22 @@ class PythonItemExporter(BaseItemExporter): def _serialize_value(self, value): if isinstance(value, _BaseItem): return self.export_item(value) - if isinstance(value, dict): - return dict(self._serialize_dict(value)) - if is_listlike(value): + elif is_item(value): + return dict(self._serialize_item(value)) + elif is_listlike(value): return [self._serialize_value(v) for v in value] encode_func = to_bytes if self.binary else to_unicode if isinstance(value, (str, bytes)): return encode_func(value, encoding=self.encoding) return value - def _serialize_dict(self, value): - for key, val in value.items(): + def _serialize_item(self, item): + for key, value in ItemAdapter(item).items(): key = to_bytes(key) if self.binary else key - yield key, self._serialize_value(val) + yield key, self._serialize_value(value) def export_item(self, item): result = dict(self._get_serialized_fields(item)) if self.binary: - result = dict(self._serialize_dict(result)) + result = dict(self._serialize_item(result)) return result diff --git a/scrapy/extensions/corestats.py b/scrapy/extensions/corestats.py index 389cb65bc..675f8276f 100644 --- a/scrapy/extensions/corestats.py +++ b/scrapy/extensions/corestats.py @@ -43,4 +43,4 @@ class CoreStats: def item_dropped(self, item, spider, exception): reason = exception.__class__.__name__ self.stats.inc_value('item_dropped_count', spider=spider) - self.stats.inc_value('item_dropped_reasons_count/%s' % reason, spider=spider) + self.stats.inc_value(f'item_dropped_reasons_count/{reason}', spider=spider) diff --git a/scrapy/extensions/debug.py b/scrapy/extensions/debug.py index 586399784..fd2a02d8d 100644 --- a/scrapy/extensions/debug.py +++ b/scrapy/extensions/debug.py @@ -48,7 +48,7 @@ class StackTraceDump: for id_, frame in sys._current_frames().items(): name = id2name.get(id_, '') dump = ''.join(traceback.format_stack(frame)) - dumps += "# Thread: {0}({1})\n{2}\n".format(name, id_, dump) + dumps += f"# Thread: {name}({id_})\n{dump}\n" return dumps diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index 998d2a5d1..bd4808e2b 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -6,10 +6,12 @@ See documentation in docs/topics/feed-exports.rst import logging import os +import re import sys import warnings from datetime import datetime from tempfile import NamedTemporaryFile +from typing import Any, Optional, Tuple from urllib.parse import unquote, urlparse from twisted.internet import defer, threads @@ -18,22 +20,73 @@ from zope.interface import implementer, Interface from scrapy import signals from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning -from scrapy.utils.boto import is_botocore +from scrapy.utils.boto import is_botocore_available from scrapy.utils.conf import feed_complete_default_values_from_settings from scrapy.utils.ftp import ftp_store_file from scrapy.utils.log import failure_to_exc_info from scrapy.utils.misc import create_instance, load_object -from scrapy.utils.python import without_none_values +from scrapy.utils.python import get_func_args, without_none_values logger = logging.getLogger(__name__) +def build_storage(builder, uri, *args, feed_options=None, preargs=(), **kwargs): + argument_names = get_func_args(builder) + if 'feed_options' in argument_names: + kwargs['feed_options'] = feed_options + else: + warnings.warn( + "{} does not support the 'feed_options' keyword argument. Add a " + "'feed_options' parameter to its signature to remove this " + "warning. This parameter will become mandatory in a future " + "version of Scrapy." + .format(builder.__qualname__), + category=ScrapyDeprecationWarning + ) + return builder(*preargs, uri, *args, **kwargs) + + +class ItemFilter: + """ + This will be used by FeedExporter to decide if an item should be allowed + to be exported to a particular feed. + + :param feed_options: feed specific options passed from FeedExporter + :type feed_options: dict + """ + feed_options: Optional[dict] + item_classes: Tuple + + def __init__(self, feed_options: Optional[dict]) -> None: + self.feed_options = feed_options + if feed_options is not None: + self.item_classes = tuple( + load_object(item_class) for item_class in feed_options.get("item_classes") or () + ) + else: + self.item_classes = tuple() + + def accepts(self, item: Any) -> bool: + """ + Return ``True`` if `item` should be exported or ``False`` otherwise. + + :param item: scraped item which user wants to check if is acceptable + :type item: :ref:`Scrapy items ` + :return: `True` if accepted, `False` otherwise + :rtype: bool + """ + if self.item_classes: + return isinstance(item, self.item_classes) + return True # accept all items by default + + class IFeedStorage(Interface): """Interface that all Feed Storages must implement""" - def __init__(uri): - """Initialize the storage with the parameters given in the URI""" + def __init__(uri, *, feed_options=None): + """Initialize the storage with the parameters given in the URI and the + feed-specific options (see :setting:`FEEDS`)""" def open(spider): """Open the storage for the given spider. It must return a file-like @@ -63,10 +116,15 @@ class BlockingFeedStorage: @implementer(IFeedStorage) class StdoutFeedStorage: - def __init__(self, uri, _stdout=None): + def __init__(self, uri, _stdout=None, *, feed_options=None): if not _stdout: _stdout = sys.stdout.buffer self._stdout = _stdout + if feed_options and feed_options.get('overwrite', False) is True: + logger.warning('Standard output (stdout) storage does not support ' + 'overwriting. To suppress this warning, remove the ' + 'overwrite option from your FEEDS setting, or set ' + 'it to False.') def open(self, spider): return self._stdout @@ -78,14 +136,16 @@ class StdoutFeedStorage: @implementer(IFeedStorage) class FileFeedStorage: - def __init__(self, uri): + def __init__(self, uri, *, feed_options=None): self.path = file_uri_to_path(uri) + feed_options = feed_options or {} + self.write_mode = 'wb' if feed_options.get('overwrite', False) else 'ab' def open(self, spider): dirname = os.path.dirname(self.path) if dirname and not os.path.exists(dirname): os.makedirs(dirname) - return open(self.path, 'ab') + return open(self.path, self.write_mode) def store(self, file): file.close() @@ -93,101 +153,117 @@ class FileFeedStorage: class S3FeedStorage(BlockingFeedStorage): - def __init__(self, uri, access_key=None, secret_key=None, acl=None): - # BEGIN Backward compatibility for initialising without keys (and - # without using from_crawler) - no_defaults = access_key is None and secret_key is None - if no_defaults: - from scrapy.utils.project import get_project_settings - settings = get_project_settings() - if 'AWS_ACCESS_KEY_ID' in settings or 'AWS_SECRET_ACCESS_KEY' in settings: - warnings.warn( - "Initialising `scrapy.extensions.feedexport.S3FeedStorage` " - "without AWS keys is deprecated. Please supply credentials or " - "use the `from_crawler()` constructor.", - category=ScrapyDeprecationWarning, - stacklevel=2 - ) - access_key = settings['AWS_ACCESS_KEY_ID'] - secret_key = settings['AWS_SECRET_ACCESS_KEY'] - # END Backward compatibility + def __init__(self, uri, access_key=None, secret_key=None, acl=None, endpoint_url=None, *, + feed_options=None): + if not is_botocore_available(): + raise NotConfigured('missing botocore library') u = urlparse(uri) self.bucketname = u.hostname self.access_key = u.username or access_key self.secret_key = u.password or secret_key - self.is_botocore = is_botocore() self.keyname = u.path[1:] # remove first "/" self.acl = acl - if self.is_botocore: - import botocore.session - session = botocore.session.get_session() - self.s3_client = session.create_client( - 's3', aws_access_key_id=self.access_key, - aws_secret_access_key=self.secret_key) - else: - import boto - self.connect_s3 = boto.connect_s3 + self.endpoint_url = endpoint_url + import botocore.session + session = botocore.session.get_session() + self.s3_client = session.create_client( + 's3', aws_access_key_id=self.access_key, + aws_secret_access_key=self.secret_key, + endpoint_url=self.endpoint_url) + if feed_options and feed_options.get('overwrite', True) is False: + logger.warning('S3 does not support appending to files. To ' + 'suppress this warning, remove the overwrite ' + 'option from your FEEDS setting or set it to True.') @classmethod - def from_crawler(cls, crawler, uri): - return cls( - uri=uri, + def from_crawler(cls, crawler, uri, *, feed_options=None): + return build_storage( + cls, + uri, access_key=crawler.settings['AWS_ACCESS_KEY_ID'], secret_key=crawler.settings['AWS_SECRET_ACCESS_KEY'], - acl=crawler.settings['FEED_STORAGE_S3_ACL'] or None + acl=crawler.settings['FEED_STORAGE_S3_ACL'] or None, + endpoint_url=crawler.settings['AWS_ENDPOINT_URL'] or None, + feed_options=feed_options, ) def _store_in_thread(self, file): file.seek(0) - if self.is_botocore: - kwargs = {'ACL': self.acl} if self.acl else {} - self.s3_client.put_object( - Bucket=self.bucketname, Key=self.keyname, Body=file, - **kwargs) - else: - conn = self.connect_s3(self.access_key, self.secret_key) - bucket = conn.get_bucket(self.bucketname, validate=False) - key = bucket.new_key(self.keyname) - kwargs = {'policy': self.acl} if self.acl else {} - key.set_contents_from_file(file, **kwargs) - key.close() + kwargs = {'ACL': self.acl} if self.acl else {} + self.s3_client.put_object( + Bucket=self.bucketname, Key=self.keyname, Body=file, + **kwargs) + file.close() -class FTPFeedStorage(BlockingFeedStorage): +class GCSFeedStorage(BlockingFeedStorage): - def __init__(self, uri, use_active_mode=False): + def __init__(self, uri, project_id, acl): + self.project_id = project_id + self.acl = acl u = urlparse(uri) - self.host = u.hostname - self.port = int(u.port or '21') - self.username = u.username - self.password = unquote(u.password) - self.path = u.path - self.use_active_mode = use_active_mode + self.bucket_name = u.hostname + self.blob_name = u.path[1:] # remove first "/" @classmethod def from_crawler(cls, crawler, uri): return cls( - uri=uri, - use_active_mode=crawler.settings.getbool('FEED_STORAGE_FTP_ACTIVE') + uri, + crawler.settings['GCS_PROJECT_ID'], + crawler.settings['FEED_STORAGE_GCS_ACL'] or None + ) + + def _store_in_thread(self, file): + file.seek(0) + from google.cloud.storage import Client + client = Client(project=self.project_id) + bucket = client.get_bucket(self.bucket_name) + blob = bucket.blob(self.blob_name) + blob.upload_from_file(file, predefined_acl=self.acl) + + +class FTPFeedStorage(BlockingFeedStorage): + + def __init__(self, uri, use_active_mode=False, *, feed_options=None): + u = urlparse(uri) + self.host = u.hostname + self.port = int(u.port or '21') + self.username = u.username + self.password = unquote(u.password or '') + self.path = u.path + self.use_active_mode = use_active_mode + self.overwrite = not feed_options or feed_options.get('overwrite', True) + + @classmethod + def from_crawler(cls, crawler, uri, *, feed_options=None): + return build_storage( + cls, + uri, + crawler.settings.getbool('FEED_STORAGE_FTP_ACTIVE'), + feed_options=feed_options, ) def _store_in_thread(self, file): ftp_store_file( path=self.path, file=file, host=self.host, port=self.port, username=self.username, - password=self.password, use_active_mode=self.use_active_mode + password=self.password, use_active_mode=self.use_active_mode, + overwrite=self.overwrite, ) class _FeedSlot: - def __init__(self, file, exporter, storage, uri, format, store_empty): + def __init__(self, file, exporter, storage, uri, format, store_empty, batch_id, uri_template, filter): self.file = file self.exporter = exporter self.storage = storage # feed params - self.uri = uri + self.batch_id = batch_id self.format = format self.store_empty = store_empty + self.uri_template = uri_template + self.uri = uri + self.filter = filter # flags self.itemcount = 0 self._exporting = False @@ -218,6 +294,7 @@ class FeedExporter: self.settings = crawler.settings self.feeds = {} self.slots = [] + self.filters = {} if not self.settings['FEEDS'] and not self.settings['FEED_URI']: raise NotConfigured @@ -230,66 +307,142 @@ class FeedExporter: category=ScrapyDeprecationWarning, stacklevel=2, ) uri = str(self.settings['FEED_URI']) # handle pathlib.Path objects - feed = {'format': self.settings.get('FEED_FORMAT', 'jsonlines')} - self.feeds[uri] = feed_complete_default_values_from_settings(feed, self.settings) + feed_options = {'format': self.settings.get('FEED_FORMAT', 'jsonlines')} + self.feeds[uri] = feed_complete_default_values_from_settings(feed_options, self.settings) + self.filters[uri] = self._load_filter(feed_options) # End: Backward compatibility for FEED_URI and FEED_FORMAT settings # 'FEEDS' setting takes precedence over 'FEED_URI' - for uri, feed in self.settings.getdict('FEEDS').items(): + for uri, feed_options in self.settings.getdict('FEEDS').items(): uri = str(uri) # handle pathlib.Path objects - self.feeds[uri] = feed_complete_default_values_from_settings(feed, self.settings) + self.feeds[uri] = feed_complete_default_values_from_settings(feed_options, self.settings) + self.filters[uri] = self._load_filter(feed_options) self.storages = self._load_components('FEED_STORAGES') self.exporters = self._load_components('FEED_EXPORTERS') - for uri, feed in self.feeds.items(): - if not self._storage_supported(uri): + for uri, feed_options in self.feeds.items(): + if not self._storage_supported(uri, feed_options): raise NotConfigured - if not self._exporter_supported(feed['format']): + if not self._settings_are_valid(): + raise NotConfigured + if not self._exporter_supported(feed_options['format']): raise NotConfigured def open_spider(self, spider): - for uri, feed in self.feeds.items(): - uri = uri % self._get_uri_params(spider, feed['uri_params']) - storage = self._get_storage(uri) - file = storage.open(spider) - exporter = self._get_exporter( - file=file, - format=feed['format'], - fields_to_export=feed['fields'], - encoding=feed['encoding'], - indent=feed['indent'], - ) - slot = _FeedSlot(file, exporter, storage, uri, feed['format'], feed['store_empty']) - self.slots.append(slot) - if slot.store_empty: - slot.start_exporting() + for uri, feed_options in self.feeds.items(): + uri_params = self._get_uri_params(spider, feed_options['uri_params']) + self.slots.append(self._start_new_batch( + batch_id=1, + uri=uri % uri_params, + feed_options=feed_options, + spider=spider, + uri_template=uri, + )) def close_spider(self, spider): deferred_list = [] for slot in self.slots: - if not slot.itemcount and not slot.store_empty: - # We need to call slot.storage.store nonetheless to get the file - # properly closed. - return defer.maybeDeferred(slot.storage.store, slot.file) - slot.finish_exporting() - logfmt = "%s %%(format)s feed (%%(itemcount)d items) in: %%(uri)s" - log_args = {'format': slot.format, - 'itemcount': slot.itemcount, - 'uri': slot.uri} - d = defer.maybeDeferred(slot.storage.store, slot.file) - d.addCallback(lambda _: logger.info(logfmt % "Stored", log_args, - extra={'spider': spider})) - d.addErrback(lambda f: logger.error(logfmt % "Error storing", log_args, - exc_info=failure_to_exc_info(f), - extra={'spider': spider})) + d = self._close_slot(slot, spider) deferred_list.append(d) return defer.DeferredList(deferred_list) if deferred_list else None + def _close_slot(self, slot, spider): + if not slot.itemcount and not slot.store_empty: + # We need to call slot.storage.store nonetheless to get the file + # properly closed. + return defer.maybeDeferred(slot.storage.store, slot.file) + slot.finish_exporting() + logfmt = "%s %%(format)s feed (%%(itemcount)d items) in: %%(uri)s" + log_args = {'format': slot.format, + 'itemcount': slot.itemcount, + 'uri': slot.uri} + d = defer.maybeDeferred(slot.storage.store, slot.file) + + # Use `largs=log_args` to copy log_args into function's scope + # instead of using `log_args` from the outer scope + d.addCallback( + self._handle_store_success, log_args, logfmt, spider, type(slot.storage).__name__ + ) + d.addErrback( + self._handle_store_error, log_args, logfmt, spider, type(slot.storage).__name__ + ) + return d + + def _handle_store_error(self, f, largs, logfmt, spider, slot_type): + logger.error( + logfmt % "Error storing", largs, + exc_info=failure_to_exc_info(f), extra={'spider': spider} + ) + self.crawler.stats.inc_value(f"feedexport/failed_count/{slot_type}") + + def _handle_store_success(self, f, largs, logfmt, spider, slot_type): + logger.info( + logfmt % "Stored", largs, extra={'spider': spider} + ) + self.crawler.stats.inc_value(f"feedexport/success_count/{slot_type}") + + def _start_new_batch(self, batch_id, uri, feed_options, spider, uri_template): + """ + Redirect the output data stream to a new file. + Execute multiple times if FEED_EXPORT_BATCH_ITEM_COUNT setting or FEEDS.batch_item_count is specified + :param batch_id: sequence number of current batch + :param uri: uri of the new batch to start + :param feed_options: dict with parameters of feed + :param spider: user spider + :param uri_template: template of uri which contains %(batch_time)s or %(batch_id)d to create new uri + """ + storage = self._get_storage(uri, feed_options) + file = storage.open(spider) + exporter = self._get_exporter( + file=file, + format=feed_options['format'], + fields_to_export=feed_options['fields'], + encoding=feed_options['encoding'], + indent=feed_options['indent'], + **feed_options['item_export_kwargs'], + ) + slot = _FeedSlot( + file=file, + exporter=exporter, + storage=storage, + uri=uri, + format=feed_options['format'], + store_empty=feed_options['store_empty'], + batch_id=batch_id, + uri_template=uri_template, + filter=self.filters[uri_template] + ) + if slot.store_empty: + slot.start_exporting() + return slot + def item_scraped(self, item, spider): + slots = [] for slot in self.slots: + if not slot.filter.accepts(item): + slots.append(slot) # if slot doesn't accept item, continue with next slot + continue + slot.start_exporting() slot.exporter.export_item(item) slot.itemcount += 1 + # create new slot for each slot with itemcount == FEED_EXPORT_BATCH_ITEM_COUNT and close the old one + if ( + self.feeds[slot.uri_template]['batch_item_count'] + and slot.itemcount >= self.feeds[slot.uri_template]['batch_item_count'] + ): + uri_params = self._get_uri_params(spider, self.feeds[slot.uri_template]['uri_params'], slot) + self._close_slot(slot, spider) + slots.append(self._start_new_batch( + batch_id=slot.batch_id + 1, + uri=slot.uri_template % uri_params, + feed_options=self.feeds[slot.uri_template], + spider=spider, + uri_template=slot.uri_template, + )) + else: + slots.append(slot) + self.slots = slots def _load_components(self, setting_prefix): conf = without_none_values(self.settings.getwithbase(setting_prefix)) @@ -306,11 +459,27 @@ class FeedExporter: return True logger.error("Unknown feed format: %(format)s", {'format': format}) - def _storage_supported(self, uri): + def _settings_are_valid(self): + """ + If FEED_EXPORT_BATCH_ITEM_COUNT setting or FEEDS.batch_item_count is specified uri has to contain + %(batch_time)s or %(batch_id)d to distinguish different files of partial output + """ + for uri_template, values in self.feeds.items(): + if values['batch_item_count'] and not re.search(r'%\(batch_time\)s|%\(batch_id\)', uri_template): + logger.error( + '%(batch_time)s or %(batch_id)d must be in the feed URI ({}) if FEED_EXPORT_BATCH_ITEM_COUNT ' + 'setting or FEEDS.batch_item_count is specified and greater than 0. For more info see: ' + 'https://docs.scrapy.org/en/latest/topics/feed-exports.html#feed-export-batch-item-count' + ''.format(uri_template) + ) + return False + return True + + def _storage_supported(self, uri, feed_options): scheme = urlparse(uri).scheme if scheme in self.storages: try: - self._get_storage(uri) + self._get_storage(uri, feed_options) return True except NotConfigured as e: logger.error("Disabled feed storage scheme: %(scheme)s. " @@ -328,15 +497,44 @@ class FeedExporter: def _get_exporter(self, file, format, *args, **kwargs): return self._get_instance(self.exporters[format], file, *args, **kwargs) - def _get_storage(self, uri): - return self._get_instance(self.storages[urlparse(uri).scheme], uri) + def _get_storage(self, uri, feed_options): + """Fork of create_instance specific to feed storage classes - def _get_uri_params(self, spider, uri_params): + It supports not passing the *feed_options* parameters to classes that + do not support it, and issuing a deprecation warning instead. + """ + feedcls = self.storages[urlparse(uri).scheme] + crawler = getattr(self, 'crawler', None) + + def build_instance(builder, *preargs): + return build_storage(builder, uri, feed_options=feed_options, preargs=preargs) + + if crawler and hasattr(feedcls, 'from_crawler'): + instance = build_instance(feedcls.from_crawler, crawler) + method_name = 'from_crawler' + elif hasattr(feedcls, 'from_settings'): + instance = build_instance(feedcls.from_settings, self.settings) + method_name = 'from_settings' + else: + instance = build_instance(feedcls) + method_name = '__new__' + if instance is None: + raise TypeError("%s.%s returned None" % (feedcls.__qualname__, method_name)) + return instance + + def _get_uri_params(self, spider, uri_params, slot=None): params = {} for k in dir(spider): params[k] = getattr(spider, k) - ts = datetime.utcnow().replace(microsecond=0).isoformat().replace(':', '-') - params['time'] = ts + utc_now = datetime.utcnow() + params['time'] = utc_now.replace(microsecond=0).isoformat().replace(':', '-') + params['batch_time'] = utc_now.isoformat().replace(':', '-') + params['batch_id'] = slot.batch_id + 1 if slot is not None else 1 uripar_function = load_object(uri_params) if uri_params else lambda x, y: None uripar_function(params, spider) return params + + def _load_filter(self, feed_options): + # load the item filter if declared else load the default filter class + item_filter_class = load_object(feed_options.get("item_filter", ItemFilter)) + return item_filter_class(feed_options) diff --git a/scrapy/extensions/httpcache.py b/scrapy/extensions/httpcache.py index 6294a9b52..e0c04b2de 100644 --- a/scrapy/extensions/httpcache.py +++ b/scrapy/extensions/httpcache.py @@ -223,7 +223,7 @@ class DbmCacheStorage: self.db = None def open_spider(self, spider): - dbpath = os.path.join(self.cachedir, '%s.db' % spider.name) + dbpath = os.path.join(self.cachedir, f'{spider.name}.db') self.db = self.dbmodule.open(dbpath, 'c') logger.debug("Using DBM cache storage in %(cachepath)s" % {'cachepath': dbpath}, extra={'spider': spider}) @@ -251,13 +251,13 @@ class DbmCacheStorage: 'headers': dict(response.headers), 'body': response.body, } - self.db['%s_data' % key] = pickle.dumps(data, protocol=4) - self.db['%s_time' % key] = str(time()) + self.db[f'{key}_data'] = pickle.dumps(data, protocol=4) + self.db[f'{key}_time'] = str(time()) def _read_data(self, spider, request): key = self._request_key(request) db = self.db - tkey = '%s_time' % key + tkey = f'{key}_time' if tkey not in db: return # not found @@ -265,7 +265,7 @@ class DbmCacheStorage: if 0 < self.expiration_secs < time() - float(ts): return # expired - return pickle.loads(db['%s_data' % key]) + return pickle.loads(db[f'{key}_data']) def _request_key(self, request): return request_fingerprint(request) diff --git a/scrapy/extensions/memdebug.py b/scrapy/extensions/memdebug.py index dc8cdbb1d..cee44ea62 100644 --- a/scrapy/extensions/memdebug.py +++ b/scrapy/extensions/memdebug.py @@ -30,4 +30,4 @@ class MemoryDebugger: for cls, wdict in live_refs.items(): if not wdict: continue - self.stats.set_value('memdebug/live_refs/%s' % cls.__name__, len(wdict), spider=spider) + self.stats.set_value(f'memdebug/live_refs/{cls.__name__}', len(wdict), spider=spider) diff --git a/scrapy/extensions/memusage.py b/scrapy/extensions/memusage.py index a0540bf8f..9de119a10 100644 --- a/scrapy/extensions/memusage.py +++ b/scrapy/extensions/memusage.py @@ -81,15 +81,15 @@ class MemoryUsage: logger.error("Memory usage exceeded %(memusage)dM. Shutting down Scrapy...", {'memusage': mem}, extra={'crawler': self.crawler}) if self.notify_mails: - subj = "%s terminated: memory usage exceeded %dM at %s" % \ - (self.crawler.settings['BOT_NAME'], mem, socket.gethostname()) + subj = ( + f"{self.crawler.settings['BOT_NAME']} terminated: " + f"memory usage exceeded {mem}M at {socket.gethostname()}" + ) self._send_report(self.notify_mails, subj) self.crawler.stats.set_value('memusage/limit_notified', 1) - open_spiders = self.crawler.engine.open_spiders - if open_spiders: - for spider in open_spiders: - self.crawler.engine.close_spider(spider, 'memusage_exceeded') + if self.crawler.engine.spider is not None: + self.crawler.engine.close_spider(self.crawler.engine.spider, 'memusage_exceeded') else: self.crawler.stop() @@ -102,8 +102,10 @@ class MemoryUsage: logger.warning("Memory usage reached %(memusage)dM", {'memusage': mem}, extra={'crawler': self.crawler}) if self.notify_mails: - subj = "%s warning: memory usage reached %dM at %s" % \ - (self.crawler.settings['BOT_NAME'], mem, socket.gethostname()) + subj = ( + f"{self.crawler.settings['BOT_NAME']} warning: " + f"memory usage reached {mem}M at {socket.gethostname()}" + ) self._send_report(self.notify_mails, subj) self.crawler.stats.set_value('memusage/warning_notified', 1) self.warned = True @@ -111,9 +113,9 @@ class MemoryUsage: def _send_report(self, rcpts, subject): """send notification mail with some additional useful info""" stats = self.crawler.stats - s = "Memory usage at engine startup : %dM\r\n" % (stats.get_value('memusage/startup')/1024/1024) - s += "Maximum memory usage : %dM\r\n" % (stats.get_value('memusage/max')/1024/1024) - s += "Current memory usage : %dM\r\n" % (self.get_virtual_size()/1024/1024) + s = f"Memory usage at engine startup : {stats.get_value('memusage/startup')/1024/1024}M\r\n" + s += f"Maximum memory usage : {stats.get_value('memusage/max')/1024/1024}M\r\n" + s += f"Current memory usage : {self.get_virtual_size()/1024/1024}M\r\n" s += "ENGINE STATUS ------------------------------------------------------- \r\n" s += "\r\n" diff --git a/scrapy/extensions/statsmailer.py b/scrapy/extensions/statsmailer.py index 320f13b29..bcdbaff24 100644 --- a/scrapy/extensions/statsmailer.py +++ b/scrapy/extensions/statsmailer.py @@ -24,11 +24,11 @@ class StatsMailer: o = cls(crawler.stats, recipients, mail) crawler.signals.connect(o.spider_closed, signal=signals.spider_closed) return o - + def spider_closed(self, spider): spider_stats = self.stats.get_stats(spider) body = "Global stats\n\n" - body += "\n".join("%-50s : %s" % i for i in self.stats.get_stats().items()) - body += "\n\n%s stats\n\n" % spider.name - body += "\n".join("%-50s : %s" % i for i in spider_stats.items()) - return self.mail.send(self.recipients, "Scrapy stats for: %s" % spider.name, body) + body += "\n".join(f"{k:<50} : {v}" for k, v in self.stats.get_stats().items()) + body += f"\n\n{spider.name} stats\n\n" + body += "\n".join(f"{k:<50} : {v}" for k, v in spider_stats.items()) + return self.mail.send(self.recipients, f"Scrapy stats for: {spider.name}", body) diff --git a/scrapy/http/common.py b/scrapy/http/common.py index ba6ab277c..98699d7fd 100644 --- a/scrapy/http/common.py +++ b/scrapy/http/common.py @@ -1,6 +1,6 @@ def obsolete_setter(setter, attrname): def newsetter(self, value): c = self.__class__.__name__ - msg = "%s.%s is not modifiable, use %s.replace() instead" % (c, attrname, c) + msg = f"{c}.{attrname} is not modifiable, use {c}.replace() instead" raise AttributeError(msg) return newsetter diff --git a/scrapy/http/cookies.py b/scrapy/http/cookies.py index 3e810992c..bf4ae7b45 100644 --- a/scrapy/http/cookies.py +++ b/scrapy/http/cookies.py @@ -1,10 +1,16 @@ +import re import time -from http.cookiejar import CookieJar as _CookieJar, DefaultCookiePolicy, IPV4_RE +from http.cookiejar import CookieJar as _CookieJar, DefaultCookiePolicy from scrapy.utils.httpobj import urlparse_cached from scrapy.utils.python import to_unicode +# Defined in the http.cookiejar module, but undocumented: +# https://github.com/python/cpython/blob/v3.9.0/Lib/http/cookiejar.py#L527 +IPV4_RE = re.compile(r"\.\d+$", re.ASCII) + + class CookieJar: def __init__(self, policy=None, check_expired_frequency=10000): self.policy = policy or DefaultCookiePolicy() @@ -186,9 +192,6 @@ class WrappedResponse: def info(self): return self - # python3 cookiejars calls get_all def get_all(self, name, default=None): return [to_unicode(v, errors='replace') for v in self.response.headers.getlist(name)] - # python2 cookiejars calls getheaders - getheaders = get_all diff --git a/scrapy/http/headers.py b/scrapy/http/headers.py index dcaaeddfa..1a2b99b0a 100644 --- a/scrapy/http/headers.py +++ b/scrapy/http/headers.py @@ -8,7 +8,7 @@ class Headers(CaselessDict): def __init__(self, seq=None, encoding='utf-8'): self.encoding = encoding - super(Headers, self).__init__(seq) + super().__init__(seq) def normkey(self, key): """Normalize key to bytes""" @@ -33,23 +33,23 @@ class Headers(CaselessDict): elif isinstance(x, int): return str(x).encode(self.encoding) else: - raise TypeError('Unsupported value type: {}'.format(type(x))) + raise TypeError(f'Unsupported value type: {type(x)}') def __getitem__(self, key): try: - return super(Headers, self).__getitem__(key)[-1] + return super().__getitem__(key)[-1] except IndexError: return None def get(self, key, def_val=None): try: - return super(Headers, self).get(key, def_val)[-1] + return super().get(key, def_val)[-1] except IndexError: return None def getlist(self, key, def_val=None): try: - return super(Headers, self).__getitem__(key) + return super().__getitem__(key) except KeyError: if def_val is not None: return self.normvalue(def_val) diff --git a/scrapy/http/request/__init__.py b/scrapy/http/request/__init__.py index a98ba9960..7672dec00 100644 --- a/scrapy/http/request/__init__.py +++ b/scrapy/http/request/__init__.py @@ -4,34 +4,69 @@ requests in Scrapy. See documentation in docs/topics/request-response.rst """ +import inspect +from typing import Callable, List, Optional, Tuple, Type, TypeVar, Union + from w3lib.url import safe_url_string +import scrapy +from scrapy.http.common import obsolete_setter from scrapy.http.headers import Headers +from scrapy.utils.curl import curl_to_request_kwargs from scrapy.utils.python import to_bytes from scrapy.utils.trackref import object_ref from scrapy.utils.url import escape_ajax -from scrapy.http.common import obsolete_setter -from scrapy.utils.curl import curl_to_request_kwargs + + +RequestTypeVar = TypeVar("RequestTypeVar", bound="Request") class Request(object_ref): + """Represents an HTTP request, which is usually generated in a Spider and + executed by the Downloader, thus generating a :class:`Response`. + """ - def __init__(self, url, callback=None, method='GET', headers=None, body=None, - cookies=None, meta=None, encoding='utf-8', priority=0, - dont_filter=False, errback=None, flags=None, cb_kwargs=None): + attributes: Tuple[str, ...] = ( + "url", "callback", "method", "headers", "body", + "cookies", "meta", "encoding", "priority", + "dont_filter", "errback", "flags", "cb_kwargs", + ) + """A tuple of :class:`str` objects containing the name of all public + attributes of the class that are also keyword parameters of the + ``__init__`` method. + Currently used by :meth:`Request.replace`, :meth:`Request.to_dict` and + :func:`~scrapy.utils.request.request_from_dict`. + """ + + def __init__( + self, + url: str, + callback: Optional[Callable] = None, + method: str = "GET", + headers: Optional[dict] = None, + body: Optional[Union[bytes, str]] = None, + cookies: Optional[Union[dict, List[dict]]] = None, + meta: Optional[dict] = None, + encoding: str = "utf-8", + priority: int = 0, + dont_filter: bool = False, + errback: Optional[Callable] = None, + flags: Optional[List[str]] = None, + cb_kwargs: Optional[dict] = None, + ) -> None: self._encoding = encoding # this one has to be set first self.method = str(method).upper() self._set_url(url) self._set_body(body) if not isinstance(priority, int): - raise TypeError("Request priority not an integer: %r" % priority) + raise TypeError(f"Request priority not an integer: {priority!r}") self.priority = priority if callback is not None and not callable(callback): - raise TypeError('callback must be a callable, got %s' % type(callback).__name__) + raise TypeError(f'callback must be a callable, got {type(callback).__name__}') if errback is not None and not callable(errback): - raise TypeError('errback must be a callable, got %s' % type(errback).__name__) + raise TypeError(f'errback must be a callable, got {type(errback).__name__}') self.callback = callback self.errback = errback @@ -44,68 +79,67 @@ class Request(object_ref): self.flags = [] if flags is None else list(flags) @property - def cb_kwargs(self): + def cb_kwargs(self) -> dict: if self._cb_kwargs is None: self._cb_kwargs = {} return self._cb_kwargs @property - def meta(self): + def meta(self) -> dict: if self._meta is None: self._meta = {} return self._meta - def _get_url(self): + def _get_url(self) -> str: return self._url - def _set_url(self, url): + def _set_url(self, url: str) -> None: if not isinstance(url, str): - raise TypeError('Request url must be str or unicode, got %s:' % type(url).__name__) + raise TypeError(f"Request url must be str, got {type(url).__name__}") s = safe_url_string(url, self.encoding) self._url = escape_ajax(s) - if ('://' not in self._url) and (not self._url.startswith('data:')): - raise ValueError('Missing scheme in request url: %s' % self._url) + if ( + '://' not in self._url + and not self._url.startswith('about:') + and not self._url.startswith('data:') + ): + raise ValueError(f'Missing scheme in request url: {self._url}') url = property(_get_url, obsolete_setter(_set_url, 'url')) - def _get_body(self): + def _get_body(self) -> bytes: return self._body - def _set_body(self, body): - if body is None: - self._body = b'' - else: - self._body = to_bytes(body, self.encoding) + def _set_body(self, body: Optional[Union[str, bytes]]) -> None: + self._body = b"" if body is None else to_bytes(body, self.encoding) body = property(_get_body, obsolete_setter(_set_body, 'body')) @property - def encoding(self): + def encoding(self) -> str: return self._encoding - def __str__(self): - return "<%s %s>" % (self.method, self.url) + def __str__(self) -> str: + return f"<{self.method} {self.url}>" __repr__ = __str__ - def copy(self): - """Return a copy of this Request""" + def copy(self) -> "Request": return self.replace() - def replace(self, *args, **kwargs): - """Create a new Request with the same attributes except for those - given new values. - """ - for x in ['url', 'method', 'headers', 'body', 'cookies', 'meta', 'flags', - 'encoding', 'priority', 'dont_filter', 'callback', 'errback', 'cb_kwargs']: + def replace(self, *args, **kwargs) -> "Request": + """Create a new Request with the same attributes except for those given new values""" + for x in self.attributes: kwargs.setdefault(x, getattr(self, x)) cls = kwargs.pop('cls', self.__class__) return cls(*args, **kwargs) @classmethod - def from_curl(cls, curl_command, ignore_unknown_options=True, **kwargs): + def from_curl( + cls: Type[RequestTypeVar], curl_command: str, ignore_unknown_options: bool = True, **kwargs + ) -> RequestTypeVar: """Create a Request object from a string containing a `cURL `_ command. It populates the HTTP method, the URL, the headers, the cookies and the body. It accepts the same @@ -132,8 +166,43 @@ class Request(object_ref): To translate a cURL command into a Scrapy request, you may use `curl2scrapy `_. - - """ + """ request_kwargs = curl_to_request_kwargs(curl_command, ignore_unknown_options) request_kwargs.update(kwargs) return cls(**request_kwargs) + + def to_dict(self, *, spider: Optional["scrapy.Spider"] = None) -> dict: + """Return a dictionary containing the Request's data. + + Use :func:`~scrapy.utils.request.request_from_dict` to convert back into a :class:`~scrapy.Request` object. + + If a spider is given, this method will try to find out the name of the spider methods used as callback + and errback and include them in the output dict, raising an exception if they cannot be found. + """ + d = { + "url": self.url, # urls are safe (safe_string_url) + "callback": _find_method(spider, self.callback) if callable(self.callback) else self.callback, + "errback": _find_method(spider, self.errback) if callable(self.errback) else self.errback, + "headers": dict(self.headers), + } + for attr in self.attributes: + d.setdefault(attr, getattr(self, attr)) + if type(self) is not Request: + d["_class"] = self.__module__ + '.' + self.__class__.__name__ + return d + + +def _find_method(obj, func): + """Helper function for Request.to_dict""" + # Only instance methods contain ``__func__`` + if obj and hasattr(func, '__func__'): + members = inspect.getmembers(obj, predicate=inspect.ismethod) + for name, obj_func in members: + # We need to use __func__ to access the original function object because instance + # method objects are generated each time attribute is retrieved from instance. + # + # Reference: The standard type hierarchy + # https://docs.python.org/3/reference/datamodel.html + if obj_func.__func__ is func.__func__: + return name + raise ValueError(f"Function {func} is not an instance method in: {obj}") diff --git a/scrapy/http/request/form.py b/scrapy/http/request/form.py index cd4e3373f..0c947565a 100644 --- a/scrapy/http/request/form.py +++ b/scrapy/http/request/form.py @@ -5,40 +5,56 @@ This module implements the FormRequest class which is a more convenient class See documentation in docs/topics/request-response.rst """ -from urllib.parse import urljoin, urlencode +from typing import Iterable, List, Optional, Tuple, Type, TypeVar, Union +from urllib.parse import urljoin, urlencode, urlsplit, urlunsplit -import lxml.html +from lxml.html import FormElement, HtmlElement, HTMLParser, SelectElement from parsel.selector import create_root_node from w3lib.html import strip_html5_whitespace from scrapy.http.request import Request +from scrapy.http.response.text import TextResponse from scrapy.utils.python import to_bytes, is_listlike from scrapy.utils.response import get_base_url +FormRequestTypeVar = TypeVar("FormRequestTypeVar", bound="FormRequest") + +FormdataType = Optional[Union[dict, List[Tuple[str, str]]]] + + class FormRequest(Request): valid_form_methods = ['GET', 'POST'] - def __init__(self, *args, **kwargs): - formdata = kwargs.pop('formdata', None) + def __init__(self, *args, formdata: FormdataType = None, **kwargs) -> None: if formdata and kwargs.get('method') is None: kwargs['method'] = 'POST' - super(FormRequest, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) if formdata: items = formdata.items() if isinstance(formdata, dict) else formdata - querystr = _urlencode(items, self.encoding) + form_query_str = _urlencode(items, self.encoding) if self.method == 'POST': self.headers.setdefault(b'Content-Type', b'application/x-www-form-urlencoded') - self._set_body(querystr) + self._set_body(form_query_str) else: - self._set_url(self.url + ('&' if '?' in self.url else '?') + querystr) + self._set_url(urlunsplit(urlsplit(self.url)._replace(query=form_query_str))) @classmethod - def from_response(cls, response, formname=None, formid=None, formnumber=0, formdata=None, - clickdata=None, dont_click=False, formxpath=None, formcss=None, **kwargs): - + def from_response( + cls: Type[FormRequestTypeVar], + response: TextResponse, + formname: Optional[str] = None, + formid: Optional[str] = None, + formnumber: Optional[int] = 0, + formdata: FormdataType = None, + clickdata: Optional[dict] = None, + dont_click: bool = False, + formxpath: Optional[str] = None, + formcss: Optional[str] = None, + **kwargs, + ) -> FormRequestTypeVar: kwargs.setdefault('encoding', response.encoding) if formcss is not None: @@ -46,7 +62,7 @@ class FormRequest(Request): formxpath = HTMLTranslator().css_to_xpath(formcss) form = _get_form(response, formname, formid, formnumber, formxpath) - formdata = _get_inputs(form, formdata, dont_click, clickdata, response) + formdata = _get_inputs(form, formdata, dont_click, clickdata) url = _get_form_url(form, kwargs.pop('url', None)) method = kwargs.pop('method', form.method) @@ -58,7 +74,7 @@ class FormRequest(Request): return cls(url=url, method=method, formdata=formdata, **kwargs) -def _get_form_url(form, url): +def _get_form_url(form: FormElement, url: Optional[str]) -> str: if url is None: action = form.get('action') if action is None: @@ -67,28 +83,33 @@ def _get_form_url(form, url): return urljoin(form.base_url, url) -def _urlencode(seq, enc): +def _urlencode(seq: Iterable, enc: str) -> str: values = [(to_bytes(k, enc), to_bytes(v, enc)) for k, vs in seq for v in (vs if is_listlike(vs) else [vs])] - return urlencode(values, doseq=1) + return urlencode(values, doseq=True) -def _get_form(response, formname, formid, formnumber, formxpath): - """Find the form element """ - root = create_root_node(response.text, lxml.html.HTMLParser, - base_url=get_base_url(response)) +def _get_form( + response: TextResponse, + formname: Optional[str], + formid: Optional[str], + formnumber: Optional[int], + formxpath: Optional[str], +) -> FormElement: + """Find the wanted form element within the given response.""" + root = create_root_node(response.text, HTMLParser, base_url=get_base_url(response)) forms = root.xpath('//form') if not forms: - raise ValueError("No element found in %s" % response) + raise ValueError(f"No element found in {response}") if formname is not None: - f = root.xpath('//form[@name="%s"]' % formname) + f = root.xpath(f'//form[@name="{formname}"]') if f: return f[0] if formid is not None: - f = root.xpath('//form[@id="%s"]' % formid) + f = root.xpath(f'//form[@id="{formid}"]') if f: return f[0] @@ -103,39 +124,44 @@ def _get_form(response, formname, formid, formnumber, formxpath): el = el.getparent() if el is None: break - raise ValueError('No element found with %s' % formxpath) + raise ValueError(f'No element found with {formxpath}') - # If we get here, it means that either formname was None - # or invalid + # If we get here, it means that either formname was None or invalid if formnumber is not None: try: form = forms[formnumber] except IndexError: - raise IndexError("Form number %d not found in %s" % - (formnumber, response)) + raise IndexError(f"Form number {formnumber} not found in {response}") else: return form -def _get_inputs(form, formdata, dont_click, clickdata, response): +def _get_inputs( + form: FormElement, + formdata: FormdataType, + dont_click: bool, + clickdata: Optional[dict], +) -> List[Tuple[str, str]]: + """Return a list of key-value pairs for the inputs found in the given form.""" try: formdata_keys = dict(formdata or ()).keys() except (ValueError, TypeError): raise ValueError('formdata should be a dict or iterable of tuples') if not formdata: - formdata = () + formdata = [] inputs = form.xpath('descendant::textarea' '|descendant::select' '|descendant::input[not(@type) or @type[' ' not(re:test(., "^(?:submit|image|reset)$", "i"))' ' and (../@checked or' ' not(re:test(., "^(?:checkbox|radio)$", "i")))]]', - namespaces={ - "re": "http://exslt.org/regular-expressions"}) - values = [(k, u'' if v is None else v) - for k, v in (_value(e) for e in inputs) - if k and k not in formdata_keys] + namespaces={"re": "http://exslt.org/regular-expressions"}) + values = [ + (k, '' if v is None else v) + for k, v in (_value(e) for e in inputs) + if k and k not in formdata_keys + ] if not dont_click: clickable = _get_clickable(clickdata, form) @@ -143,13 +169,13 @@ def _get_inputs(form, formdata, dont_click, clickdata, response): values.append(clickable) if isinstance(formdata, dict): - formdata = formdata.items() + formdata = formdata.items() # type: ignore[assignment] values.extend((k, v) for k, v in formdata if v is not None) return values -def _value(ele): +def _value(ele: HtmlElement): n = ele.name v = ele.value if ele.tag == 'select': @@ -157,22 +183,23 @@ def _value(ele): return n, v -def _select_value(ele, n, v): +def _select_value(ele: SelectElement, n: str, v: str): multiple = ele.multiple if v is None and not multiple: # Match browser behaviour on simple select tag without options selected - # And for select tags wihout options + # And for select tags without options o = ele.value_options return (n, o[0]) if o else (None, None) elif v is not None and multiple: # This is a workround to bug in lxml fixed 2.3.1 # fix https://github.com/lxml/lxml/commit/57f49eed82068a20da3db8f1b18ae00c1bab8b12#L1L1139 selected_options = ele.xpath('.//option[@selected]') - v = [(o.get('value') or o.text or u'').strip() for o in selected_options] + values = [(o.get('value') or o.text or '').strip() for o in selected_options] + return n, values return n, v -def _get_clickable(clickdata, form): +def _get_clickable(clickdata: Optional[dict], form: FormElement) -> Optional[Tuple[str, str]]: """ Returns the clickable element specified in clickdata, if the latter is given. If not, it returns the first @@ -184,7 +211,7 @@ def _get_clickable(clickdata, form): namespaces={"re": "http://exslt.org/regular-expressions"} )) if not clickables: - return + return None # If we don't have clickdata, we just use the first clickable element if clickdata is None: @@ -205,13 +232,12 @@ def _get_clickable(clickdata, form): # We didn't find it, so now we build an XPath expression out of the other # arguments, because they can be used as such - xpath = u'.//*' + \ - u''.join(u'[@%s="%s"]' % c for c in clickdata.items()) + xpath = './/*' + ''.join(f'[@{k}="{v}"]' for k, v in clickdata.items()) el = form.xpath(xpath) if len(el) == 1: return (el[0].get('name'), el[0].get('value') or '') elif len(el) > 1: - raise ValueError("Multiple elements found (%r) matching the criteria " - "in clickdata: %r" % (el, clickdata)) + raise ValueError(f"Multiple elements found ({el!r}) matching the " + f"criteria in clickdata: {clickdata!r}") else: - raise ValueError('No clickable element matching clickdata: %r' % (clickdata,)) + raise ValueError(f'No clickable element matching clickdata: {clickdata!r}') diff --git a/scrapy/http/request/json_request.py b/scrapy/http/request/json_request.py index f08b25280..728a2a104 100644 --- a/scrapy/http/request/json_request.py +++ b/scrapy/http/request/json_request.py @@ -8,14 +8,18 @@ See documentation in docs/topics/request-response.rst import copy import json import warnings +from typing import Optional, Tuple from scrapy.http.request import Request from scrapy.utils.deprecate import create_deprecated_class class JsonRequest(Request): - def __init__(self, *args, **kwargs): - dumps_kwargs = copy.deepcopy(kwargs.pop('dumps_kwargs', {})) + + attributes: Tuple[str, ...] = Request.attributes + ("dumps_kwargs",) + + def __init__(self, *args, dumps_kwargs: Optional[dict] = None, **kwargs) -> None: + dumps_kwargs = copy.deepcopy(dumps_kwargs) if dumps_kwargs is not None else {} dumps_kwargs.setdefault('sort_keys', True) self._dumps_kwargs = dumps_kwargs @@ -25,31 +29,32 @@ class JsonRequest(Request): if body_passed and data_passed: warnings.warn('Both body and data passed. data will be ignored') - elif not body_passed and data_passed: kwargs['body'] = self._dumps(data) - if 'method' not in kwargs: kwargs['method'] = 'POST' - super(JsonRequest, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.headers.setdefault('Content-Type', 'application/json') self.headers.setdefault('Accept', 'application/json, text/javascript, */*; q=0.01') - def replace(self, *args, **kwargs): + @property + def dumps_kwargs(self) -> dict: + return self._dumps_kwargs + + def replace(self, *args, **kwargs) -> Request: body_passed = kwargs.get('body', None) is not None data = kwargs.pop('data', None) data_passed = data is not None if body_passed and data_passed: warnings.warn('Both body and data passed. data will be ignored') - elif not body_passed and data_passed: kwargs['body'] = self._dumps(data) - return super(JsonRequest, self).replace(*args, **kwargs) + return super().replace(*args, **kwargs) - def _dumps(self, data): + def _dumps(self, data: dict) -> str: """Convert to JSON """ return json.dumps(data, **self._dumps_kwargs) diff --git a/scrapy/http/request/rpc.py b/scrapy/http/request/rpc.py index 811d3ad6b..06d98cea5 100644 --- a/scrapy/http/request/rpc.py +++ b/scrapy/http/request/rpc.py @@ -5,6 +5,7 @@ This module implements the XmlRpcRequest class which is a more convenient class See documentation in docs/topics/request-response.rst """ import xmlrpc.client as xmlrpclib +from typing import Optional from scrapy.http.request import Request from scrapy.utils.python import get_func_args @@ -15,8 +16,7 @@ DUMPS_ARGS = get_func_args(xmlrpclib.dumps) class XmlRpcRequest(Request): - def __init__(self, *args, **kwargs): - encoding = kwargs.get('encoding', None) + def __init__(self, *args, encoding: Optional[str] = None, **kwargs): if 'body' not in kwargs and 'params' in kwargs: kw = dict((k, kwargs.pop(k)) for k in DUMPS_ARGS if k in kwargs) kwargs['body'] = xmlrpclib.dumps(**kw) @@ -31,5 +31,5 @@ class XmlRpcRequest(Request): if encoding is not None: kwargs['encoding'] = encoding - super(XmlRpcRequest, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.headers.setdefault('Content-Type', 'text/xml') diff --git a/scrapy/http/response/__init__.py b/scrapy/http/response/__init__.py index c2c37dd1d..185a9bb67 100644 --- a/scrapy/http/response/__init__.py +++ b/scrapy/http/response/__init__.py @@ -17,8 +17,18 @@ from scrapy.utils.trackref import object_ref class Response(object_ref): - def __init__(self, url, status=200, headers=None, body=b'', flags=None, - request=None, certificate=None, ip_address=None): + def __init__( + self, + url, + status=200, + headers=None, + body=b"", + flags=None, + request=None, + certificate=None, + ip_address=None, + protocol=None, + ): self.headers = Headers(headers or {}) self.status = int(status) self._set_body(body) @@ -27,6 +37,7 @@ class Response(object_ref): self.flags = [] if flags is None else list(flags) self.certificate = certificate self.ip_address = ip_address + self.protocol = protocol @property def cb_kwargs(self): @@ -55,8 +66,8 @@ class Response(object_ref): if isinstance(url, str): self._url = url else: - raise TypeError('%s url must be str, got %s:' % - (type(self).__name__, type(url).__name__)) + raise TypeError(f'{type(self).__name__} url must be str, ' + f'got {type(url).__name__}') url = property(_get_url, obsolete_setter(_set_url, 'url')) @@ -77,7 +88,7 @@ class Response(object_ref): body = property(_get_body, obsolete_setter(_set_body, 'body')) def __str__(self): - return "<%d %s>" % (self.status, self.url) + return f"<{self.status} {self.url}>" __repr__ = __str__ @@ -89,8 +100,9 @@ class Response(object_ref): """Create a new Response with the same attributes except for those given new values. """ - for x in ['url', 'status', 'headers', 'body', - 'request', 'flags', 'certificate', 'ip_address']: + for x in [ + "url", "status", "headers", "body", "request", "flags", "certificate", "ip_address", "protocol", + ]: kwargs.setdefault(x, getattr(self, x)) cls = kwargs.pop('cls', self.__class__) return cls(*args, **kwargs) diff --git a/scrapy/http/response/text.py b/scrapy/http/response/text.py index 40cf3f483..e36e14880 100644 --- a/scrapy/http/response/text.py +++ b/scrapy/http/response/text.py @@ -35,23 +35,23 @@ class TextResponse(Response): self._cached_benc = None self._cached_ubody = None self._cached_selector = None - super(TextResponse, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) def _set_url(self, url): if isinstance(url, str): self._url = to_unicode(url, self.encoding) else: - super(TextResponse, self)._set_url(url) + super()._set_url(url) def _set_body(self, body): self._body = b'' # used by encoding detection if isinstance(body, str): if self._encoding is None: - raise TypeError('Cannot convert unicode body - %s has no encoding' % - type(self).__name__) + raise TypeError('Cannot convert unicode body - ' + f'{type(self).__name__} has no encoding') self._body = body.encode(self._encoding) else: - super(TextResponse, self)._set_body(body) + super()._set_body(body) def replace(self, *args, **kwargs): kwargs.setdefault('encoding', self.encoding) @@ -62,8 +62,11 @@ class TextResponse(Response): return self._declared_encoding() or self._body_inferred_encoding() def _declared_encoding(self): - return self._encoding or self._headers_encoding() \ + return ( + self._encoding + or self._headers_encoding() or self._body_declared_encoding() + ) def body_as_unicode(self): """Return body as unicode""" @@ -74,6 +77,8 @@ class TextResponse(Response): def json(self): """ + .. versionadded:: 2.2 + Deserialize a JSON document to a Python object. """ if self._cached_decoded_json is _NONE: @@ -87,7 +92,7 @@ class TextResponse(Response): # _body_inferred_encoding is called benc = self.encoding if self._cached_ubody is None: - charset = 'charset=%s' % benc + charset = f'charset={benc}' self._cached_ubody = html_to_unicode(charset, self.body)[1] return self._cached_ubody @@ -161,7 +166,7 @@ class TextResponse(Response): elif isinstance(url, parsel.SelectorList): raise ValueError("SelectorList is not supported") encoding = self.encoding if encoding is None else encoding - return super(TextResponse, self).follow( + return super().follow( url=url, callback=callback, method=method, @@ -221,7 +226,7 @@ class TextResponse(Response): for sel in selectors: with suppress(_InvalidSelector): urls.append(_url_from_selector(sel)) - return super(TextResponse, self).follow_all( + return super().follow_all( urls=urls, callback=callback, method=method, @@ -250,12 +255,11 @@ def _url_from_selector(sel): # e.g. ::attr(href) result return strip_html5_whitespace(sel.root) if not hasattr(sel.root, 'tag'): - raise _InvalidSelector("Unsupported selector: %s" % sel) + raise _InvalidSelector(f"Unsupported selector: {sel}") if sel.root.tag not in ('a', 'link'): - raise _InvalidSelector("Only and elements are supported; got <%s>" % - sel.root.tag) + raise _InvalidSelector("Only and elements are supported; " + f"got <{sel.root.tag}>") href = sel.root.get('href') if href is None: - raise _InvalidSelector("<%s> element has no href attribute: %s" % - (sel.root.tag, sel)) + raise _InvalidSelector(f"<{sel.root.tag}> element has no href attribute: {sel}") return strip_html5_whitespace(href) diff --git a/scrapy/item.py b/scrapy/item.py index 97dfed976..2ccd7ad18 100644 --- a/scrapy/item.py +++ b/scrapy/item.py @@ -8,6 +8,7 @@ from abc import ABCMeta from collections.abc import MutableMapping from copy import deepcopy from pprint import pformat +from typing import Dict from warnings import warn from scrapy.utils.deprecate import ScrapyDeprecationWarning @@ -36,10 +37,10 @@ class BaseItem(_BaseItem, metaclass=_BaseItemMeta): """ def __new__(cls, *args, **kwargs): - if issubclass(cls, BaseItem) and not (issubclass(cls, Item) or issubclass(cls, DictItem)): + if issubclass(cls, BaseItem) and not issubclass(cls, (Item, DictItem)): warn('scrapy.item.BaseItem is deprecated, please use scrapy.item.Item instead', ScrapyDeprecationWarning, stacklevel=2) - return super(BaseItem, cls).__new__(cls, *args, **kwargs) + return super().__new__(cls, *args, **kwargs) class Field(dict): @@ -55,7 +56,7 @@ class ItemMeta(_BaseItemMeta): def __new__(mcs, class_name, bases, attrs): classcell = attrs.pop('__classcell__', None) new_bases = tuple(base._class for base in bases if hasattr(base, '_class')) - _class = super(ItemMeta, mcs).__new__(mcs, 'x_' + class_name, new_bases, attrs) + _class = super().__new__(mcs, 'x_' + class_name, new_bases, attrs) fields = getattr(_class, 'fields', {}) new_attrs = {} @@ -70,18 +71,18 @@ class ItemMeta(_BaseItemMeta): new_attrs['_class'] = _class if classcell is not None: new_attrs['__classcell__'] = classcell - return super(ItemMeta, mcs).__new__(mcs, class_name, bases, new_attrs) + return super().__new__(mcs, class_name, bases, new_attrs) class DictItem(MutableMapping, BaseItem): - fields = {} + fields: Dict[str, Field] = {} def __new__(cls, *args, **kwargs): if issubclass(cls, DictItem) and not issubclass(cls, Item): warn('scrapy.item.DictItem is deprecated, please use scrapy.item.Item instead', ScrapyDeprecationWarning, stacklevel=2) - return super(DictItem, cls).__new__(cls, *args, **kwargs) + return super().__new__(cls, *args, **kwargs) def __init__(self, *args, **kwargs): self._values = {} @@ -96,20 +97,20 @@ class DictItem(MutableMapping, BaseItem): if key in self.fields: self._values[key] = value else: - raise KeyError("%s does not support field: %s" % (self.__class__.__name__, key)) + raise KeyError(f"{self.__class__.__name__} does not support field: {key}") def __delitem__(self, key): del self._values[key] def __getattr__(self, name): if name in self.fields: - raise AttributeError("Use item[%r] to get field value" % name) + raise AttributeError(f"Use item[{name!r}] to get field value") raise AttributeError(name) def __setattr__(self, name, value): if not name.startswith('_'): - raise AttributeError("Use item[%r] = %r to set field value" % (name, value)) - super(DictItem, self).__setattr__(name, value) + raise AttributeError(f"Use item[{name!r}] = {value!r} to set field value") + super().__setattr__(name, value) def __len__(self): return len(self._values) diff --git a/scrapy/link.py b/scrapy/link.py index 7cb0765cc..e70667361 100644 --- a/scrapy/link.py +++ b/scrapy/link.py @@ -7,26 +7,47 @@ its documentation in: docs/topics/link-extractors.rst class Link: - """Link objects represent an extracted link by the LinkExtractor.""" + """Link objects represent an extracted link by the LinkExtractor. + + Using the anchor tag sample below to illustrate the parameters:: + + Dont follow this one + + :param url: the absolute url being linked to in the anchor tag. + From the sample, this is ``https://example.com/nofollow.html``. + + :param text: the text in the anchor tag. From the sample, this is ``Dont follow this one``. + + :param fragment: the part of the url after the hash symbol. From the sample, this is ``foo``. + + :param nofollow: an indication of the presence or absence of a nofollow value in the ``rel`` attribute + of the anchor tag. + """ __slots__ = ['url', 'text', 'fragment', 'nofollow'] def __init__(self, url, text='', fragment='', nofollow=False): if not isinstance(url, str): got = url.__class__.__name__ - raise TypeError("Link urls must be str objects, got %s" % got) + raise TypeError(f"Link urls must be str objects, got {got}") self.url = url self.text = text self.fragment = fragment self.nofollow = nofollow def __eq__(self, other): - return self.url == other.url and self.text == other.text and \ - self.fragment == other.fragment and self.nofollow == other.nofollow + return ( + self.url == other.url + and self.text == other.text + and self.fragment == other.fragment + and self.nofollow == other.nofollow + ) def __hash__(self): return hash(self.url) ^ hash(self.text) ^ hash(self.fragment) ^ hash(self.nofollow) def __repr__(self): - return 'Link(url=%r, text=%r, fragment=%r, nofollow=%r)' % \ - (self.url, self.text, self.fragment, self.nofollow) + return ( + f'Link(url={self.url!r}, text={self.text!r}, ' + f'fragment={self.fragment!r}, nofollow={self.nofollow!r})' + ) diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.py index 984a5c4e1..08a6ca1e8 100644 --- a/scrapy/linkextractors/__init__.py +++ b/scrapy/linkextractors/__init__.py @@ -65,7 +65,7 @@ class FilteringLinkExtractor: warn('scrapy.linkextractors.FilteringLinkExtractor is deprecated, ' 'please use scrapy.linkextractors.LinkExtractor instead', ScrapyDeprecationWarning, stacklevel=2) - return super(FilteringLinkExtractor, cls).__new__(cls) + return super().__new__(cls) def __init__(self, link_extractor, allow, deny, allow_domains, deny_domains, restrict_xpaths, canonicalize, deny_extensions, restrict_css, restrict_text): diff --git a/scrapy/linkextractors/htmlparser.py b/scrapy/linkextractors/htmlparser.py deleted file mode 100644 index 0425d4340..000000000 --- a/scrapy/linkextractors/htmlparser.py +++ /dev/null @@ -1,91 +0,0 @@ -""" -HTMLParser-based link extractor -""" -import warnings -from html.parser import HTMLParser -from urllib.parse import urljoin - -from w3lib.url import safe_url_string -from w3lib.html import strip_html5_whitespace - -from scrapy.link import Link -from scrapy.utils.python import unique as unique_list -from scrapy.exceptions import ScrapyDeprecationWarning - - -class HtmlParserLinkExtractor(HTMLParser): - - def __init__(self, tag="a", attr="href", process=None, unique=False, - strip=True): - HTMLParser.__init__(self) - - warnings.warn( - "HtmlParserLinkExtractor is deprecated and will be removed in " - "future releases. Please use scrapy.linkextractors.LinkExtractor", - ScrapyDeprecationWarning, stacklevel=2, - ) - - self.scan_tag = tag if callable(tag) else lambda t: t == tag - self.scan_attr = attr if callable(attr) else lambda a: a == attr - self.process_attr = process if callable(process) else lambda v: v - self.unique = unique - self.strip = strip - - def _extract_links(self, response_text, response_url, response_encoding): - self.reset() - self.feed(response_text) - self.close() - - links = unique_list(self.links, key=lambda link: link.url) if self.unique else self.links - - ret = [] - base_url = urljoin(response_url, self.base_url) if self.base_url else response_url - for link in links: - if isinstance(link.url, str): - link.url = link.url.encode(response_encoding) - try: - link.url = urljoin(base_url, link.url) - except ValueError: - continue - link.url = safe_url_string(link.url, response_encoding) - link.text = link.text.decode(response_encoding) - ret.append(link) - - return ret - - def extract_links(self, response): - # wrapper needed to allow to work directly with text - return self._extract_links(response.body, response.url, response.encoding) - - def reset(self): - HTMLParser.reset(self) - - self.base_url = None - self.current_link = None - self.links = [] - - def handle_starttag(self, tag, attrs): - if tag == 'base': - self.base_url = dict(attrs).get('href') - if self.scan_tag(tag): - for attr, value in attrs: - if self.scan_attr(attr): - if self.strip: - value = strip_html5_whitespace(value) - url = self.process_attr(value) - link = Link(url=url) - self.links.append(link) - self.current_link = link - - def handle_endtag(self, tag): - if self.scan_tag(tag): - self.current_link = None - - def handle_data(self, data): - if self.current_link: - self.current_link.text = self.current_link.text + data - - def matches(self, url): - """This extractor matches with any url, since - it doesn't contain any patterns""" - return True diff --git a/scrapy/linkextractors/lxmlhtml.py b/scrapy/linkextractors/lxmlhtml.py index 1615d44d7..e941c4321 100644 --- a/scrapy/linkextractors/lxmlhtml.py +++ b/scrapy/linkextractors/lxmlhtml.py @@ -76,7 +76,7 @@ class LxmlParserLinkExtractor: url = safe_url_string(url, encoding=response_encoding) # to fix relative links after process_value url = urljoin(response_url, url) - link = Link(url, _collect_string_content(el) or u'', + link = Link(url, _collect_string_content(el) or '', nofollow=rel_has_nofollow(el.get('rel'))) links.append(link) return self._deduplicate_if_needed(links) @@ -126,7 +126,7 @@ class LxmlLinkExtractor(FilteringLinkExtractor): strip=strip, canonicalized=canonicalize ) - super(LxmlLinkExtractor, self).__init__( + super().__init__( link_extractor=lx, allow=allow, deny=deny, diff --git a/scrapy/linkextractors/regex.py b/scrapy/linkextractors/regex.py deleted file mode 100644 index 3f2557248..000000000 --- a/scrapy/linkextractors/regex.py +++ /dev/null @@ -1,41 +0,0 @@ -import re -from urllib.parse import urljoin - -from w3lib.html import remove_tags, replace_entities, replace_escape_chars, get_base_url - -from scrapy.link import Link -from scrapy.linkextractors.sgml import SgmlLinkExtractor - - -linkre = re.compile( - "|\s.*?>)(.*?)<[/ ]?a>", - re.DOTALL | re.IGNORECASE) - - -def clean_link(link_text): - """Remove leading and trailing whitespace and punctuation""" - return link_text.strip("\t\r\n '\"\x0c") - - -class RegexLinkExtractor(SgmlLinkExtractor): - """High performant link extractor""" - - def _extract_links(self, response_text, response_url, response_encoding, base_url=None): - def clean_text(text): - return replace_escape_chars(remove_tags(text.decode(response_encoding))).strip() - - def clean_url(url): - clean_url = '' - try: - clean_url = urljoin(base_url, replace_entities(clean_link(url.decode(response_encoding)))) - except ValueError: - pass - return clean_url - - if base_url is None: - base_url = get_base_url(response_text, response_url, response_encoding) - - links_text = linkre.findall(response_text) - return [Link(clean_url(url).encode(response_encoding), - clean_text(text)) - for url, _, text in links_text] diff --git a/scrapy/linkextractors/sgml.py b/scrapy/linkextractors/sgml.py deleted file mode 100644 index 2ba6bca45..000000000 --- a/scrapy/linkextractors/sgml.py +++ /dev/null @@ -1,151 +0,0 @@ -""" -SGMLParser-based Link extractors -""" -import warnings -from urllib.parse import urljoin -from sgmllib import SGMLParser - -from w3lib.url import safe_url_string, canonicalize_url -from w3lib.html import strip_html5_whitespace - -from scrapy.link import Link -from scrapy.linkextractors import FilteringLinkExtractor -from scrapy.utils.misc import arg_to_iter, rel_has_nofollow -from scrapy.utils.python import unique as unique_list, to_unicode -from scrapy.utils.response import get_base_url -from scrapy.exceptions import ScrapyDeprecationWarning - - -class BaseSgmlLinkExtractor(SGMLParser): - - def __init__(self, tag="a", attr="href", unique=False, process_value=None, - strip=True, canonicalized=False): - warnings.warn( - "BaseSgmlLinkExtractor is deprecated and will be removed in future releases. " - "Please use scrapy.linkextractors.LinkExtractor", - ScrapyDeprecationWarning, stacklevel=2, - ) - SGMLParser.__init__(self) - self.scan_tag = tag if callable(tag) else lambda t: t == tag - self.scan_attr = attr if callable(attr) else lambda a: a == attr - self.process_value = (lambda v: v) if process_value is None else process_value - self.current_link = None - self.unique = unique - self.strip = strip - if canonicalized: - self.link_key = lambda link: link.url - else: - self.link_key = lambda link: canonicalize_url(link.url, - keep_fragments=True) - - def _extract_links(self, response_text, response_url, response_encoding, base_url=None): - """ Do the real extraction work """ - self.reset() - self.feed(response_text) - self.close() - - ret = [] - if base_url is None: - base_url = urljoin(response_url, self.base_url) if self.base_url else response_url - for link in self.links: - if isinstance(link.url, str): - link.url = link.url.encode(response_encoding) - try: - link.url = urljoin(base_url, link.url) - except ValueError: - continue - link.url = safe_url_string(link.url, response_encoding) - link.text = to_unicode(link.text, response_encoding, errors='replace').strip() - ret.append(link) - - return ret - - def _process_links(self, links): - """ Normalize and filter extracted links - - The subclass should override it if necessary - """ - return unique_list(links, key=self.link_key) if self.unique else links - - def extract_links(self, response): - # wrapper needed to allow to work directly with text - links = self._extract_links(response.body, response.url, response.encoding) - links = self._process_links(links) - return links - - def reset(self): - SGMLParser.reset(self) - self.links = [] - self.base_url = None - self.current_link = None - - def unknown_starttag(self, tag, attrs): - if tag == 'base': - self.base_url = dict(attrs).get('href') - if self.scan_tag(tag): - for attr, value in attrs: - if self.scan_attr(attr): - if self.strip and value is not None: - value = strip_html5_whitespace(value) - url = self.process_value(value) - if url is not None: - link = Link(url=url, nofollow=rel_has_nofollow(dict(attrs).get('rel'))) - self.links.append(link) - self.current_link = link - - def unknown_endtag(self, tag): - if self.scan_tag(tag): - self.current_link = None - - def handle_data(self, data): - if self.current_link: - self.current_link.text = self.current_link.text + data - - def matches(self, url): - """This extractor matches with any url, since - it doesn't contain any patterns""" - return True - - -class SgmlLinkExtractor(FilteringLinkExtractor): - - def __init__(self, allow=(), deny=(), allow_domains=(), deny_domains=(), restrict_xpaths=(), - tags=('a', 'area'), attrs=('href',), canonicalize=False, unique=True, - process_value=None, deny_extensions=None, restrict_css=(), - strip=True, restrict_text=()): - warnings.warn( - "SgmlLinkExtractor is deprecated and will be removed in future releases. " - "Please use scrapy.linkextractors.LinkExtractor", - ScrapyDeprecationWarning, stacklevel=2, - ) - - tags, attrs = set(arg_to_iter(tags)), set(arg_to_iter(attrs)) - tag_func = lambda x: x in tags - attr_func = lambda x: x in attrs - - with warnings.catch_warnings(): - warnings.simplefilter('ignore', ScrapyDeprecationWarning) - lx = BaseSgmlLinkExtractor(tag=tag_func, attr=attr_func, - unique=unique, process_value=process_value, strip=strip, - canonicalized=canonicalize) - - super(SgmlLinkExtractor, self).__init__(lx, allow=allow, deny=deny, - allow_domains=allow_domains, deny_domains=deny_domains, - restrict_xpaths=restrict_xpaths, restrict_css=restrict_css, - canonicalize=canonicalize, deny_extensions=deny_extensions, - restrict_text=restrict_text) - - def extract_links(self, response): - base_url = None - if self.restrict_xpaths: - base_url = get_base_url(response) - body = u''.join(f - for x in self.restrict_xpaths - for f in response.xpath(x).getall() - ).encode(response.encoding, errors='xmlcharrefreplace') - else: - body = response.body - - links = self._extract_links(body, response.url, response.encoding, base_url) - links = self._process_links(links) - return links diff --git a/scrapy/loader/__init__.py b/scrapy/loader/__init__.py index 21c4fb376..014951a8e 100644 --- a/scrapy/loader/__init__.py +++ b/scrapy/loader/__init__.py @@ -3,219 +3,86 @@ Item Loader See documentation in docs/topics/loaders.rst """ -from collections import defaultdict -from contextlib import suppress +import itemloaders from scrapy.item import Item -from scrapy.loader.common import wrap_loader_context -from scrapy.loader.processors import Identity from scrapy.selector import Selector -from scrapy.utils.misc import arg_to_iter, extract_regex -from scrapy.utils.python import flatten -def unbound_method(method): +class ItemLoader(itemloaders.ItemLoader): """ - Allow to use single-argument functions as input or output processors - (no need to define an unused first 'self' argument) + A user-friendly abstraction to populate an :ref:`item ` with data + by applying :ref:`field processors ` to scraped data. + When instantiated with a ``selector`` or a ``response`` it supports + data extraction from web pages using :ref:`selectors `. + + :param item: The item instance to populate using subsequent calls to + :meth:`~ItemLoader.add_xpath`, :meth:`~ItemLoader.add_css`, + or :meth:`~ItemLoader.add_value`. + :type item: scrapy.item.Item + + :param selector: The selector to extract data from, when using the + :meth:`add_xpath`, :meth:`add_css`, :meth:`replace_xpath`, or + :meth:`replace_css` method. + :type selector: :class:`~scrapy.selector.Selector` object + + :param response: The response used to construct the selector using the + :attr:`default_selector_class`, unless the selector argument is given, + in which case this argument is ignored. + :type response: :class:`~scrapy.http.Response` object + + If no item is given, one is instantiated automatically using the class in + :attr:`default_item_class`. + + The item, selector, response and remaining keyword arguments are + assigned to the Loader context (accessible through the :attr:`context` attribute). + + .. attribute:: item + + The item object being parsed by this Item Loader. + This is mostly used as a property so, when attempting to override this + value, you may want to check out :attr:`default_item_class` first. + + .. attribute:: context + + The currently active :ref:`Context ` of this Item Loader. + + .. attribute:: default_item_class + + An :ref:`item ` class (or factory), used to instantiate + items when not given in the ``__init__`` method. + + .. attribute:: default_input_processor + + The default input processor to use for those fields which don't specify + one. + + .. attribute:: default_output_processor + + The default output processor to use for those fields which don't specify + one. + + .. attribute:: default_selector_class + + The class used to construct the :attr:`selector` of this + :class:`ItemLoader`, if only a response is given in the ``__init__`` method. + If a selector is given in the ``__init__`` method this attribute is ignored. + This attribute is sometimes overridden in subclasses. + + .. attribute:: selector + + The :class:`~scrapy.selector.Selector` object to extract data from. + It's either the selector given in the ``__init__`` method or one created from + the response given in the ``__init__`` method using the + :attr:`default_selector_class`. This attribute is meant to be + read-only. """ - with suppress(AttributeError): - if '.' not in method.__qualname__: - return method.__func__ - return method - - -class ItemLoader: default_item_class = Item - default_input_processor = Identity() - default_output_processor = Identity() default_selector_class = Selector def __init__(self, item=None, selector=None, response=None, parent=None, **context): if selector is None and response is not None: selector = self.default_selector_class(response) - self.selector = selector - context.update(selector=selector, response=response) - if item is None: - item = self.default_item_class() - self.context = context - self.parent = parent - self._local_item = context['item'] = item - self._local_values = defaultdict(list) - # values from initial item - for field_name, value in item.items(): - self._values[field_name] += arg_to_iter(value) - - @property - def _values(self): - if self.parent is not None: - return self.parent._values - else: - return self._local_values - - @property - def item(self): - if self.parent is not None: - return self.parent.item - else: - return self._local_item - - def nested_xpath(self, xpath, **context): - selector = self.selector.xpath(xpath) - context.update(selector=selector) - subloader = self.__class__( - item=self.item, parent=self, **context - ) - return subloader - - def nested_css(self, css, **context): - selector = self.selector.css(css) - context.update(selector=selector) - subloader = self.__class__( - item=self.item, parent=self, **context - ) - return subloader - - def add_value(self, field_name, value, *processors, **kw): - value = self.get_value(value, *processors, **kw) - if value is None: - return - if not field_name: - for k, v in value.items(): - self._add_value(k, v) - else: - self._add_value(field_name, value) - - def replace_value(self, field_name, value, *processors, **kw): - value = self.get_value(value, *processors, **kw) - if value is None: - return - if not field_name: - for k, v in value.items(): - self._replace_value(k, v) - else: - self._replace_value(field_name, value) - - def _add_value(self, field_name, value): - value = arg_to_iter(value) - processed_value = self._process_input_value(field_name, value) - if processed_value: - self._values[field_name] += arg_to_iter(processed_value) - - def _replace_value(self, field_name, value): - self._values.pop(field_name, None) - self._add_value(field_name, value) - - def get_value(self, value, *processors, **kw): - regex = kw.get('re', None) - if regex: - value = arg_to_iter(value) - value = flatten(extract_regex(regex, x) for x in value) - - for proc in processors: - if value is None: - break - _proc = proc - proc = wrap_loader_context(proc, self.context) - try: - value = proc(value) - except Exception as e: - raise ValueError("Error with processor %s value=%r error='%s: %s'" % - (_proc.__class__.__name__, value, - type(e).__name__, str(e))) - return value - - def load_item(self): - item = self.item - for field_name in tuple(self._values): - value = self.get_output_value(field_name) - if value is not None: - item[field_name] = value - - return item - - def get_output_value(self, field_name): - proc = self.get_output_processor(field_name) - proc = wrap_loader_context(proc, self.context) - try: - return proc(self._values[field_name]) - except Exception as e: - raise ValueError("Error with output processor: field=%r value=%r error='%s: %s'" % - (field_name, self._values[field_name], type(e).__name__, str(e))) - - def get_collected_values(self, field_name): - return self._values[field_name] - - def get_input_processor(self, field_name): - proc = getattr(self, '%s_in' % field_name, None) - if not proc: - proc = self._get_item_field_attr(field_name, 'input_processor', - self.default_input_processor) - return unbound_method(proc) - - def get_output_processor(self, field_name): - proc = getattr(self, '%s_out' % field_name, None) - if not proc: - proc = self._get_item_field_attr(field_name, 'output_processor', - self.default_output_processor) - return unbound_method(proc) - - def _process_input_value(self, field_name, value): - proc = self.get_input_processor(field_name) - _proc = proc - proc = wrap_loader_context(proc, self.context) - try: - return proc(value) - except Exception as e: - raise ValueError( - "Error with input processor %s: field=%r value=%r " - "error='%s: %s'" % (_proc.__class__.__name__, field_name, - value, type(e).__name__, str(e))) - - def _get_item_field_attr(self, field_name, key, default=None): - if isinstance(self.item, Item): - value = self.item.fields[field_name].get(key, default) - else: - value = default - return value - - def _check_selector_method(self): - if self.selector is None: - raise RuntimeError("To use XPath or CSS selectors, " - "%s must be instantiated with a selector " - "or a response" % self.__class__.__name__) - - def add_xpath(self, field_name, xpath, *processors, **kw): - values = self._get_xpathvalues(xpath, **kw) - self.add_value(field_name, values, *processors, **kw) - - def replace_xpath(self, field_name, xpath, *processors, **kw): - values = self._get_xpathvalues(xpath, **kw) - self.replace_value(field_name, values, *processors, **kw) - - def get_xpath(self, xpath, *processors, **kw): - values = self._get_xpathvalues(xpath, **kw) - return self.get_value(values, *processors, **kw) - - def _get_xpathvalues(self, xpaths, **kw): - self._check_selector_method() - xpaths = arg_to_iter(xpaths) - return flatten(self.selector.xpath(xpath).getall() for xpath in xpaths) - - def add_css(self, field_name, css, *processors, **kw): - values = self._get_cssvalues(css, **kw) - self.add_value(field_name, values, *processors, **kw) - - def replace_css(self, field_name, css, *processors, **kw): - values = self._get_cssvalues(css, **kw) - self.replace_value(field_name, values, *processors, **kw) - - def get_css(self, css, *processors, **kw): - values = self._get_cssvalues(css, **kw) - return self.get_value(values, *processors, **kw) - - def _get_cssvalues(self, csss, **kw): - self._check_selector_method() - csss = arg_to_iter(csss) - return flatten(self.selector.css(css).getall() for css in csss) + context.update(response=response) + super().__init__(item=item, selector=selector, parent=parent, **context) diff --git a/scrapy/loader/common.py b/scrapy/loader/common.py index 42f8de636..3b8a6ee94 100644 --- a/scrapy/loader/common.py +++ b/scrapy/loader/common.py @@ -1,14 +1,21 @@ """Common functions used in Item Loaders code""" -from functools import partial -from scrapy.utils.python import get_func_args +import warnings + +from itemloaders import common + +from scrapy.utils.deprecate import ScrapyDeprecationWarning def wrap_loader_context(function, context): """Wrap functions that receive loader_context to contain the context "pre-loaded" and expose a interface that receives only one argument """ - if 'loader_context' in get_func_args(function): - return partial(function, loader_context=context) - else: - return function + warnings.warn( + "scrapy.loader.common.wrap_loader_context has moved to a new library." + "Please update your reference to itemloaders.common.wrap_loader_context", + ScrapyDeprecationWarning, + stacklevel=2 + ) + + return common.wrap_loader_context(function, context) diff --git a/scrapy/loader/processors.py b/scrapy/loader/processors.py index a7be65609..51fbd19eb 100644 --- a/scrapy/loader/processors.py +++ b/scrapy/loader/processors.py @@ -3,102 +3,19 @@ This module provides some commonly used processors for Item Loaders. See documentation in docs/topics/loaders.rst """ -from collections import ChainMap +from itemloaders import processors -from scrapy.utils.misc import arg_to_iter -from scrapy.loader.common import wrap_loader_context +from scrapy.utils.deprecate import create_deprecated_class -class MapCompose: +MapCompose = create_deprecated_class('MapCompose', processors.MapCompose) - def __init__(self, *functions, **default_loader_context): - self.functions = functions - self.default_loader_context = default_loader_context +Compose = create_deprecated_class('Compose', processors.Compose) - def __call__(self, value, loader_context=None): - values = arg_to_iter(value) - if loader_context: - context = ChainMap(loader_context, self.default_loader_context) - else: - context = self.default_loader_context - wrapped_funcs = [wrap_loader_context(f, context) for f in self.functions] - for func in wrapped_funcs: - next_values = [] - for v in values: - try: - next_values += arg_to_iter(func(v)) - except Exception as e: - raise ValueError("Error in MapCompose with " - "%s value=%r error='%s: %s'" % - (str(func), value, type(e).__name__, - str(e))) - values = next_values - return values +TakeFirst = create_deprecated_class('TakeFirst', processors.TakeFirst) +Identity = create_deprecated_class('Identity', processors.Identity) -class Compose: +SelectJmes = create_deprecated_class('SelectJmes', processors.SelectJmes) - def __init__(self, *functions, **default_loader_context): - self.functions = functions - self.stop_on_none = default_loader_context.get('stop_on_none', True) - self.default_loader_context = default_loader_context - - def __call__(self, value, loader_context=None): - if loader_context: - context = ChainMap(loader_context, self.default_loader_context) - else: - context = self.default_loader_context - wrapped_funcs = [wrap_loader_context(f, context) for f in self.functions] - for func in wrapped_funcs: - if value is None and self.stop_on_none: - break - try: - value = func(value) - except Exception as e: - raise ValueError("Error in Compose with " - "%s value=%r error='%s: %s'" % - (str(func), value, type(e).__name__, str(e))) - return value - - -class TakeFirst: - - def __call__(self, values): - for value in values: - if value is not None and value != '': - return value - - -class Identity: - - def __call__(self, values): - return values - - -class SelectJmes: - """ - Query the input string for the jmespath (given at instantiation), - and return the answer - Requires : jmespath(https://github.com/jmespath/jmespath) - Note: SelectJmes accepts only one input element at a time. - """ - def __init__(self, json_path): - self.json_path = json_path - import jmespath - self.compiled_path = jmespath.compile(self.json_path) - - def __call__(self, value): - """Query value for the jmespath query and return answer - :param value: a data structure (dict, list) to extract from - :return: Element extracted according to jmespath query - """ - return self.compiled_path.search(value) - - -class Join: - - def __init__(self, separator=u' '): - self.separator = separator - - def __call__(self, values): - return self.separator.join(values) +Join = create_deprecated_class('Join', processors.Join) diff --git a/scrapy/logformatter.py b/scrapy/logformatter.py index 219145f13..87568b2d1 100644 --- a/scrapy/logformatter.py +++ b/scrapy/logformatter.py @@ -44,7 +44,7 @@ class LogFormatter: def dropped(self, item, exception, response, spider): return { 'level': logging.INFO, # lowering the level from logging.WARNING - 'msg': u"Dropped: %(exception)s" + os.linesep + "%(item)s", + 'msg': "Dropped: %(exception)s" + os.linesep + "%(item)s", 'args': { 'exception': exception, 'item': item, @@ -54,8 +54,8 @@ class LogFormatter: def crawled(self, request, response, spider): """Logs a message when the crawler finds a webpage.""" - request_flags = ' %s' % str(request.flags) if request.flags else '' - response_flags = ' %s' % str(response.flags) if response.flags else '' + request_flags = f' {str(request.flags)}' if request.flags else '' + response_flags = f' {str(response.flags)}' if response.flags else '' return { 'level': logging.DEBUG, 'msg': CRAWLEDMSG, diff --git a/scrapy/mail.py b/scrapy/mail.py index 7d7a2c435..2a25ccd44 100644 --- a/scrapy/mail.py +++ b/scrapy/mail.py @@ -9,7 +9,7 @@ from email.mime.base import MIMEBase from email.mime.multipart import MIMEMultipart from email.mime.nonmultipart import MIMENonMultipart from email.mime.text import MIMEText -from email.utils import COMMASPACE, formatdate +from email.utils import formatdate from io import BytesIO from twisted.internet import defer, ssl @@ -21,6 +21,11 @@ from scrapy.utils.python import to_bytes logger = logging.getLogger(__name__) +# Defined in the email.utils module, but undocumented: +# https://github.com/python/cpython/blob/v3.9.0/Lib/email/utils.py#L42 +COMMASPACE = ", " + + def _to_bytes_or_none(text): if text is None: return None diff --git a/scrapy/middleware.py b/scrapy/middleware.py index 5040378ea..bbec38086 100644 --- a/scrapy/middleware.py +++ b/scrapy/middleware.py @@ -1,8 +1,13 @@ -from collections import defaultdict, deque import logging import pprint +from collections import defaultdict, deque +from typing import Callable, Deque, Dict +from twisted.internet.defer import Deferred + +from scrapy import Spider from scrapy.exceptions import NotConfigured +from scrapy.settings import Settings from scrapy.utils.misc import create_instance, load_object from scrapy.utils.defer import process_parallel, process_chain, process_chain_both @@ -16,16 +21,16 @@ class MiddlewareManager: def __init__(self, *middlewares): self.middlewares = middlewares - self.methods = defaultdict(deque) + self.methods: Dict[str, Deque[Callable]] = defaultdict(deque) for mw in middlewares: self._add_middleware(mw) @classmethod - def _get_mwlist_from_settings(cls, settings): + def _get_mwlist_from_settings(cls, settings: Settings) -> list: raise NotImplementedError @classmethod - def from_settings(cls, settings, crawler=None): + def from_settings(cls, settings: Settings, crawler=None): mwlist = cls._get_mwlist_from_settings(settings) middlewares = [] enabled = [] @@ -52,24 +57,24 @@ class MiddlewareManager: def from_crawler(cls, crawler): return cls.from_settings(crawler.settings, crawler) - def _add_middleware(self, mw): + def _add_middleware(self, mw) -> None: if hasattr(mw, 'open_spider'): self.methods['open_spider'].append(mw.open_spider) if hasattr(mw, 'close_spider'): self.methods['close_spider'].appendleft(mw.close_spider) - def _process_parallel(self, methodname, obj, *args): + def _process_parallel(self, methodname: str, obj, *args) -> Deferred: return process_parallel(self.methods[methodname], obj, *args) - def _process_chain(self, methodname, obj, *args): + def _process_chain(self, methodname: str, obj, *args) -> Deferred: return process_chain(self.methods[methodname], obj, *args) - def _process_chain_both(self, cb_methodname, eb_methodname, obj, *args): + def _process_chain_both(self, cb_methodname: str, eb_methodname: str, obj, *args) -> Deferred: return process_chain_both(self.methods[cb_methodname], self.methods[eb_methodname], obj, *args) - def open_spider(self, spider): + def open_spider(self, spider: Spider) -> Deferred: return self._process_parallel('open_spider', spider) - def close_spider(self, spider): + def close_spider(self, spider: Spider) -> Deferred: return self._process_parallel('close_spider', spider) diff --git a/scrapy/pipelines/files.py b/scrapy/pipelines/files.py index 7d86d0d56..13ecd4e6c 100644 --- a/scrapy/pipelines/files.py +++ b/scrapy/pipelines/files.py @@ -10,24 +10,25 @@ import mimetypes import os import time from collections import defaultdict -from email.utils import parsedate_tz, mktime_tz +from contextlib import suppress from ftplib import FTP from io import BytesIO from urllib.parse import urlparse +from itemadapter import ItemAdapter from twisted.internet import defer, threads +from scrapy.exceptions import IgnoreRequest, NotConfigured +from scrapy.http import Request from scrapy.pipelines.media import MediaPipeline from scrapy.settings import Settings -from scrapy.exceptions import NotConfigured, IgnoreRequest -from scrapy.http import Request -from scrapy.utils.misc import md5sum -from scrapy.utils.log import failure_to_exc_info -from scrapy.utils.python import to_bytes -from scrapy.utils.request import referer_str -from scrapy.utils.boto import is_botocore +from scrapy.utils.boto import is_botocore_available from scrapy.utils.datatypes import CaselessDict from scrapy.utils.ftp import ftp_store_file +from scrapy.utils.log import failure_to_exc_info +from scrapy.utils.misc import md5sum +from scrapy.utils.python import to_bytes +from scrapy.utils.request import referer_str logger = logging.getLogger(__name__) @@ -89,86 +90,54 @@ class S3FilesStore: } def __init__(self, uri): - self.is_botocore = is_botocore() - if self.is_botocore: - import botocore.session - session = botocore.session.get_session() - self.s3_client = session.create_client( - 's3', - aws_access_key_id=self.AWS_ACCESS_KEY_ID, - aws_secret_access_key=self.AWS_SECRET_ACCESS_KEY, - endpoint_url=self.AWS_ENDPOINT_URL, - region_name=self.AWS_REGION_NAME, - use_ssl=self.AWS_USE_SSL, - verify=self.AWS_VERIFY - ) - else: - from boto.s3.connection import S3Connection - self.S3Connection = S3Connection + if not is_botocore_available(): + raise NotConfigured('missing botocore library') + import botocore.session + session = botocore.session.get_session() + self.s3_client = session.create_client( + 's3', + aws_access_key_id=self.AWS_ACCESS_KEY_ID, + aws_secret_access_key=self.AWS_SECRET_ACCESS_KEY, + endpoint_url=self.AWS_ENDPOINT_URL, + region_name=self.AWS_REGION_NAME, + use_ssl=self.AWS_USE_SSL, + verify=self.AWS_VERIFY + ) if not uri.startswith("s3://"): - raise ValueError("Incorrect URI scheme in %s, expected 's3'" % uri) + raise ValueError(f"Incorrect URI scheme in {uri}, expected 's3'") self.bucket, self.prefix = uri[5:].split('/', 1) def stat_file(self, path, info): def _onsuccess(boto_key): - if self.is_botocore: - checksum = boto_key['ETag'].strip('"') - last_modified = boto_key['LastModified'] - modified_stamp = time.mktime(last_modified.timetuple()) - else: - checksum = boto_key.etag.strip('"') - last_modified = boto_key.last_modified - modified_tuple = parsedate_tz(last_modified) - modified_stamp = int(mktime_tz(modified_tuple)) + checksum = boto_key['ETag'].strip('"') + last_modified = boto_key['LastModified'] + modified_stamp = time.mktime(last_modified.timetuple()) return {'checksum': checksum, 'last_modified': modified_stamp} return self._get_boto_key(path).addCallback(_onsuccess) - def _get_boto_bucket(self): - # disable ssl (is_secure=False) because of this python bug: - # https://bugs.python.org/issue5103 - c = self.S3Connection(self.AWS_ACCESS_KEY_ID, self.AWS_SECRET_ACCESS_KEY, is_secure=False) - return c.get_bucket(self.bucket, validate=False) - def _get_boto_key(self, path): - key_name = '%s%s' % (self.prefix, path) - if self.is_botocore: - return threads.deferToThread( - self.s3_client.head_object, - Bucket=self.bucket, - Key=key_name) - else: - b = self._get_boto_bucket() - return threads.deferToThread(b.get_key, key_name) + key_name = f'{self.prefix}{path}' + return threads.deferToThread( + self.s3_client.head_object, + Bucket=self.bucket, + Key=key_name) def persist_file(self, path, buf, info, meta=None, headers=None): """Upload file to S3 storage""" - key_name = '%s%s' % (self.prefix, path) + key_name = f'{self.prefix}{path}' buf.seek(0) - if self.is_botocore: - extra = self._headers_to_botocore_kwargs(self.HEADERS) - if headers: - extra.update(self._headers_to_botocore_kwargs(headers)) - return threads.deferToThread( - self.s3_client.put_object, - Bucket=self.bucket, - Key=key_name, - Body=buf, - Metadata={k: str(v) for k, v in (meta or {}).items()}, - ACL=self.POLICY, - **extra) - else: - b = self._get_boto_bucket() - k = b.new_key(key_name) - if meta: - for metakey, metavalue in meta.items(): - k.set_metadata(metakey, str(metavalue)) - h = self.HEADERS.copy() - if headers: - h.update(headers) - return threads.deferToThread( - k.set_contents_from_string, buf.getvalue(), - headers=h, policy=self.POLICY) + extra = self._headers_to_botocore_kwargs(self.HEADERS) + if headers: + extra.update(self._headers_to_botocore_kwargs(headers)) + return threads.deferToThread( + self.s3_client.put_object, + Bucket=self.bucket, + Key=key_name, + Body=buf, + Metadata={k: str(v) for k, v in (meta or {}).items()}, + ACL=self.POLICY, + **extra) def _headers_to_botocore_kwargs(self, headers): """ Convert headers to botocore keyword agruments. @@ -206,8 +175,7 @@ class S3FilesStore: try: kwarg = mapping[key] except KeyError: - raise TypeError( - 'Header "%s" is not supported by botocore' % key) + raise TypeError(f'Header "{key}" is not supported by botocore') else: extra[kwarg] = value return extra @@ -281,7 +249,7 @@ class FTPFilesStore: def __init__(self, uri): if not uri.startswith("ftp://"): - raise ValueError("Incorrect URI scheme in %s, expected 'ftp'" % uri) + raise ValueError(f"Incorrect URI scheme in {uri}, expected 'ftp'") u = urlparse(uri) self.port = u.port self.host = u.hostname @@ -291,7 +259,7 @@ class FTPFilesStore: self.basedir = u.path.rstrip('/') def persist_file(self, path, buf, info, meta=None, headers=None): - path = '%s/%s' % (self.basedir, path) + path = f'{self.basedir}/{path}' return threads.deferToThread( ftp_store_file, path=path, file=buf, host=self.host, port=self.port, username=self.username, @@ -306,10 +274,10 @@ class FTPFilesStore: ftp.login(self.username, self.password) if self.USE_ACTIVE_MODE: ftp.set_pasv(False) - file_path = "%s/%s" % (self.basedir, path) - last_modified = float(ftp.voidcmd("MDTM %s" % file_path)[4:].strip()) + file_path = f"{self.basedir}/{path}" + last_modified = float(ftp.voidcmd(f"MDTM {file_path}")[4:].strip()) m = hashlib.md5() - ftp.retrbinary('RETR %s' % file_path, m.update) + ftp.retrbinary(f'RETR {file_path}', m.update) return {'last_modified': last_modified, 'checksum': m.hexdigest()} # The file doesn't exist except Exception: @@ -374,7 +342,7 @@ class FilesPipeline(MediaPipeline): resolve('FILES_RESULT_FIELD'), self.FILES_RESULT_FIELD ) - super(FilesPipeline, self).__init__(download_func=download_func, settings=settings) + super().__init__(download_func=download_func, settings=settings) @classmethod def from_settings(cls, settings): @@ -407,7 +375,7 @@ class FilesPipeline(MediaPipeline): store_cls = self.STORE_SCHEMES[scheme] return store_cls(uri) - def media_to_download(self, request, info): + def media_to_download(self, request, info, *, item=None): def _onsuccess(result): if not result: return # returning None force download @@ -434,7 +402,7 @@ class FilesPipeline(MediaPipeline): checksum = result.get('checksum', None) return {'url': request.url, 'path': path, 'checksum': checksum, 'status': 'uptodate'} - path = self.file_path(request, info=info) + path = self.file_path(request, info=info, item=item) dfd = defer.maybeDeferred(self.store.stat_file, path, info) dfd.addCallbacks(_onsuccess, lambda _: None) dfd.addErrback( @@ -458,7 +426,7 @@ class FilesPipeline(MediaPipeline): raise FileException - def media_downloaded(self, response, request, info): + def media_downloaded(self, response, request, info, *, item=None): referer = referer_str(request) if response.status != 200: @@ -490,8 +458,8 @@ class FilesPipeline(MediaPipeline): self.inc_stats(info.spider, status) try: - path = self.file_path(request, response=response, info=info) - checksum = self.file_downloaded(response, request, info) + path = self.file_path(request, response=response, info=info, item=item) + checksum = self.file_downloaded(response, request, info, item=item) except FileException as exc: logger.warning( 'File (error): Error processing file from %(request)s ' @@ -513,14 +481,15 @@ class FilesPipeline(MediaPipeline): def inc_stats(self, spider, status): spider.crawler.stats.inc_value('file_count', spider=spider) - spider.crawler.stats.inc_value('file_status_count/%s' % status, spider=spider) + spider.crawler.stats.inc_value(f'file_status_count/{status}', spider=spider) # Overridable Interface def get_media_requests(self, item, info): - return [Request(x) for x in item.get(self.files_urls_field, [])] + urls = ItemAdapter(item).get(self.files_urls_field, []) + return [Request(u) for u in urls] - def file_downloaded(self, response, request, info): - path = self.file_path(request, response=response, info=info) + def file_downloaded(self, response, request, info, *, item=None): + path = self.file_path(request, response=response, info=info, item=item) buf = BytesIO(response.body) checksum = md5sum(buf) buf.seek(0) @@ -528,11 +497,11 @@ class FilesPipeline(MediaPipeline): return checksum def item_completed(self, results, item, info): - if isinstance(item, dict) or self.files_result_field in item.fields: - item[self.files_result_field] = [x for ok, x in results if ok] + with suppress(KeyError): + ItemAdapter(item)[self.files_result_field] = [x for ok, x in results if ok] return item - def file_path(self, request, response=None, info=None): + def file_path(self, request, response=None, info=None, *, item=None): media_guid = hashlib.sha1(to_bytes(request.url)).hexdigest() media_ext = os.path.splitext(request.url)[1] # Handles empty and wild extensions by trying to guess the @@ -542,4 +511,4 @@ class FilesPipeline(MediaPipeline): media_type = mimetypes.guess_type(request.url)[0] if media_type: media_ext = mimetypes.guess_extension(media_type) - return 'full/%s%s' % (media_guid, media_ext) + return f'full/{media_guid}{media_ext}' diff --git a/scrapy/pipelines/images.py b/scrapy/pipelines/images.py index aeb520442..e3ab23ea5 100644 --- a/scrapy/pipelines/images.py +++ b/scrapy/pipelines/images.py @@ -5,17 +5,18 @@ See documentation in topics/media-pipeline.rst """ import functools import hashlib +from contextlib import suppress from io import BytesIO -from PIL import Image +from itemadapter import ItemAdapter +from scrapy.exceptions import DropItem, NotConfigured +from scrapy.http import Request +from scrapy.pipelines.files import FileException, FilesPipeline +# TODO: from scrapy.pipelines.media import MediaPipeline +from scrapy.settings import Settings from scrapy.utils.misc import md5sum from scrapy.utils.python import to_bytes -from scrapy.http import Request -from scrapy.settings import Settings -from scrapy.exceptions import DropItem -# TODO: from scrapy.pipelines.media import MediaPipeline -from scrapy.pipelines.files import FileException, FilesPipeline class NoimagesDrop(DropItem): @@ -43,8 +44,15 @@ class ImagesPipeline(FilesPipeline): DEFAULT_IMAGES_RESULT_FIELD = 'images' def __init__(self, store_uri, download_func=None, settings=None): - super(ImagesPipeline, self).__init__(store_uri, settings=settings, - download_func=download_func) + try: + from PIL import Image + self._Image = Image + except ImportError: + raise NotConfigured( + 'ImagesPipeline requires installing Pillow 4.0.0 or later' + ) + + super().__init__(store_uri, settings=settings, download_func=download_func) if isinstance(settings, dict) or settings is None: settings = Settings(settings) @@ -102,12 +110,12 @@ class ImagesPipeline(FilesPipeline): store_uri = settings['IMAGES_STORE'] return cls(store_uri, settings=settings) - def file_downloaded(self, response, request, info): - return self.image_downloaded(response, request, info) + def file_downloaded(self, response, request, info, *, item=None): + return self.image_downloaded(response, request, info, item=item) - def image_downloaded(self, response, request, info): + def image_downloaded(self, response, request, info, *, item=None): checksum = None - for path, image, buf in self.get_images(response, request, info): + for path, image, buf in self.get_images(response, request, info, item=item): if checksum is None: buf.seek(0) checksum = md5sum(buf) @@ -118,14 +126,15 @@ class ImagesPipeline(FilesPipeline): headers={'Content-Type': 'image/jpeg'}) return checksum - def get_images(self, response, request, info): - path = self.file_path(request, response=response, info=info) - orig_image = Image.open(BytesIO(response.body)) + def get_images(self, response, request, info, *, item=None): + path = self.file_path(request, response=response, info=info, item=item) + orig_image = self._Image.open(BytesIO(response.body)) width, height = orig_image.size if width < self.min_width or height < self.min_height: - raise ImageException("Image too small (%dx%d < %dx%d)" % - (width, height, self.min_width, self.min_height)) + raise ImageException("Image too small " + f"({width}x{height} < " + f"{self.min_width}x{self.min_height})") image, buf = self.convert_image(orig_image) yield path, image, buf @@ -137,12 +146,12 @@ class ImagesPipeline(FilesPipeline): def convert_image(self, image, size=None): if image.format == 'PNG' and image.mode == 'RGBA': - background = Image.new('RGBA', image.size, (255, 255, 255)) + background = self._Image.new('RGBA', image.size, (255, 255, 255)) background.paste(image, image) image = background.convert('RGB') elif image.mode == 'P': image = image.convert("RGBA") - background = Image.new('RGBA', image.size, (255, 255, 255)) + background = self._Image.new('RGBA', image.size, (255, 255, 255)) background.paste(image, image) image = background.convert('RGB') elif image.mode != 'RGB': @@ -150,24 +159,25 @@ class ImagesPipeline(FilesPipeline): if size: image = image.copy() - image.thumbnail(size, Image.ANTIALIAS) + image.thumbnail(size, self._Image.ANTIALIAS) buf = BytesIO() image.save(buf, 'JPEG') return image, buf def get_media_requests(self, item, info): - return [Request(x) for x in item.get(self.images_urls_field, [])] + urls = ItemAdapter(item).get(self.images_urls_field, []) + return [Request(u) for u in urls] def item_completed(self, results, item, info): - if isinstance(item, dict) or self.images_result_field in item.fields: - item[self.images_result_field] = [x for ok, x in results if ok] + with suppress(KeyError): + ItemAdapter(item)[self.images_result_field] = [x for ok, x in results if ok] return item - def file_path(self, request, response=None, info=None): + def file_path(self, request, response=None, info=None, *, item=None): image_guid = hashlib.sha1(to_bytes(request.url)).hexdigest() - return 'full/%s.jpg' % (image_guid) + return f'full/{image_guid}.jpg' def thumb_path(self, request, thumb_id, response=None, info=None): thumb_guid = hashlib.sha1(to_bytes(request.url)).hexdigest() - return 'thumbs/%s/%s.jpg' % (thumb_id, thumb_guid) + return f'thumbs/{thumb_id}/{thumb_guid}.jpg' diff --git a/scrapy/pipelines/media.py b/scrapy/pipelines/media.py index aa65f4f0e..d1bccf323 100644 --- a/scrapy/pipelines/media.py +++ b/scrapy/pipelines/media.py @@ -1,12 +1,16 @@ import functools import logging from collections import defaultdict +from inspect import signature +from warnings import warn + from twisted.internet.defer import Deferred, DeferredList from twisted.python.failure import Failure from scrapy.settings import Settings from scrapy.utils.datatypes import SequenceExclude from scrapy.utils.defer import mustbe_deferred, defer_result +from scrapy.utils.deprecate import ScrapyDeprecationWarning from scrapy.utils.request import request_fingerprint from scrapy.utils.misc import arg_to_iter from scrapy.utils.log import failure_to_exc_info @@ -27,6 +31,7 @@ class MediaPipeline: def __init__(self, download_func=None, settings=None): self.download_func = download_func + self._expects_item = {} if isinstance(settings, dict) or settings is None: settings = Settings(settings) @@ -38,6 +43,9 @@ class MediaPipeline: ) self._handle_statuses(self.allow_redirects) + # Check if deprecated methods are being used and make them compatible + self._make_compatible() + def _handle_statuses(self, allow_redirects): self.handle_httpstatus_list = None if allow_redirects: @@ -53,7 +61,7 @@ class MediaPipeline: 'MYPIPE_IMAGES' """ class_name = self.__class__.__name__ - formatted_key = "{}_{}".format(class_name.upper(), key) + formatted_key = f"{class_name.upper()}_{key}" if ( not base_class_name or class_name == base_class_name @@ -77,11 +85,11 @@ class MediaPipeline: def process_item(self, item, spider): info = self.spiderinfo requests = arg_to_iter(self.get_media_requests(item, info)) - dlist = [self._process_request(r, info) for r in requests] - dfd = DeferredList(dlist, consumeErrors=1) + dlist = [self._process_request(r, info, item) for r in requests] + dfd = DeferredList(dlist, consumeErrors=True) return dfd.addCallback(self.item_completed, item, info) - def _process_request(self, request, info): + def _process_request(self, request, info, item): fp = request_fingerprint(request) cb = request.callback or (lambda _: _) eb = request.errback @@ -102,34 +110,72 @@ class MediaPipeline: # Download request checking media_to_download hook output first info.downloading.add(fp) - dfd = mustbe_deferred(self.media_to_download, request, info) - dfd.addCallback(self._check_media_to_download, request, info) + dfd = mustbe_deferred(self.media_to_download, request, info, item=item) + dfd.addCallback(self._check_media_to_download, request, info, item=item) dfd.addBoth(self._cache_result_and_execute_waiters, fp, info) dfd.addErrback(lambda f: logger.error( f.value, exc_info=failure_to_exc_info(f), extra={'spider': info.spider}) ) return dfd.addBoth(lambda _: wad) # it must return wad at last + def _make_compatible(self): + """Make overridable methods of MediaPipeline and subclasses backwards compatible""" + methods = [ + "file_path", "media_to_download", "media_downloaded", + "file_downloaded", "image_downloaded", "get_images" + ] + + for method_name in methods: + method = getattr(self, method_name, None) + if callable(method): + setattr(self, method_name, self._compatible(method)) + + def _compatible(self, func): + """Wrapper for overridable methods to allow backwards compatibility""" + self._check_signature(func) + + @functools.wraps(func) + def wrapper(*args, **kwargs): + if self._expects_item[func.__name__]: + return func(*args, **kwargs) + + kwargs.pop('item', None) + return func(*args, **kwargs) + + return wrapper + + def _check_signature(self, func): + sig = signature(func) + self._expects_item[func.__name__] = True + + if 'item' not in sig.parameters: + old_params = str(sig)[1:-1] + new_params = old_params + ", *, item=None" + warn(f'{func.__name__}(self, {old_params}) is deprecated, ' + f'please use {func.__name__}(self, {new_params})', + ScrapyDeprecationWarning, stacklevel=2) + self._expects_item[func.__name__] = False + def _modify_media_request(self, request): if self.handle_httpstatus_list: request.meta['handle_httpstatus_list'] = self.handle_httpstatus_list else: request.meta['handle_httpstatus_all'] = True - def _check_media_to_download(self, result, request, info): + def _check_media_to_download(self, result, request, info, item): if result is not None: return result if self.download_func: # this ugly code was left only to support tests. TODO: remove dfd = mustbe_deferred(self.download_func, request, info.spider) dfd.addCallbacks( - callback=self.media_downloaded, callbackArgs=(request, info), + callback=self.media_downloaded, callbackArgs=(request, info), callbackKeywords={'item': item}, errback=self.media_failed, errbackArgs=(request, info)) else: self._modify_media_request(request) - dfd = self.crawler.engine.download(request, info.spider) + dfd = self.crawler.engine.download(request) dfd.addCallbacks( - callback=self.media_downloaded, callbackArgs=(request, info), + callback=self.media_downloaded, callbackArgs=(request, info), callbackKeywords={'item': item}, errback=self.media_failed, errbackArgs=(request, info)) return dfd @@ -171,7 +217,7 @@ class MediaPipeline: defer_result(result).chainDeferred(wad) # Overridable Interface - def media_to_download(self, request, info): + def media_to_download(self, request, info, *, item=None): """Check request before starting download""" pass @@ -179,7 +225,7 @@ class MediaPipeline: """Returns the media requests to download""" pass - def media_downloaded(self, response, request, info): + def media_downloaded(self, response, request, info, *, item=None): """Handler for success downloads""" return response @@ -199,3 +245,7 @@ class MediaPipeline: extra={'spider': info.spider} ) return item + + def file_path(self, request, response=None, info=None, *, item=None): + """Returns the path where downloaded media should be stored""" + pass diff --git a/scrapy/pqueues.py b/scrapy/pqueues.py index e13d389ee..b4b63e7c7 100644 --- a/scrapy/pqueues.py +++ b/scrapy/pqueues.py @@ -3,6 +3,7 @@ import logging from scrapy.utils.misc import create_instance + logger = logging.getLogger(__name__) @@ -17,8 +18,7 @@ def _path_safe(text): >>> _path_safe('some@symbol?').startswith('some_symbol_') True """ - pathable_slot = "".join([c if c.isalnum() or c in '-._' else '_' - for c in text]) + pathable_slot = "".join([c if c.isalnum() or c in '-._' else '_' for c in text]) # as we replace some letters we can get collision for different slots # add we add unique part unique_slot = hashlib.md5(text.encode('utf8')).hexdigest() @@ -35,6 +35,9 @@ class ScrapyPriorityQueue: * close() * __len__() + Optionally, the queue could provide a ``peek`` method, that should return the + next object to be returned by ``pop``, but without removing it from the queue. + ``__init__`` method of ScrapyPriorityQueue receives a downstream_queue_cls argument, which is a class used to instantiate a new (internal) queue when a new priority is allocated. @@ -70,10 +73,12 @@ class ScrapyPriorityQueue: self.curprio = min(startprios) def qfactory(self, key): - return create_instance(self.downstream_queue_cls, - None, - self.crawler, - self.key + '/' + str(key)) + return create_instance( + self.downstream_queue_cls, + None, + self.crawler, + self.key + '/' + str(key), + ) def priority(self, request): return -request.priority @@ -99,6 +104,18 @@ class ScrapyPriorityQueue: self.curprio = min(prios) if prios else None return m + def peek(self): + """Returns the next object to be returned by :meth:`pop`, + but without removing it from the queue. + + Raises :exc:`NotImplementedError` if the underlying queue class does + not implement a ``peek`` method, which is optional for queues. + """ + if self.curprio is None: + return None + queue = self.queues[self.curprio] + return queue.peek() + def close(self): active = [] for p, q in self.queues.items(): @@ -116,8 +133,7 @@ class DownloaderInterface: self.downloader = crawler.engine.downloader def stats(self, possible_slots): - return [(self._active_downloads(slot), slot) - for slot in possible_slots] + return [(self._active_downloads(slot), slot) for slot in possible_slots] def get_slot_key(self, request): return self.downloader._get_slot_key(request, None) @@ -141,17 +157,16 @@ class DownloaderAwarePriorityQueue: def __init__(self, crawler, downstream_queue_cls, key, slot_startprios=()): if crawler.settings.getint('CONCURRENT_REQUESTS_PER_IP') != 0: - raise ValueError('"%s" does not support CONCURRENT_REQUESTS_PER_IP' - % (self.__class__,)) + raise ValueError(f'"{self.__class__}" does not support CONCURRENT_REQUESTS_PER_IP') if slot_startprios and not isinstance(slot_startprios, dict): raise ValueError("DownloaderAwarePriorityQueue accepts " - "``slot_startprios`` as a dict; %r instance " + "``slot_startprios`` as a dict; " + f"{slot_startprios.__class__!r} instance " "is passed. Most likely, it means the state is" "created by an incompatible priority queue. " "Only a crawl started with the same priority " - "queue class can be resumed." % - slot_startprios.__class__) + "queue class can be resumed.") self._downloader_interface = DownloaderInterface(crawler) self.downstream_queue_cls = downstream_queue_cls @@ -163,10 +178,12 @@ class DownloaderAwarePriorityQueue: self.pqueues[slot] = self.pqfactory(slot, startprios) def pqfactory(self, slot, startprios=()): - return ScrapyPriorityQueue(self.crawler, - self.downstream_queue_cls, - self.key + '/' + _path_safe(slot), - startprios) + return ScrapyPriorityQueue( + self.crawler, + self.downstream_queue_cls, + self.key + '/' + _path_safe(slot), + startprios, + ) def pop(self): stats = self._downloader_interface.stats(self.pqueues) @@ -188,9 +205,22 @@ class DownloaderAwarePriorityQueue: queue = self.pqueues[slot] queue.push(request) + def peek(self): + """Returns the next object to be returned by :meth:`pop`, + but without removing it from the queue. + + Raises :exc:`NotImplementedError` if the underlying queue class does + not implement a ``peek`` method, which is optional for queues. + """ + stats = self._downloader_interface.stats(self.pqueues) + if not stats: + return None + slot = min(stats)[1] + queue = self.pqueues[slot] + return queue.peek() + def close(self): - active = {slot: queue.close() - for slot, queue in self.pqueues.items()} + active = {slot: queue.close() for slot, queue in self.pqueues.items()} self.pqueues.clear() return active diff --git a/scrapy/resolver.py b/scrapy/resolver.py index f69894b1e..0bef555a6 100644 --- a/scrapy/resolver.py +++ b/scrapy/resolver.py @@ -1,6 +1,6 @@ from twisted.internet import defer from twisted.internet.base import ThreadedResolver -from twisted.internet.interfaces import IHostnameResolver, IResolutionReceiver, IResolverSimple +from twisted.internet.interfaces import IHostResolution, IHostnameResolver, IResolutionReceiver, IResolverSimple from zope.interface.declarations import implementer, provider from scrapy.utils.datatypes import LocalCache @@ -17,7 +17,7 @@ class CachingThreadedResolver(ThreadedResolver): """ def __init__(self, reactor, cache_size, timeout): - super(CachingThreadedResolver, self).__init__(reactor) + super().__init__(reactor) dnscache.limit = cache_size self.timeout = timeout @@ -40,7 +40,7 @@ class CachingThreadedResolver(ThreadedResolver): # so the input argument above is simply overridden # to enforce Scrapy's DNS_TIMEOUT setting's value timeout = (self.timeout,) - d = super(CachingThreadedResolver, self).getHostByName(name, timeout) + d = super().getHostByName(name, timeout) if dnscache.limit: d.addCallback(self._cache_result, name) return d @@ -50,6 +50,36 @@ class CachingThreadedResolver(ThreadedResolver): return result +@implementer(IHostResolution) +class HostResolution: + def __init__(self, name): + self.name = name + + def cancel(self): + raise NotImplementedError() + + +@provider(IResolutionReceiver) +class _CachingResolutionReceiver: + def __init__(self, resolutionReceiver, hostName): + self.resolutionReceiver = resolutionReceiver + self.hostName = hostName + self.addresses = [] + + def resolutionBegan(self, resolution): + self.resolutionReceiver.resolutionBegan(resolution) + self.resolution = resolution + + def addressResolved(self, address): + self.resolutionReceiver.addressResolved(address) + self.addresses.append(address) + + def resolutionComplete(self): + self.resolutionReceiver.resolutionComplete() + if self.addresses: + dnscache[self.hostName] = self.addresses + + @implementer(IHostnameResolver) class CachingHostnameResolver: """ @@ -73,33 +103,22 @@ class CachingHostnameResolver: def install_on_reactor(self): self.reactor.installNameResolver(self) - def resolveHostName(self, resolutionReceiver, hostName, portNumber=0, - addressTypes=None, transportSemantics='TCP'): - - @provider(IResolutionReceiver) - class CachingResolutionReceiver(resolutionReceiver): - - def resolutionBegan(self, resolution): - super(CachingResolutionReceiver, self).resolutionBegan(resolution) - self.resolution = resolution - self.resolved = False - - def addressResolved(self, address): - super(CachingResolutionReceiver, self).addressResolved(address) - self.resolved = True - - def resolutionComplete(self): - super(CachingResolutionReceiver, self).resolutionComplete() - if self.resolved: - dnscache[hostName] = self.resolution - + def resolveHostName( + self, resolutionReceiver, hostName, portNumber=0, addressTypes=None, transportSemantics="TCP" + ): try: - return dnscache[hostName] + addresses = dnscache[hostName] except KeyError: return self.original_resolver.resolveHostName( - CachingResolutionReceiver(), + _CachingResolutionReceiver(resolutionReceiver, hostName), hostName, portNumber, addressTypes, - transportSemantics + transportSemantics, ) + else: + resolutionReceiver.resolutionBegan(HostResolution(hostName)) + for addr in addresses: + resolutionReceiver.addressResolved(addr) + resolutionReceiver.resolutionComplete() + return resolutionReceiver diff --git a/scrapy/responsetypes.py b/scrapy/responsetypes.py index d207088e6..6ed9f8b8f 100644 --- a/scrapy/responsetypes.py +++ b/scrapy/responsetypes.py @@ -45,7 +45,7 @@ class ResponseTypes: elif mimetype in self.classes: return self.classes[mimetype] else: - basetype = "%s/*" % mimetype.split('/')[0] + basetype = f"{mimetype.split('/')[0]}/*" return self.classes.get(basetype, Response) def from_content_type(self, content_type, content_encoding=None): diff --git a/scrapy/robotstxt.py b/scrapy/robotstxt.py index 52cf09844..f8649e56b 100644 --- a/scrapy/robotstxt.py +++ b/scrapy/robotstxt.py @@ -47,10 +47,10 @@ class RobotParser(metaclass=ABCMeta): """Return ``True`` if ``user_agent`` is allowed to crawl ``url``, otherwise return ``False``. :param url: Absolute URL - :type url: string + :type url: str :param user_agent: User agent - :type user_agent: string + :type user_agent: str """ pass diff --git a/scrapy/selector/unified.py b/scrapy/selector/unified.py index 85a9bb526..08f08e8d7 100644 --- a/scrapy/selector/unified.py +++ b/scrapy/selector/unified.py @@ -66,10 +66,10 @@ class Selector(_ParselSelector, object_ref): def __init__(self, response=None, text=None, type=None, root=None, **kwargs): if response is not None and text is not None: - raise ValueError('%s.__init__() received both response and text' - % self.__class__.__name__) + raise ValueError(f'{self.__class__.__name__}.__init__() received ' + 'both response and text') - st = _st(response, type or self._default_type) + st = _st(response, type) if text is not None: response = _response_from_text(text, st) @@ -79,4 +79,4 @@ class Selector(_ParselSelector, object_ref): kwargs.setdefault('base_url', response.url) self.response = response - super(Selector, self).__init__(text=text, type=st, root=root, **kwargs) + super().__init__(text=text, type=st, root=root, **kwargs) diff --git a/scrapy/settings/__init__.py b/scrapy/settings/__init__.py index b9a13c018..1fe1e6fd1 100644 --- a/scrapy/settings/__init__.py +++ b/scrapy/settings/__init__.py @@ -52,8 +52,7 @@ class SettingsAttribute: self.priority = priority def __str__(self): - return "".format(self=self) + return f"" __repr__ = __str__ @@ -83,7 +82,8 @@ class BaseSettings(MutableMapping): def __init__(self, values=None, priority='project'): self.frozen = False self.attributes = {} - self.update(values, priority) + if values: + self.update(values, priority) def __getitem__(self, opt_name): if opt_name not in self: @@ -98,10 +98,10 @@ class BaseSettings(MutableMapping): Get a setting value without affecting its original type. :param name: the setting name - :type name: string + :type name: str :param default: the value to return if no setting is found - :type default: any + :type default: object """ return self[name] if self[name] is not None else default @@ -116,10 +116,10 @@ class BaseSettings(MutableMapping): ``'0'`` will return ``False`` when using this method. :param name: the setting name - :type name: string + :type name: str :param default: the value to return if no setting is found - :type default: any + :type default: object """ got = self.get(name, default) try: @@ -138,10 +138,10 @@ class BaseSettings(MutableMapping): Get a setting value as an int. :param name: the setting name - :type name: string + :type name: str :param default: the value to return if no setting is found - :type default: any + :type default: object """ return int(self.get(name, default)) @@ -150,10 +150,10 @@ class BaseSettings(MutableMapping): Get a setting value as a float. :param name: the setting name - :type name: string + :type name: str :param default: the value to return if no setting is found - :type default: any + :type default: object """ return float(self.get(name, default)) @@ -166,10 +166,10 @@ class BaseSettings(MutableMapping): ``'one,two'`` will return a list ['one', 'two'] when using this method. :param name: the setting name - :type name: string + :type name: str :param default: the value to return if no setting is found - :type default: any + :type default: object """ value = self.get(name, default or []) if isinstance(value, str): @@ -187,10 +187,10 @@ class BaseSettings(MutableMapping): and losing all information about priority and mutability. :param name: the setting name - :type name: string + :type name: str :param default: the value to return if no setting is found - :type default: any + :type default: object """ value = self.get(name, default or {}) if isinstance(value, str): @@ -202,7 +202,7 @@ class BaseSettings(MutableMapping): counterpart. :param name: name of the dictionary-like setting - :type name: string + :type name: str """ compbs = BaseSettings() compbs.update(self[name + '_BASE']) @@ -215,7 +215,7 @@ class BaseSettings(MutableMapping): the given ``name`` does not exist. :param name: the setting name - :type name: string + :type name: str """ if name not in self: return None @@ -245,14 +245,14 @@ class BaseSettings(MutableMapping): otherwise they won't have any effect. :param name: the setting name - :type name: string + :type name: str :param value: the value to associate with the setting - :type value: any + :type value: object :param priority: the priority of the setting. Should be a key of :attr:`~scrapy.settings.SETTINGS_PRIORITIES` or an integer - :type priority: string or int + :type priority: str or int """ self._assert_mutability() priority = get_settings_priority(priority) @@ -276,11 +276,11 @@ class BaseSettings(MutableMapping): uppercase variable of ``module`` with the provided ``priority``. :param module: the module or the path of the module - :type module: module object or string + :type module: types.ModuleType or str :param priority: the priority of the settings. Should be a key of :attr:`~scrapy.settings.SETTINGS_PRIORITIES` or an integer - :type priority: string or int + :type priority: str or int """ self._assert_mutability() if isinstance(module, str): @@ -309,7 +309,7 @@ class BaseSettings(MutableMapping): :param priority: the priority of the settings. Should be a key of :attr:`~scrapy.settings.SETTINGS_PRIORITIES` or an integer - :type priority: string or int + :type priority: str or int """ self._assert_mutability() if isinstance(values, str): @@ -440,7 +440,7 @@ class Settings(BaseSettings): # Do not pass kwarg values here. We don't want to promote user-defined # dicts, and we want to update, not replace, default dicts with the # values given by the user - super(Settings, self).__init__() + super().__init__() self.setmodule(default_settings, 'default') # Promote default dictionaries to BaseSettings instances for per-key # priorities diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index 077317c81..4ef330dd2 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -19,6 +19,8 @@ from os.path import join, abspath, dirname AJAXCRAWL_ENABLED = False +ASYNCIO_EVENT_LOOP = None + AUTOTHROTTLE_ENABLED = False AUTOTHROTTLE_DEBUG = False AUTOTHROTTLE_MAX_DELAY = 60.0 @@ -142,10 +144,12 @@ FEED_STORAGES = {} FEED_STORAGES_BASE = { '': 'scrapy.extensions.feedexport.FileFeedStorage', 'file': 'scrapy.extensions.feedexport.FileFeedStorage', - 'stdout': 'scrapy.extensions.feedexport.StdoutFeedStorage', - 's3': 'scrapy.extensions.feedexport.S3FeedStorage', 'ftp': 'scrapy.extensions.feedexport.FTPFeedStorage', + 'gs': 'scrapy.extensions.feedexport.GCSFeedStorage', + 's3': 'scrapy.extensions.feedexport.S3FeedStorage', + 'stdout': 'scrapy.extensions.feedexport.StdoutFeedStorage', } +FEED_EXPORT_BATCH_ITEM_COUNT = 0 FEED_EXPORTERS = {} FEED_EXPORTERS_BASE = { 'json': 'scrapy.exporters.JsonItemExporter', @@ -159,6 +163,7 @@ FEED_EXPORTERS_BASE = { FEED_EXPORT_INDENT = 0 FEED_STORAGE_FTP_ACTIVE = False +FEED_STORAGE_GCS_ACL = '' FEED_STORAGE_S3_ACL = '' FILES_STORE_S3_ACL = 'private' @@ -168,6 +173,8 @@ FTP_USER = 'anonymous' FTP_PASSWORD = 'guest' FTP_PASSIVE_MODE = True +GCS_PROJECT_ID = None + HTTPCACHE_ENABLED = False HTTPCACHE_DIR = 'httpcache' HTTPCACHE_IGNORE_MISSING = False @@ -280,7 +287,7 @@ TEMPLATES_DIR = abspath(join(dirname(__file__), '..', 'templates')) URLLENGTH_LIMIT = 2083 -USER_AGENT = 'Scrapy/%s (+https://scrapy.org)' % import_module('scrapy').__version__ +USER_AGENT = f'Scrapy/{import_module("scrapy").__version__} (+https://scrapy.org)' TELNETCONSOLE_ENABLED = 1 TELNETCONSOLE_PORT = [6023, 6073] diff --git a/scrapy/shell.py b/scrapy/shell.py index 3ff5a8ad8..f2dff2ae3 100644 --- a/scrapy/shell.py +++ b/scrapy/shell.py @@ -6,6 +6,7 @@ See documentation in docs/topics/shell.rst import os import signal +from itemadapter import is_item from twisted.internet import threads, defer from twisted.python import threadable from w3lib.url import any_to_uri @@ -13,20 +14,18 @@ from w3lib.url import any_to_uri from scrapy.crawler import Crawler from scrapy.exceptions import IgnoreRequest from scrapy.http import Request, Response -from scrapy.item import _BaseItem from scrapy.settings import Settings from scrapy.spiders import Spider -from scrapy.utils.console import start_python_console +from scrapy.utils.conf import get_config +from scrapy.utils.console import DEFAULT_PYTHON_SHELLS, start_python_console from scrapy.utils.datatypes import SequenceExclude from scrapy.utils.misc import load_object from scrapy.utils.response import open_in_browser -from scrapy.utils.conf import get_config -from scrapy.utils.console import DEFAULT_PYTHON_SHELLS class Shell: - relevant_classes = (Crawler, Spider, Request, Response, _BaseItem, Settings) + relevant_classes = (Crawler, Spider, Request, Response, Settings) def __init__(self, crawler, update_vars=None, code=None): self.crawler = crawler @@ -80,7 +79,7 @@ class Shell: spider = self._open_spider(request, spider) d = _request_deferred(request) d.addCallback(lambda x: (x, spider)) - self.crawler.engine.crawl(request, spider) + self.crawler.engine.crawl(request) return d def _open_spider(self, request, spider): @@ -141,7 +140,7 @@ class Shell: b.append(" scrapy scrapy module (contains scrapy.Request, scrapy.Selector, etc)") for k, v in sorted(self.vars.items()): if self._is_relevant(v): - b.append(" %-10s %s" % (k, v)) + b.append(f" {k:<10} {v}") b.append("Useful shortcuts:") if self.inthread: b.append(" fetch(url[, redirect=True]) " @@ -151,10 +150,10 @@ class Shell: b.append(" shelp() Shell help (print this help)") b.append(" view(response) View response in a browser") - return "\n".join("[s] %s" % line for line in b) + return "\n".join(f"[s] {line}" for line in b) def _is_relevant(self, value): - return isinstance(value, self.relevant_classes) + return isinstance(value, self.relevant_classes) or is_item(value) def inspect_response(response, spider): diff --git a/scrapy/signalmanager.py b/scrapy/signalmanager.py index 54eb7cfa3..ac4044c64 100644 --- a/scrapy/signalmanager.py +++ b/scrapy/signalmanager.py @@ -16,7 +16,7 @@ class SignalManager: section. :param receiver: the function to be connected - :type receiver: callable + :type receiver: collections.abc.Callable :param signal: the signal to connect to :type signal: object diff --git a/scrapy/signals.py b/scrapy/signals.py index c61ae6ec3..8cf2a4d93 100644 --- a/scrapy/signals.py +++ b/scrapy/signals.py @@ -17,6 +17,7 @@ request_reached_downloader = object() request_left_downloader = object() response_received = object() response_downloaded = object() +headers_received = object() bytes_received = object() item_scraped = object() item_dropped = object() diff --git a/scrapy/spiderloader.py b/scrapy/spiderloader.py index db4193430..04fda311f 100644 --- a/scrapy/spiderloader.py +++ b/scrapy/spiderloader.py @@ -27,7 +27,7 @@ class SpiderLoader: dupes = [] for name, locations in self._found.items(): dupes.extend([ - " {cls} named {name!r} (in {module})".format(module=mod, cls=cls, name=name) + f" {cls} named {name!r} (in {mod})" for mod, cls in locations if len(locations) > 1 ]) @@ -36,7 +36,7 @@ class SpiderLoader: dupes_string = "\n\n".join(dupes) warnings.warn( "There are several spiders with the same name:\n\n" - "{}\n\n This can cause unexpected behavior.".format(dupes_string), + f"{dupes_string}\n\n This can cause unexpected behavior.", category=UserWarning, ) @@ -53,10 +53,9 @@ class SpiderLoader: except ImportError: if self.warn_only: warnings.warn( - "\n{tb}Could not load spiders from module '{modname}'. " - "See above traceback for details.".format( - modname=name, tb=traceback.format_exc() - ), + f"\n{traceback.format_exc()}Could not load spiders " + f"from module '{name}'. " + "See above traceback for details.", category=RuntimeWarning, ) else: @@ -75,7 +74,7 @@ class SpiderLoader: try: return self._spiders[spider_name] except KeyError: - raise KeyError("Spider not found: {}".format(spider_name)) + raise KeyError(f"Spider not found: {spider_name}") def find_by_request(self, request): """ diff --git a/scrapy/spidermiddlewares/depth.py b/scrapy/spidermiddlewares/depth.py index fa7f5bef9..776a6879a 100644 --- a/scrapy/spidermiddlewares/depth.py +++ b/scrapy/spidermiddlewares/depth.py @@ -43,7 +43,7 @@ class DepthMiddleware: return False else: if self.verbose_stats: - self.stats.inc_value('request_depth_count/%s' % depth, + self.stats.inc_value(f'request_depth_count/{depth}', spider=spider) self.stats.max_value('request_depth_max', depth, spider=spider) diff --git a/scrapy/spidermiddlewares/httperror.py b/scrapy/spidermiddlewares/httperror.py index 375042340..9861456de 100644 --- a/scrapy/spidermiddlewares/httperror.py +++ b/scrapy/spidermiddlewares/httperror.py @@ -15,7 +15,7 @@ class HttpError(IgnoreRequest): def __init__(self, response, *args, **kwargs): self.response = response - super(HttpError, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) class HttpErrorMiddleware: @@ -32,7 +32,7 @@ class HttpErrorMiddleware: if 200 <= response.status < 300: # common case return meta = response.meta - if 'handle_httpstatus_all' in meta: + if meta.get('handle_httpstatus_all', False): return if 'handle_httpstatus_list' in meta: allowed_statuses = meta['handle_httpstatus_list'] @@ -48,7 +48,7 @@ class HttpErrorMiddleware: if isinstance(exception, HttpError): spider.crawler.stats.inc_value('httperror/response_ignored_count') spider.crawler.stats.inc_value( - 'httperror/response_ignored_status_count/%s' % response.status + f'httperror/response_ignored_status_count/{response.status}' ) logger.info( "Ignoring response %(response)r: HTTP status code is not handled or not allowed", diff --git a/scrapy/spidermiddlewares/offsite.py b/scrapy/spidermiddlewares/offsite.py index a006f3177..6e4efda97 100644 --- a/scrapy/spidermiddlewares/offsite.py +++ b/scrapy/spidermiddlewares/offsite.py @@ -61,15 +61,15 @@ class OffsiteMiddleware: continue elif url_pattern.match(domain): message = ("allowed_domains accepts only domains, not URLs. " - "Ignoring URL entry %s in allowed_domains." % domain) + f"Ignoring URL entry {domain} in allowed_domains.") warnings.warn(message, URLWarning) elif port_pattern.search(domain): message = ("allowed_domains accepts only domains without ports. " - "Ignoring entry %s in allowed_domains." % domain) + f"Ignoring entry {domain} in allowed_domains.") warnings.warn(message, PortWarning) else: domains.append(re.escape(domain)) - regex = r'^(.*\.)?(%s)$' % '|'.join(domains) + regex = fr'^(.*\.)?({"|".join(domains)})$' return re.compile(regex) def spider_opened(self, spider): diff --git a/scrapy/spidermiddlewares/referer.py b/scrapy/spidermiddlewares/referer.py index 434067b00..608c0eea5 100644 --- a/scrapy/spidermiddlewares/referer.py +++ b/scrapy/spidermiddlewares/referer.py @@ -3,15 +3,16 @@ RefererMiddleware: populates Request referer field, based on the Response which originated it. """ import warnings +from typing import Tuple from urllib.parse import urlparse from w3lib.url import safe_url_string -from scrapy.http import Request, Response -from scrapy.exceptions import NotConfigured from scrapy import signals -from scrapy.utils.python import to_unicode +from scrapy.exceptions import NotConfigured +from scrapy.http import Request, Response from scrapy.utils.misc import load_object +from scrapy.utils.python import to_unicode from scrapy.utils.url import strip_url @@ -30,7 +31,8 @@ POLICY_SCRAPY_DEFAULT = "scrapy-default" class ReferrerPolicy: - NOREFERRER_SCHEMES = LOCAL_SCHEMES + NOREFERRER_SCHEMES: Tuple[str, ...] = LOCAL_SCHEMES + name: str def referrer(self, response_url, request_url): raise NotImplementedError() @@ -88,7 +90,7 @@ class NoReferrerPolicy(ReferrerPolicy): is to be sent along with requests made from a particular request client to any origin. The header will be omitted entirely. """ - name = POLICY_NO_REFERRER + name: str = POLICY_NO_REFERRER def referrer(self, response_url, request_url): return None @@ -108,7 +110,7 @@ class NoReferrerWhenDowngradePolicy(ReferrerPolicy): This is a user agent's default behavior, if no policy is otherwise specified. """ - name = POLICY_NO_REFERRER_WHEN_DOWNGRADE + name: str = POLICY_NO_REFERRER_WHEN_DOWNGRADE def referrer(self, response_url, request_url): if not self.tls_protected(response_url) or self.tls_protected(request_url): @@ -125,7 +127,7 @@ class SameOriginPolicy(ReferrerPolicy): Cross-origin requests, on the other hand, will contain no referrer information. A Referer HTTP header will not be sent. """ - name = POLICY_SAME_ORIGIN + name: str = POLICY_SAME_ORIGIN def referrer(self, response_url, request_url): if self.origin(response_url) == self.origin(request_url): @@ -141,7 +143,7 @@ class OriginPolicy(ReferrerPolicy): when making both same-origin requests and cross-origin requests from a particular request client. """ - name = POLICY_ORIGIN + name: str = POLICY_ORIGIN def referrer(self, response_url, request_url): return self.origin_referrer(response_url) @@ -160,7 +162,7 @@ class StrictOriginPolicy(ReferrerPolicy): on the other hand, will contain no referrer information. A Referer HTTP header will not be sent. """ - name = POLICY_STRICT_ORIGIN + name: str = POLICY_STRICT_ORIGIN def referrer(self, response_url, request_url): if ( @@ -181,7 +183,7 @@ class OriginWhenCrossOriginPolicy(ReferrerPolicy): is sent as referrer information when making cross-origin requests from a particular request client. """ - name = POLICY_ORIGIN_WHEN_CROSS_ORIGIN + name: str = POLICY_ORIGIN_WHEN_CROSS_ORIGIN def referrer(self, response_url, request_url): origin = self.origin(response_url) @@ -208,7 +210,7 @@ class StrictOriginWhenCrossOriginPolicy(ReferrerPolicy): on the other hand, will contain no referrer information. A Referer HTTP header will not be sent. """ - name = POLICY_STRICT_ORIGIN_WHEN_CROSS_ORIGIN + name: str = POLICY_STRICT_ORIGIN_WHEN_CROSS_ORIGIN def referrer(self, response_url, request_url): origin = self.origin(response_url) @@ -234,7 +236,7 @@ class UnsafeUrlPolicy(ReferrerPolicy): to insecure origins. Carefully consider the impact of setting such a policy for potentially sensitive documents. """ - name = POLICY_UNSAFE_URL + name: str = POLICY_UNSAFE_URL def referrer(self, response_url, request_url): return self.stripped_referrer(response_url) @@ -246,8 +248,8 @@ class DefaultReferrerPolicy(NoReferrerWhenDowngradePolicy): with the addition that "Referer" is not sent if the parent request was using ``file://`` or ``s3://`` scheme. """ - NOREFERRER_SCHEMES = LOCAL_SCHEMES + ('file', 's3') - name = POLICY_SCRAPY_DEFAULT + NOREFERRER_SCHEMES: Tuple[str, ...] = LOCAL_SCHEMES + ('file', 's3') + name: str = POLICY_SCRAPY_DEFAULT _policy_classes = {p.name: p for p in ( @@ -278,7 +280,7 @@ def _load_policy_class(policy, warning_only=False): try: return _policy_classes[policy.lower()] except KeyError: - msg = "Could not load referrer policy %r" % policy + msg = f"Could not load referrer policy {policy!r}" if not warning_only: raise RuntimeError(msg) else: diff --git a/scrapy/spidermiddlewares/urllength.py b/scrapy/spidermiddlewares/urllength.py index 5be1f80cb..450d4ff40 100644 --- a/scrapy/spidermiddlewares/urllength.py +++ b/scrapy/spidermiddlewares/urllength.py @@ -27,9 +27,12 @@ class UrlLengthMiddleware: def process_spider_output(self, response, result, spider): def _filter(request): if isinstance(request, Request) and len(request.url) > self.maxlength: - logger.debug("Ignoring link (url length > %(maxlength)d): %(url)s ", - {'maxlength': self.maxlength, 'url': request.url}, - extra={'spider': spider}) + logger.info( + "Ignoring link (url length > %(maxlength)d): %(url)s ", + {'maxlength': self.maxlength, 'url': request.url}, + extra={'spider': spider} + ) + spider.crawler.stats.inc_value('urllength/request_ignored_count', spider=spider) return False else: return True diff --git a/scrapy/spiders/__init__.py b/scrapy/spiders/__init__.py index 02f87f8f5..c13ba4b3c 100644 --- a/scrapy/spiders/__init__.py +++ b/scrapy/spiders/__init__.py @@ -5,6 +5,7 @@ See documentation in docs/topics/spiders.rst """ import logging import warnings +from typing import Optional from scrapy import signals from scrapy.http import Request @@ -18,14 +19,14 @@ class Spider(object_ref): class. """ - name = None - custom_settings = None + name: Optional[str] = None + custom_settings: Optional[dict] = None def __init__(self, name=None, **kwargs): if name is not None: self.name = name elif not getattr(self, 'name', None): - raise ValueError("%s must have a name" % type(self).__name__) + raise ValueError(f"{type(self).__name__} must have a name") self.__dict__.update(kwargs) if not hasattr(self, 'start_urls'): self.start_urls = [] @@ -66,9 +67,8 @@ class Spider(object_ref): warnings.warn( "Spider.make_requests_from_url method is deprecated; it " "won't be called in future Scrapy releases. Please " - "override Spider.start_requests method instead (see %s.%s)." % ( - cls.__module__, cls.__name__ - ), + "override Spider.start_requests method instead " + f"(see {cls.__module__}.{cls.__name__}).", ) for url in self.start_urls: yield self.make_requests_from_url(url) @@ -86,8 +86,11 @@ class Spider(object_ref): ) return Request(url, dont_filter=True) - def parse(self, response): - raise NotImplementedError('{}.parse callback is not defined'.format(self.__class__.__name__)) + def _parse(self, response, **kwargs): + return self.parse(response, **kwargs) + + def parse(self, response, **kwargs): + raise NotImplementedError(f'{self.__class__.__name__}.parse callback is not defined') @classmethod def update_settings(cls, settings): @@ -104,7 +107,7 @@ class Spider(object_ref): return closed(reason) def __str__(self): - return "<%s %r at 0x%0x>" % (type(self).__name__, self.name, id(self)) + return f"<{type(self).__name__} {self.name!r} at 0x{id(self):0x}>" __repr__ = __str__ diff --git a/scrapy/spiders/crawl.py b/scrapy/spiders/crawl.py index cb021a5a7..1dcf2e6ab 100644 --- a/scrapy/spiders/crawl.py +++ b/scrapy/spiders/crawl.py @@ -6,13 +6,11 @@ See documentation in docs/topics/spiders.rst """ import copy -import warnings +from typing import Sequence -from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.http import Request, HtmlResponse from scrapy.linkextractors import LinkExtractor from scrapy.spiders import Spider -from scrapy.utils.python import get_func_args from scrapy.utils.spider import iterate_spider_output @@ -36,15 +34,22 @@ _default_link_extractor = LinkExtractor() class Rule: - def __init__(self, link_extractor=None, callback=None, cb_kwargs=None, follow=None, - process_links=None, process_request=None, errback=None): + def __init__( + self, + link_extractor=None, + callback=None, + cb_kwargs=None, + follow=None, + process_links=None, + process_request=None, + errback=None, + ): self.link_extractor = link_extractor or _default_link_extractor self.callback = callback self.errback = errback self.cb_kwargs = cb_kwargs or {} self.process_links = process_links or _identity self.process_request = process_request or _identity_process_request - self.process_request_argcount = None self.follow = follow if follow is not None else not callback def _compile(self, spider): @@ -52,36 +57,25 @@ class Rule: self.errback = _get_method(self.errback, spider) self.process_links = _get_method(self.process_links, spider) self.process_request = _get_method(self.process_request, spider) - self.process_request_argcount = len(get_func_args(self.process_request)) - if self.process_request_argcount == 1: - warnings.warn( - "Rule.process_request should accept two arguments " - "(request, response), accepting only one is deprecated", - category=ScrapyDeprecationWarning, - stacklevel=2, - ) - - def _process_request(self, request, response): - """ - Wrapper around the request processing function to maintain backward - compatibility with functions that do not take a Response object - """ - args = [request] if self.process_request_argcount == 1 else [request, response] - return self.process_request(*args) class CrawlSpider(Spider): - rules = () + rules: Sequence[Rule] = () def __init__(self, *a, **kw): - super(CrawlSpider, self).__init__(*a, **kw) + super().__init__(*a, **kw) self._compile_rules() - def parse(self, response): - return self._parse_response(response, self.parse_start_url, cb_kwargs={}, follow=True) + def _parse(self, response, **kwargs): + return self._parse_response( + response=response, + callback=self.parse_start_url, + cb_kwargs=kwargs, + follow=True, + ) - def parse_start_url(self, response): + def parse_start_url(self, response, **kwargs): return [] def process_results(self, response, results): @@ -105,7 +99,7 @@ class CrawlSpider(Spider): for link in rule.process_links(links): seen.add(link) request = self._build_request(rule_index, link) - yield rule._process_request(request, response) + yield rule.process_request(request, response) def _callback(self, response): rule = self._rules[response.meta['rule']] @@ -140,6 +134,6 @@ class CrawlSpider(Spider): @classmethod def from_crawler(cls, crawler, *args, **kwargs): - spider = super(CrawlSpider, cls).from_crawler(crawler, *args, **kwargs) + spider = super().from_crawler(crawler, *args, **kwargs) spider._follow_links = crawler.settings.getbool('CRAWLSPIDER_FOLLOW_LINKS', True) return spider diff --git a/scrapy/spiders/feed.py b/scrapy/spiders/feed.py index a4ff8010d..6ed17e4dd 100644 --- a/scrapy/spiders/feed.py +++ b/scrapy/spiders/feed.py @@ -31,7 +31,7 @@ class XMLFeedSpider(Spider): processing required before returning the results to the framework core, for example setting the item GUIDs. It receives a list of results and the response which originated that results. It must return a list of - results (Items or Requests). + results (items or requests). """ return results @@ -61,7 +61,7 @@ class XMLFeedSpider(Spider): for result_item in self.process_results(response, ret): yield result_item - def parse(self, response): + def _parse(self, response, **kwargs): if not hasattr(self, 'parse_node'): raise NotConfigured('You must define parse_node method in order to scrape this XML feed') @@ -71,11 +71,11 @@ class XMLFeedSpider(Spider): elif self.iterator == 'xml': selector = Selector(response, type='xml') self._register_namespaces(selector) - nodes = selector.xpath('//%s' % self.itertag) + nodes = selector.xpath(f'//{self.itertag}') elif self.iterator == 'html': selector = Selector(response, type='html') self._register_namespaces(selector) - nodes = selector.xpath('//%s' % self.itertag) + nodes = selector.xpath(f'//{self.itertag}') else: raise NotSupported('Unsupported node iterator') @@ -128,7 +128,7 @@ class CSVFeedSpider(Spider): for result_item in self.process_results(response, ret): yield result_item - def parse(self, response): + def _parse(self, response, **kwargs): if not hasattr(self, 'parse_row'): raise NotConfigured('You must define parse_row method in order to scrape this CSV feed') response = self.adapt_response(response) diff --git a/scrapy/spiders/init.py b/scrapy/spiders/init.py index fd41133ea..fe8c94e78 100644 --- a/scrapy/spiders/init.py +++ b/scrapy/spiders/init.py @@ -6,7 +6,7 @@ class InitSpider(Spider): """Base Spider with initialization facilities""" def start_requests(self): - self._postinit_reqs = super(InitSpider, self).start_requests() + self._postinit_reqs = super().start_requests() return iterate_spider_output(self.init_request()) def initialized(self, response=None): diff --git a/scrapy/spiders/sitemap.py b/scrapy/spiders/sitemap.py index c5360bfa7..1f72e76b7 100644 --- a/scrapy/spiders/sitemap.py +++ b/scrapy/spiders/sitemap.py @@ -18,7 +18,7 @@ class SitemapSpider(Spider): sitemap_alternate_links = False def __init__(self, *a, **kw): - super(SitemapSpider, self).__init__(*a, **kw) + super().__init__(*a, **kw) self._cbs = [] for r, c in self.sitemap_rules: if isinstance(c, str): diff --git a/scrapy/squeues.py b/scrapy/squeues.py index c7ad4d53d..dff9b1350 100644 --- a/scrapy/squeues.py +++ b/scrapy/squeues.py @@ -8,7 +8,8 @@ import pickle from queuelib import queue -from scrapy.utils.reqser import request_to_dict, request_from_dict +from scrapy.utils.deprecate import create_deprecated_class +from scrapy.utils.request import request_from_dict def _with_mkdir(queue_class): @@ -19,8 +20,7 @@ def _with_mkdir(queue_class): dirname = os.path.dirname(path) if not os.path.exists(dirname): os.makedirs(dirname, exist_ok=True) - - super(DirectoriesCreated, self).__init__(path, *args, **kwargs) + super().__init__(path, *args, **kwargs) return DirectoriesCreated @@ -31,10 +31,24 @@ def _serializable_queue(queue_class, serialize, deserialize): def push(self, obj): s = serialize(obj) - super(SerializableQueue, self).push(s) + super().push(s) def pop(self): - s = super(SerializableQueue, self).pop() + s = super().pop() + if s: + return deserialize(s) + + def peek(self): + """Returns the next object to be returned by :meth:`pop`, + but without removing it from the queue. + + Raises :exc:`NotImplementedError` if the underlying queue class does + not implement a ``peek`` method, which is optional for queues. + """ + try: + s = super().peek() + except AttributeError as ex: + raise NotImplementedError("The underlying queue class does not implement 'peek'") from ex if s: return deserialize(s) @@ -47,24 +61,33 @@ def _scrapy_serialization_queue(queue_class): def __init__(self, crawler, key): self.spider = crawler.spider - super(ScrapyRequestQueue, self).__init__(key) + super().__init__(key) @classmethod def from_crawler(cls, crawler, key, *args, **kwargs): return cls(crawler, key) def push(self, request): - request = request_to_dict(request, self.spider) - return super(ScrapyRequestQueue, self).push(request) + request = request.to_dict(spider=self.spider) + return super().push(request) def pop(self): - request = super(ScrapyRequestQueue, self).pop() - + request = super().pop() if not request: return None + return request_from_dict(request, spider=self.spider) - request = request_from_dict(request, self.spider) - return request + def peek(self): + """Returns the next object to be returned by :meth:`pop`, + but without removing it from the queue. + + Raises :exc:`NotImplementedError` if the underlying queue class does + not implement a ``peek`` method, which is optional for queues. + """ + request = super().peek() + if not request: + return None + return request_from_dict(request, spider=self.spider) return ScrapyRequestQueue @@ -76,6 +99,19 @@ def _scrapy_non_serialization_queue(queue_class): def from_crawler(cls, crawler, *args, **kwargs): return cls() + def peek(self): + """Returns the next object to be returned by :meth:`pop`, + but without removing it from the queue. + + Raises :exc:`NotImplementedError` if the underlying queue class does + not implement a ``peek`` method, which is optional for queues. + """ + try: + s = super().peek() + except AttributeError as ex: + raise NotImplementedError("The underlying queue class does not implement 'peek'") from ex + return s + return ScrapyRequestQueue @@ -88,38 +124,60 @@ def _pickle_serialize(obj): raise ValueError(str(e)) from e -PickleFifoDiskQueueNonRequest = _serializable_queue( +_PickleFifoSerializationDiskQueue = _serializable_queue( _with_mkdir(queue.FifoDiskQueue), _pickle_serialize, pickle.loads ) -PickleLifoDiskQueueNonRequest = _serializable_queue( +_PickleLifoSerializationDiskQueue = _serializable_queue( _with_mkdir(queue.LifoDiskQueue), _pickle_serialize, pickle.loads ) -MarshalFifoDiskQueueNonRequest = _serializable_queue( +_MarshalFifoSerializationDiskQueue = _serializable_queue( _with_mkdir(queue.FifoDiskQueue), marshal.dumps, marshal.loads ) -MarshalLifoDiskQueueNonRequest = _serializable_queue( +_MarshalLifoSerializationDiskQueue = _serializable_queue( _with_mkdir(queue.LifoDiskQueue), marshal.dumps, marshal.loads ) -PickleFifoDiskQueue = _scrapy_serialization_queue( - PickleFifoDiskQueueNonRequest -) -PickleLifoDiskQueue = _scrapy_serialization_queue( - PickleLifoDiskQueueNonRequest -) -MarshalFifoDiskQueue = _scrapy_serialization_queue( - MarshalFifoDiskQueueNonRequest -) -MarshalLifoDiskQueue = _scrapy_serialization_queue( - MarshalLifoDiskQueueNonRequest -) +# public queue classes +PickleFifoDiskQueue = _scrapy_serialization_queue(_PickleFifoSerializationDiskQueue) +PickleLifoDiskQueue = _scrapy_serialization_queue(_PickleLifoSerializationDiskQueue) +MarshalFifoDiskQueue = _scrapy_serialization_queue(_MarshalFifoSerializationDiskQueue) +MarshalLifoDiskQueue = _scrapy_serialization_queue(_MarshalLifoSerializationDiskQueue) FifoMemoryQueue = _scrapy_non_serialization_queue(queue.FifoMemoryQueue) LifoMemoryQueue = _scrapy_non_serialization_queue(queue.LifoMemoryQueue) + + +# deprecated queue classes +_subclass_warn_message = "{cls} inherits from deprecated class {old}" +_instance_warn_message = "{cls} is deprecated" +PickleFifoDiskQueueNonRequest = create_deprecated_class( + name="PickleFifoDiskQueueNonRequest", + new_class=_PickleFifoSerializationDiskQueue, + subclass_warn_message=_subclass_warn_message, + instance_warn_message=_instance_warn_message, +) +PickleLifoDiskQueueNonRequest = create_deprecated_class( + name="PickleLifoDiskQueueNonRequest", + new_class=_PickleLifoSerializationDiskQueue, + subclass_warn_message=_subclass_warn_message, + instance_warn_message=_instance_warn_message, +) +MarshalFifoDiskQueueNonRequest = create_deprecated_class( + name="MarshalFifoDiskQueueNonRequest", + new_class=_MarshalFifoSerializationDiskQueue, + subclass_warn_message=_subclass_warn_message, + instance_warn_message=_instance_warn_message, +) +MarshalLifoDiskQueueNonRequest = create_deprecated_class( + name="MarshalLifoDiskQueueNonRequest", + new_class=_MarshalLifoSerializationDiskQueue, + subclass_warn_message=_subclass_warn_message, + instance_warn_message=_instance_warn_message, +) diff --git a/scrapy/statscollectors.py b/scrapy/statscollectors.py index 579c60180..ba7d1a6bf 100644 --- a/scrapy/statscollectors.py +++ b/scrapy/statscollectors.py @@ -54,7 +54,7 @@ class StatsCollector: class MemoryStatsCollector(StatsCollector): def __init__(self, crawler): - super(MemoryStatsCollector, self).__init__(crawler) + super().__init__(crawler) self.spider_stats = {} def _persist_stats(self, stats, spider): diff --git a/scrapy/templates/project/module/middlewares.py.tmpl b/scrapy/templates/project/module/middlewares.py.tmpl index 6490f52a7..bd09890fe 100644 --- a/scrapy/templates/project/module/middlewares.py.tmpl +++ b/scrapy/templates/project/module/middlewares.py.tmpl @@ -5,6 +5,9 @@ from scrapy import signals +# useful for handling different item types with a single interface +from itemadapter import is_item, ItemAdapter + class ${ProjectName}SpiderMiddleware: # Not all methods need to be defined. If a method is not defined, @@ -29,7 +32,7 @@ class ${ProjectName}SpiderMiddleware: # Called with the results returned from the Spider, after # it has processed the response. - # Must return an iterable of Request, dict or Item objects. + # Must return an iterable of Request, or item objects. for i in result: yield i @@ -37,8 +40,7 @@ class ${ProjectName}SpiderMiddleware: # Called when a spider or process_spider_input() method # (from other spider middleware) raises an exception. - # Should return either None or an iterable of Request, dict - # or Item objects. + # Should return either None or an iterable of Request or item objects. pass def process_start_requests(self, start_requests, spider): diff --git a/scrapy/templates/project/module/pipelines.py.tmpl b/scrapy/templates/project/module/pipelines.py.tmpl index ce0edd335..e845f43e9 100644 --- a/scrapy/templates/project/module/pipelines.py.tmpl +++ b/scrapy/templates/project/module/pipelines.py.tmpl @@ -4,6 +4,10 @@ # See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html +# useful for handling different item types with a single interface +from itemadapter import ItemAdapter + + class ${ProjectName}Pipeline: def process_item(self, item, spider): return item diff --git a/scrapy/utils/asyncgen.py b/scrapy/utils/asyncgen.py new file mode 100644 index 000000000..c290e376c --- /dev/null +++ b/scrapy/utils/asyncgen.py @@ -0,0 +1,8 @@ +from collections.abc import AsyncIterable + + +async def collect_asyncgen(result: AsyncIterable): + results = [] + async for x in result: + results.append(x) + return results diff --git a/scrapy/utils/benchserver.py b/scrapy/utils/benchserver.py index 9d8d64612..86238c4cd 100644 --- a/scrapy/utils/benchserver.py +++ b/scrapy/utils/benchserver.py @@ -21,15 +21,14 @@ class Root(Resource): for nl in nlist: args['n'] = nl argstr = urlencode(args, doseq=True) - request.write("follow {1}
    " - .format(argstr, nl).encode('utf8')) + request.write(f"follow {nl}
    " + .encode('utf8')) request.write(b"") return b'' def _getarg(request, name, default=None, type=str): - return type(request.args[name][0]) \ - if name in request.args else default + return type(request.args[name][0]) if name in request.args else default if __name__ == '__main__': @@ -40,6 +39,6 @@ if __name__ == '__main__': def _print_listening(): httpHost = httpPort.getHost() - print("Bench server at http://{}:{}".format(httpHost.host, httpHost.port)) + print(f"Bench server at http://{httpHost.host}:{httpHost.port}") reactor.callWhenRunning(_print_listening) reactor.run() diff --git a/scrapy/utils/boto.py b/scrapy/utils/boto.py index 12321caa5..3374c57c7 100644 --- a/scrapy/utils/boto.py +++ b/scrapy/utils/boto.py @@ -1,11 +1,32 @@ """Boto/botocore helpers""" +import warnings -from scrapy.exceptions import NotConfigured +from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning def is_botocore(): + """ Returns True if botocore is available, otherwise raises NotConfigured. Never returns False. + + Previously, when boto was supported in addition to botocore, this returned False if boto was available + but botocore wasn't. + """ + message = ( + 'is_botocore() is deprecated and always returns True or raises an Exception, ' + 'so it cannot be used for checking if boto is available instead of botocore. ' + 'You can use scrapy.utils.boto.is_botocore_available() to check if botocore ' + 'is available.' + ) + warnings.warn(message, ScrapyDeprecationWarning, stacklevel=2) try: import botocore # noqa: F401 return True except ImportError: raise NotConfigured('missing botocore library') + + +def is_botocore_available(): + try: + import botocore # noqa: F401 + return True + except ImportError: + return False diff --git a/scrapy/utils/conf.py b/scrapy/utils/conf.py index 5921f82bf..b904c4a03 100644 --- a/scrapy/utils/conf.py +++ b/scrapy/utils/conf.py @@ -17,8 +17,8 @@ def build_component_list(compdict, custom=None, convert=update_classpath): def _check_components(complist): if len({convert(c) for c in complist}) != len(complist): - raise ValueError('Some paths in {!r} convert to the same object, ' - 'please update your settings'.format(complist)) + raise ValueError(f'Some paths in {complist!r} convert to the same object, ' + 'please update your settings') def _map_keys(compdict): if isinstance(compdict, BaseSettings): @@ -26,9 +26,10 @@ def build_component_list(compdict, custom=None, convert=update_classpath): for k, v in compdict.items(): prio = compdict.getpriority(k) if compbs.getpriority(convert(k)) == prio: - raise ValueError('Some paths in {!r} convert to the same ' + raise ValueError(f'Some paths in {list(compdict.keys())!r} ' + 'convert to the same ' 'object, please update your settings' - ''.format(list(compdict.keys()))) + ) else: compbs.set(convert(k), v, priority=prio) return compbs @@ -40,8 +41,8 @@ def build_component_list(compdict, custom=None, convert=update_classpath): """Fail if a value in the components dict is not a real number or None.""" for name, value in compdict.items(): if value is not None and not isinstance(value, numbers.Real): - raise ValueError('Invalid value {} for component {}, please provide ' - 'a real number or None instead'.format(value, name)) + raise ValueError(f'Invalid value {value} for component {name}, ' + 'please provide a real number or None instead') # BEGIN Backward compatibility for old (base, custom) call signature if isinstance(custom, (list, tuple)): @@ -101,11 +102,13 @@ def get_config(use_closest=True): def get_sources(use_closest=True): - xdg_config_home = os.environ.get('XDG_CONFIG_HOME') or \ - os.path.expanduser('~/.config') - sources = ['/etc/scrapy.cfg', r'c:\scrapy\scrapy.cfg', - xdg_config_home + '/scrapy.cfg', - os.path.expanduser('~/.scrapy.cfg')] + xdg_config_home = os.environ.get('XDG_CONFIG_HOME') or os.path.expanduser('~/.config') + sources = [ + '/etc/scrapy.cfg', + r'c:\scrapy\scrapy.cfg', + xdg_config_home + '/scrapy.cfg', + os.path.expanduser('~/.scrapy.cfg'), + ] if use_closest: sources.append(closest_scrapy_cfg()) return sources @@ -113,10 +116,12 @@ def get_sources(use_closest=True): def feed_complete_default_values_from_settings(feed, settings): out = feed.copy() + out.setdefault("batch_item_count", settings.getint('FEED_EXPORT_BATCH_ITEM_COUNT')) out.setdefault("encoding", settings["FEED_EXPORT_ENCODING"]) out.setdefault("fields", settings.getlist("FEED_EXPORT_FIELDS") or None) out.setdefault("store_empty", settings.getbool("FEED_STORE_EMPTY")) out.setdefault("uri_params", settings["FEED_URI_PARAMS"]) + out.setdefault("item_export_kwargs", dict()) if settings["FEED_EXPORT_INDENT"] is None: out.setdefault("indent", None) else: @@ -124,7 +129,8 @@ def feed_complete_default_values_from_settings(feed, settings): return out -def feed_process_params_from_cli(settings, output, output_format=None): +def feed_process_params_from_cli(settings, output, output_format=None, + overwrite_output=None): """ Receives feed export params (from the 'crawl' or 'runspider' commands), checks for inconsistencies in their quantities and returns a dictionary @@ -136,22 +142,37 @@ def feed_process_params_from_cli(settings, output, output_format=None): def check_valid_format(output_format): if output_format not in valid_output_formats: - raise UsageError("Unrecognized output format '%s', set one after a" - " colon using the -o option (i.e. -o :)" - " or as a file extension, from the supported list %s" % - (output_format, tuple(valid_output_formats))) + raise UsageError( + f"Unrecognized output format '{output_format}'. " + f"Set a supported one ({tuple(valid_output_formats)}) " + "after a colon at the end of the output URI (i.e. -o/-O " + ":) or as a file extension." + ) + + overwrite = False + if overwrite_output: + if output: + raise UsageError( + "Please use only one of -o/--output and -O/--overwrite-output" + ) + output = overwrite_output + overwrite = True if output_format: if len(output) == 1: check_valid_format(output_format) - warnings.warn('The -t command line option is deprecated in favor' - ' of specifying the output format within the -o' - ' option, please check the -o option docs for more details', - category=ScrapyDeprecationWarning, stacklevel=2) + message = ( + 'The -t command line option is deprecated in favor of ' + 'specifying the output format within the output URI. See the ' + 'documentation of the -o and -O options for more information.', + ) + warnings.warn(message, ScrapyDeprecationWarning, stacklevel=2) return {output[0]: {'format': output_format}} else: - raise UsageError('The -t command line option cannot be used if multiple' - ' output files are specified with the -o option') + raise UsageError( + 'The -t command-line option cannot be used if multiple output ' + 'URIs are specified' + ) result = {} for element in output: @@ -165,8 +186,10 @@ def feed_process_params_from_cli(settings, output, output_format=None): feed_uri = 'stdout:' check_valid_format(feed_format) result[feed_uri] = {'format': feed_format} + if overwrite: + result[feed_uri]['overwrite'] = True - # FEEDS setting should take precedence over the -o and -t CLI options + # FEEDS setting should take precedence over the matching CLI options result.update(settings.getdict('FEEDS')) return result diff --git a/scrapy/utils/curl.py b/scrapy/utils/curl.py index 16639356e..74f82ad75 100644 --- a/scrapy/utils/curl.py +++ b/scrapy/utils/curl.py @@ -9,16 +9,15 @@ from w3lib.http import basic_auth_header class CurlParser(argparse.ArgumentParser): def error(self, message): - error_msg = \ - 'There was an error parsing the curl command: {}'.format(message) + error_msg = f'There was an error parsing the curl command: {message}' raise ValueError(error_msg) curl_parser = CurlParser() curl_parser.add_argument('url') curl_parser.add_argument('-H', '--header', dest='headers', action='append') -curl_parser.add_argument('-X', '--request', dest='method', default='get') -curl_parser.add_argument('-d', '--data', dest='data') +curl_parser.add_argument('-X', '--request', dest='method') +curl_parser.add_argument('-d', '--data', '--data-raw', dest='data') curl_parser.add_argument('-u', '--user', dest='auth') @@ -35,39 +34,7 @@ for argument in safe_to_ignore_arguments: curl_parser.add_argument(*argument, action='store_true') -def curl_to_request_kwargs(curl_command, ignore_unknown_options=True): - """Convert a cURL command syntax to Request kwargs. - - :param str curl_command: string containing the curl command - :param bool ignore_unknown_options: If true, only a warning is emitted when - cURL options are unknown. Otherwise raises an error. (default: True) - :return: dictionary of Request kwargs - """ - - curl_args = split(curl_command) - - if curl_args[0] != 'curl': - raise ValueError('A curl command must start with "curl"') - - parsed_args, argv = curl_parser.parse_known_args(curl_args[1:]) - - if argv: - msg = 'Unrecognized options: {}'.format(', '.join(argv)) - if ignore_unknown_options: - warnings.warn(msg) - else: - raise ValueError(msg) - - url = parsed_args.url - - # curl automatically prepends 'http' if the scheme is missing, but Request - # needs the scheme to work - parsed_url = urlparse(url) - if not parsed_url.scheme: - url = 'http://' + url - - result = {'method': parsed_args.method.upper(), 'url': url} - +def _parse_headers_and_cookies(parsed_args): headers = [] cookies = {} for header in parsed_args.headers or (): @@ -84,11 +51,56 @@ def curl_to_request_kwargs(curl_command, ignore_unknown_options=True): user, password = parsed_args.auth.split(':', 1) headers.append(('Authorization', basic_auth_header(user, password))) + return headers, cookies + + +def curl_to_request_kwargs(curl_command: str, ignore_unknown_options: bool = True) -> dict: + """Convert a cURL command syntax to Request kwargs. + + :param str curl_command: string containing the curl command + :param bool ignore_unknown_options: If true, only a warning is emitted when + cURL options are unknown. Otherwise + raises an error. (default: True) + :return: dictionary of Request kwargs + """ + + curl_args = split(curl_command) + + if curl_args[0] != 'curl': + raise ValueError('A curl command must start with "curl"') + + parsed_args, argv = curl_parser.parse_known_args(curl_args[1:]) + + if argv: + msg = f'Unrecognized options: {", ".join(argv)}' + if ignore_unknown_options: + warnings.warn(msg) + else: + raise ValueError(msg) + + url = parsed_args.url + + # curl automatically prepends 'http' if the scheme is missing, but Request + # needs the scheme to work + parsed_url = urlparse(url) + if not parsed_url.scheme: + url = 'http://' + url + + method = parsed_args.method or 'GET' + + result = {'method': method.upper(), 'url': url} + + headers, cookies = _parse_headers_and_cookies(parsed_args) + if headers: result['headers'] = headers if cookies: result['cookies'] = cookies if parsed_args.data: result['body'] = parsed_args.data + if not parsed_args.method: + # if the "data" is specified but the "method" is not specified, + # the default method is 'POST' + result['method'] = 'POST' return result diff --git a/scrapy/utils/datatypes.py b/scrapy/utils/datatypes.py index 2a92d0588..e31284a7f 100644 --- a/scrapy/utils/datatypes.py +++ b/scrapy/utils/datatypes.py @@ -15,7 +15,7 @@ class CaselessDict(dict): __slots__ = () def __init__(self, seq=None): - super(CaselessDict, self).__init__() + super().__init__() if seq: self.update(seq) @@ -53,7 +53,7 @@ class CaselessDict(dict): def update(self, seq): seq = seq.items() if isinstance(seq, Mapping) else seq iseq = ((self.normkey(k), self.normvalue(v)) for k, v in seq) - super(CaselessDict, self).update(iseq) + super().update(iseq) @classmethod def fromkeys(cls, keys, value=None): @@ -70,14 +70,14 @@ class LocalCache(collections.OrderedDict): """ def __init__(self, limit=None): - super(LocalCache, self).__init__() + super().__init__() self.limit = limit def __setitem__(self, key, value): if self.limit: while len(self) >= self.limit: self.popitem(last=False) - super(LocalCache, self).__setitem__(key, value) + super().__setitem__(key, value) class LocalWeakReferencedCache(weakref.WeakKeyDictionary): @@ -93,18 +93,18 @@ class LocalWeakReferencedCache(weakref.WeakKeyDictionary): """ def __init__(self, limit=None): - super(LocalWeakReferencedCache, self).__init__() + super().__init__() self.data = LocalCache(limit=limit) def __setitem__(self, key, value): try: - super(LocalWeakReferencedCache, self).__setitem__(key, value) + super().__setitem__(key, value) except TypeError: pass # key is not weak-referenceable, skip caching def __getitem__(self, key): try: - return super(LocalWeakReferencedCache, self).__getitem__(key) + return super().__getitem__(key) except (TypeError, KeyError): return None # key is either not weak-referenceable or not cached diff --git a/scrapy/utils/decorators.py b/scrapy/utils/decorators.py index 2e2c7adc1..fef3882cb 100644 --- a/scrapy/utils/decorators.py +++ b/scrapy/utils/decorators.py @@ -14,9 +14,9 @@ def deprecated(use_instead=None): def deco(func): @wraps(func) def wrapped(*args, **kwargs): - message = "Call to deprecated function %s." % func.__name__ + message = f"Call to deprecated function {func.__name__}." if use_instead: - message += " Use %s instead." % use_instead + message += f" Use {use_instead} instead." warnings.warn(message, category=ScrapyDeprecationWarning, stacklevel=2) return func(*args, **kwargs) return wrapped diff --git a/scrapy/utils/defer.py b/scrapy/utils/defer.py index a3950db75..b317c12a3 100644 --- a/scrapy/utils/defer.py +++ b/scrapy/utils/defer.py @@ -3,16 +3,21 @@ Helper functions for dealing with Twisted deferreds """ import asyncio import inspect +from collections.abc import Coroutine from functools import wraps +from typing import Any, Callable, Generator, Iterable -from twisted.internet import defer, task +from twisted.internet import defer +from twisted.internet.defer import Deferred, DeferredList, ensureDeferred +from twisted.internet.task import Cooperator from twisted.python import failure +from twisted.python.failure import Failure from scrapy.exceptions import IgnoreRequest from scrapy.utils.reactor import is_asyncio_reactor_installed -def defer_fail(_failure): +def defer_fail(_failure: Failure) -> Deferred: """Same as twisted.internet.defer.fail but delay calling errback until next reactor loop @@ -20,12 +25,12 @@ def defer_fail(_failure): before attending pending delayed calls, so do not set delay to zero. """ from twisted.internet import reactor - d = defer.Deferred() + d = Deferred() reactor.callLater(0.1, d.errback, _failure) return d -def defer_succeed(result): +def defer_succeed(result) -> Deferred: """Same as twisted.internet.defer.succeed but delay calling callback until next reactor loop @@ -33,13 +38,13 @@ def defer_succeed(result): before attending pending delayed calls, so do not set delay to zero. """ from twisted.internet import reactor - d = defer.Deferred() + d = Deferred() reactor.callLater(0.1, d.callback, result) return d -def defer_result(result): - if isinstance(result, defer.Deferred): +def defer_result(result) -> Deferred: + if isinstance(result, Deferred): return result elif isinstance(result, failure.Failure): return defer_fail(result) @@ -47,7 +52,7 @@ def defer_result(result): return defer_succeed(result) -def mustbe_deferred(f, *args, **kw): +def mustbe_deferred(f: Callable, *args, **kw) -> Deferred: """Same as twisted.internet.defer.maybeDeferred, but delay calling callback/errback to next reactor loop """ @@ -64,29 +69,29 @@ def mustbe_deferred(f, *args, **kw): return defer_result(result) -def parallel(iterable, count, callable, *args, **named): +def parallel(iterable: Iterable, count: int, callable: Callable, *args, **named) -> DeferredList: """Execute a callable over the objects in the given iterable, in parallel, using no more than ``count`` concurrent calls. Taken from: https://jcalderone.livejournal.com/24285.html """ - coop = task.Cooperator() + coop = Cooperator() work = (callable(elem, *args, **named) for elem in iterable) - return defer.DeferredList([coop.coiterate(work) for _ in range(count)]) + return DeferredList([coop.coiterate(work) for _ in range(count)]) -def process_chain(callbacks, input, *a, **kw): +def process_chain(callbacks: Iterable[Callable], input, *a, **kw) -> Deferred: """Return a Deferred built by chaining the given callbacks""" - d = defer.Deferred() + d = Deferred() for x in callbacks: d.addCallback(x, *a, **kw) d.callback(input) return d -def process_chain_both(callbacks, errbacks, input, *a, **kw): +def process_chain_both(callbacks: Iterable[Callable], errbacks: Iterable[Callable], input, *a, **kw) -> Deferred: """Return a Deferred built by chaining the given callbacks and errbacks""" - d = defer.Deferred() + d = Deferred() for cb, eb in zip(callbacks, errbacks): d.addCallbacks( callback=cb, errback=eb, @@ -100,17 +105,17 @@ def process_chain_both(callbacks, errbacks, input, *a, **kw): return d -def process_parallel(callbacks, input, *a, **kw): +def process_parallel(callbacks: Iterable[Callable], input, *a, **kw) -> Deferred: """Return a Deferred with the output of all successful calls to the given callbacks """ dfds = [defer.succeed(input).addCallback(x, *a, **kw) for x in callbacks] - d = defer.DeferredList(dfds, fireOnOneErrback=1, consumeErrors=1) + d = DeferredList(dfds, fireOnOneErrback=True, consumeErrors=True) d.addCallbacks(lambda r: [x[1] for x in r], lambda f: f.value.subFailure) return d -def iter_errback(iterable, errback, *a, **kw): +def iter_errback(iterable: Iterable, errback: Callable, *a, **kw) -> Generator: """Wraps an iterable calling an errback if an error is caught while iterating it. """ @@ -124,29 +129,22 @@ def iter_errback(iterable, errback, *a, **kw): errback(failure.Failure(), *a, **kw) -def _isfuture(o): - # workaround for Python before 3.5.3 not having asyncio.isfuture - if hasattr(asyncio, 'isfuture'): - return asyncio.isfuture(o) - return isinstance(o, asyncio.Future) - - -def deferred_from_coro(o): +def deferred_from_coro(o) -> Any: """Converts a coroutine into a Deferred, or returns the object as is if it isn't a coroutine""" - if isinstance(o, defer.Deferred): + if isinstance(o, Deferred): return o - if _isfuture(o) or inspect.isawaitable(o): + if asyncio.isfuture(o) or inspect.isawaitable(o): if not is_asyncio_reactor_installed(): # wrapping the coroutine directly into a Deferred, this doesn't work correctly with coroutines # that use asyncio, e.g. "await asyncio.sleep(1)" - return defer.ensureDeferred(o) + return ensureDeferred(o) else: # wrapping the coroutine into a Future and then into a Deferred, this requires AsyncioSelectorReactor - return defer.Deferred.fromFuture(asyncio.ensure_future(o)) + return Deferred.fromFuture(asyncio.ensure_future(o)) return o -def deferred_f_from_coro_f(coro_f): +def deferred_f_from_coro_f(coro_f: Callable[..., Coroutine]) -> Callable: """ Converts a coroutine function into a function that returns a Deferred. The coroutine function will be called at the time when the wrapper is called. Wrapper args will be passed to it. @@ -158,16 +156,16 @@ def deferred_f_from_coro_f(coro_f): return f -def maybeDeferred_coro(f, *args, **kw): +def maybeDeferred_coro(f: Callable, *args, **kw) -> Deferred: """ Copy of defer.maybeDeferred that also converts coroutines to Deferreds. """ try: result = f(*args, **kw) except: # noqa: E722 - return defer.fail(failure.Failure(captureVars=defer.Deferred.debug)) + return defer.fail(failure.Failure(captureVars=Deferred.debug)) - if isinstance(result, defer.Deferred): + if isinstance(result, Deferred): return result - elif _isfuture(result) or inspect.isawaitable(result): + elif asyncio.isfuture(result) or inspect.isawaitable(result): return deferred_from_coro(result) elif isinstance(result, failure.Failure): return defer.fail(result) diff --git a/scrapy/utils/deprecate.py b/scrapy/utils/deprecate.py index 3dbea5fee..f5b17416f 100644 --- a/scrapy/utils/deprecate.py +++ b/scrapy/utils/deprecate.py @@ -8,9 +8,8 @@ from scrapy.exceptions import ScrapyDeprecationWarning def attribute(obj, oldattr, newattr, version='0.12'): cname = obj.__class__.__name__ warnings.warn( - "%s.%s attribute is deprecated and will be no longer supported " - "in Scrapy %s, use %s.%s attribute instead" - % (cname, oldattr, version, cname, newattr), + f"{cname}.{oldattr} attribute is deprecated and will be no longer supported " + f"in Scrapy {version}, use {cname}.{newattr} attribute instead", ScrapyDeprecationWarning, stacklevel=3) @@ -57,7 +56,7 @@ def create_deprecated_class( warned_on_subclass = False def __new__(metacls, name, bases, clsdict_): - cls = super(DeprecatedClass, metacls).__new__(metacls, name, bases, clsdict_) + cls = super().__new__(metacls, name, bases, clsdict_) if metacls.deprecated_class is None: metacls.deprecated_class = cls return cls @@ -73,7 +72,7 @@ def create_deprecated_class( if warn_once: msg += ' (warning only on first subclass, there may be others)' warnings.warn(msg, warn_category, stacklevel=2) - super(DeprecatedClass, cls).__init__(name, bases, clsdict_) + super().__init__(name, bases, clsdict_) # see https://www.python.org/dev/peps/pep-3119/#overloading-isinstance-and-issubclass # and https://docs.python.org/reference/datamodel.html#customizing-instance-and-subclass-checks @@ -88,7 +87,7 @@ def create_deprecated_class( # is the deprecated class itself - subclasses of the # deprecated class should not use custom `__subclasscheck__` # method. - return super(DeprecatedClass, cls).__subclasscheck__(sub) + return super().__subclasscheck__(sub) if not inspect.isclass(sub): raise TypeError("issubclass() arg 1 must be a class") @@ -102,7 +101,7 @@ def create_deprecated_class( msg = instance_warn_message.format(cls=_clspath(cls, old_class_path), new=_clspath(new_class, new_class_path)) warnings.warn(msg, warn_category, stacklevel=2) - return super(DeprecatedClass, cls).__call__(*args, **kwargs) + return super().__call__(*args, **kwargs) deprecated_cls = DeprecatedClass(name, (new_class,), clsdict or {}) @@ -116,7 +115,7 @@ def create_deprecated_class( # deprecated class is in jinja2 template). __module__ attribute is not # important enough to raise an exception as users may be unable # to fix inspect.stack() errors. - warnings.warn("Error detecting parent module: %r" % e) + warnings.warn(f"Error detecting parent module: {e!r}") return deprecated_cls @@ -124,7 +123,7 @@ def create_deprecated_class( def _clspath(cls, forced=None): if forced is not None: return forced - return '{}.{}'.format(cls.__module__, cls.__name__) + return f'{cls.__module__}.{cls.__name__}' DEPRECATION_RULES = [ @@ -135,9 +134,9 @@ DEPRECATION_RULES = [ def update_classpath(path): """Update a deprecated path from an object with its new location""" for prefix, replacement in DEPRECATION_RULES: - if path.startswith(prefix): + if isinstance(path, str) and path.startswith(prefix): new_path = path.replace(prefix, replacement, 1) - warnings.warn("`{}` class is deprecated, use `{}` instead".format(path, new_path), + warnings.warn(f"`{path}` class is deprecated, use `{new_path}` instead", ScrapyDeprecationWarning) return new_path return path diff --git a/scrapy/utils/display.py b/scrapy/utils/display.py index 9735220ef..f4d17224b 100644 --- a/scrapy/utils/display.py +++ b/scrapy/utils/display.py @@ -2,20 +2,42 @@ pprint and pformat wrappers with colorization support """ +import ctypes +import platform import sys +from distutils.version import LooseVersion as parse_version from pprint import pformat as pformat_ +def _enable_windows_terminal_processing(): + # https://stackoverflow.com/a/36760881 + kernel32 = ctypes.windll.kernel32 + return bool(kernel32.SetConsoleMode(kernel32.GetStdHandle(-11), 7)) + + +def _tty_supports_color(): + if sys.platform != "win32": + return True + + if parse_version(platform.version()) < parse_version("10.0.14393"): + return True + + # Windows >= 10.0.14393 interprets ANSI escape sequences providing terminal + # processing is enabled. + return _enable_windows_terminal_processing() + + def _colorize(text, colorize=True): - if not colorize or not sys.stdout.isatty(): + if not colorize or not sys.stdout.isatty() or not _tty_supports_color(): return text try: from pygments import highlight + except ImportError: + return text + else: from pygments.formatters import TerminalFormatter from pygments.lexers import PythonLexer return highlight(text, PythonLexer(), TerminalFormatter()) - except ImportError: - return text def pformat(obj, *args, **kwargs): diff --git a/scrapy/utils/engine.py b/scrapy/utils/engine.py index 267c7ecd1..8e3ec2c37 100644 --- a/scrapy/utils/engine.py +++ b/scrapy/utils/engine.py @@ -8,11 +8,10 @@ def get_engine_status(engine): """Return a report of the current engine status""" tests = [ "time()-engine.start_time", - "engine.has_capacity()", "len(engine.downloader.active)", "engine.scraper.is_idle()", "engine.spider.name", - "engine.spider_is_idle(engine.spider)", + "engine.spider_is_idle()", "engine.slot.closing", "len(engine.slot.inprogress)", "len(engine.slot.scheduler.dqs or [])", @@ -29,7 +28,7 @@ def get_engine_status(engine): try: checks += [(test, eval(test))] except Exception as e: - checks += [(test, "%s (exception)" % type(e).__name__)] + checks += [(test, f"{type(e).__name__} (exception)")] return checks @@ -38,7 +37,7 @@ def format_engine_status(engine=None): checks = get_engine_status(engine) s = "Execution engine status\n\n" for test, result in checks: - s += "%-47s : %s\n" % (test, result) + s += f"{test:<47} : {result}\n" s += "\n" return s diff --git a/scrapy/utils/ftp.py b/scrapy/utils/ftp.py index f07bdd748..6cace4f07 100644 --- a/scrapy/utils/ftp.py +++ b/scrapy/utils/ftp.py @@ -20,7 +20,7 @@ def ftp_makedirs_cwd(ftp, path, first_call=True): def ftp_store_file( *, path, file, host, port, - username, password, use_active_mode=False): + username, password, use_active_mode=False, overwrite=True): """Opens a FTP connection with passed credentials,sets current directory to the directory extracted from given path, then uploads the file to server """ @@ -32,4 +32,6 @@ def ftp_store_file( file.seek(0) dirname, filename = posixpath.split(path) ftp_makedirs_cwd(ftp, dirname) - ftp.storbinary('STOR %s' % filename, file) + command = 'STOR' if overwrite else 'APPE' + ftp.storbinary(f'{command} {filename}', file) + file.close() diff --git a/scrapy/utils/gz.py b/scrapy/utils/gz.py index fbd7bd18f..76156a4b8 100644 --- a/scrapy/utils/gz.py +++ b/scrapy/utils/gz.py @@ -1,16 +1,14 @@ +import struct from gzip import GzipFile from io import BytesIO -import re -import struct from scrapy.utils.decorators import deprecated -# - Python>=3.5 GzipFile's read() has issues returning leftover -# uncompressed data when input is corrupted -# (regression or bug-fix compared to Python 3.4) +# - GzipFile's read() has issues returning leftover uncompressed data when +# input is corrupted # - read1(), which fetches data before raising EOFError on next call -# works here but is only available from Python>=3.3 +# works here @deprecated('GzipFile.read1') def read1(gzf, size=-1): return gzf.read1(size) @@ -43,17 +41,5 @@ def gunzip(data): return b''.join(output_list) -_is_gzipped = re.compile(br'^application/(x-)?gzip\b', re.I).search -_is_octetstream = re.compile(br'^(application|binary)/octet-stream\b', re.I).search - - -@deprecated -def is_gzipped(response): - """Return True if the response is gzipped, or False otherwise""" - ctype = response.headers.get('Content-Type', b'') - cenc = response.headers.get('Content-Encoding', b'').lower() - return _is_gzipped(ctype) or _is_octetstream(ctype) and cenc in (b'gzip', b'x-gzip') - - def gzip_magic_number(response): return response.body[:3] == b'\x1f\x8b\x08' diff --git a/scrapy/utils/http.py b/scrapy/utils/http.py deleted file mode 100644 index ceb3f0509..000000000 --- a/scrapy/utils/http.py +++ /dev/null @@ -1,36 +0,0 @@ -""" -Transitional module for moving to the w3lib library. - -For new code, always import from w3lib.http instead of this module -""" - -import warnings - -from scrapy.exceptions import ScrapyDeprecationWarning -from scrapy.utils.decorators import deprecated -from w3lib.http import * # noqa: F401 - - -warnings.warn("Module `scrapy.utils.http` is deprecated, " - "Please import from `w3lib.http` instead.", - ScrapyDeprecationWarning, stacklevel=2) - - -@deprecated -def decode_chunked_transfer(chunked_body): - """Parsed body received with chunked transfer encoding, and return the - decoded body. - - For more info see: - https://en.wikipedia.org/wiki/Chunked_transfer_encoding - - """ - body, h, t = '', '', chunked_body - while t: - h, t = t.split('\r\n', 1) - if h == '0': - break - size = int(h, 16) - body += t[:size] - t = t[size + 2:] - return body diff --git a/scrapy/utils/httpobj.py b/scrapy/utils/httpobj.py index c8d4391b1..a90f1d278 100644 --- a/scrapy/utils/httpobj.py +++ b/scrapy/utils/httpobj.py @@ -1,13 +1,16 @@ """Helper functions for scrapy.http objects (Request, Response)""" -import weakref -from urllib.parse import urlparse +from typing import Union +from urllib.parse import urlparse, ParseResult +from weakref import WeakKeyDictionary + +from scrapy.http import Request, Response -_urlparse_cache = weakref.WeakKeyDictionary() +_urlparse_cache: "WeakKeyDictionary[Union[Request, Response], ParseResult]" = WeakKeyDictionary() -def urlparse_cached(request_or_response): +def urlparse_cached(request_or_response: Union[Request, Response]) -> ParseResult: """Return urlparse.urlparse caching the result, where the argument can be a Request or Response object """ diff --git a/scrapy/utils/iterators.py b/scrapy/utils/iterators.py index 5e15bf0c8..3b504e56a 100644 --- a/scrapy/utils/iterators.py +++ b/scrapy/utils/iterators.py @@ -22,27 +22,43 @@ def xmliter(obj, nodename): """ nodename_patt = re.escape(nodename) - HEADER_START_RE = re.compile(r'^(.*?)<\s*%s(?:\s|>)' % nodename_patt, re.S) - HEADER_END_RE = re.compile(r'<\s*/%s\s*>' % nodename_patt, re.S) + DOCUMENT_HEADER_RE = re.compile(r'<\?xml[^>]+>\s*', re.S) + HEADER_END_RE = re.compile(fr'<\s*/{nodename_patt}\s*>', re.S) + END_TAG_RE = re.compile(r'<\s*/([^\s>]+)\s*>', re.S) + NAMESPACE_RE = re.compile(r'((xmlns[:A-Za-z]*)=[^>\s]+)', re.S) text = _body_or_str(obj) - header_start = re.search(HEADER_START_RE, text) - header_start = header_start.group(1).strip() if header_start else '' - header_end = re_rsearch(HEADER_END_RE, text) - header_end = text[header_end[1]:].strip() if header_end else '' + document_header = re.search(DOCUMENT_HEADER_RE, text) + document_header = document_header.group().strip() if document_header else '' + header_end_idx = re_rsearch(HEADER_END_RE, text) + header_end = text[header_end_idx[1]:].strip() if header_end_idx else '' + namespaces = {} + if header_end: + for tagname in reversed(re.findall(END_TAG_RE, header_end)): + tag = re.search(fr'<\s*{tagname}.*?xmlns[:=][^>]*>', text[:header_end_idx[1]], re.S) + if tag: + namespaces.update(reversed(x) for x in re.findall(NAMESPACE_RE, tag.group())) - r = re.compile(r'<%(np)s[\s>].*?' % {'np': nodename_patt}, re.DOTALL) + r = re.compile(fr'<{nodename_patt}[\s>].*?', re.DOTALL) for match in r.finditer(text): - nodetext = header_start + match.group() + header_end - yield Selector(text=nodetext, type='xml').xpath('//' + nodename)[0] + nodetext = ( + document_header + + match.group().replace( + nodename, + f'{nodename} {" ".join(namespaces.values())}', + 1 + ) + + header_end + ) + yield Selector(text=nodetext, type='xml') def xmliter_lxml(obj, nodename, namespace=None, prefix='x'): from lxml import etree reader = _StreamReader(obj) - tag = '{%s}%s' % (namespace, nodename) if namespace else nodename + tag = f'{{{namespace}}}{nodename}' if namespace else nodename iterable = etree.iterparse(reader, tag=tag, encoding=reader.encoding) - selxpath = '//' + ('%s:%s' % (prefix, nodename) if namespace else nodename) + selxpath = '//' + (f'{prefix}:{nodename}' if namespace else nodename) for _, node in iterable: nodetext = etree.tostring(node, encoding='unicode') node.clear() @@ -131,8 +147,7 @@ def _body_or_str(obj, unicode=True): if not isinstance(obj, expected_types): expected_types_str = " or ".join(t.__name__ for t in expected_types) raise TypeError( - "Object %r must be %s, not %s" - % (obj, expected_types_str, type(obj).__name__) + f"Object {obj!r} must be {expected_types_str}, not {type(obj).__name__}" ) if isinstance(obj, Response): if not unicode: diff --git a/scrapy/utils/job.py b/scrapy/utils/job.py index 4f1e601fc..c92ef36f5 100644 --- a/scrapy/utils/job.py +++ b/scrapy/utils/job.py @@ -1,7 +1,10 @@ import os +from typing import Optional + +from scrapy.settings import BaseSettings -def job_dir(settings): +def job_dir(settings: BaseSettings) -> Optional[str]: path = settings['JOBDIR'] if path and not os.path.exists(path): os.makedirs(path) diff --git a/scrapy/utils/log.py b/scrapy/utils/log.py index 51d276097..6c456ed60 100644 --- a/scrapy/utils/log.py +++ b/scrapy/utils/log.py @@ -46,6 +46,9 @@ DEFAULT_LOGGING = { 'version': 1, 'disable_existing_loggers': False, 'loggers': { + 'hpack': { + 'level': 'ERROR', + }, 'scrapy': { 'level': 'DEBUG', }, @@ -143,13 +146,20 @@ def log_scrapy_info(settings): logger.info("Scrapy %(version)s started (bot: %(bot)s)", {'version': scrapy.__version__, 'bot': settings['BOT_NAME']}) versions = [ - "%s %s" % (name, version) + f"{name} {version}" for name, version in scrapy_components_versions() if name != "Scrapy" ] logger.info("Versions: %(versions)s", {'versions': ", ".join(versions)}) from twisted.internet import reactor logger.debug("Using reactor: %s.%s", reactor.__module__, reactor.__class__.__name__) + from twisted.internet import asyncioreactor + if isinstance(reactor, asyncioreactor.AsyncioSelectorReactor): + logger.debug( + "Using asyncio event loop: %s.%s", + reactor._asyncioEventloop.__module__, + reactor._asyncioEventloop.__class__.__name__, + ) class StreamLogger: @@ -176,11 +186,11 @@ class LogCounterHandler(logging.Handler): """Record log levels count into a crawler stats""" def __init__(self, crawler, *args, **kwargs): - super(LogCounterHandler, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.crawler = crawler def emit(self, record): - sname = 'log_count/{}'.format(record.levelname) + sname = f'log_count/{record.levelname}' self.crawler.stats.inc_value(sname) diff --git a/scrapy/utils/markup.py b/scrapy/utils/markup.py deleted file mode 100644 index 9728c542a..000000000 --- a/scrapy/utils/markup.py +++ /dev/null @@ -1,14 +0,0 @@ -""" -Transitional module for moving to the w3lib library. - -For new code, always import from w3lib.html instead of this module -""" -import warnings - -from scrapy.exceptions import ScrapyDeprecationWarning -from w3lib.html import * # noqa: F401 - - -warnings.warn("Module `scrapy.utils.markup` is deprecated. " - "Please import from `w3lib.html` instead.", - ScrapyDeprecationWarning, stacklevel=2) diff --git a/scrapy/utils/misc.py b/scrapy/utils/misc.py index a7808cb2c..5c986eedc 100644 --- a/scrapy/utils/misc.py +++ b/scrapy/utils/misc.py @@ -5,16 +5,17 @@ import os import re import hashlib import warnings +from collections import deque from contextlib import contextmanager from importlib import import_module from pkgutil import iter_modules -from textwrap import dedent from w3lib.html import replace_entities from scrapy.utils.datatypes import LocalWeakReferencedCache from scrapy.utils.python import flatten, to_unicode from scrapy.item import _BaseItem +from scrapy.utils.deprecate import ScrapyDeprecationWarning _ITERABLE_SINGLE_VALUES = dict, _BaseItem, str, bytes @@ -37,14 +38,24 @@ def arg_to_iter(arg): def load_object(path): """Load an object given its absolute object path, and return it. - object can be the import path of a class, function, variable or an - instance, e.g. 'scrapy.downloadermiddlewares.redirect.RedirectMiddleware' + The object can be the import path of a class, function, variable or an + instance, e.g. 'scrapy.downloadermiddlewares.redirect.RedirectMiddleware'. + + If ``path`` is not a string, but is a callable object, such as a class or + a function, then return it as is. """ + if not isinstance(path, str): + if callable(path): + return path + else: + raise TypeError("Unexpected argument type, expected string " + "or object, got: %s" % type(path)) + try: dot = path.rindex('.') except ValueError: - raise ValueError("Error loading object '%s': not a full path" % path) + raise ValueError(f"Error loading object '{path}': not a full path") module, name = path[:dot], path[dot + 1:] mod = import_module(module) @@ -52,7 +63,7 @@ def load_object(path): try: obj = getattr(mod, name) except AttributeError: - raise NameError("Module '%s' doesn't define any object named '%s'" % (module, name)) + raise NameError(f"Module '{module}' doesn't define any object named '{name}'") return obj @@ -86,6 +97,11 @@ def extract_regex(regex, text, encoding='utf-8'): * if the regex contains multiple numbered groups, all those will be returned (flattened) * if the regex doesn't contain any group the entire regex matching is returned """ + warnings.warn( + "scrapy.utils.misc.extract_regex has moved to parsel.utils.extract_regex.", + ScrapyDeprecationWarning, + stacklevel=2 + ) if isinstance(regex, str): regex = re.compile(regex, re.UNICODE) @@ -138,8 +154,9 @@ def create_instance(objcls, settings, crawler, *args, **kwargs): Raises ``ValueError`` if both ``settings`` and ``crawler`` are ``None``. - Raises ``TypeError`` if the resulting instance is ``None`` (e.g. if an - extension has not been implemented correctly). + .. versionchanged:: 2.2 + Raises ``TypeError`` if the resulting instance is ``None`` (e.g. if an + extension has not been implemented correctly). """ if settings is None: if crawler is None: @@ -155,7 +172,7 @@ def create_instance(objcls, settings, crawler, *args, **kwargs): instance = objcls(*args, **kwargs) method_name = '__new__' if instance is None: - raise TypeError("%s.%s returned None" % (objcls.__qualname__, method_name)) + raise TypeError(f"{objcls.__qualname__}.{method_name} returned None") return instance @@ -177,6 +194,22 @@ def set_environ(**kwargs): os.environ[k] = v +def walk_callable(node): + """Similar to ``ast.walk``, but walks only function body and skips nested + functions defined within the node. + """ + todo = deque([node]) + walked_func_def = False + while todo: + node = todo.popleft() + if isinstance(node, ast.FunctionDef): + if walked_func_def: + continue + walked_func_def = True + todo.extend(ast.iter_child_nodes(node)) + yield node + + _generator_callbacks_cache = LocalWeakReferencedCache(limit=128) @@ -193,8 +226,9 @@ def is_generator_with_return_value(callable): return value is None or isinstance(value, ast.NameConstant) and value.value is None if inspect.isgeneratorfunction(callable): - tree = ast.parse(dedent(inspect.getsource(callable))) - for node in ast.walk(tree): + code = re.sub(r"^[\t ]+", "", inspect.getsource(callable)) + tree = ast.parse(code) + for node in walk_callable(tree): if isinstance(node, ast.Return) and not returns_none(node): _generator_callbacks_cache[callable] = True return _generator_callbacks_cache[callable] @@ -208,11 +242,23 @@ def warn_on_generator_with_return_value(spider, callable): Logs a warning if a callable is a generator function and includes a 'return' statement with a value different than None """ - if is_generator_with_return_value(callable): + try: + if is_generator_with_return_value(callable): + warnings.warn( + f'The "{spider.__class__.__name__}.{callable.__name__}" method is ' + 'a generator and includes a "return" statement with a value ' + 'different than None. This could lead to unexpected behaviour. Please see ' + 'https://docs.python.org/3/reference/simple_stmts.html#the-return-statement ' + 'for details about the semantics of the "return" statement within generators', + stacklevel=2, + ) + except IndentationError: + callable_name = spider.__class__.__name__ + "." + callable.__name__ warnings.warn( - 'The "{}.{}" method is a generator and includes a "return" statement with a ' - 'value different than None. This could lead to unexpected behaviour. Please see ' - 'https://docs.python.org/3/reference/simple_stmts.html#the-return-statement ' - 'for details about the semantics of the "return" statement within generators' - .format(spider.__class__.__name__, callable.__name__), stacklevel=2, + f'Unable to determine whether or not "{callable_name}" is a generator with a return value. ' + 'This will not prevent your code from working, but it prevents Scrapy from detecting ' + f'potential issues in your implementation of "{callable_name}". Please, report this in the ' + 'Scrapy issue tracker (https://github.com/scrapy/scrapy/issues), ' + f'including the code of "{callable_name}"', + stacklevel=2, ) diff --git a/scrapy/utils/multipart.py b/scrapy/utils/multipart.py deleted file mode 100644 index 5dcf791b8..000000000 --- a/scrapy/utils/multipart.py +++ /dev/null @@ -1,15 +0,0 @@ -""" -Transitional module for moving to the w3lib library. - -For new code, always import from w3lib.form instead of this module -""" -import warnings - -from scrapy.exceptions import ScrapyDeprecationWarning -from w3lib.form import * # noqa: F401 - - -warnings.warn("Module `scrapy.utils.multipart` is deprecated. " - "If you're using `encode_multipart` function, please use " - "`urllib3.filepost.encode_multipart_formdata` instead", - ScrapyDeprecationWarning, stacklevel=2) diff --git a/scrapy/utils/ossignal.py b/scrapy/utils/ossignal.py index 45c9cef0c..cf867f3f8 100644 --- a/scrapy/utils/ossignal.py +++ b/scrapy/utils/ossignal.py @@ -18,8 +18,7 @@ def install_shutdown_handlers(function, override_sigint=True): from twisted.internet import reactor reactor._handleSignals() signal.signal(signal.SIGTERM, function) - if signal.getsignal(signal.SIGINT) == signal.default_int_handler or \ - override_sigint: + if signal.getsignal(signal.SIGINT) == signal.default_int_handler or override_sigint: signal.signal(signal.SIGINT, function) # Catch Ctrl-Break in windows if hasattr(signal, 'SIGBREAK'): diff --git a/scrapy/utils/project.py b/scrapy/utils/project.py index b8d3ebf9d..c66af497e 100644 --- a/scrapy/utils/project.py +++ b/scrapy/utils/project.py @@ -1,5 +1,4 @@ import os -import pickle import warnings from importlib import import_module @@ -20,7 +19,7 @@ def inside_project(): try: import_module(scrapy_module) except ImportError as exc: - warnings.warn("Cannot import scrapy settings module %s: %s" % (scrapy_module, exc)) + warnings.warn(f"Cannot import scrapy settings module {scrapy_module}: {exc}") else: return True return bool(closest_scrapy_cfg()) @@ -68,18 +67,10 @@ def get_project_settings(): if settings_module_path: settings.setmodule(settings_module_path, priority='project') - pickled_settings = os.environ.get("SCRAPY_PICKLED_SETTINGS_TO_OVERRIDE") - if pickled_settings: - warnings.warn("Use of environment variable " - "'SCRAPY_PICKLED_SETTINGS_TO_OVERRIDE' " - "is deprecated.", ScrapyDeprecationWarning) - settings.setdict(pickle.loads(pickled_settings), priority='project') - scrapy_envvars = {k[7:]: v for k, v in os.environ.items() if k.startswith('SCRAPY_')} valid_envvars = { 'CHECK', - 'PICKLED_SETTINGS_TO_OVERRIDE', 'PROJECT', 'PYTHON_SHELL', 'SETTINGS_MODULE', @@ -90,7 +81,7 @@ def get_project_settings(): warnings.warn( 'Use of environment variables prefixed with SCRAPY_ to override ' 'settings is deprecated. The following environment variables are ' - 'currently defined: {}'.format(setting_envvar_list), + f'currently defined: {setting_envvar_list}', ScrapyDeprecationWarning ) settings.setdict(scrapy_envvars, priority='project') diff --git a/scrapy/utils/py36.py b/scrapy/utils/py36.py index c8c24076e..653e2bbbb 100644 --- a/scrapy/utils/py36.py +++ b/scrapy/utils/py36.py @@ -1,10 +1,11 @@ -""" -Helpers using Python 3.6+ syntax (ignore SyntaxError on import). -""" +import warnings + +from scrapy.exceptions import ScrapyDeprecationWarning +from scrapy.utils.asyncgen import collect_asyncgen # noqa: F401 -async def collect_asyncgen(result): - results = [] - async for x in result: - results.append(x) - return results +warnings.warn( + "Module `scrapy.utils.py36` is deprecated, please import from `scrapy.utils.asyncgen` instead.", + category=ScrapyDeprecationWarning, + stacklevel=2, +) diff --git a/scrapy/utils/python.py b/scrapy/utils/python.py index 9c1f3c2fe..bcc12f24f 100644 --- a/scrapy/utils/python.py +++ b/scrapy/utils/python.py @@ -6,10 +6,13 @@ import gc import inspect import re import sys +import warnings import weakref +from collections.abc import Iterable from functools import partial, wraps from itertools import chain +from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.utils.decorators import deprecated @@ -89,7 +92,7 @@ def to_unicode(text, encoding=None, errors='strict'): return text if not isinstance(text, (bytes, str)): raise TypeError('to_unicode must receive a bytes or str ' - 'object, got %s' % type(text).__name__) + f'object, got {type(text).__name__}') if encoding is None: encoding = 'utf-8' return text.decode(encoding, errors) @@ -102,7 +105,7 @@ def to_bytes(text, encoding=None, errors='strict'): return text if not isinstance(text, str): raise TypeError('to_bytes must receive a str or bytes ' - 'object, got %s' % type(text).__name__) + f'object, got {type(text).__name__}') if encoding is None: encoding = 'utf-8' return text.encode(encoding, errors) @@ -127,6 +130,7 @@ def re_rsearch(pattern, text, chunk_size=1024): In case the pattern wasn't found, None is returned, otherwise it returns a tuple containing the start position of the match, and the ending (regarding the entire text). """ + def _chunk_iter(): offset = len(text) while True: @@ -158,6 +162,7 @@ def memoizemethod_noargs(method): if self not in cache: cache[self] = method(self, *args, **kwargs) return cache[self] + return new_method @@ -170,7 +175,7 @@ def binary_is_text(data): does not contain unprintable control characters. """ if not isinstance(data, bytes): - raise TypeError("data must be bytes, got '%s'" % type(data).__name__) + raise TypeError(f"data must be bytes, got '{type(data).__name__}'") return all(c not in _BINARYCHARS for c in data) @@ -194,7 +199,8 @@ def _getargspec_py23(func): def get_func_args(func, stripself=False): """Return the argument name list of a callable""" if inspect.isfunction(func): - func_args, _, _, _ = _getargspec_py23(func) + spec = inspect.getfullargspec(func) + func_args = spec.args + spec.kwonlyargs elif inspect.isclass(func): return get_func_args(func.__init__, True) elif inspect.ismethod(func): @@ -212,7 +218,7 @@ def get_func_args(func, stripself=False): else: return get_func_args(func.__call__, True) else: - raise TypeError('%s is not callable' % type(func)) + raise TypeError(f'{type(func)} is not callable') if stripself: func_args.pop(0) return func_args @@ -245,7 +251,7 @@ def get_spec(func): elif hasattr(func, '__call__'): spec = _getargspec_py23(func.__call__) else: - raise TypeError('%s is not callable' % type(func)) + raise TypeError(f'{type(func)} is not callable') defaults = spec.defaults or [] @@ -276,6 +282,7 @@ def equal_attributes(obj1, obj2, attributes): class WeakKeyCache: def __init__(self, default_factory): + warnings.warn("The WeakKeyCache class is deprecated", category=ScrapyDeprecationWarning, stacklevel=2) self.default_factory = default_factory self._weakdict = weakref.WeakKeyDictionary() @@ -285,6 +292,7 @@ class WeakKeyCache: return self._weakdict[key] +@deprecated def retry_on_eintr(function, *args, **kw): """Run a function and retry it while getting EINTR errors""" while True: @@ -315,7 +323,7 @@ def global_object_name(obj): >>> global_object_name(Request) 'scrapy.http.request.Request' """ - return "%s.%s" % (obj.__module__, obj.__name__) + return f"{obj.__module__}.{obj.__name__}" if hasattr(sys, "pypy_version_info"): @@ -328,16 +336,16 @@ else: gc.collect() -class MutableChain: +class MutableChain(Iterable): """ Thin wrapper around itertools.chain, allowing to add iterables "in-place" """ - def __init__(self, *args): - self.data = chain(*args) + def __init__(self, *args: Iterable): + self.data = chain.from_iterable(args) - def extend(self, *iterables): - self.data = chain(self.data, *iterables) + def extend(self, *iterables: Iterable): + self.data = chain(self.data, chain.from_iterable(iterables)) def __iter__(self): return self diff --git a/scrapy/utils/reactor.py b/scrapy/utils/reactor.py index 3c705f69b..6723d9b37 100644 --- a/scrapy/utils/reactor.py +++ b/scrapy/utils/reactor.py @@ -10,7 +10,7 @@ def listen_tcp(portrange, host, factory): """Like reactor.listenTCP but tries different ports in a range.""" from twisted.internet import reactor if len(portrange) > 2: - raise ValueError("invalid portrange: %s" % portrange) + raise ValueError(f"invalid portrange: {portrange}") if not portrange: return reactor.listenTCP(0, factory, interface=host) if not hasattr(portrange, '__iter__'): @@ -50,13 +50,20 @@ class CallLaterOnce: return self._func(*self._a, **self._kw) -def install_reactor(reactor_path): +def install_reactor(reactor_path, event_loop_path=None): """Installs the :mod:`~twisted.internet.reactor` with the specified - import path.""" + import path. Also installs the asyncio event loop with the specified import + path if the asyncio reactor is enabled""" reactor_class = load_object(reactor_path) if reactor_class is asyncioreactor.AsyncioSelectorReactor: with suppress(error.ReactorAlreadyInstalledError): - asyncioreactor.install(asyncio.get_event_loop()) + if event_loop_path is not None: + event_loop_class = load_object(event_loop_path) + event_loop = event_loop_class() + asyncio.set_event_loop(event_loop) + else: + event_loop = asyncio.get_event_loop() + asyncioreactor.install(eventloop=event_loop) else: *module, _ = reactor_path.split(".") installer_path = module + ["install"] @@ -72,9 +79,9 @@ def verify_installed_reactor(reactor_path): from twisted.internet import reactor reactor_class = load_object(reactor_path) if not isinstance(reactor, reactor_class): - msg = "The installed reactor ({}.{}) does not match the requested one ({})".format( - reactor.__module__, reactor.__class__.__name__, reactor_path - ) + msg = ("The installed reactor " + f"({reactor.__module__}.{reactor.__class__.__name__}) does not " + f"match the requested one ({reactor_path})") raise Exception(msg) diff --git a/scrapy/utils/reqser.py b/scrapy/utils/reqser.py index 5ea2aafb8..c254b9f82 100644 --- a/scrapy/utils/reqser.py +++ b/scrapy/utils/reqser.py @@ -1,100 +1,22 @@ -""" -Helper functions for serializing (and deserializing) requests. -""" -import inspect +import warnings +from typing import Optional -from scrapy.http import Request -from scrapy.utils.python import to_unicode -from scrapy.utils.misc import load_object +import scrapy +from scrapy.exceptions import ScrapyDeprecationWarning +from scrapy.utils.request import request_from_dict as _from_dict -def request_to_dict(request, spider=None): - """Convert Request object to a dict. - - If a spider is given, it will try to find out the name of the spider method - used in the callback and store that as the callback. - """ - cb = request.callback - if callable(cb): - cb = _find_method(spider, cb) - eb = request.errback - if callable(eb): - eb = _find_method(spider, eb) - d = { - 'url': to_unicode(request.url), # urls should be safe (safe_string_url) - 'callback': cb, - 'errback': eb, - 'method': request.method, - 'headers': dict(request.headers), - 'body': request.body, - 'cookies': request.cookies, - 'meta': request.meta, - '_encoding': request._encoding, - 'priority': request.priority, - 'dont_filter': request.dont_filter, - 'flags': request.flags, - 'cb_kwargs': request.cb_kwargs, - } - if type(request) is not Request: - d['_class'] = request.__module__ + '.' + request.__class__.__name__ - return d +warnings.warn( + ("Module scrapy.utils.reqser is deprecated, please use request.to_dict method" + " and/or scrapy.utils.request.request_from_dict instead"), + category=ScrapyDeprecationWarning, + stacklevel=2, +) -def request_from_dict(d, spider=None): - """Create Request object from a dict. - - If a spider is given, it will try to resolve the callbacks looking at the - spider for methods with the same name. - """ - cb = d['callback'] - if cb and spider: - cb = _get_method(spider, cb) - eb = d['errback'] - if eb and spider: - eb = _get_method(spider, eb) - request_cls = load_object(d['_class']) if '_class' in d else Request - return request_cls( - url=to_unicode(d['url']), - callback=cb, - errback=eb, - method=d['method'], - headers=d['headers'], - body=d['body'], - cookies=d['cookies'], - meta=d['meta'], - encoding=d['_encoding'], - priority=d['priority'], - dont_filter=d['dont_filter'], - flags=d.get('flags'), - cb_kwargs=d.get('cb_kwargs'), - ) +def request_to_dict(request: "scrapy.Request", spider: Optional["scrapy.Spider"] = None) -> dict: + return request.to_dict(spider=spider) -def _find_method(obj, func): - if obj: - try: - func_self = func.__self__ - except AttributeError: # func has no __self__ - pass - else: - if func_self is obj: - members = inspect.getmembers(obj, predicate=inspect.ismethod) - for name, obj_func in members: - # We need to use __func__ to access the original - # function object because instance method objects - # are generated each time attribute is retrieved from - # instance. - # - # Reference: The standard type hierarchy - # https://docs.python.org/3/reference/datamodel.html - if obj_func.__func__ is func.__func__: - return name - raise ValueError("Function %s is not a method of: %s" % (func, obj)) - - -def _get_method(obj, name): - name = str(name) - try: - return getattr(obj, name) - except AttributeError: - raise ValueError("Method %r not found in: %s" % (name, obj)) +def request_from_dict(d: dict, spider: Optional["scrapy.Spider"] = None) -> "scrapy.Request": + return _from_dict(d, spider=spider) diff --git a/scrapy/utils/request.py b/scrapy/utils/request.py index 12c03d78e..57dcc5f2c 100644 --- a/scrapy/utils/request.py +++ b/scrapy/utils/request.py @@ -4,20 +4,28 @@ scrapy.http.Request objects """ import hashlib -import weakref +from typing import Dict, Iterable, Optional, Tuple, Union from urllib.parse import urlunparse +from weakref import WeakKeyDictionary from w3lib.http import basic_auth_header from w3lib.url import canonicalize_url +from scrapy import Request, Spider from scrapy.utils.httpobj import urlparse_cached +from scrapy.utils.misc import load_object from scrapy.utils.python import to_bytes, to_unicode -_fingerprint_cache = weakref.WeakKeyDictionary() +_fingerprint_cache: "WeakKeyDictionary[Request, Dict[Tuple[Optional[Tuple[bytes, ...]], bool], str]]" +_fingerprint_cache = WeakKeyDictionary() -def request_fingerprint(request, include_headers=None, keep_fragments=False): +def request_fingerprint( + request: Request, + include_headers: Optional[Iterable[Union[bytes, str]]] = None, + keep_fragments: bool = False, +) -> str: """ Return the request fingerprint. @@ -49,17 +57,18 @@ def request_fingerprint(request, include_headers=None, keep_fragments=False): (for instance when handling requests with a headless browser). """ + headers: Optional[Tuple[bytes, ...]] = None if include_headers: - include_headers = tuple(to_bytes(h.lower()) for h in sorted(include_headers)) + headers = tuple(to_bytes(h.lower()) for h in sorted(include_headers)) cache = _fingerprint_cache.setdefault(request, {}) - cache_key = (include_headers, keep_fragments) + cache_key = (headers, keep_fragments) if cache_key not in cache: fp = hashlib.sha1() fp.update(to_bytes(request.method)) fp.update(to_bytes(canonicalize_url(request.url, keep_fragments=keep_fragments))) fp.update(request.body or b'') - if include_headers: - for hdr in include_headers: + if headers: + for hdr in headers: if hdr in request.headers: fp.update(hdr) for v in request.headers.getlist(hdr): @@ -68,14 +77,14 @@ def request_fingerprint(request, include_headers=None, keep_fragments=False): return cache[cache_key] -def request_authenticate(request, username, password): +def request_authenticate(request: Request, username: str, password: str) -> None: """Autenticate the given request (in place) using the HTTP basic access authentication mechanism (RFC 2617) and the given username and password """ request.headers['Authorization'] = basic_auth_header(username, password) -def request_httprepr(request): +def request_httprepr(request: Request) -> bytes: """Return the raw HTTP representation (as bytes) of the given request. This is provided only for reference since it's not the actual stream of bytes that will be send when performing the request (that's controlled @@ -92,9 +101,33 @@ def request_httprepr(request): return s -def referer_str(request): +def referer_str(request: Request) -> Optional[str]: """ Return Referer HTTP header suitable for logging. """ referrer = request.headers.get('Referer') if referrer is None: return referrer return to_unicode(referrer, errors='replace') + + +def request_from_dict(d: dict, *, spider: Optional[Spider] = None) -> Request: + """Create a :class:`~scrapy.Request` object from a dict. + + If a spider is given, it will try to resolve the callbacks looking at the + spider for methods with the same name. + """ + request_cls = load_object(d["_class"]) if "_class" in d else Request + kwargs = {key: value for key, value in d.items() if key in request_cls.attributes} + if d.get("callback") and spider: + kwargs["callback"] = _get_method(spider, d["callback"]) + if d.get("errback") and spider: + kwargs["errback"] = _get_method(spider, d["errback"]) + return request_cls(**kwargs) + + +def _get_method(obj, name): + """Helper function for request_from_dict""" + name = str(name) + try: + return getattr(obj, name) + except AttributeError: + raise ValueError(f"Method {name!r} not found in: {obj}") diff --git a/scrapy/utils/response.py b/scrapy/utils/response.py index edbc0db25..b3ef7b463 100644 --- a/scrapy/utils/response.py +++ b/scrapy/utils/response.py @@ -3,19 +3,23 @@ This module provides some useful functions for working with scrapy.http.Response objects """ import os -import weakref import webbrowser import tempfile +from typing import Any, Callable, Iterable, Optional, Tuple, Union +from weakref import WeakKeyDictionary + +import scrapy +from scrapy.http.response import Response from twisted.web import http from scrapy.utils.python import to_bytes, to_unicode from w3lib import html -_baseurl_cache = weakref.WeakKeyDictionary() +_baseurl_cache: "WeakKeyDictionary[Response, str]" = WeakKeyDictionary() -def get_base_url(response): +def get_base_url(response: "scrapy.http.response.text.TextResponse") -> str: """Return the base url of the given response, joined with the response url""" if response not in _baseurl_cache: text = response.text[0:4096] @@ -23,10 +27,13 @@ def get_base_url(response): return _baseurl_cache[response] -_metaref_cache = weakref.WeakKeyDictionary() +_metaref_cache: "WeakKeyDictionary[Response, Union[Tuple[None, None], Tuple[float, str]]]" = WeakKeyDictionary() -def get_meta_refresh(response, ignore_tags=('script', 'noscript')): +def get_meta_refresh( + response: "scrapy.http.response.text.TextResponse", + ignore_tags: Optional[Iterable[str]] = ('script', 'noscript'), +) -> Union[Tuple[None, None], Tuple[float, str]]: """Parse the http-equiv refrsh parameter from the given response""" if response not in _metaref_cache: text = response.text[0:4096] @@ -35,28 +42,36 @@ def get_meta_refresh(response, ignore_tags=('script', 'noscript')): return _metaref_cache[response] -def response_status_message(status): +def response_status_message(status: Union[bytes, float, int, str]) -> str: """Return status code plus status text descriptive message """ - message = http.RESPONSES.get(int(status), "Unknown Status") - return '%s %s' % (status, to_unicode(message)) + status_int = int(status) + message = http.RESPONSES.get(status_int, "Unknown Status") + return f'{status_int} {to_unicode(message)}' -def response_httprepr(response): +def response_httprepr(response: Response) -> bytes: """Return raw HTTP representation (as bytes) of the given response. This is provided only for reference, since it's not the exact stream of bytes that was received (that's not exposed by Twisted). """ - s = b"HTTP/1.1 " + to_bytes(str(response.status)) + b" " + \ - to_bytes(http.RESPONSES.get(response.status, b'')) + b"\r\n" + values = [ + b"HTTP/1.1 ", + to_bytes(str(response.status)), + b" ", + to_bytes(http.RESPONSES.get(response.status, b'')), + b"\r\n", + ] if response.headers: - s += response.headers.to_string() + b"\r\n" - s += b"\r\n" - s += response.body - return s + values.extend([response.headers.to_string(), b"\r\n"]) + values.extend([b"\r\n", response.body]) + return b"".join(values) -def open_in_browser(response, _openfunc=webbrowser.open): +def open_in_browser( + response: Union["scrapy.http.response.html.HtmlResponse", "scrapy.http.response.text.TextResponse"], + _openfunc: Callable[[str], Any] = webbrowser.open, +) -> Any: """Open the given response in a local web browser, populating the tag for external links to work """ @@ -65,15 +80,15 @@ def open_in_browser(response, _openfunc=webbrowser.open): body = response.body if isinstance(response, HtmlResponse): if b'' body = body.replace(b'', to_bytes(repl)) ext = '.html' elif isinstance(response, TextResponse): ext = '.txt' else: - raise TypeError("Unsupported response type: %s" % - response.__class__.__name__) + raise TypeError("Unsupported response type: " + f"{response.__class__.__name__}") fd, fname = tempfile.mkstemp(ext) os.write(fd, body) os.close(fd) - return _openfunc("file://%s" % fname) + return _openfunc(f"file://{fname}") diff --git a/scrapy/utils/serialize.py b/scrapy/utils/serialize.py index bf73dfa18..a73cf03c5 100644 --- a/scrapy/utils/serialize.py +++ b/scrapy/utils/serialize.py @@ -2,10 +2,10 @@ import json import datetime import decimal +from itemadapter import is_item, ItemAdapter from twisted.internet import defer from scrapy.http import Request, Response -from scrapy.item import _BaseItem class ScrapyJSONEncoder(json.JSONEncoder): @@ -17,7 +17,7 @@ class ScrapyJSONEncoder(json.JSONEncoder): if isinstance(o, set): return list(o) elif isinstance(o, datetime.datetime): - return o.strftime("%s %s" % (self.DATE_FORMAT, self.TIME_FORMAT)) + return o.strftime(f"{self.DATE_FORMAT} {self.TIME_FORMAT}") elif isinstance(o, datetime.date): return o.strftime(self.DATE_FORMAT) elif isinstance(o, datetime.time): @@ -26,14 +26,14 @@ class ScrapyJSONEncoder(json.JSONEncoder): return str(o) elif isinstance(o, defer.Deferred): return str(o) - elif isinstance(o, _BaseItem): - return dict(o) + elif is_item(o): + return ItemAdapter(o).asdict() elif isinstance(o, Request): - return "<%s %s %s>" % (type(o).__name__, o.method, o.url) + return f"<{type(o).__name__} {o.method} {o.url}>" elif isinstance(o, Response): - return "<%s %s %s>" % (type(o).__name__, o.status, o.url) + return f"<{type(o).__name__} {o.status} {o.url}>" else: - return super(ScrapyJSONEncoder, self).default(o) + return super().default(o) class ScrapyJSONDecoder(json.JSONDecoder): diff --git a/scrapy/utils/signal.py b/scrapy/utils/signal.py index 115707182..62808f3ce 100644 --- a/scrapy/utils/signal.py +++ b/scrapy/utils/signal.py @@ -1,5 +1,5 @@ """Helper functions for working with signals""" - +import collections import logging from twisted.internet.defer import DeferredList, Deferred @@ -16,15 +16,13 @@ from scrapy.utils.log import failure_to_exc_info logger = logging.getLogger(__name__) -class _IgnoredException(Exception): - pass - - def send_catch_log(signal=Any, sender=Anonymous, *arguments, **named): """Like pydispatcher.robust.sendRobust but it also logs errors and returns Failures instead of exceptions. """ - dont_log = (named.pop('dont_log', _IgnoredException), StopDownload) + dont_log = named.pop('dont_log', ()) + dont_log = tuple(dont_log) if isinstance(dont_log, collections.Sequence) else (dont_log,) + dont_log += (StopDownload, ) spider = named.get('spider', None) responses = [] for receiver in liveReceivers(getAllReceivers(sender, signal)): diff --git a/scrapy/utils/spider.py b/scrapy/utils/spider.py index 7e7a50c88..59fc9202f 100644 --- a/scrapy/utils/spider.py +++ b/scrapy/utils/spider.py @@ -4,17 +4,14 @@ import logging from scrapy.spiders import Spider from scrapy.utils.defer import deferred_from_coro from scrapy.utils.misc import arg_to_iter -try: - from scrapy.utils.py36 import collect_asyncgen -except SyntaxError: - collect_asyncgen = None +from scrapy.utils.asyncgen import collect_asyncgen logger = logging.getLogger(__name__) def iterate_spider_output(result): - if collect_asyncgen and hasattr(inspect, 'isasyncgen') and inspect.isasyncgen(result): + if inspect.isasyncgen(result): d = deferred_from_coro(collect_asyncgen(result)) d.addCallback(iterate_spider_output) return d @@ -34,10 +31,12 @@ def iter_spider_classes(module): from scrapy.spiders import Spider for obj in vars(module).values(): - if inspect.isclass(obj) and \ - issubclass(obj, Spider) and \ - obj.__module__ == module.__name__ and \ - getattr(obj, 'name', None): + if ( + inspect.isclass(obj) + and issubclass(obj, Spider) + and obj.__module__ == module.__name__ + and getattr(obj, 'name', None) + ): yield obj diff --git a/scrapy/utils/ssl.py b/scrapy/utils/ssl.py index c3c5e329b..ea4dde882 100644 --- a/scrapy/utils/ssl.py +++ b/scrapy/utils/ssl.py @@ -50,7 +50,7 @@ def get_temp_key_info(ssl_object): key_info.append(ffi_buf_to_string(cname)) else: key_info.append(ffi_buf_to_string(pyOpenSSLutil.lib.OBJ_nid2sn(key_type))) - key_info.append('%s bits' % pyOpenSSLutil.lib.EVP_PKEY_bits(temp_key)) + key_info.append(f'{pyOpenSSLutil.lib.EVP_PKEY_bits(temp_key)} bits') return ', '.join(key_info) @@ -58,4 +58,4 @@ def get_openssl_version(): system_openssl = OpenSSL.SSL.SSLeay_version( OpenSSL.SSL.SSLEAY_VERSION ).decode('ascii', errors='replace') - return '{} ({})'.format(OpenSSL.version.__version__, system_openssl) + return f'{OpenSSL.version.__version__} ({system_openssl})' diff --git a/scrapy/utils/template.py b/scrapy/utils/template.py index 96ff4b09b..f068be737 100644 --- a/scrapy/utils/template.py +++ b/scrapy/utils/template.py @@ -12,10 +12,12 @@ def render_templatefile(path, **kwargs): content = string.Template(raw).substitute(**kwargs) render_path = path[:-len('.tmpl')] if path.endswith('.tmpl') else path + + if path.endswith('.tmpl'): + os.rename(path, render_path) + with open(render_path, 'wb') as fp: fp.write(content.encode('utf8')) - if path.endswith('.tmpl'): - os.remove(path) CAMELCASE_INVALID_CHARS = re.compile(r'[^a-zA-Z\d]') diff --git a/scrapy/utils/test.py b/scrapy/utils/test.py index faac0b12f..24c38283a 100644 --- a/scrapy/utils/test.py +++ b/scrapy/utils/test.py @@ -2,25 +2,15 @@ This module contains some assorted functions used in tests """ -from __future__ import absolute_import -from posixpath import split import asyncio import os +from posixpath import split +from unittest import mock from importlib import import_module from twisted.trial.unittest import SkipTest -from scrapy.exceptions import NotConfigured -from scrapy.utils.boto import is_botocore - - -def assert_aws_environ(): - """Asserts the current environment is suitable for running AWS testsi. - Raises SkipTest with the reason if it's not. - """ - skip_if_no_boto() - if 'AWS_ACCESS_KEY_ID' not in os.environ: - raise SkipTest("AWS keys not found") +from scrapy.utils.boto import is_botocore_available def assert_gcs_environ(): @@ -29,30 +19,8 @@ def assert_gcs_environ(): def skip_if_no_boto(): - try: - is_botocore() - except NotConfigured as e: - raise SkipTest(e) - - -def get_s3_content_and_delete(bucket, path, with_key=False): - """ Get content from s3 key, and delete key afterwards. - """ - if is_botocore(): - import botocore.session - session = botocore.session.get_session() - client = session.create_client('s3') - key = client.get_object(Bucket=bucket, Key=path) - content = key['Body'].read() - client.delete_object(Bucket=bucket, Key=path) - else: - import boto - # assuming boto=2.2.2 - bucket = boto.connect_s3().get_bucket(bucket, validate=False) - key = bucket.get_key(path) - content = key.get_contents_as_string() - bucket.delete_key(path) - return (content, key) if with_key else content + if not is_botocore_available(): + raise SkipTest('missing botocore library') def get_gcs_content_and_delete(bucket, path): @@ -79,7 +47,7 @@ def get_ftp_content_and_delete( def buffer_data(data): ftp_data.append(data) - ftp.retrbinary('RETR %s' % path, buffer_data) + ftp.retrbinary(f'RETR {path}', buffer_data) dirname, filename = split(path) ftp.cwd(dirname) ftp.delete(filename) @@ -126,3 +94,19 @@ def get_from_asyncio_queue(value): getter = q.get() q.put_nowait(value) return getter + + +def mock_google_cloud_storage(): + """Creates autospec mocks for google-cloud-storage Client, Bucket and Blob + classes and set their proper return values. + """ + from google.cloud.storage import Client, Bucket, Blob + client_mock = mock.create_autospec(Client) + + bucket_mock = mock.create_autospec(Bucket) + client_mock.get_bucket.return_value = bucket_mock + + blob_mock = mock.create_autospec(Blob) + bucket_mock.blob.return_value = blob_mock + + return (client_mock, bucket_mock, blob_mock) diff --git a/scrapy/utils/testproc.py b/scrapy/utils/testproc.py index a63c9a942..a54c7db95 100644 --- a/scrapy/utils/testproc.py +++ b/scrapy/utils/testproc.py @@ -23,10 +23,10 @@ class ProcessTest: def _process_finished(self, pp, cmd, check_code): if pp.exitcode and check_code: - msg = "process %s exit with code %d" % (cmd, pp.exitcode) - msg += "\n>>> stdout <<<\n%s" % pp.out + msg = f"process {cmd} exit with code {pp.exitcode}" + msg += f"\n>>> stdout <<<\n{pp.out}" msg += "\n" - msg += "\n>>> stderr <<<\n%s" % pp.err + msg += f"\n>>> stderr <<<\n{pp.err}" raise RuntimeError(msg) return pp.exitcode, pp.out, pp.err diff --git a/scrapy/utils/testsite.py b/scrapy/utils/testsite.py index 66930ad2c..fce77be32 100644 --- a/scrapy/utils/testsite.py +++ b/scrapy/utils/testsite.py @@ -7,12 +7,12 @@ class SiteTest: def setUp(self): from twisted.internet import reactor - super(SiteTest, self).setUp() + super().setUp() self.site = reactor.listenTCP(0, test_site(), interface="127.0.0.1") - self.baseurl = "http://localhost:%d/" % self.site.getHost().port + self.baseurl = f"http://localhost:{self.site.getHost().port}/" def tearDown(self): - super(SiteTest, self).tearDown() + super().tearDown() self.site.stopListening() def url(self, path): @@ -40,5 +40,5 @@ def test_site(): if __name__ == '__main__': from twisted.internet import reactor port = reactor.listenTCP(0, test_site(), interface="127.0.0.1") - print("http://localhost:%d/" % port.getHost().port) + print(f"http://localhost:{port.getHost().port}/") reactor.run() diff --git a/scrapy/utils/trackref.py b/scrapy/utils/trackref.py index baed5c536..b0c6a2424 100644 --- a/scrapy/utils/trackref.py +++ b/scrapy/utils/trackref.py @@ -9,14 +9,15 @@ and no performance penalty at all when disabled (as object_ref becomes just an alias to object in that case). """ -import weakref -from time import time -from operator import itemgetter from collections import defaultdict +from operator import itemgetter +from time import time +from typing import DefaultDict +from weakref import WeakKeyDictionary NoneType = type(None) -live_refs = defaultdict(weakref.WeakKeyDictionary) +live_refs: DefaultDict[type, WeakKeyDictionary] = defaultdict(WeakKeyDictionary) class object_ref: @@ -41,9 +42,7 @@ def format_live_refs(ignore=NoneType): if issubclass(cls, ignore): continue oldest = min(wdict.values()) - s += "%-30s %6d oldest: %ds ago\n" % ( - cls.__name__, len(wdict), now - oldest - ) + s += f"{cls.__name__:<30} {len(wdict):6} oldest: {int(now - oldest)}s ago\n" return s diff --git a/scrapy/utils/url.py b/scrapy/utils/url.py index 955b63d4b..a6a2a9e8b 100644 --- a/scrapy/utils/url.py +++ b/scrapy/utils/url.py @@ -22,7 +22,7 @@ def url_is_from_any_domain(url, domains): if not host: return False domains = [d.lower() for d in domains] - return any((host == d) or (host.endswith('.%s' % d)) for d in domains) + return any((host == d) or (host.endswith(f'.{d}')) for d in domains) def url_is_from_spider(url, spider): @@ -83,25 +83,54 @@ def add_http_if_no_scheme(url): return url +def _is_posix_path(string): + return bool( + re.match( + r''' + ^ # start with... + ( + \. # ...a single dot, + ( + \. | [^/\.]+ # optionally followed by + )? # either a second dot or some characters + | + ~ # $HOME + )? # optional match of ".", ".." or ".blabla" + / # at least one "/" for a file path, + . # and something after the "/" + ''', + string, + flags=re.VERBOSE, + ) + ) + + +def _is_windows_path(string): + return bool( + re.match( + r''' + ^ + ( + [a-z]:\\ + | \\\\ + ) + ''', + string, + flags=re.IGNORECASE | re.VERBOSE, + ) + ) + + +def _is_filesystem_path(string): + return _is_posix_path(string) or _is_windows_path(string) + + def guess_scheme(url): - """Add an URL scheme if missing: file:// for filepath-like input or http:// otherwise.""" - parts = urlparse(url) - if parts.scheme: - return url - # Note: this does not match Windows filepath - if re.match(r'''^ # start with... - ( - \. # ...a single dot, - ( - \. | [^/\.]+ # optionally followed by - )? # either a second dot or some characters - )? # optional match of ".", ".." or ".blabla" - / # at least one "/" for a file path, - . # and something after the "/" - ''', parts.path, flags=re.VERBOSE): + """Add an URL scheme if missing: file:// for filepath-like input or + http:// otherwise.""" + if _is_filesystem_path(url): return any_to_uri(url) - else: - return add_http_if_no_scheme(url) + return add_http_if_no_scheme(url) def strip_url(url, strip_credentials=True, strip_default_port=True, origin_only=False, strip_fragment=True): @@ -124,7 +153,7 @@ def strip_url(url, strip_credentials=True, strip_default_port=True, origin_only= if (parsed_url.scheme, parsed_url.port) in (('http', 80), ('https', 443), ('ftp', 21)): - netloc = netloc.replace(':{p.port}'.format(p=parsed_url), '') + netloc = netloc.replace(f':{parsed_url.port}', '') return urlunparse(( parsed_url.scheme, netloc, diff --git a/setup.cfg b/setup.cfg index 2296a1052..1fab6fe22 100644 --- a/setup.cfg +++ b/setup.cfg @@ -3,3 +3,84 @@ doc_files = docs AUTHORS INSTALL LICENSE README.rst [bdist_wheel] universal=1 + +[mypy] +ignore_missing_imports = true +follow_imports = skip + +# FIXME: remove the following sections once the issues are solved + +[mypy-scrapy.downloadermiddlewares.httpproxy] +ignore_errors = True + +[mypy-scrapy.interfaces] +ignore_errors = True + +[mypy-scrapy.pipelines.images] +ignore_errors = True + +[mypy-scrapy.settings.default_settings] +ignore_errors = True + +[mypy-tests.mocks.dummydbm] +ignore_errors = True + +[mypy-tests.test_command_fetch] +ignore_errors = True + +[mypy-tests.test_command_parse] +ignore_errors = True + +[mypy-tests.test_command_shell] +ignore_errors = True + +[mypy-tests.test_command_version] +ignore_errors = True + +[mypy-tests.test_contracts] +ignore_errors = True + +[mypy-tests.test_downloader_handlers] +ignore_errors = True + +[mypy-tests.test_exporters] +ignore_errors = True + +[mypy-tests.test_http_request] +ignore_errors = True + +[mypy-tests.test_linkextractors] +ignore_errors = True + +[mypy-tests.test_loader] +ignore_errors = True + +[mypy-tests.test_loader_deprecated] +ignore_errors = True + +[mypy-tests.test_pipeline_crawl] +ignore_errors = True + +[mypy-tests.test_pipeline_files] +ignore_errors = True + +[mypy-tests.test_pipeline_images] +ignore_errors = True + +[mypy-tests.test_request_cb_kwargs] +ignore_errors = True + +[mypy-tests.test_scheduler] +ignore_errors = True + +[mypy-tests.test_spidermiddleware_httperror] +ignore_errors = True + +[mypy-tests.test_spidermiddleware_referer] +ignore_errors = True + +[mypy-tests.test_utils_serialize] +ignore_errors = True + +[mypy-tests.test_utils_url] +ignore_errors = True diff --git a/setup.py b/setup.py index 1b3c6771a..ed2b6e347 100644 --- a/setup.py +++ b/setup.py @@ -18,19 +18,46 @@ def has_environment_marker_platform_impl_support(): return parse_version(setuptools_version) >= parse_version('18.5') +install_requires = [ + 'Twisted>=17.9.0', + 'cryptography>=2.0', + 'cssselect>=0.9.1', + 'itemloaders>=1.0.1', + 'parsel>=1.5.0', + 'pyOpenSSL>=16.2.0', + 'queuelib>=1.4.2', + 'service_identity>=16.0.0', + 'w3lib>=1.17.0', + 'zope.interface>=4.1.3', + 'protego>=0.1.15', + 'itemadapter>=0.1.0', + 'setuptools', +] extras_require = {} - +cpython_dependencies = [ + 'lxml>=3.5.0', + 'PyDispatcher>=2.0.5', +] if has_environment_marker_platform_impl_support(): + extras_require[':platform_python_implementation == "CPython"'] = cpython_dependencies extras_require[':platform_python_implementation == "PyPy"'] = [ + # Earlier lxml versions are affected by + # https://foss.heptapod.net/pypy/pypy/-/issues/2498, + # which was fixed in Cython 0.26, released on 2017-06-19, and used to + # generate the C headers of lxml release tarballs published since then, the + # first of which was: + 'lxml>=4.0.0', 'PyPyDispatcher>=2.1.0', ] +else: + install_requires.extend(cpython_dependencies) setup( name='Scrapy', version=version, url='https://scrapy.org', - project_urls = { + project_urls={ 'Documentation': 'https://docs.scrapy.org/', 'Source': 'https://github.com/scrapy/scrapy', 'Tracker': 'https://github.com/scrapy/scrapy/issues', @@ -56,30 +83,17 @@ setup( 'Operating System :: OS Independent', 'Programming Language :: Python', 'Programming Language :: Python :: 3', - 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: 3.6', 'Programming Language :: Python :: 3.7', 'Programming Language :: Python :: 3.8', + 'Programming Language :: Python :: 3.9', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: PyPy', 'Topic :: Internet :: WWW/HTTP', 'Topic :: Software Development :: Libraries :: Application Frameworks', 'Topic :: Software Development :: Libraries :: Python Modules', ], - python_requires='>=3.5', - install_requires=[ - 'Twisted>=17.9.0', - 'cryptography>=2.0', - 'cssselect>=0.9.1', - 'lxml>=3.5.0', - 'parsel>=1.5.0', - 'PyDispatcher>=2.0.5', - 'pyOpenSSL>=16.2.0', - 'queuelib>=1.4.2', - 'service_identity>=16.0.0', - 'w3lib>=1.17.0', - 'zope.interface>=4.1.3', - 'protego>=0.1.15', - ], + python_requires='>=3.6', + install_requires=install_requires, extras_require=extras_require, ) diff --git a/tests/CrawlerProcess/alternative_name_resolver.py b/tests/CrawlerProcess/alternative_name_resolver.py deleted file mode 100644 index 2c466da04..000000000 --- a/tests/CrawlerProcess/alternative_name_resolver.py +++ /dev/null @@ -1,15 +0,0 @@ -import scrapy -from scrapy.crawler import CrawlerProcess - - -class IPv6Spider(scrapy.Spider): - name = "ipv6_spider" - start_urls = ["http://[::1]"] - - -process = CrawlerProcess(settings={ - "RETRY_ENABLED": False, - "DNS_RESOLVER": "scrapy.resolver.CachingHostnameResolver", -}) -process.crawl(IPv6Spider) -process.start() diff --git a/tests/CrawlerProcess/asyncio_custom_loop.py b/tests/CrawlerProcess/asyncio_custom_loop.py new file mode 100644 index 000000000..1e4ada722 --- /dev/null +++ b/tests/CrawlerProcess/asyncio_custom_loop.py @@ -0,0 +1,17 @@ +import scrapy +from scrapy.crawler import CrawlerProcess + + +class NoRequestsSpider(scrapy.Spider): + name = 'no_request' + + def start_requests(self): + return [] + + +process = CrawlerProcess(settings={ + "TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor", + "ASYNCIO_EVENT_LOOP": "uvloop.Loop" +}) +process.crawl(NoRequestsSpider) +process.start() diff --git a/tests/CrawlerProcess/asyncio_deferred_signal.py b/tests/CrawlerProcess/asyncio_deferred_signal.py new file mode 100644 index 000000000..bdd3c1fef --- /dev/null +++ b/tests/CrawlerProcess/asyncio_deferred_signal.py @@ -0,0 +1,46 @@ +import asyncio +import sys +from typing import Optional + +from scrapy import Spider +from scrapy.crawler import CrawlerProcess +from scrapy.utils.defer import deferred_from_coro +from twisted.internet.defer import Deferred + + +class UppercasePipeline: + async def _open_spider(self, spider): + spider.logger.info("async pipeline opened!") + await asyncio.sleep(0.1) + + def open_spider(self, spider): + return deferred_from_coro(self._open_spider(spider)) + + def process_item(self, item, spider): + return {"url": item["url"].upper()} + + +class UrlSpider(Spider): + name = "url_spider" + start_urls = ["data:,"] + custom_settings = { + "ITEM_PIPELINES": {UppercasePipeline: 100}, + } + + def parse(self, response): + yield {"url": response.url} + + +if __name__ == "__main__": + ASYNCIO_EVENT_LOOP: Optional[str] + try: + ASYNCIO_EVENT_LOOP = sys.argv[1] + except IndexError: + ASYNCIO_EVENT_LOOP = None + + process = CrawlerProcess(settings={ + "TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor", + "ASYNCIO_EVENT_LOOP": ASYNCIO_EVENT_LOOP, + }) + process.crawl(UrlSpider) + process.start() diff --git a/tests/CrawlerProcess/caching_hostname_resolver.py b/tests/CrawlerProcess/caching_hostname_resolver.py new file mode 100644 index 000000000..f9eab3543 --- /dev/null +++ b/tests/CrawlerProcess/caching_hostname_resolver.py @@ -0,0 +1,30 @@ +import sys + +import scrapy +from scrapy.crawler import CrawlerProcess + + +class CachingHostnameResolverSpider(scrapy.Spider): + """ + Finishes in a finite amount of time (does not hang indefinitely in the DNS resolution) + """ + name = "caching_hostname_resolver_spider" + + def start_requests(self): + yield scrapy.Request(self.url) + + def parse(self, response): + for _ in range(10): + yield scrapy.Request(response.url, dont_filter=True, callback=self.ignore_response) + + def ignore_response(self, response): + self.logger.info(repr(response.ip_address)) + + +if __name__ == "__main__": + process = CrawlerProcess(settings={ + "RETRY_ENABLED": False, + "DNS_RESOLVER": "scrapy.resolver.CachingHostnameResolver", + }) + process.crawl(CachingHostnameResolverSpider, url=sys.argv[1]) + process.start() diff --git a/tests/CrawlerProcess/caching_hostname_resolver_ipv6.py b/tests/CrawlerProcess/caching_hostname_resolver_ipv6.py new file mode 100644 index 000000000..3340d2f84 --- /dev/null +++ b/tests/CrawlerProcess/caching_hostname_resolver_ipv6.py @@ -0,0 +1,19 @@ +import scrapy +from scrapy.crawler import CrawlerProcess + + +class CachingHostnameResolverSpider(scrapy.Spider): + """ + Finishes without a twisted.internet.error.DNSLookupError exception + """ + name = "caching_hostname_resolver_spider" + start_urls = ["http://[::1]"] + + +if __name__ == "__main__": + process = CrawlerProcess(settings={ + "RETRY_ENABLED": False, + "DNS_RESOLVER": "scrapy.resolver.CachingHostnameResolver", + }) + process.crawl(CachingHostnameResolverSpider) + process.start() diff --git a/tests/CrawlerProcess/default_name_resolver.py b/tests/CrawlerProcess/default_name_resolver.py index 60d91b68b..05a98fbec 100644 --- a/tests/CrawlerProcess/default_name_resolver.py +++ b/tests/CrawlerProcess/default_name_resolver.py @@ -3,10 +3,15 @@ from scrapy.crawler import CrawlerProcess class IPv6Spider(scrapy.Spider): + """ + Raises a twisted.internet.error.DNSLookupError: + the default name resolver does not handle IPv6 addresses. + """ name = "ipv6_spider" start_urls = ["http://[::1]"] -process = CrawlerProcess(settings={"RETRY_ENABLED": False}) -process.crawl(IPv6Spider) -process.start() +if __name__ == "__main__": + process = CrawlerProcess(settings={"RETRY_ENABLED": False}) + process.crawl(IPv6Spider) + process.start() diff --git a/tests/CrawlerRunner/ip_address.py b/tests/CrawlerRunner/ip_address.py index 826374cd4..f545de39f 100644 --- a/tests/CrawlerRunner/ip_address.py +++ b/tests/CrawlerRunner/ip_address.py @@ -1,7 +1,9 @@ from urllib.parse import urlparse from twisted.internet import reactor -from twisted.names.client import createResolver +from twisted.names import cache, hosts as hostsModule, resolve +from twisted.names.client import Resolver +from twisted.python.runtime import platform from scrapy import Spider, Request from scrapy.crawler import CrawlerRunner @@ -10,6 +12,16 @@ from scrapy.utils.log import configure_logging from tests.mockserver import MockServer, MockDNSServer +# https://stackoverflow.com/a/32784190 +def createResolver(servers=None, resolvconf=None, hosts=None): + if hosts is None: + hosts = b'/etc/hosts' if platform.getType() == 'posix' else r'c:\windows\hosts' + theResolver = Resolver(resolvconf, servers) + hostResolver = hostsModule.Resolver(hosts) + chain = [hostResolver, cache.CacheResolver(), theResolver] + return resolve.ResolverChain(chain) + + class LocalhostSpider(Spider): name = "localhost_spider" @@ -26,7 +38,7 @@ class LocalhostSpider(Spider): if __name__ == "__main__": with MockServer() as mock_http_server, MockDNSServer() as mock_dns_server: port = urlparse(mock_http_server.http_address).port - url = "http://not.a.real.domain:{port}/echo".format(port=port) + url = f"http://not.a.real.domain:{port}/echo" servers = [(mock_dns_server.host, mock_dns_server.port)] reactor.installResolver(createResolver(servers=servers)) diff --git a/tests/constraints.txt b/tests/constraints.txt deleted file mode 100644 index 5655ac2d3..000000000 --- a/tests/constraints.txt +++ /dev/null @@ -1 +0,0 @@ -Twisted!=18.4.0 \ No newline at end of file diff --git a/tests/ftpserver.py b/tests/ftpserver.py new file mode 100644 index 000000000..6f0289e08 --- /dev/null +++ b/tests/ftpserver.py @@ -0,0 +1,24 @@ +from argparse import ArgumentParser + +from pyftpdlib.authorizers import DummyAuthorizer +from pyftpdlib.handlers import FTPHandler +from pyftpdlib.servers import FTPServer + + +def main(): + parser = ArgumentParser() + parser.add_argument('-d', '--directory') + args = parser.parse_args() + + authorizer = DummyAuthorizer() + full_permissions = 'elradfmwMT' + authorizer.add_anonymous(args.directory, perm=full_permissions) + handler = FTPHandler + handler.authorizer = authorizer + address = ('127.0.0.1', 2121) + server = FTPServer(address, handler) + server.serve_forever() + + +if __name__ == '__main__': + main() diff --git a/tests/ignores.txt b/tests/ignores.txt index 45cf6fb92..222288841 100644 --- a/tests/ignores.txt +++ b/tests/ignores.txt @@ -1,6 +1,3 @@ -scrapy/linkextractors/sgml.py -scrapy/linkextractors/regex.py -scrapy/linkextractors/htmlparser.py scrapy/downloadermiddlewares/cookies.py scrapy/extensions/statsmailer.py scrapy/extensions/memusage.py diff --git a/tests/keys/__init__.py b/tests/keys/__init__.py new file mode 100644 index 000000000..da202be4d --- /dev/null +++ b/tests/keys/__init__.py @@ -0,0 +1,63 @@ +import os +from datetime import datetime, timedelta + +from cryptography.hazmat.backends import default_backend +from cryptography.hazmat.primitives.asymmetric import rsa +from cryptography.hazmat.primitives.hashes import SHA256 +from cryptography.hazmat.primitives.serialization import ( + Encoding, + NoEncryption, + PrivateFormat, +) +from cryptography.x509 import ( + CertificateBuilder, + DNSName, + Name, + NameAttribute, + random_serial_number, + SubjectAlternativeName, +) +from cryptography.x509.oid import NameOID + + +# https://cryptography.io/en/latest/x509/tutorial/#creating-a-self-signed-certificate +def generate_keys(): + folder = os.path.dirname(__file__) + + key = rsa.generate_private_key( + public_exponent=65537, + key_size=2048, + backend=default_backend(), + ) + with open(os.path.join(folder, 'localhost.key'), "wb") as f: + f.write( + key.private_bytes( + encoding=Encoding.PEM, + format=PrivateFormat.TraditionalOpenSSL, + encryption_algorithm=NoEncryption(), + ) + ) + + subject = issuer = Name( + [ + NameAttribute(NameOID.COUNTRY_NAME, u"IE"), + NameAttribute(NameOID.ORGANIZATION_NAME, u"Scrapy"), + NameAttribute(NameOID.COMMON_NAME, u"localhost"), + ] + ) + cert = ( + CertificateBuilder() + .subject_name(subject) + .issuer_name(issuer) + .public_key(key.public_key()) + .serial_number(random_serial_number()) + .not_valid_before(datetime.utcnow()) + .not_valid_after(datetime.utcnow() + timedelta(days=10)) + .add_extension( + SubjectAlternativeName([DNSName(u"localhost")]), + critical=False, + ) + .sign(key, SHA256(), default_backend()) + ) + with open(os.path.join(folder, 'localhost.crt'), "wb") as f: + f.write(cert.public_bytes(Encoding.PEM)) diff --git a/tests/keys/localhost.crt b/tests/keys/localhost.crt deleted file mode 100644 index 13c5b5bd6..000000000 --- a/tests/keys/localhost.crt +++ /dev/null @@ -1,20 +0,0 @@ ------BEGIN CERTIFICATE----- -MIIDNzCCAh+gAwIBAgIJANWqWyPdTY8CMA0GCSqGSIb3DQEBCwUAMDIxCzAJBgNV -BAYTAklFMQ8wDQYDVQQKDAZTY3JhcHkxEjAQBgNVBAMMCWxvY2FsaG9zdDAeFw0x -NzA0MjcxNzQxNTdaFw0xODA0MjcxNzQxNTdaMDIxCzAJBgNVBAYTAklFMQ8wDQYD -VQQKDAZTY3JhcHkxEjAQBgNVBAMMCWxvY2FsaG9zdDCCASIwDQYJKoZIhvcNAQEB -BQADggEPADCCAQoCggEBAK1jcwlJ+bpr63lmK1mSk83nduF+27EPTU3RyteoPM2K -o/RqZnr/mR29U6Pu42YuhLvBUu7rQxGi+rgkwno6lMFP4y5glxRygIlPsP4WQO3Y -njmysWfYxQoIml2A+tiLewrMZocHI2cNgrO8Fd0u7KMiLlvUCN0pVyOwZ/ym9rPY -ObfquG/xYTFzgYD/wy1n4AXE4ve3uZPfB3ZGtB3fUmuowg5KZ1L3uWpviyqr1qB/ -8NXcORLegAPsquLA05gnDPOuMs7dSMeKMphvpbSerRXLGxLIfWOZ0rs8oV96Re52 -gSEg/kIIS+ts37sJofcEnx9C4FkTR8zXin9eZhgCYs0CAwEAAaNQME4wHQYDVR0O -BBYEFOoYbg0MvcnbTN0jxISsP2ctMbjpMB8GA1UdIwQYMBaAFOoYbg0MvcnbTN0j -xISsP2ctMbjpMAwGA1UdEwQFMAMBAf8wDQYJKoZIhvcNAQELBQADggEBAF/JlzES -9Z3Azaj60gvJHyPJsPSM4tUfnWoFfFrui3oPG5TJPxWqrLBsTEachUTKOd5+XR2i -jxUuREMkcRjbc0jjsqhsxPvfgrUrbIvKjEFLfAPvvLvcQIMUJf09SEjaaMkUAYd+ -TJaxFn5kd9Q6HbkD/fEN+lKhNZI40IJvfu7u4emUj3uKy9zrw576/T8aDYUl/own -tqqfXh/jN8wnKCQwma7gaPmMOMqBt6zCsrN9/eKnMBpdULkUtjJD4NDg03XUFLlM -am/oQ+MnasCcctkaXKbTGx3WfBVmkGj4b3Au18CVZkRWN2QsMdBC8JLRTICKse8U -Mjybr/hQK3mnVdE= ------END CERTIFICATE----- diff --git a/tests/keys/localhost.key b/tests/keys/localhost.key deleted file mode 100644 index da975e6d3..000000000 --- a/tests/keys/localhost.key +++ /dev/null @@ -1,28 +0,0 @@ ------BEGIN PRIVATE KEY----- -MIIEvQIBADANBgkqhkiG9w0BAQEFAASCBKcwggSjAgEAAoIBAQCtY3MJSfm6a+t5 -ZitZkpPN53bhftuxD01N0crXqDzNiqP0amZ6/5kdvVOj7uNmLoS7wVLu60MRovq4 -JMJ6OpTBT+MuYJcUcoCJT7D+FkDt2J45srFn2MUKCJpdgPrYi3sKzGaHByNnDYKz -vBXdLuyjIi5b1AjdKVcjsGf8pvaz2Dm36rhv8WExc4GA/8MtZ+AFxOL3t7mT3wd2 -RrQd31JrqMIOSmdS97lqb4sqq9agf/DV3DkS3oAD7KriwNOYJwzzrjLO3UjHijKY -b6W0nq0VyxsSyH1jmdK7PKFfekXudoEhIP5CCEvrbN+7CaH3BJ8fQuBZE0fM14p/ -XmYYAmLNAgMBAAECggEAQKY4GlqO1seugRFrUHaqzbdkSCf42kgOVtnGfCqqoSj0 -gQm7NFlhSglxykokV9E4hJlMxvDJjSXrvgVWziRRmtKiroQtUN5wtsIUCGlbxFNk -i7bpFwNoVJlolTymS1+WfSxBfk9XD/GlrkaPEG2SpjD0gCDLPUtQxmncHARVMDDu -Eysk3njGghsTF7XMh8ljTE3CqqNSx9BkeWQr6EYfXcgaQ2jp9E+FspB5+KWeO4ss -ELVHgtwmYSRPAEuz4XHz87RLuakqafko6ftvh3upVQwm0VXuwM+lEUYZrzoU2JQ4 -hePKHRaWQC4tawV6FyVHK4X0MuKP4uESr7YHbJ03sQKBgQDV4CyQU6xccW6hMxlD -7hvrGcPQEPg6M4rX2uqWpB6RCh6stZEydYeh5S+A6ltml/2csw9Bl8nZM6KbArZa -EKrZcOn7JgFyPpiDHqgEIx+9XL/mnsKMSkBKTFcvucVgjIWE8GT7jfAqMkcSysWf -uRyUvtNpshmRLcdNhEjrr3vcwwKBgQDPid6sxBVcoyvrYUsRRVpXATJ9tsmU93LG -HMHDlXkZ2CMfEuA0xLK+B9iyHMhh8NwYFjcG5oeVyVjE8SbifX4Sg49hde8ykXSR -UBSNt22/JaWgreL95LEC/y9q+G4osli7NwRW1x6tB5cN1mE0hZI8Z0ETvyr3DoWO -j/dbdFYJLwKBgDjVLCJiCbA6+EHfuTwC3upXW2BD0iJtJdz8MFA9Zl32SXZtfRri -fls38qqYHBekFeF493nfouSTwwbb7qb6PNwxFAwH6mR4W8Cj+dO3nayNI/VdhKcQ -6AqWRKjK/bcNQEG2O69Y5VPhLl/BAEjUQNMJ7lXs3LxmZMqld1cht5FPAoGBAJbI -xXbiU97lUmCGZKLcr4EtBoEdz6GiksnrVMAEFmM3jHTkIu9TxcWZL9BgZxn5g/8g -DMS/styZ2BvmVWkS4gkTepXFuI8V7Qoyk2xPS7Yn5QkzrQroH89clhfy/R4mTZ9f -npB1ZP0z2YSdMCyXqyKlpjtxlga/jzt/z6irgmLTAoGAPrmudajtSBq534Ql2lPM -8U6baRSAMMzV7MXcR8F1CRewQiYOzlgsB8toELNtjg1IGPqmoiNDDKmkHs3R2mO6 -J45kDPLFe9DTyZLZj0pWWK6yRLc/BA/gGzKFpMkNcyzLlQjNPqY/9mrrYea4J9Cj -Z+pMCFLbwAbFZ9Qb/NFlUv0= ------END PRIVATE KEY----- diff --git a/tests/keys/mitmproxy-ca.pem b/tests/keys/mitmproxy-ca.pem index 08004feca..cdef75f99 100644 --- a/tests/keys/mitmproxy-ca.pem +++ b/tests/keys/mitmproxy-ca.pem @@ -1,32 +1,50 @@ ------BEGIN RSA PRIVATE KEY----- -MIICWwIBAAKBgQDKLbznLxS7HSWvrmGcvVS6eQvjEWD705/csvnk/WtqAPfQMJKt -auFBxzPt6RT60SHtj/2FKt2gqsiE6cNINxGN6fGYD7HtaM5HXRVPUKJaMipJwHha -QivjIZoueraY/MtlyCkpp6dmMnHEpGY7OzwMyh1eCBHQ2JYx6VEzbks9ewIDAQAB -AoGAMpS2ye/Rc+6a2xT5fskvRWe7PZe/d8E+IWz1cACmuuJ7HS7Jw3EV4esAZukF -QqrHnjOD7akHwYZ4nCgPnyWH0lLx/4TIXE5QeLPFrhKOsSLCyhlCwNVJAdcOrDol -Qh2694Dsd4gAy5o6TA02cBpqArnbAUERX46bHBZRA+ths8ECQQD6r1Ls+bTBR52w -T3rPPhYj7EsXp40MJt0pLf1kjf+EH1bxsUqnxLawwo/lLE9omU73DFnfrAflk2Ll -KUPCjjYpAkEAznchXk2ITeRcClrBNA+1Izpb5yG1qkfc79u/CEVDDOvt7RO/89Oj -58R3pKTyffoo34fBdJz8GYDsmOeiyJEjAwJANpSHrJrtlQt/tMyJQ6gT7/xZmSvc -1OF9U6L0wbj9AgpExtjAFWkKEdA6vj34iCChBb8FrmJpUb3WUWi7nReTiQJAFyIT -9Av93LRcd7CJezrTUdolF/WX9DdPEvTtJ5ETHSyGIQ0Yccph0AMcYK82mFTiJYGB -dH5uZLEkUVGK1KwmXwJAGWLdYiQyQitRWdoURcLb4OZ2gF3+7PASgFilI8YuoYhn -Rl2Va3UtErPKJeMg2dTH18PuXykQMsQR1+rPxf1WSA== ------END RSA PRIVATE KEY----- +-----BEGIN PRIVATE KEY----- +MIIEvgIBADANBgkqhkiG9w0BAQEFAASCBKgwggSkAgEAAoIBAQCYp6U4G9YWITYB +/JlZ+Hd08c/9a157WVl03hbR2DSK8FnK+D8cp2dGzuTfC08w8M/yvVYPcbb7ZDiT +NUsVwboFvmr/6mN6M9uQioCRStrP6Rkm2Wuagyj+GjqLwogTJlPiPwEPhlMgz1BJ +u6jQQSgiMsxKWMkVz3pCYERUMRX0DEgYST9rjYUAwD4rPv8XXtLLSPs0VniIggUH +JrngDUrtoK5Wuf098NJPIwW8uE2ev+DXH2Iuwn2fNKt5lSYypJdUZjyamwuE6HFB +eIBAIIKijMz/8UV1+H8Q0OcU2Sva2FglHREQtA/S5FlpcuTZt/77Vnxv75y/0zls +90iyQ3E/AgMBAAECggEBAJA1dyAdM85uC04vKVNUJM1GDp0xS+0syBReJaKRI3nJ +epoCj+RqxGag1pdaYLI0G84NTPqECz9LOyLdqpPgEfKRIxWlf9oWmSnfnXskArd8 +VfVcWYl6tEPv1TToTZIBmCbYLBFVbLxG/GrbK6uokdhUsqbdXwEKok2IEaSTRlDn +v8BVXte00d9VEKKpmI6EY3f45uPQPHuJNcitP2HGW1mT/C6XoZR6wj+VvoRgUGQT +I7PuktbYpQlLV+oX0uZz9frPGhjydUq0Jti5v3QAJEb+7D0cKrkZW+7fYDx4YkRU +oDiuWEyO2kfpff52Qxs+xUXMiAyw6/8+TamKoAi1TIECgYEAyAzoztW6W4CjL2au +/hN5VmbAvuBxq1m1G5KgXM1myX9V2CgH6OKwzJQNSCEfKMNOjqxB99T7C3tMCjgG +gmbUzylTeciQFF+crrl2Rn/6qZS9dCo1hagb3K5eXMhLXoP425Y4sypNPPqULhPn +YrUDFNAf89rRLqP1KMPLZ+uO7EECgYEAw1lWPxGV+X85iQxYN9xoX85htfJSBXTf +dLirQ4bkykOxSA6ZzFuhDO/G373Q1rze4tmEO790uOCeaiXGgeWC1A+2PMO957i5 +9FqhDIkmerfdIttdEUMM9rQwuTcLnixGZkT5GHDzjtNinaIVB+pv7twRAESqN9dC +QXh7IF7g/X8CgYBMhQOX+hCqZ24D95cAAJrs/ajEWj2geVPZFCDa3oZulJJVeBpu +bieKWScra9/rS6mE0Ub6cTEFl0fisMNspcDI7NnNP3Y9FMVt3+rp1JIgw5AkGvEW +CtN9egUGIGcT5A8Qj0lo3slkhcSgS2S6UNq431MZh51z5askyJ/JREULAQKBgFrR +OatwfYzUfOcd+hVePpfr1rlDwqYOw6P8BoMKP2tZNR4Oy6maH7Fn98kk8eYjQGuu +PC+avqUEqCEpFrRlAwGbnFl7ltoXozvatmyhhmYe/Iur+ASCa5B2DQDOenQ6mTAK +eNPIDzMjSwGFzMk1UHx3it/ZDFmRlZfibzuJYIf5AoGBAIaPHk4qadK/XpcD4Wwx +BOsDEIz27DGWdwWfd5r3EcV4zX/wNzH0G1Z8eydNjUqKzufMZgFwpcTu0Evesl1/ +B8kC8sLHxQoG5SvBu4dBxMwKIU9O9uFnX5SUYZUDpCtUYyZ+GtGom41Jwg5ENrwy +HzPh2taMnCA0h1fNLFFBkw88 +-----END PRIVATE KEY----- -----BEGIN CERTIFICATE----- -MIICnzCCAgigAwIBAgIGDI2K/EOjMA0GCSqGSIb3DQEBBQUAMCgxEjAQBgNVBAMT -CW1pdG1wcm94eTESMBAGA1UEChMJbWl0bXByb3h5MB4XDTEzMDkyNjE0MzYxMVoX -DTE1MDkxNjE0MzYxMVowKDESMBAGA1UEAxMJbWl0bXByb3h5MRIwEAYDVQQKEwlt -aXRtcHJveHkwgZ8wDQYJKoZIhvcNAQEBBQADgY0AMIGJAoGBAMotvOcvFLsdJa+u -YZy9VLp5C+MRYPvTn9yy+eT9a2oA99Awkq1q4UHHM+3pFPrRIe2P/YUq3aCqyITp -w0g3EY3p8ZgPse1ozkddFU9QoloyKknAeFpCK+Mhmi56tpj8y2XIKSmnp2YyccSk -Zjs7PAzKHV4IEdDYljHpUTNuSz17AgMBAAGjgdMwgdAwDwYDVR0TAQH/BAUwAwEB -/zAUBglghkgBhvhCAQEBAf8EBAMCAgQwewYDVR0lAQH/BHEwbwYIKwYBBQUHAwEG -CCsGAQUFBwMCBggrBgEFBQcDBAYIKwYBBQUHAwgGCisGAQQBgjcCARUGCisGAQQB -gjcCARYGCisGAQQBgjcKAwEGCisGAQQBgjcKAwMGCisGAQQBgjcKAwQGCWCGSAGG -+EIEATALBgNVHQ8EBAMCAQYwHQYDVR0OBBYEFJBEfawVwhEHHW6rS8nvZFlJ582n -MA0GCSqGSIb3DQEBBQUAA4GBAHGl28Ip2CWS/MibCaFztLDxGiMBT4MW2yI2hf3D -y9g1o7ra/fSEFdIc849xXyCsGWSkMsbDML272rCH4K73MUBxxkJm46AIyRVH1z2Z -e96u4py1wNT8cznY15phr8pn36snlaHaYa+JcwGINMdSOk1VPHv6gqSC/vgUCgF1 -n95u +MIIDoTCCAomgAwIBAgIGDodLQx9+MA0GCSqGSIb3DQEBCwUAMCgxEjAQBgNVBAMM +CW1pdG1wcm94eTESMBAGA1UECgwJbWl0bXByb3h5MB4XDTIwMDgxMjE3MDMyNloX +DTIzMDgxNDE3MDMyNlowKDESMBAGA1UEAwwJbWl0bXByb3h5MRIwEAYDVQQKDAlt +aXRtcHJveHkwggEiMA0GCSqGSIb3DQEBAQUAA4IBDwAwggEKAoIBAQCYp6U4G9YW +ITYB/JlZ+Hd08c/9a157WVl03hbR2DSK8FnK+D8cp2dGzuTfC08w8M/yvVYPcbb7 +ZDiTNUsVwboFvmr/6mN6M9uQioCRStrP6Rkm2Wuagyj+GjqLwogTJlPiPwEPhlMg +z1BJu6jQQSgiMsxKWMkVz3pCYERUMRX0DEgYST9rjYUAwD4rPv8XXtLLSPs0VniI +ggUHJrngDUrtoK5Wuf098NJPIwW8uE2ev+DXH2Iuwn2fNKt5lSYypJdUZjyamwuE +6HFBeIBAIIKijMz/8UV1+H8Q0OcU2Sva2FglHREQtA/S5FlpcuTZt/77Vnxv75y/ +0zls90iyQ3E/AgMBAAGjgdAwgc0wDwYDVR0TAQH/BAUwAwEB/zARBglghkgBhvhC +AQEEBAMCAgQweAYDVR0lBHEwbwYIKwYBBQUHAwEGCCsGAQUFBwMCBggrBgEFBQcD +BAYIKwYBBQUHAwgGCisGAQQBgjcCARUGCisGAQQBgjcCARYGCisGAQQBgjcKAwEG +CisGAQQBgjcKAwMGCisGAQQBgjcKAwQGCWCGSAGG+EIEATAOBgNVHQ8BAf8EBAMC +AQYwHQYDVR0OBBYEFBCsLPpFz3l9rOOfGmfs+VRc3jhJMA0GCSqGSIb3DQEBCwUA +A4IBAQADTpA15na6U5qqDCe0rr39fkS1/dY804Xnz7g/L3AsxPE1KOMijuJa8sKd +kKwba1173FwMupfK39zY8jUxL8Qprdi92RO6CpoFUsL/icpA///lYhzUSqt32qwe +gRNW3mtYBimOk6KH1NOfQnJolWpJh+g1OEsitQKEeKwIn5Hz+8/yS5tbwLgdnMlY +1/it1H70JSdE7nfJueqN4cFfBsm6XaHZzacJJmN7WP88fd+zztnSQsBFbLlnjnqj +envCDIwCrMywKNMqEBMwmBEGSAF47fVNYj6KzDAtMvBdDkYaHWpBf4tnFfk6v0wj +wiKjdLjCmJgjGAQjRw5VYJ8JI0XO -----END CERTIFICATE----- diff --git a/tests/mockserver.py b/tests/mockserver.py index 30d9bc0e8..ab9aec6a6 100644 --- a/tests/mockserver.py +++ b/tests/mockserver.py @@ -3,7 +3,10 @@ import json import os import random import sys +from pathlib import Path +from shutil import rmtree from subprocess import Popen, PIPE +from tempfile import mkdtemp from urllib.parse import urlencode from OpenSSL import SSL @@ -70,7 +73,7 @@ class Follow(LeafResource): for nl in nlist: args[b"n"] = [to_bytes(str(nl))] argstr = urlencode(args, doseq=True) - s += "follow %d
    " % (argstr, nl) + s += f"follow {nl}
    " s += """""" request.write(to_bytes(s)) request.finish() @@ -88,7 +91,7 @@ class Delay(LeafResource): return NOT_DONE_YET def _delayedRender(self, request, n): - request.write(to_bytes("Response delayed for %0.3f seconds\n" % n)) + request.write(to_bytes(f"Response delayed for {n:.3f} seconds\n")) request.finish() @@ -218,9 +221,8 @@ class MockServer: self.proc.communicate() def url(self, path, is_secure=False): - host = self.http_address.replace('0.0.0.0', '127.0.0.1') - if is_secure: - host = self.https_address + host = self.https_address if is_secure else self.http_address + host = host.replace('0.0.0.0', '127.0.0.1') return host + path @@ -248,9 +250,8 @@ class MockDNSServer: def __enter__(self): self.proc = Popen([sys.executable, '-u', '-m', 'tests.mockserver', '-t', 'dns'], stdout=PIPE, env=get_testenv()) - host, port = self.proc.stdout.readline().strip().decode('ascii').split(":") - self.host = host - self.port = int(port) + self.host = '127.0.0.1' + self.port = int(self.proc.stdout.readline().strip().decode('ascii').split(":")[1]) return self def __exit__(self, exc_type, exc_value, traceback): @@ -258,6 +259,29 @@ class MockDNSServer: self.proc.communicate() +class MockFTPServer: + """Creates an FTP server on port 2121 with a default passwordless user + (anonymous) and a temporary root path that you can read from the + :attr:`path` attribute.""" + + def __enter__(self): + self.path = Path(mkdtemp()) + self.proc = Popen([sys.executable, '-u', '-m', 'tests.ftpserver', '-d', str(self.path)], + stderr=PIPE, env=get_testenv()) + for line in self.proc.stderr: + if b'starting FTP server' in line: + break + return self + + def __exit__(self, exc_type, exc_value, traceback): + rmtree(str(self.path)) + self.proc.kill() + self.proc.communicate() + + def url(self, path): + return 'ftp://127.0.0.1:2121/' + path + + def ssl_context_factory(keyfile='keys/localhost.key', certfile='keys/localhost.crt', cipher_string=None): factory = ssl.DefaultOpenSSLContextFactory( os.path.join(os.path.dirname(__file__), keyfile), @@ -265,8 +289,8 @@ def ssl_context_factory(keyfile='keys/localhost.key', certfile='keys/localhost.c ) if cipher_string: ctx = factory.getContext() - # disabling TLS1.2+ because it unconditionally enables some strong ciphers - ctx.set_options(SSL.OP_CIPHER_SERVER_PREFERENCE | SSL.OP_NO_TLSv1_2 | SSL_OP_NO_TLSv1_3) + # disabling TLS1.3 because it unconditionally enables some strong ciphers + ctx.set_options(SSL.OP_CIPHER_SERVER_PREFERENCE | SSL_OP_NO_TLSv1_3) ctx.set_cipher_list(to_bytes(cipher_string)) return factory @@ -286,8 +310,8 @@ if __name__ == "__main__": def print_listening(): httpHost = httpPort.getHost() httpsHost = httpsPort.getHost() - httpAddress = "http://%s:%d" % (httpHost.host, httpHost.port) - httpsAddress = "https://%s:%d" % (httpsHost.host, httpsHost.port) + httpAddress = f'http://{httpHost.host}:{httpHost.port}' + httpsAddress = f'https://{httpsHost.host}:{httpsHost.port}' print(httpAddress) print(httpsAddress) @@ -299,7 +323,7 @@ if __name__ == "__main__": def print_listening(): host = listener.getHost() - print("%s:%s" % (host.host, host.port)) + print(f"{host.host}:{host.port}") reactor.callWhenRunning(print_listening) reactor.run() diff --git a/tests/py36/_test_crawl.py b/tests/py36/_test_crawl.py deleted file mode 100644 index 162a53760..000000000 --- a/tests/py36/_test_crawl.py +++ /dev/null @@ -1,57 +0,0 @@ -import asyncio - -from scrapy import Request -from tests.spiders import SimpleSpider - - -class AsyncDefAsyncioGenSpider(SimpleSpider): - - name = 'asyncdef_asyncio_gen' - - async def parse(self, response): - await asyncio.sleep(0.2) - yield {'foo': 42} - self.logger.info("Got response %d" % response.status) - - -class AsyncDefAsyncioGenLoopSpider(SimpleSpider): - - name = 'asyncdef_asyncio_gen_loop' - - async def parse(self, response): - for i in range(10): - await asyncio.sleep(0.1) - yield {'foo': i} - self.logger.info("Got response %d" % response.status) - - -class AsyncDefAsyncioGenComplexSpider(SimpleSpider): - - name = 'asyncdef_asyncio_gen_complex' - initial_reqs = 4 - following_reqs = 3 - depth = 2 - - def _get_req(self, index, cb=None): - return Request(self.mockserver.url("/status?n=200&request=%d" % index), - meta={'index': index}, - dont_filter=True, - callback=cb) - - def start_requests(self): - for i in range(1, self.initial_reqs + 1): - yield self._get_req(i) - - async def parse(self, response): - index = response.meta['index'] - yield {'index': index} - if index < 10 ** self.depth: - for new_index in range(10 * index, 10 * index + self.following_reqs): - yield self._get_req(new_index) - yield self._get_req(index, cb=self.parse2) - await asyncio.sleep(0.1) - yield {'index': index + 5} - - async def parse2(self, response): - await asyncio.sleep(0.1) - yield {'index2': response.meta['index']} diff --git a/tests/requirements-py3.txt b/tests/requirements-py3.txt index 91fa1c5b5..bd72c8c46 100644 --- a/tests/requirements-py3.txt +++ b/tests/requirements-py3.txt @@ -1,17 +1,18 @@ # Tests requirements -jmespath -mitmproxy; python_version >= '3.6' -mitmproxy<4.0.0; python_version < '3.6' -# https://github.com/pytest-dev/pytest-twisted/issues/93 -pytest != 5.4, != 5.4.1 +attrs +dataclasses; python_version == '3.6' +pyftpdlib +pytest pytest-cov -pytest-twisted >= 1.11 pytest-xdist -sybil +sybil >= 1.3.0 # https://github.com/cjw296/sybil/issues/20#issuecomment-605433422 testfixtures +uvloop < 0.15.0; platform_system != "Windows" and python_version == '3.6' +uvloop; platform_system != "Windows" and python_version > '3.6' # optional for shell wrapper tests bpython -brotlipy +brotlipy # optional for HTTP compress downloader middleware tests +zstandard; implementation_name != 'pypy' # optional for HTTP compress downloader middleware tests ipython pywin32; sys_platform == "win32" diff --git a/tests/sample_data/compressed/html-zstd-static-content-size.bin b/tests/sample_data/compressed/html-zstd-static-content-size.bin new file mode 100644 index 000000000..b5c2038e8 Binary files /dev/null and b/tests/sample_data/compressed/html-zstd-static-content-size.bin differ diff --git a/tests/sample_data/compressed/html-zstd-static-no-content-size.bin b/tests/sample_data/compressed/html-zstd-static-no-content-size.bin new file mode 100644 index 000000000..3d494192e Binary files /dev/null and b/tests/sample_data/compressed/html-zstd-static-no-content-size.bin differ diff --git a/tests/sample_data/compressed/html-zstd-streaming-no-content-size.bin b/tests/sample_data/compressed/html-zstd-streaming-no-content-size.bin new file mode 100644 index 000000000..97bdbcae0 Binary files /dev/null and b/tests/sample_data/compressed/html-zstd-streaming-no-content-size.bin differ diff --git a/tests/sample_data/link_extractor/linkextractor.html b/tests/sample_data/link_extractor/linkextractor.html index 7d5db368a..2307ea865 100644 --- a/tests/sample_data/link_extractor/linkextractor.html +++ b/tests/sample_data/link_extractor/linkextractor.html @@ -1,7 +1,7 @@ -Sample page with links for testing RegexLinkExtractor +Sample page with links for testing LinkExtractor
    diff --git a/tests/sample_data/link_extractor/linkextractor_latin1.html b/tests/sample_data/link_extractor/linkextractor_latin1.html index fc31d7e5d..e7eee18de 100644 --- a/tests/sample_data/link_extractor/linkextractor_latin1.html +++ b/tests/sample_data/link_extractor/linkextractor_latin1.html @@ -2,7 +2,7 @@ - Sample page with links for testing RegexLinkExtractor + Sample page with links for testing LinkExtractor
    diff --git a/tests/spiders.py b/tests/spiders.py index a360d8206..5b45f897e 100644 --- a/tests/spiders.py +++ b/tests/spiders.py @@ -19,7 +19,7 @@ from scrapy.utils.test import get_from_asyncio_queue class MockServerSpider(Spider): def __init__(self, mockserver=None, *args, **kwargs): - super(MockServerSpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.mockserver = mockserver @@ -28,7 +28,7 @@ class MetaSpider(MockServerSpider): name = 'meta' def __init__(self, *args, **kwargs): - super(MetaSpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.meta = {} def closed(self, reason): @@ -41,11 +41,11 @@ class FollowAllSpider(MetaSpider): link_extractor = LinkExtractor() def __init__(self, total=10, show=20, order="rand", maxlatency=0.0, *args, **kwargs): - super(FollowAllSpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.urls_visited = [] self.times = [] qargs = {'total': total, 'show': show, 'order': order, 'maxlatency': maxlatency} - url = self.mockserver.url("/follow?%s" % urlencode(qargs, doseq=1)) + url = self.mockserver.url(f"/follow?{urlencode(qargs, doseq=True)}") self.start_urls = [url] def parse(self, response): @@ -60,14 +60,14 @@ class DelaySpider(MetaSpider): name = 'delay' def __init__(self, n=1, b=0, *args, **kwargs): - super(DelaySpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.n = n self.b = b self.t1 = self.t2 = self.t2_err = 0 def start_requests(self): self.t1 = time.time() - url = self.mockserver.url("/delay?n=%s&b=%s" % (self.n, self.b)) + url = self.mockserver.url(f"/delay?n={self.n}&b={self.b}") yield Request(url, callback=self.parse, errback=self.errback) def parse(self, response): @@ -82,7 +82,7 @@ class SimpleSpider(MetaSpider): name = 'simple' def __init__(self, url="http://localhost:8998", *args, **kwargs): - super(SimpleSpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.start_urls = [url] def parse(self, response): @@ -148,12 +148,65 @@ class AsyncDefAsyncioReqsReturnSpider(SimpleSpider): return reqs +class AsyncDefAsyncioGenSpider(SimpleSpider): + + name = 'asyncdef_asyncio_gen' + + async def parse(self, response): + await asyncio.sleep(0.2) + yield {'foo': 42} + self.logger.info("Got response %d" % response.status) + + +class AsyncDefAsyncioGenLoopSpider(SimpleSpider): + + name = 'asyncdef_asyncio_gen_loop' + + async def parse(self, response): + for i in range(10): + await asyncio.sleep(0.1) + yield {'foo': i} + self.logger.info("Got response %d" % response.status) + + +class AsyncDefAsyncioGenComplexSpider(SimpleSpider): + + name = 'asyncdef_asyncio_gen_complex' + initial_reqs = 4 + following_reqs = 3 + depth = 2 + + def _get_req(self, index, cb=None): + return Request(self.mockserver.url(f"/status?n=200&request={index}"), + meta={'index': index}, + dont_filter=True, + callback=cb) + + def start_requests(self): + for i in range(1, self.initial_reqs + 1): + yield self._get_req(i) + + async def parse(self, response): + index = response.meta['index'] + yield {'index': index} + if index < 10 ** self.depth: + for new_index in range(10 * index, 10 * index + self.following_reqs): + yield self._get_req(new_index) + yield self._get_req(index, cb=self.parse2) + await asyncio.sleep(0.1) + yield {'index': index + 5} + + async def parse2(self, response): + await asyncio.sleep(0.1) + yield {'index2': response.meta['index']} + + class ItemSpider(FollowAllSpider): name = 'item' def parse(self, response): - for request in super(ItemSpider, self).parse(response): + for request in super().parse(response): yield request yield Item() yield {} @@ -172,7 +225,7 @@ class ErrorSpider(FollowAllSpider): raise self.exception_cls('Expected exception') def parse(self, response): - for request in super(ErrorSpider, self).parse(response): + for request in super().parse(response): yield request self.raise_exception() @@ -183,7 +236,7 @@ class BrokenStartRequestsSpider(FollowAllSpider): fail_yielding = False def __init__(self, *a, **kw): - super(BrokenStartRequestsSpider, self).__init__(*a, **kw) + super().__init__(*a, **kw) self.seedsseen = [] def start_requests(self): @@ -192,7 +245,7 @@ class BrokenStartRequestsSpider(FollowAllSpider): for s in range(100): qargs = {'total': 10, 'seed': s} - url = self.mockserver.url("/follow?%s") % urlencode(qargs, doseq=1) + url = self.mockserver.url(f"/follow?{urlencode(qargs, doseq=True)}") yield Request(url, meta={'seed': s}) if self.fail_yielding: 2 / 0 @@ -201,7 +254,7 @@ class BrokenStartRequestsSpider(FollowAllSpider): def parse(self, response): self.seedsseen.append(response.meta.get('seed')) - for req in super(BrokenStartRequestsSpider, self).parse(response): + for req in super().parse(response): yield req @@ -239,24 +292,51 @@ class DuplicateStartRequestsSpider(MockServerSpider): def start_requests(self): for i in range(0, self.distinct_urls): for j in range(0, self.dupe_factor): - url = self.mockserver.url("/echo?headers=1&body=test%d" % i) + url = self.mockserver.url(f"/echo?headers=1&body=test{i}") yield Request(url, dont_filter=self.dont_filter) def __init__(self, url="http://localhost:8998", *args, **kwargs): - super(DuplicateStartRequestsSpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.visited = 0 def parse(self, response): self.visited += 1 -class CrawlSpiderWithErrback(MockServerSpider, CrawlSpider): - name = 'crawl_spider_with_errback' - custom_settings = { +class CrawlSpiderWithParseMethod(MockServerSpider, CrawlSpider): + """ + A CrawlSpider which overrides the 'parse' method + """ + name = 'crawl_spider_with_parse_method' + custom_settings: dict = { 'RETRY_HTTP_CODES': [], # no need to retry } rules = ( - Rule(LinkExtractor(), callback='callback', errback='errback', follow=True), + Rule(LinkExtractor(), callback='parse', follow=True), + ) + + def start_requests(self): + test_body = b""" + + Page title<title></head> + <body> + <p><a href="/status?n=200">Item 200</a></p> <!-- callback --> + <p><a href="/status?n=201">Item 201</a></p> <!-- callback --> + </body> + </html> + """ + url = self.mockserver.url("/alpayload") + yield Request(url, method="POST", body=test_body) + + def parse(self, response, foo=None): + self.logger.info('[parse] status %i (foo: %s)', response.status, foo) + yield Request(self.mockserver.url("/status?n=202"), self.parse, cb_kwargs={"foo": "bar"}) + + +class CrawlSpiderWithErrback(CrawlSpiderWithParseMethod): + name = 'crawl_spider_with_errback' + rules = ( + Rule(LinkExtractor(), callback='parse', errback='errback', follow=True), ) def start_requests(self): @@ -275,9 +355,6 @@ class CrawlSpiderWithErrback(MockServerSpider, CrawlSpider): url = self.mockserver.url("/alpayload") yield Request(url, method="POST", body=test_body) - def callback(self, response): - self.logger.info('[callback] status %i', response.status) - def errback(self, failure): self.logger.info('[errback] status %i', failure.value.response.status) @@ -313,3 +390,32 @@ class BytesReceivedErrbackSpider(BytesReceivedCallbackSpider): def bytes_received(self, data, request, spider): self.meta["bytes_received"] = data raise StopDownload(fail=True) + + +class HeadersReceivedCallbackSpider(MetaSpider): + + @classmethod + def from_crawler(cls, crawler, *args, **kwargs): + spider = super().from_crawler(crawler, *args, **kwargs) + crawler.signals.connect(spider.headers_received, signals.headers_received) + return spider + + def start_requests(self): + yield Request(self.mockserver.url("/status"), errback=self.errback) + + def parse(self, response): + self.meta["response"] = response + + def errback(self, failure): + self.meta["failure"] = failure + + def headers_received(self, headers, body_length, request, spider): + self.meta["headers_received"] = headers + raise StopDownload(fail=False) + + +class HeadersReceivedErrbackSpider(HeadersReceivedCallbackSpider): + + def headers_received(self, headers, body_length, request, spider): + self.meta["headers_received"] = headers + raise StopDownload(fail=True) diff --git a/tests/test_cmdline/__init__.py b/tests/test_cmdline/__init__.py index da99a6be8..591075a98 100644 --- a/tests/test_cmdline/__init__.py +++ b/tests/test_cmdline/__init__.py @@ -59,7 +59,7 @@ class CmdlineTest(unittest.TestCase): 'EXTENSIONS=' + json.dumps(EXTENSIONS)) # XXX: There's gotta be a smarter way to do this... self.assertNotIn("...", settingsstr) - for char in ("'", "<", ">", 'u"'): + for char in ("'", "<", ">"): settingsstr = settingsstr.replace(char, '"') settingsdict = json.loads(settingsstr) self.assertCountEqual(settingsdict.keys(), EXTENSIONS.keys()) diff --git a/tests/test_cmdline/extensions.py b/tests/test_cmdline/extensions.py index 6504b4d2c..005e45214 100644 --- a/tests/test_cmdline/extensions.py +++ b/tests/test_cmdline/extensions.py @@ -4,7 +4,7 @@ class TestExtension: def __init__(self, settings): - settings.set('TEST1', "%s + %s" % (settings['TEST1'], 'started')) + settings.set('TEST1', f"{settings['TEST1']} + started") @classmethod def from_crawler(cls, crawler): diff --git a/tests/test_command_check.py b/tests/test_command_check.py new file mode 100644 index 000000000..34f5e59dd --- /dev/null +++ b/tests/test_command_check.py @@ -0,0 +1,97 @@ +from os.path import join, abspath + +from tests.test_commands import CommandTest + + +class CheckCommandTest(CommandTest): + + command = 'check' + + def setUp(self): + super(CheckCommandTest, self).setUp() + self.spider_name = 'check_spider' + self.spider = abspath(join(self.proj_mod_path, 'spiders', 'checkspider.py')) + + def _write_contract(self, contracts, parse_def): + with open(self.spider, 'w') as file: + file.write(f""" +import scrapy + +class CheckSpider(scrapy.Spider): + name = '{self.spider_name}' + start_urls = ['http://example.com'] + + def parse(self, response, **cb_kwargs): + \"\"\" + @url http://example.com + {contracts} + \"\"\" + {parse_def} + """) + + def _test_contract(self, contracts='', parse_def='pass'): + self._write_contract(contracts, parse_def) + p, out, err = self.proc('check') + self.assertNotIn('F', out) + self.assertIn('OK', err) + self.assertEqual(p.returncode, 0) + + def test_check_returns_requests_contract(self): + contracts = """ + @returns requests 1 + """ + parse_def = """ + yield scrapy.Request(url='http://next-url.com') + """ + self._test_contract(contracts, parse_def) + + def test_check_returns_items_contract(self): + contracts = """ + @returns items 1 + """ + parse_def = """ + yield {'key1': 'val1', 'key2': 'val2'} + """ + self._test_contract(contracts, parse_def) + + def test_check_cb_kwargs_contract(self): + contracts = """ + @cb_kwargs {"arg1": "val1", "arg2": "val2"} + """ + parse_def = """ + if len(cb_kwargs.items()) == 0: + raise Exception("Callback args not set") + """ + self._test_contract(contracts, parse_def) + + def test_check_scrapes_contract(self): + contracts = """ + @scrapes key1 key2 + """ + parse_def = """ + yield {'key1': 'val1', 'key2': 'val2'} + """ + self._test_contract(contracts, parse_def) + + def test_check_all_default_contracts(self): + contracts = """ + @returns items 1 + @returns requests 1 + @scrapes key1 key2 + @cb_kwargs {"arg1": "val1", "arg2": "val2"} + """ + parse_def = """ + yield {'key1': 'val1', 'key2': 'val2'} + yield scrapy.Request(url='http://next-url.com') + if len(cb_kwargs.items()) == 0: + raise Exception("Callback args not set") + """ + self._test_contract(contracts, parse_def) + + def test_SCRAPY_CHECK_set(self): + parse_def = """ + import os + if not os.environ.get('SCRAPY_CHECK'): + raise Exception('SCRAPY_CHECK not set') + """ + self._test_contract(parse_def=parse_def) diff --git a/tests/test_command_parse.py b/tests/test_command_parse.py index a09dcf072..ed3848d88 100644 --- a/tests/test_command_parse.py +++ b/tests/test_command_parse.py @@ -1,5 +1,5 @@ import os -from os.path import join, abspath +from os.path import join, abspath, isfile, exists from twisted.internet import defer from scrapy.utils.testsite import SiteTest from scrapy.utils.testproc import ProcessTest @@ -17,18 +17,18 @@ class ParseCommandTest(ProcessTest, SiteTest, CommandTest): command = 'parse' def setUp(self): - super(ParseCommandTest, self).setUp() + super().setUp() self.spider_name = 'parse_spider' fname = abspath(join(self.proj_mod_path, 'spiders', 'myspider.py')) with open(fname, 'w') as f: - f.write(""" + f.write(f""" import scrapy from scrapy.linkextractors import LinkExtractor from scrapy.spiders import CrawlSpider, Rule class MySpider(scrapy.Spider): - name = '{0}' + name = '{self.spider_name}' def parse(self, response): if getattr(self, 'test_arg', None): @@ -58,7 +58,7 @@ class MySpider(scrapy.Spider): self.logger.debug('It Does Not Work :(') class MyGoodCrawlSpider(CrawlSpider): - name = 'goodcrawl{0}' + name = 'goodcrawl{self.spider_name}' rules = ( Rule(LinkExtractor(allow=r'/html'), callback='parse_item', follow=True), @@ -74,7 +74,7 @@ class MyGoodCrawlSpider(CrawlSpider): class MyBadCrawlSpider(CrawlSpider): '''Spider which doesn't define a parse_item callback while using it in a rule.''' - name = 'badcrawl{0}' + name = 'badcrawl{self.spider_name}' rules = ( Rule(LinkExtractor(allow=r'/html'), callback='parse_item', follow=True), @@ -82,7 +82,7 @@ class MyBadCrawlSpider(CrawlSpider): def parse(self, response): return [scrapy.Item(), dict(foo='bar')] -""".format(self.spider_name)) +""") fname = abspath(join(self.proj_mod_path, 'pipelines.py')) with open(fname, 'w') as f: @@ -99,9 +99,9 @@ class MyPipeline: fname = abspath(join(self.proj_mod_path, 'settings.py')) with open(fname, 'a') as f: - f.write(""" -ITEM_PIPELINES = {'%s.pipelines.MyPipeline': 1} -""" % self.project_name) + f.write(f""" +ITEM_PIPELINES = {{'{self.project_name}.pipelines.MyPipeline': 1}} +""") @defer.inlineCallbacks def test_spider_arguments(self): @@ -218,3 +218,24 @@ ITEM_PIPELINES = {'%s.pipelines.MyPipeline': 1} ) self.assertRegex(_textmode(out), r"""# Scraped Items -+\n\[\]""") self.assertIn("""Cannot find a rule that matches""", _textmode(stderr)) + + @defer.inlineCallbacks + def test_output_flag(self): + """Checks if a file was created successfully having + correct format containing correct data in it. + """ + file_name = 'data.json' + file_path = join(self.proj_path, file_name) + yield self.execute([ + '--spider', self.spider_name, + '-c', 'parse', + '-o', file_name, + self.url('/html') + ]) + + self.assertTrue(exists(file_path)) + self.assertTrue(isfile(file_path)) + + content = '[\n{},\n{"foo": "bar"}\n]' + with open(file_path, 'r') as f: + self.assertEqual(f.read(), content) diff --git a/tests/test_command_shell.py b/tests/test_command_shell.py index 01f164727..16c9559b5 100644 --- a/tests/test_command_shell.py +++ b/tests/test_command_shell.py @@ -65,8 +65,8 @@ class ShellTest(ProcessTest, SiteTest, unittest.TestCase): def test_fetch_redirect_follow_302(self): """Test that calling ``fetch(url)`` follows HTTP redirects by default.""" url = self.url('/redirect-no-meta-refresh') - code = "fetch('{0}')" - errcode, out, errout = yield self.execute(['-c', code.format(url)]) + code = f"fetch('{url}')" + errcode, out, errout = yield self.execute(['-c', code]) self.assertEqual(errcode, 0, out) assert b'Redirecting (302)' in errout assert b'Crawled (200)' in errout @@ -75,28 +75,28 @@ class ShellTest(ProcessTest, SiteTest, unittest.TestCase): def test_fetch_redirect_not_follow_302(self): """Test that calling ``fetch(url, redirect=False)`` disables automatic redirects.""" url = self.url('/redirect-no-meta-refresh') - code = "fetch('{0}', redirect=False)" - errcode, out, errout = yield self.execute(['-c', code.format(url)]) + code = f"fetch('{url}', redirect=False)" + errcode, out, errout = yield self.execute(['-c', code]) self.assertEqual(errcode, 0, out) assert b'Crawled (302)' in errout @defer.inlineCallbacks def test_request_replace(self): url = self.url('/text') - code = "fetch('{0}') or fetch(response.request.replace(method='POST'))" - errcode, out, _ = yield self.execute(['-c', code.format(url)]) + code = f"fetch('{url}') or fetch(response.request.replace(method='POST'))" + errcode, out, _ = yield self.execute(['-c', code]) self.assertEqual(errcode, 0, out) @defer.inlineCallbacks def test_scrapy_import(self): url = self.url('/text') - code = "fetch(scrapy.Request('{0}'))" - errcode, out, _ = yield self.execute(['-c', code.format(url)]) + code = f"fetch(scrapy.Request('{url}'))" + errcode, out, _ = yield self.execute(['-c', code]) self.assertEqual(errcode, 0, out) @defer.inlineCallbacks def test_local_file(self): - filepath = join(tests_datadir, 'test_site/index.html') + filepath = join(tests_datadir, 'test_site', 'index.html') _, out, _ = yield self.execute([filepath, '-c', 'item']) assert b'{}' in out diff --git a/tests/test_command_version.py b/tests/test_command_version.py index 99c01c2b7..00d998388 100644 --- a/tests/test_command_version.py +++ b/tests/test_command_version.py @@ -16,7 +16,7 @@ class VersionTest(ProcessTest, unittest.TestCase): _, out, _ = yield self.execute([]) self.assertEqual( out.strip().decode(encoding), - "Scrapy %s" % scrapy.__version__, + f"Scrapy {scrapy.__version__}", ) @defer.inlineCallbacks diff --git a/tests/test_commands.py b/tests/test_commands.py index 24a341759..eec1f02ee 100644 --- a/tests/test_commands.py +++ b/tests/test_commands.py @@ -2,19 +2,28 @@ import inspect import json import optparse import os +import platform import subprocess import sys import tempfile from contextlib import contextmanager -from os.path import exists, join, abspath +from itertools import chain +from os.path import exists, join, abspath, getmtime +from pathlib import Path from shutil import rmtree, copytree +from stat import S_IWRITE as ANYONE_WRITE_PERMISSION from tempfile import mkdtemp from threading import Timer +from unittest import skipIf +from pytest import mark +from twisted import version as twisted_version +from twisted.python.versions import Version from twisted.trial import unittest import scrapy from scrapy.commands import ScrapyCommand +from scrapy.commands.startproject import IGNORE from scrapy.settings import Settings from scrapy.utils.python import to_unicode from scrapy.utils.test import get_testenv @@ -35,7 +44,7 @@ class CommandSettings(unittest.TestCase): def test_settings_json_string(self): feeds_json = '{"data.json": {"format": "json"}, "data.xml": {"format": "xml"}}' - opts, args = self.parser.parse_args(args=['-s', 'FEEDS={}'.format(feeds_json), 'spider.py']) + opts, args = self.parser.parse_args(args=['-s', f'FEEDS={feeds_json}', 'spider.py']) self.command.process_options(args, opts) self.assertIsInstance(self.command.settings['FEEDS'], scrapy.settings.BaseSettings) self.assertEqual(dict(self.command.settings['FEEDS']), json.loads(feeds_json)) @@ -68,6 +77,7 @@ class ProjectTest(unittest.TestCase): def kill_proc(): p.kill() + p.communicate() assert False, 'Command took too much time to complete' timer = Timer(15, kill_proc) @@ -119,10 +129,39 @@ class StartprojectTest(ProjectTest): self.assertEqual(2, self.call('startproject', self.project_name, project_dir, 'another_params')) +def get_permissions_dict(path, renamings=None, ignore=None): + + def get_permissions(path): + return oct(os.stat(path).st_mode) + + renamings = renamings or tuple() + permissions_dict = { + '.': get_permissions(path), + } + for root, dirs, files in os.walk(path): + nodes = list(chain(dirs, files)) + if ignore: + ignored_names = ignore(root, nodes) + nodes = [node for node in nodes if node not in ignored_names] + for node in nodes: + absolute_path = os.path.join(root, node) + relative_path = os.path.relpath(absolute_path, path) + for search_string, replacement in renamings: + relative_path = relative_path.replace( + search_string, + replacement + ) + permissions = get_permissions(absolute_path) + permissions_dict[relative_path] = permissions + return permissions_dict + + class StartprojectTemplatesTest(ProjectTest): + maxDiff = None + def setUp(self): - super(StartprojectTemplatesTest, self).setUp() + super().setUp() self.tmpl = join(self.temp_path, 'templates') self.tmpl_proj = join(self.tmpl, 'project') @@ -132,21 +171,211 @@ class StartprojectTemplatesTest(ProjectTest): pass assert exists(join(self.tmpl_proj, 'root_template')) - args = ['--set', 'TEMPLATES_DIR=%s' % self.tmpl] + args = ['--set', f'TEMPLATES_DIR={self.tmpl}'] p, out, err = self.proc('startproject', self.project_name, *args) - self.assertIn("New Scrapy project '%s', using template directory" - % self.project_name, out) + self.assertIn(f"New Scrapy project '{self.project_name}', " + "using template directory", out) self.assertIn(self.tmpl_proj, out) assert exists(join(self.proj_path, 'root_template')) + def test_startproject_permissions_from_writable(self): + """Check that generated files have the right permissions when the + template folder has the same permissions as in the project, i.e. + everything is writable.""" + scrapy_path = scrapy.__path__[0] + project_template = os.path.join(scrapy_path, 'templates', 'project') + project_name = 'startproject1' + renamings = ( + ('module', project_name), + ('.tmpl', ''), + ) + expected_permissions = get_permissions_dict( + project_template, + renamings, + IGNORE, + ) + + destination = mkdtemp() + process = subprocess.Popen( + ( + sys.executable, + '-m', + 'scrapy.cmdline', + 'startproject', + project_name, + ), + cwd=destination, + env=self.env, + ) + process.wait() + + project_dir = os.path.join(destination, project_name) + actual_permissions = get_permissions_dict(project_dir) + + self.assertEqual(actual_permissions, expected_permissions) + + def test_startproject_permissions_from_read_only(self): + """Check that generated files have the right permissions when the + template folder has been made read-only, which is something that some + systems do. + + See https://github.com/scrapy/scrapy/pull/4604 + """ + scrapy_path = scrapy.__path__[0] + templates_dir = os.path.join(scrapy_path, 'templates') + project_template = os.path.join(templates_dir, 'project') + project_name = 'startproject2' + renamings = ( + ('module', project_name), + ('.tmpl', ''), + ) + expected_permissions = get_permissions_dict( + project_template, + renamings, + IGNORE, + ) + + def _make_read_only(path): + current_permissions = os.stat(path).st_mode + os.chmod(path, current_permissions & ~ANYONE_WRITE_PERMISSION) + + read_only_templates_dir = str(Path(mkdtemp()) / 'templates') + copytree(templates_dir, read_only_templates_dir) + + for root, dirs, files in os.walk(read_only_templates_dir): + for node in chain(dirs, files): + _make_read_only(os.path.join(root, node)) + + destination = mkdtemp() + process = subprocess.Popen( + ( + sys.executable, + '-m', + 'scrapy.cmdline', + 'startproject', + project_name, + '--set', + f'TEMPLATES_DIR={read_only_templates_dir}', + ), + cwd=destination, + env=self.env, + ) + process.wait() + + project_dir = os.path.join(destination, project_name) + actual_permissions = get_permissions_dict(project_dir) + + self.assertEqual(actual_permissions, expected_permissions) + + def test_startproject_permissions_unchanged_in_destination(self): + """Check that pre-existing folders and files in the destination folder + do not see their permissions modified.""" + scrapy_path = scrapy.__path__[0] + project_template = os.path.join(scrapy_path, 'templates', 'project') + project_name = 'startproject3' + renamings = ( + ('module', project_name), + ('.tmpl', ''), + ) + expected_permissions = get_permissions_dict( + project_template, + renamings, + IGNORE, + ) + + destination = mkdtemp() + project_dir = os.path.join(destination, project_name) + + existing_nodes = { + oct(permissions)[2:] + extension: permissions + for extension in ('', '.d') + for permissions in ( + 0o444, 0o555, 0o644, 0o666, 0o755, 0o777, + ) + } + os.mkdir(project_dir) + project_dir_path = Path(project_dir) + for node, permissions in existing_nodes.items(): + path = project_dir_path / node + if node.endswith('.d'): + path.mkdir(mode=permissions) + else: + path.touch(mode=permissions) + expected_permissions[node] = oct(path.stat().st_mode) + + process = subprocess.Popen( + ( + sys.executable, + '-m', + 'scrapy.cmdline', + 'startproject', + project_name, + '.', + ), + cwd=project_dir, + env=self.env, + ) + process.wait() + + actual_permissions = get_permissions_dict(project_dir) + + self.assertEqual(actual_permissions, expected_permissions) + + def test_startproject_permissions_umask_022(self): + """Check that generated files have the right permissions when the + system uses a umask value that causes new files to have different + permissions than those from the template folder.""" + @contextmanager + def umask(new_mask): + cur_mask = os.umask(new_mask) + yield + os.umask(cur_mask) + + scrapy_path = scrapy.__path__[0] + project_template = os.path.join( + scrapy_path, + 'templates', + 'project' + ) + project_name = 'umaskproject' + renamings = ( + ('module', project_name), + ('.tmpl', ''), + ) + expected_permissions = get_permissions_dict( + project_template, + renamings, + IGNORE, + ) + + with umask(0o002): + destination = mkdtemp() + process = subprocess.Popen( + ( + sys.executable, + '-m', + 'scrapy.cmdline', + 'startproject', + project_name, + ), + cwd=destination, + env=self.env, + ) + process.wait() + + project_dir = os.path.join(destination, project_name) + actual_permissions = get_permissions_dict(project_dir) + + self.assertEqual(actual_permissions, expected_permissions) + class CommandTest(ProjectTest): def setUp(self): - super(CommandTest, self).setUp() + super().setUp() self.call('startproject', self.project_name) self.cwd = join(self.temp_path, self.project_name) - self.env['SCRAPY_SETTINGS_MODULE'] = '%s.settings' % self.project_name + self.env['SCRAPY_SETTINGS_MODULE'] = f'{self.project_name}.settings' class GenspiderCommandTest(CommandTest): @@ -160,13 +389,17 @@ class GenspiderCommandTest(CommandTest): assert exists(join(self.proj_mod_path, 'spiders', 'test_name.py')) def test_template(self, tplname='crawl'): - args = ['--template=%s' % tplname] if tplname else [] + args = [f'--template={tplname}'] if tplname else [] spname = 'test_spider' + spmodule = f"{self.project_name}.spiders.{spname}" p, out, err = self.proc('genspider', spname, 'test.com', *args) - self.assertIn("Created spider %r using template %r in module" % (spname, tplname), out) + self.assertIn(f"Created spider {spname!r} using template {tplname!r} in module:{os.linesep} {spmodule}", out) self.assertTrue(exists(join(self.proj_mod_path, 'spiders', 'test_spider.py'))) + modify_time_before = getmtime(join(self.proj_mod_path, 'spiders', 'test_spider.py')) p, out, err = self.proc('genspider', spname, 'test.com', *args) - self.assertIn("Spider %r already exists in module" % spname, out) + self.assertIn(f"Spider {spname!r} already exists in module", out) + modify_time_after = getmtime(join(self.proj_mod_path, 'spiders', 'test_spider.py')) + self.assertEqual(modify_time_after, modify_time_before) def test_template_basic(self): self.test_template('basic') @@ -186,7 +419,41 @@ class GenspiderCommandTest(CommandTest): def test_same_name_as_project(self): self.assertEqual(2, self.call('genspider', self.project_name)) - assert not exists(join(self.proj_mod_path, 'spiders', '%s.py' % self.project_name)) + assert not exists(join(self.proj_mod_path, 'spiders', f'{self.project_name}.py')) + + def test_same_filename_as_existing_spider(self, force=False): + file_name = 'example' + file_path = join(self.proj_mod_path, 'spiders', f'{file_name}.py') + self.assertEqual(0, self.call('genspider', file_name, 'example.com')) + assert exists(file_path) + + # change name of spider but not its file name + with open(file_path, 'r+') as spider_file: + file_data = spider_file.read() + file_data = file_data.replace("name = \'example\'", "name = \'renamed\'") + spider_file.seek(0) + spider_file.write(file_data) + spider_file.truncate() + modify_time_before = getmtime(file_path) + file_contents_before = file_data + + if force: + p, out, err = self.proc('genspider', '--force', file_name, 'example.com') + self.assertIn(f"Created spider {file_name!r} using template \'basic\' in module", out) + modify_time_after = getmtime(file_path) + self.assertNotEqual(modify_time_after, modify_time_before) + file_contents_after = open(file_path, 'r').read() + self.assertNotEqual(file_contents_after, file_contents_before) + else: + p, out, err = self.proc('genspider', file_name, 'example.com') + self.assertIn(f"{file_path} already exists", out) + modify_time_after = getmtime(file_path) + self.assertEqual(modify_time_after, modify_time_before) + file_contents_after = open(file_path, 'r').read() + self.assertEqual(file_contents_after, file_contents_before) + + def test_same_filename_as_existing_spider_force(self): + self.test_same_filename_as_existing_spider(force=True) class GenspiderStandaloneCommandTest(ProjectTest): @@ -195,6 +462,34 @@ class GenspiderStandaloneCommandTest(ProjectTest): self.call('genspider', 'example', 'example.com') assert exists(join(self.temp_path, 'example.py')) + def test_same_name_as_existing_file(self, force=False): + file_name = 'example' + file_path = join(self.temp_path, file_name + '.py') + p, out, err = self.proc('genspider', file_name, 'example.com') + self.assertIn(f"Created spider {file_name!r} using template \'basic\' ", out) + assert exists(file_path) + modify_time_before = getmtime(file_path) + file_contents_before = open(file_path, 'r').read() + + if force: + # use different template to ensure contents were changed + p, out, err = self.proc('genspider', '--force', '-t', 'crawl', file_name, 'example.com') + self.assertIn(f"Created spider {file_name!r} using template \'crawl\' ", out) + modify_time_after = getmtime(file_path) + self.assertNotEqual(modify_time_after, modify_time_before) + file_contents_after = open(file_path, 'r').read() + self.assertNotEqual(file_contents_after, file_contents_before) + else: + p, out, err = self.proc('genspider', file_name, 'example.com') + self.assertIn(f"{join(self.temp_path, file_name + '.py')} already exists", out) + modify_time_after = getmtime(file_path) + self.assertEqual(modify_time_after, modify_time_before) + file_contents_after = open(file_path, 'r').read() + self.assertEqual(file_contents_after, file_contents_before) + + def test_same_name_as_existing_file_force(self): + self.test_same_name_as_existing_file(force=True) + class MiscCommandsTest(CommandTest): @@ -204,6 +499,8 @@ class MiscCommandsTest(CommandTest): class RunSpiderCommandTest(CommandTest): + spider_filename = 'myspider.py' + debug_log_spider = """ import scrapy @@ -215,11 +512,23 @@ class MySpider(scrapy.Spider): return [] """ + badspider = """ +import scrapy + +class BadSpider(scrapy.Spider): + name = "bad" + def start_requests(self): + raise Exception("oops!") + """ + @contextmanager - def _create_file(self, content, name): + def _create_file(self, content, name=None): tmpdir = self.mktemp() os.mkdir(tmpdir) - fname = abspath(join(tmpdir, name)) + if name: + fname = abspath(join(tmpdir, name)) + else: + fname = abspath(join(tmpdir, self.spider_filename)) with open(fname, 'w') as f: f.write(content) try: @@ -227,12 +536,12 @@ class MySpider(scrapy.Spider): finally: rmtree(tmpdir) - def runspider(self, code, name='myspider.py', args=()): + def runspider(self, code, name=None, args=()): with self._create_file(code, name) as fname: return self.proc('runspider', fname, *args) - def get_log(self, code, name='myspider.py', args=()): - p, stdout, stderr = self.runspider(code, name=name, args=args) + def get_log(self, code, name=None, args=()): + p, stdout, stderr = self.runspider(code, name, args=args) return stderr def test_runspider(self): @@ -264,7 +573,7 @@ class MySpider(scrapy.Spider): # which is intended, # but this should not be because of DNS lookup error # assumption: localhost will resolve in all cases (true?) - log = self.get_log(""" + dnscache_spider = """ import scrapy class MySpider(scrapy.Spider): @@ -273,23 +582,20 @@ class MySpider(scrapy.Spider): def parse(self, response): return {'test': 'value'} -""", - args=('-s', 'DNSCACHE_ENABLED=False')) - print(log) +""" + log = self.get_log(dnscache_spider, args=('-s', 'DNSCACHE_ENABLED=False')) self.assertNotIn("DNSLookupError", log) self.assertIn("INFO: Spider opened", log) def test_runspider_log_short_names(self): log1 = self.get_log(self.debug_log_spider, args=('-s', 'LOG_SHORT_NAMES=1')) - print(log1) self.assertIn("[myspider] DEBUG: It Works!", log1) self.assertIn("[scrapy]", log1) self.assertNotIn("[scrapy.core.engine]", log1) log2 = self.get_log(self.debug_log_spider, args=('-s', 'LOG_SHORT_NAMES=0')) - print(log2) self.assertIn("[myspider] DEBUG: It Works!", log2) self.assertNotIn("[scrapy]", log2) self.assertIn("[scrapy.core.engine]", log2) @@ -307,18 +613,13 @@ class MySpider(scrapy.Spider): self.assertIn('Unable to load', log) def test_start_requests_errors(self): - log = self.get_log(""" -import scrapy - -class BadSpider(scrapy.Spider): - name = "bad" - def start_requests(self): - raise Exception("oops!") - """, name="badspider.py") - print(log) + log = self.get_log(self.badspider, name='badspider.py') self.assertIn("start_requests", log) self.assertIn("badspider.py", log) + # https://twistedmatrix.com/trac/ticket/9766 + @skipIf(platform.system() == 'Windows' and sys.version_info >= (3, 8), + "the asyncio reactor is broken on Windows when running Python ≥ 3.8") def test_asyncio_enabled_true(self): log = self.get_log(self.debug_log_spider, args=[ '-s', 'TWISTED_REACTOR=twisted.internet.asyncioreactor.AsyncioSelectorReactor' @@ -329,6 +630,131 @@ class BadSpider(scrapy.Spider): log = self.get_log(self.debug_log_spider, args=[]) self.assertNotIn("Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor", log) + @mark.skipif(sys.implementation.name == 'pypy', reason='uvloop does not support pypy properly') + @mark.skipif(platform.system() == 'Windows', reason='uvloop does not support Windows') + @mark.skipif(twisted_version == Version('twisted', 21, 2, 0), reason='https://twistedmatrix.com/trac/ticket/10106') + def test_custom_asyncio_loop_enabled_true(self): + log = self.get_log(self.debug_log_spider, args=[ + '-s', + 'TWISTED_REACTOR=twisted.internet.asyncioreactor.AsyncioSelectorReactor', + '-s', + 'ASYNCIO_EVENT_LOOP=uvloop.Loop', + ]) + self.assertIn("Using asyncio event loop: uvloop.Loop", log) + + # https://twistedmatrix.com/trac/ticket/9766 + @skipIf(platform.system() == 'Windows' and sys.version_info >= (3, 8), + "the asyncio reactor is broken on Windows when running Python ≥ 3.8") + def test_custom_asyncio_loop_enabled_false(self): + log = self.get_log(self.debug_log_spider, args=[ + '-s', 'TWISTED_REACTOR=twisted.internet.asyncioreactor.AsyncioSelectorReactor' + ]) + import asyncio + loop = asyncio.new_event_loop() + self.assertIn("Using asyncio event loop: %s.%s" % (loop.__module__, loop.__class__.__name__), log) + + def test_output(self): + spider_code = """ +import scrapy + +class MySpider(scrapy.Spider): + name = 'myspider' + + def start_requests(self): + self.logger.debug('FEEDS: {}'.format(self.settings.getdict('FEEDS'))) + return [] +""" + args = ['-o', 'example.json'] + log = self.get_log(spider_code, args=args) + self.assertIn("[myspider] DEBUG: FEEDS: {'example.json': {'format': 'json'}}", log) + + def test_overwrite_output(self): + spider_code = """ +import json +import scrapy + +class MySpider(scrapy.Spider): + name = 'myspider' + + def start_requests(self): + self.logger.debug( + 'FEEDS: {}'.format( + json.dumps(self.settings.getdict('FEEDS'), sort_keys=True) + ) + ) + return [] +""" + with open(os.path.join(self.cwd, "example.json"), "w") as f1: + f1.write("not empty") + args = ['-O', 'example.json'] + log = self.get_log(spider_code, args=args) + self.assertIn('[myspider] DEBUG: FEEDS: {"example.json": {"format": "json", "overwrite": true}}', log) + with open(os.path.join(self.cwd, "example.json")) as f2: + first_line = f2.readline() + self.assertNotEqual(first_line, "not empty") + + def test_output_and_overwrite_output(self): + spider_code = """ +import scrapy + +class MySpider(scrapy.Spider): + name = 'myspider' + + def start_requests(self): + return [] +""" + args = ['-o', 'example1.json', '-O', 'example2.json'] + log = self.get_log(spider_code, args=args) + self.assertIn("error: Please use only one of -o/--output and -O/--overwrite-output", log) + + +class WindowsRunSpiderCommandTest(RunSpiderCommandTest): + + spider_filename = 'myspider.pyw' + + def setUp(self): + super(WindowsRunSpiderCommandTest, self).setUp() + + def test_start_requests_errors(self): + log = self.get_log(self.badspider, name='badspider.pyw') + self.assertIn("start_requests", log) + self.assertIn("badspider.pyw", log) + + @skipIf(platform.system() != 'Windows', "Windows required for .pyw files") + def test_run_good_spider(self): + super().test_run_good_spider() + + @skipIf(platform.system() != 'Windows', "Windows required for .pyw files") + def test_runspider(self): + super().test_runspider() + + @skipIf(platform.system() != 'Windows', "Windows required for .pyw files") + def test_runspider_dnscache_disabled(self): + super().test_runspider_dnscache_disabled() + + @skipIf(platform.system() != 'Windows', "Windows required for .pyw files") + def test_runspider_log_level(self): + super().test_runspider_log_level() + + @skipIf(platform.system() != 'Windows', "Windows required for .pyw files") + def test_runspider_log_short_names(self): + super().test_runspider_log_short_names() + + @skipIf(platform.system() != 'Windows', "Windows required for .pyw files") + def test_runspider_no_spider_found(self): + super().test_runspider_no_spider_found() + + @skipIf(platform.system() != 'Windows', "Windows required for .pyw files") + def test_output(self): + super().test_output() + + @skipIf(platform.system() != 'Windows', "Windows required for .pyw files") + def test_overwrite_output(self): + super().test_overwrite_output() + + def test_runspider_unable_to_load(self): + raise unittest.SkipTest("Already Tested in 'RunSpiderCommandTest' ") + class BenchCommandTest(CommandTest): @@ -337,3 +763,84 @@ class BenchCommandTest(CommandTest): '-s', 'CLOSESPIDER_TIMEOUT=0.01') self.assertIn('INFO: Crawled', log) self.assertNotIn('Unhandled Error', log) + + +class CrawlCommandTest(CommandTest): + + def crawl(self, code, args=()): + fname = abspath(join(self.proj_mod_path, 'spiders', 'myspider.py')) + with open(fname, 'w') as f: + f.write(code) + return self.proc('crawl', 'myspider', *args) + + def get_log(self, code, args=()): + _, _, stderr = self.crawl(code, args=args) + return stderr + + def test_no_output(self): + spider_code = """ +import scrapy + +class MySpider(scrapy.Spider): + name = 'myspider' + + def start_requests(self): + self.logger.debug('It works!') + return [] +""" + log = self.get_log(spider_code) + self.assertIn("[myspider] DEBUG: It works!", log) + + def test_output(self): + spider_code = """ +import scrapy + +class MySpider(scrapy.Spider): + name = 'myspider' + + def start_requests(self): + self.logger.debug('FEEDS: {}'.format(self.settings.getdict('FEEDS'))) + return [] +""" + args = ['-o', 'example.json'] + log = self.get_log(spider_code, args=args) + self.assertIn("[myspider] DEBUG: FEEDS: {'example.json': {'format': 'json'}}", log) + + def test_overwrite_output(self): + spider_code = """ +import json +import scrapy + +class MySpider(scrapy.Spider): + name = 'myspider' + + def start_requests(self): + self.logger.debug( + 'FEEDS: {}'.format( + json.dumps(self.settings.getdict('FEEDS'), sort_keys=True) + ) + ) + return [] +""" + with open(os.path.join(self.cwd, "example.json"), "w") as f1: + f1.write("not empty") + args = ['-O', 'example.json'] + log = self.get_log(spider_code, args=args) + self.assertIn('[myspider] DEBUG: FEEDS: {"example.json": {"format": "json", "overwrite": true}}', log) + with open(os.path.join(self.cwd, "example.json")) as f2: + first_line = f2.readline() + self.assertNotEqual(first_line, "not empty") + + def test_output_and_overwrite_output(self): + spider_code = """ +import scrapy + +class MySpider(scrapy.Spider): + name = 'myspider' + + def start_requests(self): + return [] +""" + args = ['-o', 'example1.json', '-O', 'example2.json'] + log = self.get_log(spider_code, args=args) + self.assertIn("error: Please use only one of -o/--output and -O/--overwrite-output", log) diff --git a/tests/test_contracts.py b/tests/test_contracts.py index 99120b128..d0f4a68c2 100644 --- a/tests/test_contracts.py +++ b/tests/test_contracts.py @@ -378,7 +378,7 @@ class ContractsManagerTest(unittest.TestCase): name = 'test_same_url' def __init__(self, *args, **kwargs): - super(TestSameUrlSpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.visited = 0 def start_requests(s): @@ -393,7 +393,7 @@ class ContractsManagerTest(unittest.TestCase): return TestItem() with MockServer() as mockserver: - contract_doc = '@url {}'.format(mockserver.url('/status?n=200')) + contract_doc = f'@url {mockserver.url("/status?n=200")}' TestSameUrlSpider.parse_first.__doc__ = contract_doc TestSameUrlSpider.parse_second.__doc__ = contract_doc diff --git a/tests/test_core_downloader.py b/tests/test_core_downloader.py new file mode 100644 index 000000000..113ea8f19 --- /dev/null +++ b/tests/test_core_downloader.py @@ -0,0 +1,10 @@ +from twisted.trial import unittest + +from scrapy.core.downloader import Slot + + +class SlotTest(unittest.TestCase): + + def test_repr(self): + slot = Slot(concurrency=8, delay=0.1, randomize_delay=True) + self.assertEqual(repr(slot), 'Slot(concurrency=8, delay=0.10, randomize_delay=True)') diff --git a/tests/test_crawl.py b/tests/test_crawl.py index df920f2a2..84bac9b50 100644 --- a/tests/test_crawl.py +++ b/tests/test_crawl.py @@ -1,6 +1,5 @@ import json import logging -import sys from ipaddress import IPv4Address from socket import gethostbyname from urllib.parse import urlparse @@ -20,6 +19,9 @@ from scrapy.http.response import Response from scrapy.utils.python import to_unicode from tests.mockserver import MockServer from tests.spiders import ( + AsyncDefAsyncioGenComplexSpider, + AsyncDefAsyncioGenLoopSpider, + AsyncDefAsyncioGenSpider, AsyncDefAsyncioReqsReturnSpider, AsyncDefAsyncioReturnSingleElementSpider, AsyncDefAsyncioReturnSpider, @@ -29,9 +31,12 @@ from tests.spiders import ( BytesReceivedCallbackSpider, BytesReceivedErrbackSpider, CrawlSpiderWithErrback, + CrawlSpiderWithParseMethod, DelaySpider, DuplicateStartRequestsSpider, FollowAllSpider, + HeadersReceivedCallbackSpider, + HeadersReceivedErrbackSpider, SimpleSpider, SingleRequestSpider, ) @@ -78,7 +83,7 @@ class CrawlTestCase(TestCase): total_time = times[-1] - times[0] average = total_time / (len(times) - 1) self.assertTrue(average > delay * tolerance, - "download delay too small: %s" % average) + f"download delay too small: {average}") # Ensure that the same test parameters would cause a failure if no # download delay is set. Otherwise, it means we are using a combination @@ -203,7 +208,7 @@ with multiples lines '''}) crawler = self.runner.create_crawler(SimpleSpider) with LogCapture() as log: - yield crawler.crawl(self.mockserver.url("/raw?{0}".format(query)), mockserver=self.mockserver) + yield crawler.crawl(self.mockserver.url(f"/raw?{query}"), mockserver=self.mockserver) self.assertEqual(str(log).count("Got response 200"), 1) @defer.inlineCallbacks @@ -321,6 +326,41 @@ with multiples lines self._assert_retried(log) self.assertIn("Got response 200", str(log)) + +class CrawlSpiderTestCase(TestCase): + + def setUp(self): + self.mockserver = MockServer() + self.mockserver.__enter__() + self.runner = CrawlerRunner() + + def tearDown(self): + self.mockserver.__exit__(None, None, None) + + @defer.inlineCallbacks + def _run_spider(self, spider_cls): + items = [] + + def _on_item_scraped(item): + items.append(item) + + crawler = self.runner.create_crawler(spider_cls) + crawler.signals.connect(_on_item_scraped, signals.item_scraped) + with LogCapture() as log: + yield crawler.crawl(self.mockserver.url("/status?n=200"), mockserver=self.mockserver) + return log, items, crawler.stats + + @defer.inlineCallbacks + def test_crawlspider_with_parse(self): + self.runner.crawl(CrawlSpiderWithParseMethod, mockserver=self.mockserver) + + with LogCapture() as log: + yield self.runner.join() + + self.assertIn("[parse] status 200 (foo: None)", str(log)) + self.assertIn("[parse] status 201 (foo: None)", str(log)) + self.assertIn("[parse] status 202 (foo: bar)", str(log)) + @defer.inlineCallbacks def test_crawlspider_with_errback(self): self.runner.crawl(CrawlSpiderWithErrback, mockserver=self.mockserver) @@ -328,10 +368,12 @@ with multiples lines with LogCapture() as log: yield self.runner.join() - self.assertIn("[callback] status 200", str(log)) - self.assertIn("[callback] status 201", str(log)) + self.assertIn("[parse] status 200 (foo: None)", str(log)) + self.assertIn("[parse] status 201 (foo: None)", str(log)) + self.assertIn("[parse] status 202 (foo: bar)", str(log)) self.assertIn("[errback] status 404", str(log)) self.assertIn("[errback] status 500", str(log)) + self.assertIn("[errback] status 501", str(log)) @defer.inlineCallbacks def test_async_def_parse(self): @@ -352,15 +394,7 @@ with multiples lines @mark.only_asyncio() @defer.inlineCallbacks def test_async_def_asyncio_parse_items_list(self): - items = [] - - def _on_item_scraped(item): - items.append(item) - - crawler = self.runner.create_crawler(AsyncDefAsyncioReturnSpider) - crawler.signals.connect(_on_item_scraped, signals.item_scraped) - with LogCapture() as log: - yield crawler.crawl(self.mockserver.url("/status?n=200"), mockserver=self.mockserver) + log, items, _ = yield self._run_spider(AsyncDefAsyncioReturnSpider) self.assertIn("Got response 200", str(log)) self.assertIn({'id': 1}, items) self.assertIn({'id': 2}, items) @@ -380,52 +414,29 @@ with multiples lines self.assertIn("Got response 200", str(log)) self.assertIn({"foo": 42}, items) - @mark.skipif(sys.version_info < (3, 6), reason="Async generators require Python 3.6 or higher") @mark.only_asyncio() @defer.inlineCallbacks def test_async_def_asyncgen_parse(self): - from tests.py36._test_crawl import AsyncDefAsyncioGenSpider - crawler = self.runner.create_crawler(AsyncDefAsyncioGenSpider) - with LogCapture() as log: - yield crawler.crawl(self.mockserver.url("/status?n=200"), mockserver=self.mockserver) + log, _, stats = yield self._run_spider(AsyncDefAsyncioGenSpider) self.assertIn("Got response 200", str(log)) - itemcount = crawler.stats.get_value('item_scraped_count') + itemcount = stats.get_value('item_scraped_count') self.assertEqual(itemcount, 1) - @mark.skipif(sys.version_info < (3, 6), reason="Async generators require Python 3.6 or higher") @mark.only_asyncio() @defer.inlineCallbacks def test_async_def_asyncgen_parse_loop(self): - items = [] - - def _on_item_scraped(item): - items.append(item) - - from tests.py36._test_crawl import AsyncDefAsyncioGenLoopSpider - crawler = self.runner.create_crawler(AsyncDefAsyncioGenLoopSpider) - crawler.signals.connect(_on_item_scraped, signals.item_scraped) - with LogCapture() as log: - yield crawler.crawl(self.mockserver.url("/status?n=200"), mockserver=self.mockserver) + log, items, stats = yield self._run_spider(AsyncDefAsyncioGenLoopSpider) self.assertIn("Got response 200", str(log)) - itemcount = crawler.stats.get_value('item_scraped_count') + itemcount = stats.get_value('item_scraped_count') self.assertEqual(itemcount, 10) for i in range(10): self.assertIn({'foo': i}, items) - @mark.skipif(sys.version_info < (3, 6), reason="Async generators require Python 3.6 or higher") @mark.only_asyncio() @defer.inlineCallbacks def test_async_def_asyncgen_parse_complex(self): - items = [] - - def _on_item_scraped(item): - items.append(item) - - from tests.py36._test_crawl import AsyncDefAsyncioGenComplexSpider - crawler = self.runner.create_crawler(AsyncDefAsyncioGenComplexSpider) - crawler.signals.connect(_on_item_scraped, signals.item_scraped) - yield crawler.crawl(mockserver=self.mockserver) - itemcount = crawler.stats.get_value('item_scraped_count') + _, items, stats = yield self._run_spider(AsyncDefAsyncioGenComplexSpider) + itemcount = stats.get_value('item_scraped_count') self.assertEqual(itemcount, 156) # some random items for i in [1, 4, 21, 22, 207, 311]: @@ -436,11 +447,9 @@ with multiples lines @mark.only_asyncio() @defer.inlineCallbacks def test_async_def_asyncio_parse_reqs_list(self): - crawler = self.runner.create_crawler(AsyncDefAsyncioReqsReturnSpider) - with LogCapture() as log: - yield crawler.crawl(self.mockserver.url("/status?n=200"), mockserver=self.mockserver) + log, *_ = yield self._run_spider(AsyncDefAsyncioReqsReturnSpider) for req_id in range(3): - self.assertIn("Got response 200, req_id %d" % req_id, str(log)) + self.assertIn(f"Got response 200, req_id {req_id}", str(log)) @defer.inlineCallbacks def test_response_ssl_certificate_none(self): @@ -489,7 +498,7 @@ with multiples lines self.assertEqual(str(ip_address), gethostbyname(expected_netloc)) @defer.inlineCallbacks - def test_stop_download_callback(self): + def test_bytes_received_stop_download_callback(self): crawler = self.runner.create_crawler(BytesReceivedCallbackSpider) yield crawler.crawl(mockserver=self.mockserver) self.assertIsNone(crawler.spider.meta.get("failure")) @@ -498,7 +507,7 @@ with multiples lines self.assertLess(len(crawler.spider.meta["response"].body), crawler.spider.full_response_length) @defer.inlineCallbacks - def test_stop_download_errback(self): + def test_bytes_received_stop_download_errback(self): crawler = self.runner.create_crawler(BytesReceivedErrbackSpider) yield crawler.crawl(mockserver=self.mockserver) self.assertIsNone(crawler.spider.meta.get("response")) @@ -511,3 +520,23 @@ with multiples lines self.assertLess( len(crawler.spider.meta["failure"].value.response.body), crawler.spider.full_response_length) + + @defer.inlineCallbacks + def test_headers_received_stop_download_callback(self): + crawler = self.runner.create_crawler(HeadersReceivedCallbackSpider) + yield crawler.crawl(mockserver=self.mockserver) + self.assertIsNone(crawler.spider.meta.get("failure")) + self.assertIsInstance(crawler.spider.meta["response"], Response) + self.assertEqual(crawler.spider.meta["response"].headers, crawler.spider.meta.get("headers_received")) + + @defer.inlineCallbacks + def test_headers_received_stop_download_errback(self): + crawler = self.runner.create_crawler(HeadersReceivedErrbackSpider) + yield crawler.crawl(mockserver=self.mockserver) + self.assertIsNone(crawler.spider.meta.get("response")) + self.assertIsInstance(crawler.spider.meta["failure"], Failure) + self.assertIsInstance(crawler.spider.meta["failure"].value, StopDownload) + self.assertIsInstance(crawler.spider.meta["failure"].value.response, Response) + self.assertEqual( + crawler.spider.meta["failure"].value.response.headers, + crawler.spider.meta.get("headers_received")) diff --git a/tests/test_crawler.py b/tests/test_crawler.py index 038fae323..dec517bb6 100644 --- a/tests/test_crawler.py +++ b/tests/test_crawler.py @@ -1,12 +1,16 @@ import logging import os +import platform import subprocess import sys import warnings +from unittest import skipIf from pytest import raises, mark from testfixtures import LogCapture +from twisted import version as twisted_version from twisted.internet import defer +from twisted.python.versions import Version from twisted.trial import unittest import scrapy @@ -20,6 +24,8 @@ from scrapy.extensions.throttle import AutoThrottle from scrapy.extensions import telnet from scrapy.utils.test import get_testenv +from tests.mockserver import MockServer + class BaseCrawlerTest(unittest.TestCase): @@ -140,7 +146,7 @@ class CrawlerRunnerTestCase(BaseCrawlerTest): def test_spider_manager_verify_interface(self): settings = Settings({ - 'SPIDER_LOADER_CLASS': 'tests.test_crawler.SpiderLoaderWithWrongInterface' + 'SPIDER_LOADER_CLASS': SpiderLoaderWithWrongInterface, }) with warnings.catch_warnings(record=True) as w: self.assertRaises(AttributeError, CrawlerRunner, settings) @@ -251,6 +257,9 @@ class CrawlerRunnerHasSpider(unittest.TestCase): }) @defer.inlineCallbacks + # https://twistedmatrix.com/trac/ticket/9766 + @skipIf(platform.system() == 'Windows' and sys.version_info >= (3, 8), + "the asyncio reactor is broken on Windows when running Python ≥ 3.8") def test_crawler_process_asyncio_enabled_true(self): with LogCapture(level=logging.DEBUG) as log: if self.reactor_pytest == 'asyncio': @@ -275,9 +284,9 @@ class CrawlerRunnerHasSpider(unittest.TestCase): class ScriptRunnerMixin: - def run_script(self, script_name): + def run_script(self, script_name, *script_args): script_path = os.path.join(self.script_dir, script_name) - args = (sys.executable, script_path) + args = [sys.executable, script_path] + list(script_args) p = subprocess.Popen(args, env=get_testenv(), stdout=subprocess.PIPE, stderr=subprocess.PIPE) stdout, stderr = p.communicate() @@ -292,11 +301,17 @@ class CrawlerProcessSubprocess(ScriptRunnerMixin, unittest.TestCase): self.assertIn('Spider closed (finished)', log) self.assertNotIn("Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor", log) + # https://twistedmatrix.com/trac/ticket/9766 + @skipIf(platform.system() == 'Windows' and sys.version_info >= (3, 8), + "the asyncio reactor is broken on Windows when running Python ≥ 3.8") def test_asyncio_enabled_no_reactor(self): log = self.run_script('asyncio_enabled_no_reactor.py') self.assertIn('Spider closed (finished)', log) self.assertIn("Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor", log) + # https://twistedmatrix.com/trac/ticket/9766 + @skipIf(platform.system() == 'Windows' and sys.version_info >= (3, 8), + "the asyncio reactor is broken on Windows when running Python ≥ 3.8") def test_asyncio_enabled_reactor(self): log = self.run_script('asyncio_enabled_reactor.py') self.assertIn('Spider closed (finished)', log) @@ -310,26 +325,68 @@ class CrawlerProcessSubprocess(ScriptRunnerMixin, unittest.TestCase): "twisted.internet.error.DNSLookupError: DNS lookup failed: no results for hostname lookup: ::1.", log) - def test_ipv6_alternative_name_resolver(self): - log = self.run_script('alternative_name_resolver.py') - self.assertIn('Spider closed (finished)', log) + def test_caching_hostname_resolver_ipv6(self): + log = self.run_script("caching_hostname_resolver_ipv6.py") + self.assertIn("Spider closed (finished)", log) self.assertNotIn("twisted.internet.error.DNSLookupError", log) + def test_caching_hostname_resolver_finite_execution(self): + with MockServer() as mock_server: + http_address = mock_server.http_address.replace("0.0.0.0", "127.0.0.1") + log = self.run_script("caching_hostname_resolver.py", http_address) + self.assertIn("Spider closed (finished)", log) + self.assertNotIn("ERROR: Error downloading", log) + self.assertNotIn("TimeoutError", log) + self.assertNotIn("twisted.internet.error.DNSLookupError", log) + def test_reactor_select(self): log = self.run_script("twisted_reactor_select.py") self.assertIn("Spider closed (finished)", log) self.assertIn("Using reactor: twisted.internet.selectreactor.SelectReactor", log) + @mark.skipif(platform.system() == 'Windows', reason="PollReactor is not supported on Windows") def test_reactor_poll(self): log = self.run_script("twisted_reactor_poll.py") self.assertIn("Spider closed (finished)", log) self.assertIn("Using reactor: twisted.internet.pollreactor.PollReactor", log) + # https://twistedmatrix.com/trac/ticket/9766 + @skipIf(platform.system() == 'Windows' and sys.version_info >= (3, 8), + "the asyncio reactor is broken on Windows when running Python ≥ 3.8") def test_reactor_asyncio(self): log = self.run_script("twisted_reactor_asyncio.py") self.assertIn("Spider closed (finished)", log) self.assertIn("Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor", log) + @mark.skipif(sys.implementation.name == 'pypy', reason='uvloop does not support pypy properly') + @mark.skipif(platform.system() == 'Windows', reason='uvloop does not support Windows') + @mark.skipif(twisted_version == Version('twisted', 21, 2, 0), reason='https://twistedmatrix.com/trac/ticket/10106') + def test_custom_loop_asyncio(self): + log = self.run_script("asyncio_custom_loop.py") + self.assertIn("Spider closed (finished)", log) + self.assertIn("Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor", log) + self.assertIn("Using asyncio event loop: uvloop.Loop", log) + + @mark.skipif(sys.implementation.name == "pypy", reason="uvloop does not support pypy properly") + @mark.skipif(platform.system() == "Windows", reason="uvloop does not support Windows") + @mark.skipif(twisted_version == Version('twisted', 21, 2, 0), reason='https://twistedmatrix.com/trac/ticket/10106') + def test_custom_loop_asyncio_deferred_signal(self): + log = self.run_script("asyncio_deferred_signal.py", "uvloop.Loop") + self.assertIn("Spider closed (finished)", log) + self.assertIn("Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor", log) + self.assertIn("Using asyncio event loop: uvloop.Loop", log) + self.assertIn("async pipeline opened!", log) + + # https://twistedmatrix.com/trac/ticket/9766 + @skipIf(platform.system() == 'Windows' and sys.version_info >= (3, 8), + "the asyncio reactor is broken on Windows when running Python ≥ 3.8") + def test_default_loop_asyncio_deferred_signal(self): + log = self.run_script("asyncio_deferred_signal.py") + self.assertIn("Spider closed (finished)", log) + self.assertIn("Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor", log) + self.assertNotIn("Using asyncio event loop: uvloop.Loop", log) + self.assertIn("async pipeline opened!", log) + class CrawlerRunnerSubprocess(ScriptRunnerMixin, unittest.TestCase): script_dir = os.path.join(os.path.abspath(os.path.dirname(__file__)), 'CrawlerRunner') diff --git a/tests/test_dependencies.py b/tests/test_dependencies.py index 5d0a1d0c9..5e63ebffb 100644 --- a/tests/test_dependencies.py +++ b/tests/test_dependencies.py @@ -1,8 +1,14 @@ +import os +import re +from configparser import ConfigParser from importlib import import_module + +from twisted import version as twisted_version from twisted.trial import unittest class ScrapyUtilsTest(unittest.TestCase): + def test_required_openssl_version(self): try: module = import_module('OpenSSL') @@ -13,6 +19,32 @@ class ScrapyUtilsTest(unittest.TestCase): installed_version = [int(x) for x in module.__version__.split('.')[:2]] assert installed_version >= [0, 6], "OpenSSL >= 0.6 required" + def test_pinned_twisted_version(self): + """When running tests within a Tox environment with pinned + dependencies, make sure that the version of Twisted is the pinned + version. + + See https://github.com/scrapy/scrapy/pull/4814#issuecomment-706230011 + """ + if not os.environ.get('_SCRAPY_PINNED', None): + self.skipTest('Not in a pinned environment') + + tox_config_file_path = os.path.join( + os.path.dirname(__file__), + '..', + 'tox.ini', + ) + config_parser = ConfigParser() + config_parser.read(tox_config_file_path) + pattern = r'Twisted\[http2\]==([\d.]+)' + match = re.search(pattern, config_parser['pinned']['deps']) + pinned_twisted_version_string = match[1] + + self.assertEqual( + twisted_version.short(), + pinned_twisted_version_string + ) + if __name__ == "__main__": unittest.main() diff --git a/tests/test_downloader_handlers.py b/tests/test_downloader_handlers.py index 51deb20f4..9c11820e5 100644 --- a/tests/test_downloader_handlers.py +++ b/tests/test_downloader_handlers.py @@ -2,6 +2,7 @@ import contextlib import os import shutil import tempfile +from typing import Optional, Type from unittest import mock from testfixtures import LogCapture @@ -24,7 +25,6 @@ from scrapy.core.downloader.handlers.http import HTTPDownloadHandler from scrapy.core.downloader.handlers.http10 import HTTP10DownloadHandler from scrapy.core.downloader.handlers.http11 import HTTP11DownloadHandler from scrapy.core.downloader.handlers.s3 import S3DownloadHandler - from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning from scrapy.http import Headers, Request from scrapy.http.response.text import TextResponse @@ -33,7 +33,6 @@ from scrapy.spiders import Spider from scrapy.utils.misc import create_instance from scrapy.utils.python import to_bytes from scrapy.utils.test import get_crawler, skip_if_no_boto - from tests.mockserver import MockServer, ssl_context_factory, Echo from tests.spiders import SingleRequestSpider @@ -61,7 +60,7 @@ class OffDH: class LoadTestCase(unittest.TestCase): def test_enabled_handler(self): - handlers = {'scheme': 'tests.test_downloader_handlers.DummyDH'} + handlers = {'scheme': DummyDH} crawler = get_crawler(settings_dict={'DOWNLOAD_HANDLERS': handlers}) dh = DownloadHandlers(crawler) self.assertIn('scheme', dh._schemes) @@ -69,7 +68,7 @@ class LoadTestCase(unittest.TestCase): self.assertNotIn('scheme', dh._notconfigured) def test_not_configured_handler(self): - handlers = {'scheme': 'tests.test_downloader_handlers.OffDH'} + handlers = {'scheme': OffDH} crawler = get_crawler(settings_dict={'DOWNLOAD_HANDLERS': handlers}) dh = DownloadHandlers(crawler) self.assertIn('scheme', dh._schemes) @@ -87,7 +86,7 @@ class LoadTestCase(unittest.TestCase): self.assertIn('scheme', dh._notconfigured) def test_lazy_handlers(self): - handlers = {'scheme': 'tests.test_downloader_handlers.DummyLazyDH'} + handlers = {'scheme': DummyLazyDH} crawler = get_crawler(settings_dict={'DOWNLOAD_HANDLERS': handlers}) dh = DownloadHandlers(crawler) self.assertIn('scheme', dh._schemes) @@ -115,13 +114,14 @@ class FileTestCase(unittest.TestCase): self.assertEqual(response.url, request.url) self.assertEqual(response.status, 200) self.assertEqual(response.body, b'0123456789') + self.assertEqual(response.protocol, None) request = Request(path_to_file_uri(self.tmpname + '^')) assert request.url.upper().endswith('%5E') return self.download_request(request, Spider('foo')).addCallback(_test) def test_non_existent(self): - request = Request('file://%s' % self.mktemp()) + request = Request(f'file://{self.mktemp()}') d = self.download_request(request, Spider('foo')) return self.assertFailure(d, IOError) @@ -131,6 +131,7 @@ class ContentLengthHeaderResource(resource.Resource): A testing resource which renders itself as the value of the Content-Length header from the request. """ + def render(self, request): return request.requestHeaders.getRawHeaders(b"content-length")[0] @@ -142,6 +143,7 @@ class ChunkedResource(resource.Resource): request.write(b"chunked ") request.write(b"content\n") request.finish() + reactor.callLater(0, response) return server.NOT_DONE_YET @@ -155,6 +157,7 @@ class BrokenChunkedResource(resource.Resource): # Disable terminating chunk on finish. request.chunked = False closeConnection(request) + reactor.callLater(0, response) return server.NOT_DONE_YET @@ -186,6 +189,7 @@ class EmptyContentTypeHeaderResource(resource.Resource): A testing resource which renders itself as the value of request body without content-type header in response. """ + def render(self, request): request.setHeader("content-type", "") return request.content.read() @@ -197,14 +201,14 @@ class LargeChunkedFileResource(resource.Resource): for i in range(1024): request.write(b"x" * 1024) request.finish() + reactor.callLater(0, response) return server.NOT_DONE_YET class HttpTestCase(unittest.TestCase): - scheme = 'http' - download_handler_cls = HTTPDownloadHandler + download_handler_cls: Type = HTTPDownloadHandler # only used for HTTPS tests keyfile = 'keys/localhost.key' @@ -232,8 +236,10 @@ class HttpTestCase(unittest.TestCase): self.wrapper = WrappingFactory(self.site) self.host = 'localhost' if self.scheme == 'https': + # Using WrappingFactory do not enable HTTP/2 failing all the + # tests with H2DownloadHandler self.port = reactor.listenSSL( - 0, self.wrapper, ssl_context_factory(self.keyfile, self.certfile), + 0, self.site, ssl_context_factory(self.keyfile, self.certfile), interface=self.host) else: self.port = reactor.listenTCP(0, self.wrapper, interface=self.host) @@ -249,7 +255,7 @@ class HttpTestCase(unittest.TestCase): shutil.rmtree(self.tmpname) def getURL(self, path): - return "%s://%s:%d/%s" % (self.scheme, self.host, self.portno, path) + return f"{self.scheme}://{self.host}:{self.portno}/{path}" def test_download(self): request = Request(self.getURL('file')) @@ -283,7 +289,7 @@ class HttpTestCase(unittest.TestCase): def test_timeout_download_from_spider_nodata_rcvd(self): # client connects but no data is received spider = Spider('foo') - meta = {'download_timeout': 0.2} + meta = {'download_timeout': 0.5} request = Request(self.getURL('wait'), meta=meta) d = self.download_request(request, spider) yield self.assertFailure(d, defer.TimeoutError, error.TimeoutError) @@ -292,7 +298,7 @@ class HttpTestCase(unittest.TestCase): def test_timeout_download_from_spider_server_hangs(self): # client connects, server send headers and some body bytes but hangs spider = Spider('foo') - meta = {'download_timeout': 0.2} + meta = {'download_timeout': 0.5} request = Request(self.getURL('hang-after-headers'), meta=meta) d = self.download_request(request, spider) yield self.assertFailure(d, defer.TimeoutError, error.TimeoutError) @@ -300,23 +306,25 @@ class HttpTestCase(unittest.TestCase): def test_host_header_not_in_request_headers(self): def _test(response): self.assertEqual( - response.body, to_bytes('%s:%d' % (self.host, self.portno))) + response.body, to_bytes(f'{self.host}:{self.portno}')) self.assertEqual(request.headers, {}) request = Request(self.getURL('host')) return self.download_request(request, Spider('foo')).addCallback(_test) def test_host_header_seted_in_request_headers(self): - def _test(response): - self.assertEqual(response.body, b'example.com') - self.assertEqual(request.headers.get('Host'), b'example.com') + host = self.host + ':' + str(self.portno) - request = Request(self.getURL('host'), headers={'Host': 'example.com'}) + def _test(response): + self.assertEqual(response.body, host.encode()) + self.assertEqual(request.headers.get('Host'), host.encode()) + + request = Request(self.getURL('host'), headers={'Host': host}) return self.download_request(request, Spider('foo')).addCallback(_test) d = self.download_request(request, Spider('foo')) d.addCallback(lambda r: r.body) - d.addCallback(self.assertEqual, b'example.com') + d.addCallback(self.assertEqual, b'localhost') return d def test_content_length_zero_bodyless_post_request_headers(self): @@ -330,10 +338,11 @@ class HttpTestCase(unittest.TestCase): https://github.com/kennethreitz/requests/issues/405 https://bugs.python.org/issue14721 """ + def _test(response): self.assertEqual(response.body, b'0') - request = Request(self.getURL('contentlength'), method='POST', headers={'Host': 'example.com'}) + request = Request(self.getURL('contentlength'), method='POST') return self.download_request(request, Spider('foo')).addCallback(_test) def test_content_length_zero_bodyless_post_only_one(self): @@ -355,10 +364,24 @@ class HttpTestCase(unittest.TestCase): d.addCallback(self.assertEqual, body) return d + def test_response_header_content_length(self): + request = Request(self.getURL("file"), method=b"GET") + d = self.download_request(request, Spider("foo")) + d.addCallback(lambda r: r.headers[b'content-length']) + d.addCallback(self.assertEqual, b'159') + return d + class Http10TestCase(HttpTestCase): """HTTP 1.0 test case""" - download_handler_cls = HTTP10DownloadHandler + download_handler_cls: Type = HTTP10DownloadHandler + + def test_protocol(self): + request = Request(self.getURL("host"), method="GET") + d = self.download_request(request, Spider("foo")) + d.addCallback(lambda r: r.protocol) + d.addCallback(self.assertEqual, "HTTP/1.0") + return d class Https10TestCase(Http10TestCase): @@ -367,7 +390,7 @@ class Https10TestCase(Http10TestCase): class Http11TestCase(HttpTestCase): """HTTP 1.1 test case""" - download_handler_cls = HTTP11DownloadHandler + download_handler_cls: Type = HTTP11DownloadHandler def test_download_without_maxsize_limit(self): request = Request(self.getURL('file')) @@ -410,7 +433,7 @@ class Http11TestCase(HttpTestCase): request = Request(self.getURL('largechunkedfile')) def check(logger): - logger.error.assert_called_once_with(mock.ANY, mock.ANY) + logger.warning.assert_called_once_with(mock.ANY, mock.ANY) d = self.download_request(request, Spider('foo', download_maxsize=1500)) yield self.assertFailure(d, defer.CancelledError, error.ConnectionAborted) @@ -489,6 +512,13 @@ class Http11TestCase(HttpTestCase): def test_download_broken_chunked_content_allow_data_loss_via_setting(self): return self.test_download_broken_content_allow_data_loss_via_setting('broken-chunked') + def test_protocol(self): + request = Request(self.getURL("host"), method="GET") + d = self.download_request(request, Spider("foo")) + d.addCallback(lambda r: r.protocol) + d.addCallback(self.assertEqual, "HTTP/1.1") + return d + class Https11TestCase(Http11TestCase): scheme = 'https' @@ -530,7 +560,7 @@ class Https11InvalidDNSId(Https11TestCase): """Connect to HTTPS hosts with IP while certificate uses domain names IDs.""" def setUp(self): - super(Https11InvalidDNSId, self).setUp() + super().setUp() self.host = '127.0.0.1' @@ -549,12 +579,12 @@ class Https11InvalidDNSPattern(Https11TestCase): 'SSL connection certificate: issuer "/C=IE/O=Scrapy/CN=127.0.0.1", ' 'subject "/C=IE/O=Scrapy/CN=127.0.0.1"' ) - super(Https11InvalidDNSPattern, self).setUp() + super().setUp() class Https11CustomCiphers(unittest.TestCase): scheme = 'https' - download_handler_cls = HTTP11DownloadHandler + download_handler_cls: Type = HTTP11DownloadHandler keyfile = 'keys/localhost.key' certfile = 'keys/localhost.crt' @@ -565,10 +595,9 @@ class Https11CustomCiphers(unittest.TestCase): FilePath(self.tmpname).child("file").setContent(b"0123456789") r = static.File(self.tmpname) self.site = server.Site(r, timeout=None) - self.wrapper = WrappingFactory(self.site) self.host = 'localhost' self.port = reactor.listenSSL( - 0, self.wrapper, ssl_context_factory(self.keyfile, self.certfile, cipher_string='CAMELLIA256-SHA'), + 0, self.site, ssl_context_factory(self.keyfile, self.certfile, cipher_string='CAMELLIA256-SHA'), interface=self.host) self.portno = self.port.getHost().port crawler = get_crawler(settings_dict={'DOWNLOADER_CLIENT_TLS_CIPHERS': 'CAMELLIA256-SHA'}) @@ -583,7 +612,7 @@ class Https11CustomCiphers(unittest.TestCase): shutil.rmtree(self.tmpname) def getURL(self, path): - return "%s://%s:%d/%s" % (self.scheme, self.host, self.portno, path) + return f"{self.scheme}://{self.host}:{self.portno}/{path}" def test_download(self): request = Request(self.getURL('file')) @@ -595,6 +624,7 @@ class Https11CustomCiphers(unittest.TestCase): class Http11MockServerTestCase(unittest.TestCase): """HTTP 1.1 test case with MockServer""" + settings_dict: Optional[dict] = None def setUp(self): self.mockserver = MockServer() @@ -605,7 +635,7 @@ class Http11MockServerTestCase(unittest.TestCase): @defer.inlineCallbacks def test_download_with_content_length(self): - crawler = get_crawler(SingleRequestSpider) + crawler = get_crawler(SingleRequestSpider, self.settings_dict) # http://localhost:8998/partial set Content-Length to 1024, use download_maxsize= 1000 to avoid # download it yield crawler.crawl(seed=Request(url=self.mockserver.url('/partial'), meta={'download_maxsize': 1000})) @@ -614,7 +644,7 @@ class Http11MockServerTestCase(unittest.TestCase): @defer.inlineCallbacks def test_download(self): - crawler = get_crawler(SingleRequestSpider) + crawler = get_crawler(SingleRequestSpider, self.settings_dict) yield crawler.crawl(seed=Request(url=self.mockserver.url(''))) failure = crawler.spider.meta.get('failure') self.assertTrue(failure is None) @@ -623,7 +653,7 @@ class Http11MockServerTestCase(unittest.TestCase): @defer.inlineCallbacks def test_download_gzip_response(self): - crawler = get_crawler(SingleRequestSpider) + crawler = get_crawler(SingleRequestSpider, self.settings_dict) body = b'1' * 100 # PayloadResource requires body length to be 100 request = Request(self.mockserver.url('/payload'), method='POST', body=body, meta={'download_maxsize': 50}) @@ -661,7 +691,8 @@ class UriResource(resource.Resource): class HttpProxyTestCase(unittest.TestCase): - download_handler_cls = HTTPDownloadHandler + download_handler_cls: Type = HTTPDownloadHandler + expected_http_proxy_request_body = b'http://example.com' def setUp(self): site = server.Site(UriResource(), timeout=None) @@ -678,13 +709,13 @@ class HttpProxyTestCase(unittest.TestCase): yield self.download_handler.close() def getURL(self, path): - return "http://127.0.0.1:%d/%s" % (self.portno, path) + return f"http://127.0.0.1:{self.portno}/{path}" def test_download_with_proxy(self): def _test(response): self.assertEqual(response.status, 200) self.assertEqual(response.url, request.url) - self.assertEqual(response.body, b'http://example.com') + self.assertEqual(response.body, self.expected_http_proxy_request_body) http_proxy = self.getURL('') request = Request('http://example.com', meta={'proxy': http_proxy}) @@ -696,7 +727,7 @@ class HttpProxyTestCase(unittest.TestCase): self.assertEqual(response.url, request.url) self.assertEqual(response.body, b'https://example.com') - http_proxy = '%s?noconnect' % self.getURL('') + http_proxy = f'{self.getURL("")}?noconnect' request = Request('https://example.com', meta={'proxy': http_proxy}) with self.assertWarnsRegex(ScrapyDeprecationWarning, r'Using HTTPS proxies in the noconnect mode is deprecated'): @@ -713,14 +744,14 @@ class HttpProxyTestCase(unittest.TestCase): class Http10ProxyTestCase(HttpProxyTestCase): - download_handler_cls = HTTP10DownloadHandler + download_handler_cls: Type = HTTP10DownloadHandler def test_download_with_proxy_https_noconnect(self): raise unittest.SkipTest('noconnect is not supported in HTTP10DownloadHandler') class Http11ProxyTestCase(HttpProxyTestCase): - download_handler_cls = HTTP11DownloadHandler + download_handler_cls: Type = HTTP11DownloadHandler @defer.inlineCallbacks def test_download_with_proxy_https_timeout(self): @@ -733,6 +764,16 @@ class Http11ProxyTestCase(HttpProxyTestCase): timeout = yield self.assertFailure(d, error.TimeoutError) self.assertIn(domain, timeout.osError) + def test_download_with_proxy_without_http_scheme(self): + def _test(response): + self.assertEqual(response.status, 200) + self.assertEqual(response.url, request.url) + self.assertEqual(response.body, self.expected_http_proxy_request_body) + + http_proxy = self.getURL('').replace('http://', '') + request = Request('http://example.com', meta={'proxy': http_proxy}) + return self.download_request(request, Spider('foo')).addCallback(_test) + class HttpDownloadHandlerMock: @@ -768,7 +809,7 @@ class S3AnonTestCase(unittest.TestCase): class S3TestCase(unittest.TestCase): - download_handler_cls = S3DownloadHandler + download_handler_cls: Type = S3DownloadHandler # test use same example keys than amazon developer guide # http://s3.amazonaws.com/awsdocs/S3/20060301/s3-dg-20060301.pdf @@ -868,29 +909,6 @@ class S3TestCase(unittest.TestCase): self.assertEqual(httpreq.headers['Authorization'], b'AWS 0PN5J17HBGZHT7JJ3X82:thdUi9VAkzhkniLj96JIrOPGi0g=') - def test_request_signing5(self): - try: - import botocore # noqa: F401 - except ImportError: - pass - else: - raise unittest.SkipTest( - 'botocore does not support overriding date with x-amz-date') - # deletes an object from the 'johnsmith' bucket using the - # path-style and Date alternative. - date = 'Tue, 27 Mar 2007 21:20:27 +0000' - req = Request( - 's3://johnsmith/photos/puppy.jpg', method='DELETE', headers={ - 'Date': date, - 'x-amz-date': 'Tue, 27 Mar 2007 21:20:26 +0000', - }) - with self._mocked_date(date): - httpreq = self.download_request(req, self.spider) - # botocore does not override Date with x-amz-date - self.assertEqual( - httpreq.headers['Authorization'], - b'AWS 0PN5J17HBGZHT7JJ3X82:k3nL7gH3+PadhTEVn5Ip83xlYzk=') - def test_request_signing6(self): # uploads an object to a CNAME style virtual hosted bucket with metadata. date = 'Tue, 27 Mar 2007 21:06:08 +0000' @@ -931,7 +949,6 @@ class S3TestCase(unittest.TestCase): class BaseFTPTestCase(unittest.TestCase): - username = "scrapy" password = "passwd" req_meta = {"ftp_user": username, "ftp_password": password} @@ -969,6 +986,7 @@ class BaseFTPTestCase(unittest.TestCase): def _clean(data): self.download_handler.client.transport.loseConnection() return data + deferred.addCallback(_clean) if callback: deferred.addCallback(callback) @@ -977,7 +995,7 @@ class BaseFTPTestCase(unittest.TestCase): return deferred def test_ftp_download_success(self): - request = Request(url="ftp://127.0.0.1:%s/file.txt" % self.portNum, + request = Request(url=f"ftp://127.0.0.1:{self.portNum}/file.txt", meta=self.req_meta) d = self.download_handler.download_request(request, None) @@ -985,11 +1003,12 @@ class BaseFTPTestCase(unittest.TestCase): self.assertEqual(r.status, 200) self.assertEqual(r.body, b'I have the power!') self.assertEqual(r.headers, {b'Local Filename': [b''], b'Size': [b'17']}) + self.assertIsNone(r.protocol) return self._add_test_callbacks(d, _test) def test_ftp_download_path_with_spaces(self): request = Request( - url="ftp://127.0.0.1:%s/file with spaces.txt" % self.portNum, + url=f"ftp://127.0.0.1:{self.portNum}/file with spaces.txt", meta=self.req_meta ) d = self.download_handler.download_request(request, None) @@ -998,15 +1017,17 @@ class BaseFTPTestCase(unittest.TestCase): self.assertEqual(r.status, 200) self.assertEqual(r.body, b'Moooooooooo power!') self.assertEqual(r.headers, {b'Local Filename': [b''], b'Size': [b'18']}) + return self._add_test_callbacks(d, _test) def test_ftp_download_notexist(self): - request = Request(url="ftp://127.0.0.1:%s/notexist.txt" % self.portNum, + request = Request(url=f"ftp://127.0.0.1:{self.portNum}/notexist.txt", meta=self.req_meta) d = self.download_handler.download_request(request, None) def _test(r): self.assertEqual(r.status, 404) + return self._add_test_callbacks(d, _test) def test_ftp_local_filename(self): @@ -1015,7 +1036,7 @@ class BaseFTPTestCase(unittest.TestCase): os.close(f) meta = {"ftp_local_filename": local_fname} meta.update(self.req_meta) - request = Request(url="ftp://127.0.0.1:%s/file.txt" % self.portNum, + request = Request(url=f"ftp://127.0.0.1:{self.portNum}/file.txt", meta=meta) d = self.download_handler.download_request(request, None) @@ -1027,6 +1048,7 @@ class BaseFTPTestCase(unittest.TestCase): with open(local_fname, "rb") as f: self.assertEqual(f.read(), b"I have the power!") os.remove(local_fname) + return self._add_test_callbacks(d, _test) @@ -1037,17 +1059,17 @@ class FTPTestCase(BaseFTPTestCase): meta = dict(self.req_meta) meta.update({"ftp_password": 'invalid'}) - request = Request(url="ftp://127.0.0.1:%s/file.txt" % self.portNum, + request = Request(url=f"ftp://127.0.0.1:{self.portNum}/file.txt", meta=meta) d = self.download_handler.download_request(request, None) def _test(r): self.assertEqual(r.type, ConnectionLost) + return self._add_test_callbacks(d, errback=_test) class AnonymousFTPTestCase(BaseFTPTestCase): - username = "anonymous" req_meta = {} @@ -1110,7 +1132,7 @@ class DataURITestCase(unittest.TestCase): def test_default_mediatype(self): def _test(response): - self.assertEqual(response.text, u'\u038e\u03a3\u038e') + self.assertEqual(response.text, '\u038e\u03a3\u038e') self.assertEqual(type(response), responsetypes.from_mimetype("text/plain")) self.assertEqual(response.encoding, "iso-8859-7") @@ -1119,7 +1141,7 @@ class DataURITestCase(unittest.TestCase): def test_text_charset(self): def _test(response): - self.assertEqual(response.text, u'\u038e\u03a3\u038e') + self.assertEqual(response.text, '\u038e\u03a3\u038e') self.assertEqual(response.body, b'\xbe\xd3\xbe') self.assertEqual(response.encoding, "iso-8859-7") @@ -1128,7 +1150,7 @@ class DataURITestCase(unittest.TestCase): def test_mediatype_parameters(self): def _test(response): - self.assertEqual(response.text, u'\u038e\u03a3\u038e') + self.assertEqual(response.text, '\u038e\u03a3\u038e') self.assertEqual(type(response), responsetypes.from_mimetype("text/plain")) self.assertEqual(response.encoding, "utf-8") @@ -1143,3 +1165,10 @@ class DataURITestCase(unittest.TestCase): request = Request('data:text/plain;base64,SGVsbG8sIHdvcmxkLg%3D%3D') return self.download_request(request, self.spider).addCallback(_test) + + def test_protocol(self): + def _test(response): + self.assertIsNone(response.protocol) + + request = Request("data:,") + return self.download_request(request, self.spider).addCallback(_test) diff --git a/tests/test_downloader_handlers_http2.py b/tests/test_downloader_handlers_http2.py new file mode 100644 index 000000000..53bb4fe92 --- /dev/null +++ b/tests/test_downloader_handlers_http2.py @@ -0,0 +1,263 @@ +import json +from unittest import mock, skipIf + +from pytest import mark +from testfixtures import LogCapture +from twisted.internet import defer, error, reactor +from twisted.trial import unittest +from twisted.web import server +from twisted.web.error import SchemeNotSupported +from twisted.web.http import H2_ENABLED + +from scrapy.http import Request +from scrapy.spiders import Spider +from scrapy.utils.misc import create_instance +from scrapy.utils.test import get_crawler +from tests.mockserver import ssl_context_factory +from tests.test_downloader_handlers import ( + Https11TestCase, Https11CustomCiphers, + Http11MockServerTestCase, Http11ProxyTestCase, + UriResource +) + + +@skipIf(not H2_ENABLED, "HTTP/2 support in Twisted is not enabled") +class Https2TestCase(Https11TestCase): + + scheme = 'https' + HTTP2_DATALOSS_SKIP_REASON = "Content-Length mismatch raises InvalidBodyLengthError" + + @classmethod + def setUpClass(cls): + from scrapy.core.downloader.handlers.http2 import H2DownloadHandler + cls.download_handler_cls = H2DownloadHandler + + def test_protocol(self): + request = Request(self.getURL("host"), method="GET") + d = self.download_request(request, Spider("foo")) + d.addCallback(lambda r: r.protocol) + d.addCallback(self.assertEqual, "h2") + return d + + @defer.inlineCallbacks + def test_download_with_maxsize_very_large_file(self): + with mock.patch('scrapy.core.http2.stream.logger') as logger: + request = Request(self.getURL('largechunkedfile')) + + def check(logger): + logger.error.assert_called_once_with(mock.ANY) + + d = self.download_request(request, Spider('foo', download_maxsize=1500)) + yield self.assertFailure(d, defer.CancelledError, error.ConnectionAborted) + + # As the error message is logged in the dataReceived callback, we + # have to give a bit of time to the reactor to process the queue + # after closing the connection. + d = defer.Deferred() + d.addCallback(check) + reactor.callLater(.1, d.callback, logger) + yield d + + @defer.inlineCallbacks + def test_unsupported_scheme(self): + request = Request("ftp://unsupported.scheme") + d = self.download_request(request, Spider("foo")) + yield self.assertFailure(d, SchemeNotSupported) + + def test_download_broken_content_cause_data_loss(self, url='broken'): + raise unittest.SkipTest(self.HTTP2_DATALOSS_SKIP_REASON) + + def test_download_broken_chunked_content_cause_data_loss(self): + raise unittest.SkipTest(self.HTTP2_DATALOSS_SKIP_REASON) + + def test_download_broken_content_allow_data_loss(self, url='broken'): + raise unittest.SkipTest(self.HTTP2_DATALOSS_SKIP_REASON) + + def test_download_broken_chunked_content_allow_data_loss(self): + raise unittest.SkipTest(self.HTTP2_DATALOSS_SKIP_REASON) + + def test_download_broken_content_allow_data_loss_via_setting(self, url='broken'): + raise unittest.SkipTest(self.HTTP2_DATALOSS_SKIP_REASON) + + def test_download_broken_chunked_content_allow_data_loss_via_setting(self): + raise unittest.SkipTest(self.HTTP2_DATALOSS_SKIP_REASON) + + def test_concurrent_requests_same_domain(self): + spider = Spider('foo') + + request1 = Request(self.getURL('file')) + d1 = self.download_request(request1, spider) + d1.addCallback(lambda r: r.body) + d1.addCallback(self.assertEqual, b"0123456789") + + request2 = Request(self.getURL('echo'), method='POST') + d2 = self.download_request(request2, spider) + d2.addCallback(lambda r: r.headers['Content-Length']) + d2.addCallback(self.assertEqual, b"79") + + return defer.DeferredList([d1, d2]) + + @mark.xfail(reason="https://github.com/python-hyper/h2/issues/1247") + def test_connect_request(self): + request = Request(self.getURL('file'), method='CONNECT') + d = self.download_request(request, Spider('foo')) + d.addCallback(lambda r: r.body) + d.addCallback(self.assertEqual, b'') + return d + + def test_custom_content_length_good(self): + request = Request(self.getURL('contentlength')) + custom_content_length = str(len(request.body)) + request.headers['Content-Length'] = custom_content_length + d = self.download_request(request, Spider('foo')) + d.addCallback(lambda r: r.text) + d.addCallback(self.assertEqual, custom_content_length) + return d + + def test_custom_content_length_bad(self): + request = Request(self.getURL('contentlength')) + actual_content_length = str(len(request.body)) + bad_content_length = str(len(request.body) + 1) + request.headers['Content-Length'] = bad_content_length + log = LogCapture() + d = self.download_request(request, Spider('foo')) + d.addCallback(lambda r: r.text) + d.addCallback(self.assertEqual, actual_content_length) + d.addCallback( + lambda _: log.check_present( + ( + 'scrapy.core.http2.stream', + 'WARNING', + f'Ignoring bad Content-Length header ' + f'{bad_content_length!r} of request {request}, sending ' + f'{actual_content_length!r} instead', + ) + ) + ) + d.addCallback( + lambda _: log.uninstall() + ) + return d + + def test_duplicate_header(self): + request = Request(self.getURL('echo')) + header, value1, value2 = 'Custom-Header', 'foo', 'bar' + request.headers.appendlist(header, value1) + request.headers.appendlist(header, value2) + d = self.download_request(request, Spider('foo')) + d.addCallback(lambda r: json.loads(r.text)['headers'][header]) + d.addCallback(self.assertEqual, [value1, value2]) + return d + + +class Https2WrongHostnameTestCase(Https2TestCase): + tls_log_message = ( + 'SSL connection certificate: issuer "/C=XW/ST=XW/L=The ' + 'Internet/O=Scrapy/CN=www.example.com/emailAddress=test@example.com", ' + 'subject "/C=XW/ST=XW/L=The ' + 'Internet/O=Scrapy/CN=www.example.com/emailAddress=test@example.com"' + ) + + # above tests use a server certificate for "localhost", + # client connection to "localhost" too. + # here we test that even if the server certificate is for another domain, + # "www.example.com" in this case, + # the tests still pass + keyfile = 'keys/example-com.key.pem' + certfile = 'keys/example-com.cert.pem' + + +class Https2InvalidDNSId(Https2TestCase): + """Connect to HTTPS hosts with IP while certificate uses domain names IDs.""" + + def setUp(self): + super(Https2InvalidDNSId, self).setUp() + self.host = '127.0.0.1' + + +class Https2InvalidDNSPattern(Https2TestCase): + """Connect to HTTPS hosts where the certificate are issued to an ip instead of a domain.""" + + keyfile = 'keys/localhost.ip.key' + certfile = 'keys/localhost.ip.crt' + + def setUp(self): + try: + from service_identity.exceptions import CertificateError # noqa: F401 + except ImportError: + raise unittest.SkipTest("cryptography lib is too old") + self.tls_log_message = ( + 'SSL connection certificate: issuer "/C=IE/O=Scrapy/CN=127.0.0.1", ' + 'subject "/C=IE/O=Scrapy/CN=127.0.0.1"' + ) + super(Https2InvalidDNSPattern, self).setUp() + + +@skipIf(not H2_ENABLED, "HTTP/2 support in Twisted is not enabled") +class Https2CustomCiphers(Https11CustomCiphers): + scheme = 'https' + + @classmethod + def setUpClass(cls): + from scrapy.core.downloader.handlers.http2 import H2DownloadHandler + cls.download_handler_cls = H2DownloadHandler + + +class Http2MockServerTestCase(Http11MockServerTestCase): + """HTTP 2.0 test case with MockServer""" + settings_dict = { + 'DOWNLOAD_HANDLERS': { + 'https': 'scrapy.core.downloader.handlers.http2.H2DownloadHandler' + } + } + + +@skipIf(not H2_ENABLED, "HTTP/2 support in Twisted is not enabled") +class Https2ProxyTestCase(Http11ProxyTestCase): + # only used for HTTPS tests + keyfile = 'keys/localhost.key' + certfile = 'keys/localhost.crt' + + scheme = 'https' + host = u'127.0.0.1' + + expected_http_proxy_request_body = b'/' + + @classmethod + def setUpClass(cls): + from scrapy.core.downloader.handlers.http2 import H2DownloadHandler + cls.download_handler_cls = H2DownloadHandler + + def setUp(self): + site = server.Site(UriResource(), timeout=None) + self.port = reactor.listenSSL( + 0, site, + ssl_context_factory(self.keyfile, self.certfile), + interface=self.host + ) + self.portno = self.port.getHost().port + self.download_handler = create_instance(self.download_handler_cls, None, get_crawler()) + self.download_request = self.download_handler.download_request + + def getURL(self, path): + return f"{self.scheme}://{self.host}:{self.portno}/{path}" + + def test_download_with_proxy_https_noconnect(self): + def _test(response): + self.assertEqual(response.status, 200) + self.assertEqual(response.url, request.url) + self.assertEqual(response.body, b'/') + + http_proxy = '%s?noconnect' % self.getURL('') + request = Request('https://example.com', meta={'proxy': http_proxy}) + with self.assertWarnsRegex( + Warning, + r'Using HTTPS proxies in the noconnect mode is not supported by the ' + r'downloader handler.' + ): + return self.download_request(request, Spider('foo')).addCallback(_test) + + @defer.inlineCallbacks + def test_download_with_proxy_https_timeout(self): + with self.assertRaises(NotImplementedError): + yield super(Https2ProxyTestCase, self).test_download_with_proxy_https_timeout() diff --git a/tests/test_downloadermiddleware.py b/tests/test_downloadermiddleware.py index a9190c62b..b538a0ed3 100644 --- a/tests/test_downloadermiddleware.py +++ b/tests/test_downloadermiddleware.py @@ -1,11 +1,13 @@ import asyncio -from unittest import mock +from unittest import mock, SkipTest from pytest import mark +from twisted import version as twisted_version from twisted.internet import defer from twisted.internet.defer import Deferred from twisted.trial.unittest import TestCase from twisted.python.failure import Failure +from twisted.python.versions import Version from scrapy.http import Request, Response from scrapy.spiders import Spider @@ -84,7 +86,7 @@ class DefaultsTest(ManagerTestCase): }) ret = self._download(request=req, response=resp) self.assertTrue(isinstance(ret, Request), - "Not redirected: {0!r}".format(ret)) + f"Not redirected: {ret!r}") self.assertEqual(to_bytes(ret.url), resp.headers['Location'], "Not redirected to location header") @@ -211,10 +213,21 @@ class MiddlewareUsingDeferreds(ManagerTestCase): self.assertFalse(download_func.called) +@mark.usefixtures('reactor_pytest') class MiddlewareUsingCoro(ManagerTestCase): """Middlewares using asyncio coroutines should work""" def test_asyncdef(self): + if ( + self.reactor_pytest == 'asyncio' + and twisted_version < Version('twisted', 18, 4, 0) + ): + raise SkipTest( + 'Due to https://twistedmatrix.com/trac/ticket/9390, this test ' + 'hangs when using AsyncIO and Twisted versions lower than ' + '18.4.0' + ) + resp = Response('http://example.com/index.html') class CoroMiddleware: @@ -235,6 +248,12 @@ class MiddlewareUsingCoro(ManagerTestCase): @mark.only_asyncio() def test_asyncdef_asyncio(self): + if twisted_version < Version('twisted', 18, 4, 0): + raise SkipTest( + 'Due to https://twistedmatrix.com/trac/ticket/9390, this test ' + 'hangs when using Twisted versions lower than 18.4.0' + ) + resp = Response('http://example.com/index.html') class CoroMiddleware: diff --git a/tests/test_downloadermiddleware_cookies.py b/tests/test_downloadermiddleware_cookies.py index 9ccc2110b..aff8542e9 100644 --- a/tests/test_downloadermiddleware_cookies.py +++ b/tests/test_downloadermiddleware_cookies.py @@ -2,6 +2,8 @@ import logging from testfixtures import LogCapture from unittest import TestCase +import pytest + from scrapy.downloadermiddlewares.cookies import CookiesMiddleware from scrapy.downloadermiddlewares.defaultheaders import DefaultHeadersMiddleware from scrapy.exceptions import NotConfigured @@ -243,6 +245,7 @@ class CookiesMiddlewareTest(TestCase): self.assertIn('Cookie', request.headers) self.assertEqual(b'currencyCookie=USD', request.headers['Cookie']) + @pytest.mark.xfail(reason="Cookie header is not currently being processed") def test_keep_cookie_from_default_request_headers_middleware(self): DEFAULT_REQUEST_HEADERS = dict(Cookie='default=value; asdf=qwerty') mw_default_headers = DefaultHeadersMiddleware(DEFAULT_REQUEST_HEADERS.items()) @@ -257,6 +260,7 @@ class CookiesMiddlewareTest(TestCase): assert self.mw.process_request(req2, self.spider) is None self.assertCookieValEqual(req2.headers['Cookie'], b'default=value; a=b; asdf=qwerty') + @pytest.mark.xfail(reason="Cookie header is not currently being processed") def test_keep_cookie_header(self): # keep only cookies from 'Cookie' request header req1 = Request('http://scrapytest.org', headers={'Cookie': 'a=b; c=d'}) @@ -277,33 +281,34 @@ class CookiesMiddlewareTest(TestCase): def test_request_cookies_encoding(self): # 1) UTF8-encoded bytes - req1 = Request('http://example.org', cookies={'a': u'á'.encode('utf8')}) + req1 = Request('http://example.org', cookies={'a': 'á'.encode('utf8')}) assert self.mw.process_request(req1, self.spider) is None self.assertCookieValEqual(req1.headers['Cookie'], b'a=\xc3\xa1') # 2) Non UTF8-encoded bytes - req2 = Request('http://example.org', cookies={'a': u'á'.encode('latin1')}) + req2 = Request('http://example.org', cookies={'a': 'á'.encode('latin1')}) assert self.mw.process_request(req2, self.spider) is None self.assertCookieValEqual(req2.headers['Cookie'], b'a=\xc3\xa1') - # 3) Unicode string - req3 = Request('http://example.org', cookies={'a': u'á'}) + # 3) String + req3 = Request('http://example.org', cookies={'a': 'á'}) assert self.mw.process_request(req3, self.spider) is None self.assertCookieValEqual(req3.headers['Cookie'], b'a=\xc3\xa1') + @pytest.mark.xfail(reason="Cookie header is not currently being processed") def test_request_headers_cookie_encoding(self): # 1) UTF8-encoded bytes - req1 = Request('http://example.org', headers={'Cookie': u'a=á'.encode('utf8')}) + req1 = Request('http://example.org', headers={'Cookie': 'a=á'.encode('utf8')}) assert self.mw.process_request(req1, self.spider) is None self.assertCookieValEqual(req1.headers['Cookie'], b'a=\xc3\xa1') # 2) Non UTF8-encoded bytes - req2 = Request('http://example.org', headers={'Cookie': u'a=á'.encode('latin1')}) + req2 = Request('http://example.org', headers={'Cookie': 'a=á'.encode('latin1')}) assert self.mw.process_request(req2, self.spider) is None self.assertCookieValEqual(req2.headers['Cookie'], b'a=\xc3\xa1') - # 3) Unicode string - req3 = Request('http://example.org', headers={'Cookie': u'a=á'}) + # 3) String + req3 = Request('http://example.org', headers={'Cookie': 'a=á'}) assert self.mw.process_request(req3, self.spider) is None self.assertCookieValEqual(req3.headers['Cookie'], b'a=\xc3\xa1') @@ -322,6 +327,9 @@ class CookiesMiddlewareTest(TestCase): cookies2 = [{'name': 'foo'}, {'name': 'key', 'value': 'value2'}] req2 = Request('http://example.org/2', cookies=cookies2) assert self.mw.process_request(req2, self.spider) is None + cookies3 = [{'name': 'foo', 'value': None}, {'name': 'key', 'value': ''}] + req3 = Request('http://example.org/3', cookies=cookies3) + assert self.mw.process_request(req3, self.spider) is None lc.check( ("scrapy.downloadermiddlewares.cookies", "WARNING", @@ -331,6 +339,11 @@ class CookiesMiddlewareTest(TestCase): "WARNING", "Invalid cookie found in request <GET http://example.org/2>:" " {'name': 'foo'} ('value' is missing)"), + ("scrapy.downloadermiddlewares.cookies", + "WARNING", + "Invalid cookie found in request <GET http://example.org/3>:" + " {'name': 'foo', 'value': None} ('value' is missing)"), ) self.assertCookieValEqual(req1.headers['Cookie'], 'key=value1') self.assertCookieValEqual(req2.headers['Cookie'], 'key=value2') + self.assertCookieValEqual(req3.headers['Cookie'], 'key=') diff --git a/tests/test_downloadermiddleware_decompression.py b/tests/test_downloadermiddleware_decompression.py index dbae4d3ae..b2b5ce77d 100644 --- a/tests/test_downloadermiddleware_decompression.py +++ b/tests/test_downloadermiddleware_decompression.py @@ -28,7 +28,7 @@ class DecompressionMiddlewareTest(TestCase): for fmt in self.test_formats: rsp = self.test_responses[fmt] new = self.mw.process_response(None, rsp, self.spider) - error_msg = 'Failed %s, response type %s' % (fmt, type(new).__name__) + error_msg = f'Failed {fmt}, response type {type(new).__name__}' assert isinstance(new, XmlResponse), error_msg assert_samelines(self, new.body, self.uncompressed_body, fmt) diff --git a/tests/test_downloadermiddleware_httpcache.py b/tests/test_downloadermiddleware_httpcache.py index 9b77c97a8..0c6dcf2aa 100644 --- a/tests/test_downloadermiddleware_httpcache.py +++ b/tests/test_downloadermiddleware_httpcache.py @@ -134,7 +134,7 @@ class DbmStorageWithCustomDbmModuleTest(DbmStorageTest): def _get_settings(self, **new_settings): new_settings.setdefault('HTTPCACHE_DBM_MODULE', self.dbm_module) - return super(DbmStorageWithCustomDbmModuleTest, self)._get_settings(**new_settings) + return super()._get_settings(**new_settings) def test_custom_dbm_module_loaded(self): # make sure our dbm module has been loaded @@ -151,7 +151,7 @@ class FilesystemStorageGzipTest(FilesystemStorageTest): def _get_settings(self, **new_settings): new_settings.setdefault('HTTPCACHE_GZIP', True) - return super(FilesystemStorageTest, self)._get_settings(**new_settings) + return super()._get_settings(**new_settings) class DummyPolicyTest(_BaseTest): @@ -324,7 +324,7 @@ class RFC2616PolicyTest(DefaultStorageTest): ] with self._middleware() as mw: for idx, (shouldcache, status, headers) in enumerate(responses): - req0 = Request('http://example-%d.com' % idx) + req0 = Request(f'http://example-{idx}.com') res0 = Response(req0.url, status=status, headers=headers) res1 = self._process_requestresponse(mw, req0, res0) res304 = res0.replace(status=304) @@ -343,7 +343,7 @@ class RFC2616PolicyTest(DefaultStorageTest): with self._middleware(HTTPCACHE_ALWAYS_STORE=True) as mw: for idx, (_, status, headers) in enumerate(responses): shouldcache = 'no-store' not in headers.get('Cache-Control', '') and status != 304 - req0 = Request('http://example2-%d.com' % idx) + req0 = Request(f'http://example2-{idx}.com') res0 = Response(req0.url, status=status, headers=headers) res1 = self._process_requestresponse(mw, req0, res0) res304 = res0.replace(status=304) @@ -386,7 +386,7 @@ class RFC2616PolicyTest(DefaultStorageTest): ] with self._middleware() as mw: for idx, (status, headers) in enumerate(sampledata): - req0 = Request('http://example-%d.com' % idx) + req0 = Request(f'http://example-{idx}.com') res0 = Response(req0.url, status=status, headers=headers) # cache fresh response res1 = self._process_requestresponse(mw, req0, res0) @@ -423,7 +423,7 @@ class RFC2616PolicyTest(DefaultStorageTest): ] with self._middleware() as mw: for idx, (status, headers) in enumerate(sampledata): - req0 = Request('http://example-%d.com' % idx) + req0 = Request(f'http://example-{idx}.com') res0a = Response(req0.url, status=status, headers=headers) # cache expired response res1 = self._process_requestresponse(mw, req0, res0a) @@ -490,7 +490,7 @@ class RFC2616PolicyTest(DefaultStorageTest): ] with self._middleware(HTTPCACHE_IGNORE_RESPONSE_CACHE_CONTROLS=['no-cache', 'no-store']) as mw: for idx, (status, headers) in enumerate(sampledata): - req0 = Request('http://example-%d.com' % idx) + req0 = Request(f'http://example-{idx}.com') res0 = Response(req0.url, status=status, headers=headers) # cache fresh response res1 = self._process_requestresponse(mw, req0, res0) diff --git a/tests/test_downloadermiddleware_httpcompression.py b/tests/test_downloadermiddleware_httpcompression.py index 87304d76c..40e9f3a96 100644 --- a/tests/test_downloadermiddleware_httpcompression.py +++ b/tests/test_downloadermiddleware_httpcompression.py @@ -1,14 +1,16 @@ -from io import BytesIO -from unittest import TestCase, SkipTest -from os.path import join from gzip import GzipFile +from io import BytesIO +from os.path import join +from unittest import TestCase, SkipTest +from warnings import catch_warnings from scrapy.spiders import Spider from scrapy.http import Response, Request, HtmlResponse -from scrapy.downloadermiddlewares.httpcompression import HttpCompressionMiddleware, \ - ACCEPTED_ENCODINGS +from scrapy.downloadermiddlewares.httpcompression import HttpCompressionMiddleware, ACCEPTED_ENCODINGS +from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning from scrapy.responsetypes import responsetypes from scrapy.utils.gz import gunzip +from scrapy.utils.test import get_crawler from tests import tests_datadir from w3lib.encoding import resolve_encoding @@ -21,14 +23,22 @@ FORMAT = { 'rawdeflate': ('html-rawdeflate.bin', 'deflate'), 'zlibdeflate': ('html-zlibdeflate.bin', 'deflate'), 'br': ('html-br.bin', 'br'), + # $ zstd raw.html --content-size -o html-zstd-static-content-size.bin + 'zstd-static-content-size': ('html-zstd-static-content-size.bin', 'zstd'), + # $ zstd raw.html --no-content-size -o html-zstd-static-no-content-size.bin + 'zstd-static-no-content-size': ('html-zstd-static-no-content-size.bin', 'zstd'), + # $ cat raw.html | zstd -o html-zstd-streaming-no-content-size.bin + 'zstd-streaming-no-content-size': ('html-zstd-streaming-no-content-size.bin', 'zstd'), } class HttpCompressionTest(TestCase): def setUp(self): - self.spider = Spider('foo') - self.mw = HttpCompressionMiddleware() + self.crawler = get_crawler(Spider) + self.spider = self.crawler._create_spider('scrapytest.org') + self.mw = HttpCompressionMiddleware.from_crawler(self.crawler) + self.crawler.stats.open_spider(self.spider) def _getresponse(self, coding): if coding not in FORMAT: @@ -51,6 +61,34 @@ class HttpCompressionTest(TestCase): response.request = Request('http://scrapytest.org', headers={'Accept-Encoding': 'gzip, deflate'}) return response + def assertStatsEqual(self, key, value): + self.assertEqual( + self.crawler.stats.get_value(key, spider=self.spider), + value, + str(self.crawler.stats.get_stats(self.spider)) + ) + + def test_setting_false_compression_enabled(self): + self.assertRaises( + NotConfigured, + HttpCompressionMiddleware.from_crawler, + get_crawler(settings_dict={'COMPRESSION_ENABLED': False}) + ) + + def test_setting_default_compression_enabled(self): + self.assertIsInstance( + HttpCompressionMiddleware.from_crawler(get_crawler()), + HttpCompressionMiddleware + ) + + def test_setting_true_compression_enabled(self): + self.assertIsInstance( + HttpCompressionMiddleware.from_crawler( + get_crawler(settings_dict={'COMPRESSION_ENABLED': True}) + ), + HttpCompressionMiddleware + ) + def test_process_request(self): request = Request('http://scrapytest.org') assert 'Accept-Encoding' not in request.headers @@ -67,6 +105,20 @@ class HttpCompressionTest(TestCase): assert newresponse is not response assert newresponse.body.startswith(b'<!DOCTYPE') assert 'Content-Encoding' not in newresponse.headers + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 74837) + + def test_process_response_gzip_no_stats(self): + mw = HttpCompressionMiddleware() + response = self._getresponse('gzip') + request = response.request + + self.assertEqual(response.headers['Content-Encoding'], b'gzip') + newresponse = mw.process_response(request, response, self.spider) + self.assertEqual(mw.stats, None) + assert newresponse is not response + assert newresponse.body.startswith(b'<!DOCTYPE') + assert 'Content-Encoding' not in newresponse.headers def test_process_response_br(self): try: @@ -80,6 +132,29 @@ class HttpCompressionTest(TestCase): assert newresponse is not response assert newresponse.body.startswith(b"<!DOCTYPE") assert 'Content-Encoding' not in newresponse.headers + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 74837) + + def test_process_response_zstd(self): + try: + import zstandard # noqa: F401 + except ImportError: + raise SkipTest("no zstd support (zstandard)") + raw_content = None + for check_key in FORMAT: + if not check_key.startswith('zstd-'): + continue + response = self._getresponse(check_key) + request = response.request + self.assertEqual(response.headers['Content-Encoding'], b'zstd') + newresponse = self.mw.process_response(request, response, self.spider) + if raw_content is None: + raw_content = newresponse.body + else: + assert raw_content == newresponse.body + assert newresponse is not response + assert newresponse.body.startswith(b"<!DOCTYPE") + assert 'Content-Encoding' not in newresponse.headers def test_process_response_rawdeflate(self): response = self._getresponse('rawdeflate') @@ -90,6 +165,8 @@ class HttpCompressionTest(TestCase): assert newresponse is not response assert newresponse.body.startswith(b'<!DOCTYPE') assert 'Content-Encoding' not in newresponse.headers + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 74840) def test_process_response_zlibdelate(self): response = self._getresponse('zlibdeflate') @@ -100,6 +177,8 @@ class HttpCompressionTest(TestCase): assert newresponse is not response assert newresponse.body.startswith(b'<!DOCTYPE') assert 'Content-Encoding' not in newresponse.headers + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 74840) def test_process_response_plain(self): response = Response('http://scrapytest.org', body=b'<!DOCTYPE...') @@ -109,6 +188,8 @@ class HttpCompressionTest(TestCase): newresponse = self.mw.process_response(request, response, self.spider) assert newresponse is response assert newresponse.body.startswith(b'<!DOCTYPE') + self.assertStatsEqual('httpcompression/response_count', None) + self.assertStatsEqual('httpcompression/response_bytes', None) def test_multipleencodings(self): response = self._getresponse('gzip') @@ -136,6 +217,8 @@ class HttpCompressionTest(TestCase): assert isinstance(newresponse, HtmlResponse) self.assertEqual(newresponse.body, plainbody) self.assertEqual(newresponse.encoding, resolve_encoding('gb2312')) + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 104) def test_process_response_force_recalculate_encoding(self): headers = { @@ -155,6 +238,8 @@ class HttpCompressionTest(TestCase): assert isinstance(newresponse, HtmlResponse) self.assertEqual(newresponse.body, plainbody) self.assertEqual(newresponse.encoding, resolve_encoding('gb2312')) + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 104) def test_process_response_no_content_type_header(self): headers = { @@ -170,6 +255,8 @@ class HttpCompressionTest(TestCase): assert isinstance(newresponse, respcls) self.assertEqual(newresponse.body, plainbody) self.assertEqual(newresponse.encoding, resolve_encoding('gb2312')) + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 104) def test_process_response_gzipped_contenttype(self): response = self._getresponse('gzip') @@ -180,6 +267,8 @@ class HttpCompressionTest(TestCase): self.assertIsNot(newresponse, response) self.assertTrue(newresponse.body.startswith(b'<!DOCTYPE')) self.assertNotIn('Content-Encoding', newresponse.headers) + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 74837) def test_process_response_gzip_app_octetstream_contenttype(self): response = self._getresponse('gzip') @@ -190,6 +279,8 @@ class HttpCompressionTest(TestCase): self.assertIsNot(newresponse, response) self.assertTrue(newresponse.body.startswith(b'<!DOCTYPE')) self.assertNotIn('Content-Encoding', newresponse.headers) + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 74837) def test_process_response_gzip_binary_octetstream_contenttype(self): response = self._getresponse('x-gzip') @@ -200,6 +291,8 @@ class HttpCompressionTest(TestCase): self.assertIsNot(newresponse, response) self.assertTrue(newresponse.body.startswith(b'<!DOCTYPE')) self.assertNotIn('Content-Encoding', newresponse.headers) + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 74837) def test_process_response_gzipped_gzip_file(self): """Test that a gzip Content-Encoded .gz file is gunzipped @@ -242,6 +335,8 @@ class HttpCompressionTest(TestCase): newresponse = self.mw.process_response(request, response, self.spider) self.assertEqual(gunzip(newresponse.body), plainbody) + self.assertStatsEqual('httpcompression/response_count', 1) + self.assertStatsEqual('httpcompression/response_bytes', 230) def test_process_response_head_request_no_decode_required(self): response = self._getresponse('gzip') @@ -252,3 +347,32 @@ class HttpCompressionTest(TestCase): newresponse = self.mw.process_response(request, response, self.spider) self.assertIs(newresponse, response) self.assertEqual(response.body, b'') + self.assertStatsEqual('httpcompression/response_count', None) + self.assertStatsEqual('httpcompression/response_bytes', None) + + +class HttpCompressionSubclassTest(TestCase): + + def test_init_missing_stats(self): + class HttpCompressionMiddlewareSubclass(HttpCompressionMiddleware): + + def __init__(self): + super().__init__() + + crawler = get_crawler(Spider) + with catch_warnings(record=True) as caught_warnings: + HttpCompressionMiddlewareSubclass.from_crawler(crawler) + messages = tuple( + str(warning.message) for warning in caught_warnings + if warning.category is ScrapyDeprecationWarning + ) + self.assertEqual( + messages, + ( + ( + "HttpCompressionMiddleware subclasses must either modify " + "their '__init__' method to support a 'stats' parameter " + "or reimplement the 'from_crawler' method." + ), + ) + ) diff --git a/tests/test_downloadermiddleware_httpproxy.py b/tests/test_downloadermiddleware_httpproxy.py index 9841d7a76..7c97bf32a 100644 --- a/tests/test_downloadermiddleware_httpproxy.py +++ b/tests/test_downloadermiddleware_httpproxy.py @@ -88,7 +88,7 @@ class TestHttpProxyMiddleware(TestCase): def test_proxy_auth_encoding(self): # utf-8 encoding - os.environ['http_proxy'] = u'https://m\u00E1n:pass@proxy:3128' + os.environ['http_proxy'] = 'https://m\u00E1n:pass@proxy:3128' mw = HttpProxyMiddleware(auth_encoding='utf-8') req = Request('http://scrapytest.org') assert mw.process_request(req, spider) is None @@ -96,7 +96,7 @@ class TestHttpProxyMiddleware(TestCase): self.assertEqual(req.headers.get('Proxy-Authorization'), b'Basic bcOhbjpwYXNz') # proxy from request.meta - req = Request('http://scrapytest.org', meta={'proxy': u'https://\u00FCser:pass@proxy:3128'}) + req = Request('http://scrapytest.org', meta={'proxy': 'https://\u00FCser:pass@proxy:3128'}) assert mw.process_request(req, spider) is None self.assertEqual(req.meta, {'proxy': 'https://proxy:3128'}) self.assertEqual(req.headers.get('Proxy-Authorization'), b'Basic w7xzZXI6cGFzcw==') @@ -109,7 +109,7 @@ class TestHttpProxyMiddleware(TestCase): self.assertEqual(req.headers.get('Proxy-Authorization'), b'Basic beFuOnBhc3M=') # proxy from request.meta, latin-1 encoding - req = Request('http://scrapytest.org', meta={'proxy': u'https://\u00FCser:pass@proxy:3128'}) + req = Request('http://scrapytest.org', meta={'proxy': 'https://\u00FCser:pass@proxy:3128'}) assert mw.process_request(req, spider) is None self.assertEqual(req.meta, {'proxy': 'https://proxy:3128'}) self.assertEqual(req.headers.get('Proxy-Authorization'), b'Basic /HNlcjpwYXNz') @@ -145,3 +145,10 @@ class TestHttpProxyMiddleware(TestCase): req = Request('http://noproxy.com', meta={'proxy': 'http://proxy.com'}) assert mw.process_request(req, spider) is None self.assertEqual(req.meta, {'proxy': 'http://proxy.com'}) + + def test_no_proxy_invalid_values(self): + os.environ['no_proxy'] = '/var/run/docker.sock' + mw = HttpProxyMiddleware() + # '/var/run/docker.sock' may be used by the user for + # no_proxy value but is not parseable and should be skipped + assert 'no' not in mw.proxies diff --git a/tests/test_downloadermiddleware_redirect.py b/tests/test_downloadermiddleware_redirect.py index c46b1bb87..816ac1440 100644 --- a/tests/test_downloadermiddleware_redirect.py +++ b/tests/test_downloadermiddleware_redirect.py @@ -22,7 +22,7 @@ class RedirectMiddlewareTest(unittest.TestCase): def test_redirect_3xx_permanent(self): def _test(method, status=301): - url = 'http://www.example.com/{}'.format(status) + url = f'http://www.example.com/{status}' url2 = 'http://www.example.com/redirected' req = Request(url, method=method) rsp = Response(url, headers={'Location': url2}, status=status) @@ -77,12 +77,9 @@ class RedirectMiddlewareTest(unittest.TestCase): assert isinstance(req2, Request) self.assertEqual(req2.url, url2) self.assertEqual(req2.method, 'GET') - assert 'Content-Type' not in req2.headers, \ - "Content-Type header must not be present in redirected request" - assert 'Content-Length' not in req2.headers, \ - "Content-Length header must not be present in redirected request" - assert not req2.body, \ - "Redirected body must be empty, not '%s'" % req2.body + assert 'Content-Type' not in req2.headers, "Content-Type header must not be present in redirected request" + assert 'Content-Length' not in req2.headers, "Content-Length header must not be present in redirected request" + assert not req2.body, f"Redirected body must be empty, not '{req2.body}'" # response without Location header but with status code is 3XX should be ignored del rsp.headers['Location'] @@ -187,7 +184,7 @@ class RedirectMiddlewareTest(unittest.TestCase): def test_latin1_location(self): req = Request('http://scrapytest.org/first') - latin1_location = u'/ação'.encode('latin1') # HTTP historically supports latin1 + latin1_location = '/ação'.encode('latin1') # HTTP historically supports latin1 resp = Response('http://scrapytest.org/first', headers={'Location': latin1_location}, status=302) req_result = self.mw.process_response(req, resp, self.spider) perc_encoded_utf8_url = 'http://scrapytest.org/a%E7%E3o' @@ -195,7 +192,7 @@ class RedirectMiddlewareTest(unittest.TestCase): def test_utf8_location(self): req = Request('http://scrapytest.org/first') - utf8_location = u'/ação'.encode('utf-8') # header using UTF-8 encoding + utf8_location = '/ação'.encode('utf-8') # header using UTF-8 encoding resp = Response('http://scrapytest.org/first', headers={'Location': utf8_location}, status=302) req_result = self.mw.process_response(req, resp, self.spider) perc_encoded_utf8_url = 'http://scrapytest.org/a%C3%A7%C3%A3o' @@ -210,8 +207,8 @@ class MetaRefreshMiddlewareTest(unittest.TestCase): self.mw = MetaRefreshMiddleware.from_crawler(crawler) def _body(self, interval=5, url='http://example.org/newpage'): - html = u"""<html><head><meta http-equiv="refresh" content="{0};url={1}"/></head></html>""" - return html.format(interval, url).encode('utf-8') + html = f"""<html><head><meta http-equiv="refresh" content="{interval};url={url}"/></head></html>""" + return html.encode('utf-8') def test_priority_adjust(self): req = Request('http://a.com') @@ -244,12 +241,9 @@ class MetaRefreshMiddlewareTest(unittest.TestCase): assert isinstance(req2, Request) self.assertEqual(req2.url, 'http://example.org/newpage') self.assertEqual(req2.method, 'GET') - assert 'Content-Type' not in req2.headers, \ - "Content-Type header must not be present in redirected request" - assert 'Content-Length' not in req2.headers, \ - "Content-Length header must not be present in redirected request" - assert not req2.body, \ - "Redirected body must be empty, not '%s'" % req2.body + assert 'Content-Type' not in req2.headers, "Content-Type header must not be present in redirected request" + assert 'Content-Length' not in req2.headers, "Content-Length header must not be present in redirected request" + assert not req2.body, f"Redirected body must be empty, not '{req2.body}'" def test_max_redirect_times(self): self.mw.max_redirect_times = 1 diff --git a/tests/test_downloadermiddleware_retry.py b/tests/test_downloadermiddleware_retry.py index 29357ba94..915bd3a3e 100644 --- a/tests/test_downloadermiddleware_retry.py +++ b/tests/test_downloadermiddleware_retry.py @@ -1,19 +1,21 @@ +import logging import unittest + +from testfixtures import LogCapture from twisted.internet import defer from twisted.internet.error import ( ConnectError, ConnectionDone, ConnectionLost, - ConnectionRefusedError, DNSLookupError, TCPTimedOutError, - TimeoutError, ) from twisted.web.client import ResponseFailed -from scrapy.downloadermiddlewares.retry import RetryMiddleware -from scrapy.spiders import Spider +from scrapy.downloadermiddlewares.retry import get_retry_request, RetryMiddleware +from scrapy.exceptions import IgnoreRequest from scrapy.http import Request, Response +from scrapy.spiders import Spider from scrapy.utils.test import get_crawler @@ -94,7 +96,7 @@ class RetryTest(unittest.TestCase): ] for exc in exceptions: - req = Request('http://www.scrapytest.org/%s' % exc.__name__) + req = Request(f'http://www.scrapytest.org/{exc.__name__}') self._test_retry_exception(req, exc('foo')) stats = self.crawler.stats @@ -119,82 +121,514 @@ class RetryTest(unittest.TestCase): class MaxRetryTimesTest(unittest.TestCase): - def setUp(self): - self.crawler = get_crawler(Spider) - self.spider = self.crawler._create_spider('foo') - self.mw = RetryMiddleware.from_crawler(self.crawler) - self.mw.max_retry_times = 2 - self.invalid_url = 'http://www.scrapytest.org/invalid_url' + + invalid_url = 'http://www.scrapytest.org/invalid_url' + + def get_spider_and_middleware(self, settings=None): + crawler = get_crawler(Spider, settings or {}) + spider = crawler._create_spider('foo') + middleware = RetryMiddleware.from_crawler(crawler) + return spider, middleware def test_with_settings_zero(self): - - # SETTINGS: RETRY_TIMES = 0 - self.mw.max_retry_times = 0 - + max_retry_times = 0 + settings = {'RETRY_TIMES': max_retry_times} + spider, middleware = self.get_spider_and_middleware(settings) req = Request(self.invalid_url) - self._test_retry(req, DNSLookupError('foo'), self.mw.max_retry_times) + self._test_retry( + req, + DNSLookupError('foo'), + max_retry_times, + spider=spider, + middleware=middleware, + ) def test_with_metakey_zero(self): - - # SETTINGS: meta(max_retry_times) = 0 - meta_max_retry_times = 0 - - req = Request(self.invalid_url, meta={'max_retry_times': meta_max_retry_times}) - self._test_retry(req, DNSLookupError('foo'), meta_max_retry_times) + max_retry_times = 0 + spider, middleware = self.get_spider_and_middleware() + meta = {'max_retry_times': max_retry_times} + req = Request(self.invalid_url, meta=meta) + self._test_retry( + req, + DNSLookupError('foo'), + max_retry_times, + spider=spider, + middleware=middleware, + ) def test_without_metakey(self): - - # SETTINGS: RETRY_TIMES is NON-ZERO - self.mw.max_retry_times = 5 - + max_retry_times = 5 + settings = {'RETRY_TIMES': max_retry_times} + spider, middleware = self.get_spider_and_middleware(settings) req = Request(self.invalid_url) - self._test_retry(req, DNSLookupError('foo'), self.mw.max_retry_times) + self._test_retry( + req, + DNSLookupError('foo'), + max_retry_times, + spider=spider, + middleware=middleware, + ) def test_with_metakey_greater(self): - - # SETINGS: RETRY_TIMES < meta(max_retry_times) - self.mw.max_retry_times = 2 meta_max_retry_times = 3 + middleware_max_retry_times = 2 req1 = Request(self.invalid_url, meta={'max_retry_times': meta_max_retry_times}) req2 = Request(self.invalid_url) - self._test_retry(req1, DNSLookupError('foo'), meta_max_retry_times) - self._test_retry(req2, DNSLookupError('foo'), self.mw.max_retry_times) + settings = {'RETRY_TIMES': middleware_max_retry_times} + spider, middleware = self.get_spider_and_middleware(settings) + + self._test_retry( + req1, + DNSLookupError('foo'), + meta_max_retry_times, + spider=spider, + middleware=middleware, + ) + self._test_retry( + req2, + DNSLookupError('foo'), + middleware_max_retry_times, + spider=spider, + middleware=middleware, + ) def test_with_metakey_lesser(self): - - # SETINGS: RETRY_TIMES > meta(max_retry_times) - self.mw.max_retry_times = 5 meta_max_retry_times = 4 + middleware_max_retry_times = 5 req1 = Request(self.invalid_url, meta={'max_retry_times': meta_max_retry_times}) req2 = Request(self.invalid_url) - self._test_retry(req1, DNSLookupError('foo'), meta_max_retry_times) - self._test_retry(req2, DNSLookupError('foo'), self.mw.max_retry_times) + settings = {'RETRY_TIMES': middleware_max_retry_times} + spider, middleware = self.get_spider_and_middleware(settings) + + self._test_retry( + req1, + DNSLookupError('foo'), + meta_max_retry_times, + spider=spider, + middleware=middleware, + ) + self._test_retry( + req2, + DNSLookupError('foo'), + middleware_max_retry_times, + spider=spider, + middleware=middleware, + ) def test_with_dont_retry(self): + max_retry_times = 4 + spider, middleware = self.get_spider_and_middleware() + meta = { + 'max_retry_times': max_retry_times, + 'dont_retry': True, + } + req = Request(self.invalid_url, meta=meta) + self._test_retry( + req, + DNSLookupError('foo'), + 0, + spider=spider, + middleware=middleware, + ) - # SETTINGS: meta(max_retry_times) = 4 - meta_max_retry_times = 4 - - req = Request(self.invalid_url, meta={ - 'max_retry_times': meta_max_retry_times, 'dont_retry': True - }) - - self._test_retry(req, DNSLookupError('foo'), 0) - - def _test_retry(self, req, exception, max_retry_times): + def _test_retry( + self, + req, + exception, + max_retry_times, + spider=None, + middleware=None, + ): + spider = spider or self.spider + middleware = middleware or self.mw for i in range(0, max_retry_times): - req = self.mw.process_exception(req, exception, self.spider) + req = middleware.process_exception(req, exception, spider) assert isinstance(req, Request) # discard it - req = self.mw.process_exception(req, exception, self.spider) + req = middleware.process_exception(req, exception, spider) self.assertEqual(req, None) +class GetRetryRequestTest(unittest.TestCase): + + def get_spider(self, settings=None): + crawler = get_crawler(Spider, settings or {}) + return crawler._create_spider('foo') + + def test_basic_usage(self): + request = Request('https://example.com') + spider = self.get_spider() + with LogCapture() as log: + new_request = get_retry_request( + request, + spider=spider, + ) + self.assertIsInstance(new_request, Request) + self.assertNotEqual(new_request, request) + self.assertEqual(new_request.dont_filter, True) + expected_retry_times = 1 + self.assertEqual(new_request.meta['retry_times'], expected_retry_times) + self.assertEqual(new_request.priority, -1) + expected_reason = "unspecified" + for stat in ('retry/count', f'retry/reason_count/{expected_reason}'): + self.assertEqual(spider.crawler.stats.get_value(stat), 1) + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "DEBUG", + f"Retrying {request} (failed {expected_retry_times} times): " + f"{expected_reason}", + ) + ) + + def test_max_retries_reached(self): + request = Request('https://example.com') + spider = self.get_spider() + max_retry_times = 0 + with LogCapture() as log: + new_request = get_retry_request( + request, + spider=spider, + max_retry_times=max_retry_times, + ) + self.assertEqual(new_request, None) + self.assertEqual( + spider.crawler.stats.get_value('retry/max_reached'), + 1 + ) + failure_count = max_retry_times + 1 + expected_reason = "unspecified" + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "ERROR", + f"Gave up retrying {request} (failed {failure_count} times): " + f"{expected_reason}", + ) + ) + + def test_one_retry(self): + request = Request('https://example.com') + spider = self.get_spider() + with LogCapture() as log: + new_request = get_retry_request( + request, + spider=spider, + max_retry_times=1, + ) + self.assertIsInstance(new_request, Request) + self.assertNotEqual(new_request, request) + self.assertEqual(new_request.dont_filter, True) + expected_retry_times = 1 + self.assertEqual(new_request.meta['retry_times'], expected_retry_times) + self.assertEqual(new_request.priority, -1) + expected_reason = "unspecified" + for stat in ('retry/count', f'retry/reason_count/{expected_reason}'): + self.assertEqual(spider.crawler.stats.get_value(stat), 1) + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "DEBUG", + f"Retrying {request} (failed {expected_retry_times} times): " + f"{expected_reason}", + ) + ) + + def test_two_retries(self): + spider = self.get_spider() + request = Request('https://example.com') + new_request = request + max_retry_times = 2 + for index in range(max_retry_times): + with LogCapture() as log: + new_request = get_retry_request( + new_request, + spider=spider, + max_retry_times=max_retry_times, + ) + self.assertIsInstance(new_request, Request) + self.assertNotEqual(new_request, request) + self.assertEqual(new_request.dont_filter, True) + expected_retry_times = index + 1 + self.assertEqual(new_request.meta['retry_times'], expected_retry_times) + self.assertEqual(new_request.priority, -expected_retry_times) + expected_reason = "unspecified" + for stat in ('retry/count', f'retry/reason_count/{expected_reason}'): + value = spider.crawler.stats.get_value(stat) + self.assertEqual(value, expected_retry_times) + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "DEBUG", + f"Retrying {request} (failed {expected_retry_times} times): " + f"{expected_reason}", + ) + ) + + with LogCapture() as log: + new_request = get_retry_request( + new_request, + spider=spider, + max_retry_times=max_retry_times, + ) + self.assertEqual(new_request, None) + self.assertEqual( + spider.crawler.stats.get_value('retry/max_reached'), + 1 + ) + failure_count = max_retry_times + 1 + expected_reason = "unspecified" + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "ERROR", + f"Gave up retrying {request} (failed {failure_count} times): " + f"{expected_reason}", + ) + ) + + def test_no_spider(self): + request = Request('https://example.com') + with self.assertRaises(TypeError): + get_retry_request(request) # pylint: disable=missing-kwoa + + def test_max_retry_times_setting(self): + max_retry_times = 0 + spider = self.get_spider({'RETRY_TIMES': max_retry_times}) + request = Request('https://example.com') + new_request = get_retry_request( + request, + spider=spider, + ) + self.assertEqual(new_request, None) + + def test_max_retry_times_meta(self): + max_retry_times = 0 + spider = self.get_spider({'RETRY_TIMES': max_retry_times + 1}) + meta = {'max_retry_times': max_retry_times} + request = Request('https://example.com', meta=meta) + new_request = get_retry_request( + request, + spider=spider, + ) + self.assertEqual(new_request, None) + + def test_max_retry_times_argument(self): + max_retry_times = 0 + spider = self.get_spider({'RETRY_TIMES': max_retry_times + 1}) + meta = {'max_retry_times': max_retry_times + 1} + request = Request('https://example.com', meta=meta) + new_request = get_retry_request( + request, + spider=spider, + max_retry_times=max_retry_times, + ) + self.assertEqual(new_request, None) + + def test_priority_adjust_setting(self): + priority_adjust = 1 + spider = self.get_spider({'RETRY_PRIORITY_ADJUST': priority_adjust}) + request = Request('https://example.com') + new_request = get_retry_request( + request, + spider=spider, + ) + self.assertEqual(new_request.priority, priority_adjust) + + def test_priority_adjust_argument(self): + priority_adjust = 1 + spider = self.get_spider({'RETRY_PRIORITY_ADJUST': priority_adjust + 1}) + request = Request('https://example.com') + new_request = get_retry_request( + request, + spider=spider, + priority_adjust=priority_adjust, + ) + self.assertEqual(new_request.priority, priority_adjust) + + def test_log_extra_retry_success(self): + request = Request('https://example.com') + spider = self.get_spider() + with LogCapture(attributes=('spider',)) as log: + get_retry_request( + request, + spider=spider, + ) + log.check_present(spider) + + def test_log_extra_retries_exceeded(self): + request = Request('https://example.com') + spider = self.get_spider() + with LogCapture(attributes=('spider',)) as log: + get_retry_request( + request, + spider=spider, + max_retry_times=0, + ) + log.check_present(spider) + + def test_reason_string(self): + request = Request('https://example.com') + spider = self.get_spider() + expected_reason = 'because' + with LogCapture() as log: + get_retry_request( + request, + spider=spider, + reason=expected_reason, + ) + expected_retry_times = 1 + for stat in ('retry/count', f'retry/reason_count/{expected_reason}'): + self.assertEqual(spider.crawler.stats.get_value(stat), 1) + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "DEBUG", + f"Retrying {request} (failed {expected_retry_times} times): " + f"{expected_reason}", + ) + ) + + def test_reason_builtin_exception(self): + request = Request('https://example.com') + spider = self.get_spider() + expected_reason = NotImplementedError() + expected_reason_string = 'builtins.NotImplementedError' + with LogCapture() as log: + get_retry_request( + request, + spider=spider, + reason=expected_reason, + ) + expected_retry_times = 1 + stat = spider.crawler.stats.get_value( + f'retry/reason_count/{expected_reason_string}' + ) + self.assertEqual(stat, 1) + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "DEBUG", + f"Retrying {request} (failed {expected_retry_times} times): " + f"{expected_reason}", + ) + ) + + def test_reason_builtin_exception_class(self): + request = Request('https://example.com') + spider = self.get_spider() + expected_reason = NotImplementedError + expected_reason_string = 'builtins.NotImplementedError' + with LogCapture() as log: + get_retry_request( + request, + spider=spider, + reason=expected_reason, + ) + expected_retry_times = 1 + stat = spider.crawler.stats.get_value( + f'retry/reason_count/{expected_reason_string}' + ) + self.assertEqual(stat, 1) + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "DEBUG", + f"Retrying {request} (failed {expected_retry_times} times): " + f"{expected_reason}", + ) + ) + + def test_reason_custom_exception(self): + request = Request('https://example.com') + spider = self.get_spider() + expected_reason = IgnoreRequest() + expected_reason_string = 'scrapy.exceptions.IgnoreRequest' + with LogCapture() as log: + get_retry_request( + request, + spider=spider, + reason=expected_reason, + ) + expected_retry_times = 1 + stat = spider.crawler.stats.get_value( + f'retry/reason_count/{expected_reason_string}' + ) + self.assertEqual(stat, 1) + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "DEBUG", + f"Retrying {request} (failed {expected_retry_times} times): " + f"{expected_reason}", + ) + ) + + def test_reason_custom_exception_class(self): + request = Request('https://example.com') + spider = self.get_spider() + expected_reason = IgnoreRequest + expected_reason_string = 'scrapy.exceptions.IgnoreRequest' + with LogCapture() as log: + get_retry_request( + request, + spider=spider, + reason=expected_reason, + ) + expected_retry_times = 1 + stat = spider.crawler.stats.get_value( + f'retry/reason_count/{expected_reason_string}' + ) + self.assertEqual(stat, 1) + log.check_present( + ( + "scrapy.downloadermiddlewares.retry", + "DEBUG", + f"Retrying {request} (failed {expected_retry_times} times): " + f"{expected_reason}", + ) + ) + + def test_custom_logger(self): + logger = logging.getLogger("custom-logger") + request = Request("https://example.com") + spider = self.get_spider() + expected_reason = "because" + with LogCapture() as log: + get_retry_request( + request, + spider=spider, + reason=expected_reason, + logger=logger, + ) + log.check_present( + ( + "custom-logger", + "DEBUG", + f"Retrying {request} (failed 1 times): {expected_reason}", + ) + ) + + def test_custom_stats_key(self): + request = Request("https://example.com") + spider = self.get_spider() + expected_reason = "because" + stats_key = "custom_retry" + get_retry_request( + request, + spider=spider, + reason=expected_reason, + stats_base_key=stats_key, + ) + for stat in (f"{stats_key}/count", f"{stats_key}/reason_count/{expected_reason}"): + self.assertEqual(spider.crawler.stats.get_value(stat), 1) + + if __name__ == "__main__": unittest.main() diff --git a/tests/test_downloadermiddleware_robotstxt.py b/tests/test_downloadermiddleware_robotstxt.py index b9452a0e7..1460d88eb 100644 --- a/tests/test_downloadermiddleware_robotstxt.py +++ b/tests/test_downloadermiddleware_robotstxt.py @@ -30,7 +30,7 @@ class RobotsTxtMiddlewareTest(unittest.TestCase): def _get_successful_crawler(self): crawler = self.crawler crawler.settings.set('ROBOTSTXT_OBEY', True) - ROBOTS = u""" + ROBOTS = """ User-Agent: * Disallow: /admin/ Disallow: /static/ @@ -42,7 +42,7 @@ Disallow: /some/randome/page.html """.encode('utf-8') response = TextResponse('http://site.local/robots.txt', body=ROBOTS) - def return_response(request, spider): + def return_response(request): deferred = Deferred() reactor.callFromThread(deferred.callback, response) return deferred @@ -56,7 +56,7 @@ Disallow: /some/randome/page.html self.assertIgnored(Request('http://site.local/admin/main'), middleware), self.assertIgnored(Request('http://site.local/static/'), middleware), self.assertIgnored(Request('http://site.local/wiki/K%C3%A4ytt%C3%A4j%C3%A4:'), middleware), - self.assertIgnored(Request(u'http://site.local/wiki/Käyttäjä:'), middleware) + self.assertIgnored(Request('http://site.local/wiki/Käyttäjä:'), middleware) ], fireOnOneErrback=True) def test_robotstxt_ready_parser(self): @@ -79,7 +79,7 @@ Disallow: /some/randome/page.html crawler.settings.set('ROBOTSTXT_OBEY', True) response = Response('http://site.local/robots.txt', body=b'GIF89a\xd3\x00\xfe\x00\xa2') - def return_response(request, spider): + def return_response(request): deferred = Deferred() reactor.callFromThread(deferred.callback, response) return deferred @@ -102,7 +102,7 @@ Disallow: /some/randome/page.html crawler.settings.set('ROBOTSTXT_OBEY', True) response = Response('http://site.local/robots.txt') - def return_response(request, spider): + def return_response(request): deferred = Deferred() reactor.callFromThread(deferred.callback, response) return deferred @@ -122,7 +122,7 @@ Disallow: /some/randome/page.html self.crawler.settings.set('ROBOTSTXT_OBEY', True) err = error.DNSLookupError('Robotstxt address not found') - def return_failure(request, spider): + def return_failure(request): deferred = Deferred() reactor.callFromThread(deferred.errback, failure.Failure(err)) return deferred @@ -138,7 +138,7 @@ Disallow: /some/randome/page.html self.crawler.settings.set('ROBOTSTXT_OBEY', True) err = error.DNSLookupError('Robotstxt address not found') - def immediate_failure(request, spider): + def immediate_failure(request): deferred = Deferred() deferred.errback(failure.Failure(err)) return deferred @@ -150,7 +150,7 @@ Disallow: /some/randome/page.html def test_ignore_robotstxt_request(self): self.crawler.settings.set('ROBOTSTXT_OBEY', True) - def ignore_request(request, spider): + def ignore_request(request): deferred = Deferred() reactor.callFromThread(deferred.errback, failure.Failure(IgnoreRequest())) return deferred @@ -189,7 +189,7 @@ class RobotsTxtMiddlewareWithRerpTest(RobotsTxtMiddlewareTest): skip = "Rerp parser is not installed" def setUp(self): - super(RobotsTxtMiddlewareWithRerpTest, self).setUp() + super().setUp() self.crawler.settings.set('ROBOTSTXT_PARSER', 'scrapy.robotstxt.RerpRobotParser') @@ -198,5 +198,5 @@ class RobotsTxtMiddlewareWithReppyTest(RobotsTxtMiddlewareTest): skip = "Reppy parser is not installed" def setUp(self): - super(RobotsTxtMiddlewareWithReppyTest, self).setUp() + super().setUp() self.crawler.settings.set('ROBOTSTXT_PARSER', 'scrapy.robotstxt.ReppyRobotParser') diff --git a/tests/test_dupefilters.py b/tests/test_dupefilters.py index 95a4fca0d..680bb6dc8 100644 --- a/tests/test_dupefilters.py +++ b/tests/test_dupefilters.py @@ -43,7 +43,7 @@ class RFPDupeFilterTest(unittest.TestCase): def test_df_from_crawler_scheduler(self): settings = {'DUPEFILTER_DEBUG': True, - 'DUPEFILTER_CLASS': __name__ + '.FromCrawlerRFPDupeFilter'} + 'DUPEFILTER_CLASS': FromCrawlerRFPDupeFilter} crawler = get_crawler(settings_dict=settings) scheduler = Scheduler.from_crawler(crawler) self.assertTrue(scheduler.df.debug) @@ -51,14 +51,14 @@ class RFPDupeFilterTest(unittest.TestCase): def test_df_from_settings_scheduler(self): settings = {'DUPEFILTER_DEBUG': True, - 'DUPEFILTER_CLASS': __name__ + '.FromSettingsRFPDupeFilter'} + 'DUPEFILTER_CLASS': FromSettingsRFPDupeFilter} crawler = get_crawler(settings_dict=settings) scheduler = Scheduler.from_crawler(crawler) self.assertTrue(scheduler.df.debug) self.assertEqual(scheduler.df.method, 'from_settings') def test_df_direct_scheduler(self): - settings = {'DUPEFILTER_CLASS': __name__ + '.DirectDupeFilter'} + settings = {'DUPEFILTER_CLASS': DirectDupeFilter} crawler = get_crawler(settings_dict=settings) scheduler = Scheduler.from_crawler(crawler) self.assertEqual(scheduler.df.method, 'n/a') @@ -162,7 +162,7 @@ class RFPDupeFilterTest(unittest.TestCase): def test_log(self): with LogCapture() as log: settings = {'DUPEFILTER_DEBUG': False, - 'DUPEFILTER_CLASS': __name__ + '.FromCrawlerRFPDupeFilter'} + 'DUPEFILTER_CLASS': FromCrawlerRFPDupeFilter} crawler = get_crawler(SimpleSpider, settings_dict=settings) scheduler = Scheduler.from_crawler(crawler) spider = SimpleSpider.from_crawler(crawler) @@ -191,7 +191,7 @@ class RFPDupeFilterTest(unittest.TestCase): def test_log_debug(self): with LogCapture() as log: settings = {'DUPEFILTER_DEBUG': True, - 'DUPEFILTER_CLASS': __name__ + '.FromCrawlerRFPDupeFilter'} + 'DUPEFILTER_CLASS': FromCrawlerRFPDupeFilter} crawler = get_crawler(SimpleSpider, settings_dict=settings) scheduler = Scheduler.from_crawler(crawler) spider = SimpleSpider.from_crawler(crawler) diff --git a/tests/test_engine.py b/tests/test_engine.py index 6696ee52e..92bf45f25 100644 --- a/tests/test_engine.py +++ b/tests/test_engine.py @@ -13,18 +13,20 @@ module with the ``runserver`` argument:: import os import re import sys +import warnings from collections import defaultdict from urllib.parse import urlparse +import attr +from itemadapter import ItemAdapter from pydispatch import dispatcher -from testfixtures import LogCapture -from twisted.internet import reactor, defer +from twisted.internet import defer, reactor from twisted.trial import unittest from twisted.web import server, static, util from scrapy import signals from scrapy.core.engine import ExecutionEngine -from scrapy.exceptions import StopDownload +from scrapy.exceptions import CloseSpider, ScrapyDeprecationWarning from scrapy.http import Request from scrapy.item import Item, Field from scrapy.linkextractors import LinkExtractor @@ -32,7 +34,7 @@ from scrapy.spiders import Spider from scrapy.utils.signal import disconnect_all from scrapy.utils.test import get_crawler -from tests import tests_datadir, get_testdata +from tests import get_testdata, tests_datadir class TestItem(Item): @@ -41,6 +43,13 @@ class TestItem(Item): price = Field() +@attr.s +class AttrsItem: + name = attr.ib(default="") + url = attr.ib(default="") + price = attr.ib(default=0) + + class TestSpider(Spider): name = "scrapytest.org" allowed_domains = ["scrapytest.org", "localhost"] @@ -49,7 +58,7 @@ class TestSpider(Spider): name_re = re.compile(r"<h1>(.*?)</h1>", re.M) price_re = re.compile(r">Price: \$(.*?)<", re.M) - item_cls = TestItem + item_cls: type = TestItem def parse(self, response): xlink = LinkExtractor() @@ -59,15 +68,15 @@ class TestSpider(Spider): yield Request(url=link.url, callback=self.parse_item) def parse_item(self, response): - item = self.item_cls() + adapter = ItemAdapter(self.item_cls()) m = self.name_re.search(response.text) if m: - item['name'] = m.group(1) - item['url'] = response.url + adapter['name'] = m.group(1) + adapter['url'] = response.url m = self.price_re.search(response.text) if m: - item['price'] = m.group(1) - return item + adapter['price'] = m.group(1) + return adapter.item class TestDupeFilterSpider(TestSpider): @@ -79,6 +88,23 @@ class DictItemsSpider(TestSpider): item_cls = dict +class AttrsItemsSpider(TestSpider): + item_cls = AttrsItem + + +try: + from dataclasses import make_dataclass +except ImportError: + DataClassItemsSpider = None +else: + TestDataClass = make_dataclass("TestDataClass", [("name", str), ("url", str), ("price", int)]) + + class DataClassItemsSpider(DictItemsSpider): # type: ignore[no-redef] + def parse_item(self, response): + item = super().parse_item(response) + return TestDataClass(**item) + + class ItemZeroDivisionErrorSpider(TestSpider): custom_settings = { "ITEM_PIPELINES": { @@ -87,6 +113,18 @@ class ItemZeroDivisionErrorSpider(TestSpider): } +class ChangeCloseReasonSpider(TestSpider): + @classmethod + def from_crawler(cls, crawler, *args, **kwargs): + spider = cls(*args, **kwargs) + spider._set_crawler(crawler) + crawler.signals.connect(spider.spider_idle, signals.spider_idle) + return spider + + def spider_idle(self): + raise CloseSpider(reason="custom_reason") + + def start_test_site(debug=False): root_dir = os.path.join(tests_datadir, "test_site") r = static.File(root_dir) @@ -97,8 +135,8 @@ def start_test_site(debug=False): port = reactor.listenTCP(0, server.Site(r), interface="127.0.0.1") if debug: - print("Test server running at http://localhost:%d/ - hit Ctrl-C to finish." - % port.getHost().port) + print(f"Test server running at http://localhost:{port.getHost().port}/ " + "- hit Ctrl-C to finish.") return port @@ -113,6 +151,7 @@ class CrawlerRun: self.reqreached = [] self.itemerror = [] self.itemresp = [] + self.headers = {} self.bytes = defaultdict(lambda: list()) self.signals_caught = {} self.spider_class = spider_class @@ -135,6 +174,7 @@ class CrawlerRun: self.crawler = get_crawler(self.spider_class) self.crawler.signals.connect(self.item_scraped, signals.item_scraped) self.crawler.signals.connect(self.item_error, signals.item_error) + self.crawler.signals.connect(self.headers_received, signals.headers_received) self.crawler.signals.connect(self.bytes_received, signals.bytes_received) self.crawler.signals.connect(self.request_scheduled, signals.request_scheduled) self.crawler.signals.connect(self.request_dropped, signals.request_dropped) @@ -153,9 +193,10 @@ class CrawlerRun: if not name.startswith('_'): disconnect_all(signal) self.deferred.callback(None) + return self.crawler.stop() def geturl(self, path): - return "http://localhost:%s%s" % (self.portno, path) + return f"http://localhost:{self.portno}{path}" def getpath(self, url): u = urlparse(url) @@ -167,6 +208,9 @@ class CrawlerRun: def item_scraped(self, item, spider, response): self.itemresp.append((item, response)) + def headers_received(self, headers, body_length, request, spider): + self.headers[request] = headers + def bytes_received(self, data, request, spider): self.bytes[request].append(data) @@ -190,26 +234,18 @@ class CrawlerRun: self.signals_caught[sig] = signalargs -class StopDownloadCrawlerRun(CrawlerRun): - """ - Make sure raising the StopDownload exception stops the download of the response body - """ - - def bytes_received(self, data, request, spider): - super().bytes_received(data, request, spider) - raise StopDownload(fail=False) - - class EngineTest(unittest.TestCase): - @defer.inlineCallbacks def test_crawler(self): - for spider in TestSpider, DictItemsSpider: + + for spider in (TestSpider, DictItemsSpider, AttrsItemsSpider, DataClassItemsSpider): + if spider is None: + continue self.run = CrawlerRun(spider) yield self.run.run() self._assert_visited_urls() - self._assert_scheduled_requests(urls_to_visit=9) - self._assert_downloaded_responses() + self._assert_scheduled_requests(count=9) + self._assert_downloaded_responses(count=9) self._assert_scraped_items() self._assert_signals_caught() self._assert_bytes_received() @@ -218,7 +254,7 @@ class EngineTest(unittest.TestCase): def test_crawler_dupefilter(self): self.run = CrawlerRun(TestDupeFilterSpider) yield self.run.run() - self._assert_scheduled_requests(urls_to_visit=8) + self._assert_scheduled_requests(count=8) self._assert_dropped_requests() @defer.inlineCallbacks @@ -227,15 +263,22 @@ class EngineTest(unittest.TestCase): yield self.run.run() self._assert_items_error() + @defer.inlineCallbacks + def test_crawler_change_close_reason_on_idle(self): + self.run = CrawlerRun(ChangeCloseReasonSpider) + yield self.run.run() + self.assertEqual({'spider': self.run.spider, 'reason': 'custom_reason'}, + self.run.signals_caught[signals.spider_closed]) + def _assert_visited_urls(self): must_be_visited = ["/", "/redirect", "/redirected", "/item1.html", "/item2.html", "/item999.html"] urls_visited = {rp[0].url for rp in self.run.respplug} urls_expected = {self.run.geturl(p) for p in must_be_visited} - assert urls_expected <= urls_visited, "URLs not visited: %s" % list(urls_expected - urls_visited) + assert urls_expected <= urls_visited, f"URLs not visited: {list(urls_expected - urls_visited)}" - def _assert_scheduled_requests(self, urls_to_visit=None): - self.assertEqual(urls_to_visit, len(self.run.reqplug)) + def _assert_scheduled_requests(self, count=None): + self.assertEqual(count, len(self.run.reqplug)) paths_expected = ['/item999.html', '/item2.html', '/item1.html'] @@ -253,10 +296,10 @@ class EngineTest(unittest.TestCase): def _assert_dropped_requests(self): self.assertEqual(len(self.run.reqdropped), 1) - def _assert_downloaded_responses(self): + def _assert_downloaded_responses(self, count): # response tests - self.assertEqual(9, len(self.run.respplug)) - self.assertEqual(9, len(self.run.reqreached)) + self.assertEqual(count, len(self.run.respplug)) + self.assertEqual(count, len(self.run.reqreached)) for response, _ in self.run.respplug: if self.run.getpath(response.url) == '/item999.html': @@ -281,6 +324,7 @@ class EngineTest(unittest.TestCase): def _assert_scraped_items(self): self.assertEqual(2, len(self.run.itemresp)) for item, response in self.run.itemresp: + item = ItemAdapter(item) self.assertEqual(item['url'], response.url) if 'item1.html' in item['url']: self.assertEqual('Item 1 name', item['name']) @@ -289,6 +333,13 @@ class EngineTest(unittest.TestCase): self.assertEqual('Item 2 name', item['name']) self.assertEqual('200', item['price']) + def _assert_headers_received(self): + for headers in self.run.headers.values(): + self.assertIn(b"Server", headers) + self.assertIn(b"TwistedWeb", headers[b"Server"]) + self.assertIn(b"Date", headers) + self.assertIn(b"Content-Type", headers) + def _assert_bytes_received(self): self.assertEqual(9, len(self.run.bytes)) for request, data in self.run.bytes.items(): @@ -337,6 +388,7 @@ class EngineTest(unittest.TestCase): assert signals.spider_opened in self.run.signals_caught assert signals.spider_idle in self.run.signals_caught assert signals.spider_closed in self.run.signals_caught + assert signals.headers_received in self.run.signals_caught self.assertEqual({'spider': self.run.spider}, self.run.signals_caught[signals.spider_opened]) @@ -351,61 +403,104 @@ class EngineTest(unittest.TestCase): yield e.close() @defer.inlineCallbacks - def test_close_spiders_downloader(self): - e = ExecutionEngine(get_crawler(TestSpider), lambda _: None) - yield e.open_spider(TestSpider(), []) - self.assertEqual(len(e.open_spiders), 1) - yield e.close() - self.assertEqual(len(e.open_spiders), 0) - - @defer.inlineCallbacks - def test_close_engine_spiders_downloader(self): + def test_start_already_running_exception(self): e = ExecutionEngine(get_crawler(TestSpider), lambda _: None) yield e.open_spider(TestSpider(), []) e.start() - self.assertTrue(e.running) - yield e.close() - self.assertFalse(e.running) - self.assertEqual(len(e.open_spiders), 0) - - -class StopDownloadEngineTest(EngineTest): + yield self.assertFailure(e.start(), RuntimeError).addBoth( + lambda exc: self.assertEqual(str(exc), "Engine already running") + ) + yield e.stop() @defer.inlineCallbacks - def test_crawler(self): - for spider in TestSpider, DictItemsSpider: - self.run = StopDownloadCrawlerRun(spider) - with LogCapture() as log: - yield self.run.run() - log.check_present(("scrapy.core.downloader.handlers.http11", - "DEBUG", - "Download stopped for <GET http://localhost:{}/redirected> from signal handler" - " StopDownloadCrawlerRun.bytes_received".format(self.run.portno))) - log.check_present(("scrapy.core.downloader.handlers.http11", - "DEBUG", - "Download stopped for <GET http://localhost:{}/> from signal handler" - " StopDownloadCrawlerRun.bytes_received".format(self.run.portno))) - log.check_present(("scrapy.core.downloader.handlers.http11", - "DEBUG", - "Download stopped for <GET http://localhost:{}/numbers> from signal handler" - " StopDownloadCrawlerRun.bytes_received".format(self.run.portno))) - self._assert_visited_urls() - self._assert_scheduled_requests(urls_to_visit=9) - self._assert_downloaded_responses() - self._assert_signals_caught() - self._assert_bytes_received() + def test_close_spiders_downloader(self): + with warnings.catch_warnings(record=True) as warning_list: + e = ExecutionEngine(get_crawler(TestSpider), lambda _: None) + yield e.open_spider(TestSpider(), []) + self.assertEqual(len(e.open_spiders), 1) + yield e.close() + self.assertEqual(len(e.open_spiders), 0) + self.assertEqual(warning_list[0].category, ScrapyDeprecationWarning) + self.assertEqual( + str(warning_list[0].message), + "ExecutionEngine.open_spiders is deprecated, please use ExecutionEngine.spider instead", + ) - def _assert_bytes_received(self): - self.assertEqual(9, len(self.run.bytes)) - for request, data in self.run.bytes.items(): - joined_data = b"".join(data) - self.assertTrue(len(data) == 1) # signal was fired only once - if self.run.getpath(request.url) == "/numbers": - # Received bytes are not the complete response. The exact amount depends - # on the buffer size, which can vary, so we only check that the amount - # of received bytes is strictly less than the full response. - numbers = [str(x).encode("utf8") for x in range(2**18)] - self.assertTrue(len(joined_data) < len(b"".join(numbers))) + @defer.inlineCallbacks + def test_close_engine_spiders_downloader(self): + with warnings.catch_warnings(record=True) as warning_list: + e = ExecutionEngine(get_crawler(TestSpider), lambda _: None) + yield e.open_spider(TestSpider(), []) + e.start() + self.assertTrue(e.running) + yield e.close() + self.assertFalse(e.running) + self.assertEqual(len(e.open_spiders), 0) + self.assertEqual(warning_list[0].category, ScrapyDeprecationWarning) + self.assertEqual( + str(warning_list[0].message), + "ExecutionEngine.open_spiders is deprecated, please use ExecutionEngine.spider instead", + ) + + @defer.inlineCallbacks + def test_crawl_deprecated_spider_arg(self): + with warnings.catch_warnings(record=True) as warning_list: + e = ExecutionEngine(get_crawler(TestSpider), lambda _: None) + spider = TestSpider() + yield e.open_spider(spider, []) + e.start() + e.crawl(Request("data:,"), spider) + yield e.close() + self.assertEqual(warning_list[0].category, ScrapyDeprecationWarning) + self.assertEqual( + str(warning_list[0].message), + "Passing a 'spider' argument to ExecutionEngine.crawl is deprecated", + ) + + @defer.inlineCallbacks + def test_download_deprecated_spider_arg(self): + with warnings.catch_warnings(record=True) as warning_list: + e = ExecutionEngine(get_crawler(TestSpider), lambda _: None) + spider = TestSpider() + yield e.open_spider(spider, []) + e.start() + e.download(Request("data:,"), spider) + yield e.close() + self.assertEqual(warning_list[0].category, ScrapyDeprecationWarning) + self.assertEqual( + str(warning_list[0].message), + "Passing a 'spider' argument to ExecutionEngine.download is deprecated", + ) + + @defer.inlineCallbacks + def test_deprecated_schedule(self): + with warnings.catch_warnings(record=True) as warning_list: + e = ExecutionEngine(get_crawler(TestSpider), lambda _: None) + spider = TestSpider() + yield e.open_spider(spider, []) + e.start() + e.schedule(Request("data:,"), spider) + yield e.close() + self.assertEqual(warning_list[0].category, ScrapyDeprecationWarning) + self.assertEqual( + str(warning_list[0].message), + "ExecutionEngine.schedule is deprecated, please use " + "ExecutionEngine.crawl or ExecutionEngine.download instead", + ) + + @defer.inlineCallbacks + def test_deprecated_has_capacity(self): + with warnings.catch_warnings(record=True) as warning_list: + e = ExecutionEngine(get_crawler(TestSpider), lambda _: None) + self.assertTrue(e.has_capacity()) + spider = TestSpider() + yield e.open_spider(spider, []) + self.assertFalse(e.has_capacity()) + e.start() + yield e.close() + self.assertTrue(e.has_capacity()) + self.assertEqual(warning_list[0].category, ScrapyDeprecationWarning) + self.assertEqual(str(warning_list[0].message), "ExecutionEngine.has_capacity is deprecated") if __name__ == "__main__": diff --git a/tests/test_engine_stop_download_bytes.py b/tests/test_engine_stop_download_bytes.py new file mode 100644 index 000000000..0ba69e096 --- /dev/null +++ b/tests/test_engine_stop_download_bytes.py @@ -0,0 +1,60 @@ +from testfixtures import LogCapture +from twisted.internet import defer + +from scrapy.exceptions import StopDownload + +from tests.test_engine import ( + AttrsItemsSpider, + DataClassItemsSpider, + DictItemsSpider, + TestSpider, + CrawlerRun, + EngineTest, +) + + +class BytesReceivedCrawlerRun(CrawlerRun): + def bytes_received(self, data, request, spider): + super().bytes_received(data, request, spider) + raise StopDownload(fail=False) + + +class BytesReceivedEngineTest(EngineTest): + @defer.inlineCallbacks + def test_crawler(self): + for spider in (TestSpider, DictItemsSpider, AttrsItemsSpider, DataClassItemsSpider): + if spider is None: + continue + self.run = BytesReceivedCrawlerRun(spider) + with LogCapture() as log: + yield self.run.run() + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + f"Download stopped for <GET http://localhost:{self.run.portno}/redirected> " + "from signal handler BytesReceivedCrawlerRun.bytes_received")) + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + f"Download stopped for <GET http://localhost:{self.run.portno}/> " + "from signal handler BytesReceivedCrawlerRun.bytes_received")) + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + f"Download stopped for <GET http://localhost:{self.run.portno}/numbers> " + "from signal handler BytesReceivedCrawlerRun.bytes_received")) + self._assert_visited_urls() + self._assert_scheduled_requests(count=9) + self._assert_downloaded_responses(count=9) + self._assert_signals_caught() + self._assert_headers_received() + self._assert_bytes_received() + + def _assert_bytes_received(self): + self.assertEqual(9, len(self.run.bytes)) + for request, data in self.run.bytes.items(): + joined_data = b"".join(data) + self.assertTrue(len(data) == 1) # signal was fired only once + if self.run.getpath(request.url) == "/numbers": + # Received bytes are not the complete response. The exact amount depends + # on the buffer size, which can vary, so we only check that the amount + # of received bytes is strictly less than the full response. + numbers = [str(x).encode("utf8") for x in range(2**18)] + self.assertTrue(len(joined_data) < len(b"".join(numbers))) diff --git a/tests/test_engine_stop_download_headers.py b/tests/test_engine_stop_download_headers.py new file mode 100644 index 000000000..fad6643ad --- /dev/null +++ b/tests/test_engine_stop_download_headers.py @@ -0,0 +1,56 @@ +from testfixtures import LogCapture +from twisted.internet import defer + +from scrapy.exceptions import StopDownload + +from tests.test_engine import ( + AttrsItemsSpider, + DataClassItemsSpider, + DictItemsSpider, + TestSpider, + CrawlerRun, + EngineTest, +) + + +class HeadersReceivedCrawlerRun(CrawlerRun): + def headers_received(self, headers, body_length, request, spider): + super().headers_received(headers, body_length, request, spider) + raise StopDownload(fail=False) + + +class HeadersReceivedEngineTest(EngineTest): + @defer.inlineCallbacks + def test_crawler(self): + for spider in (TestSpider, DictItemsSpider, AttrsItemsSpider, DataClassItemsSpider): + if spider is None: + continue + self.run = HeadersReceivedCrawlerRun(spider) + with LogCapture() as log: + yield self.run.run() + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + f"Download stopped for <GET http://localhost:{self.run.portno}/redirected> from" + " signal handler HeadersReceivedCrawlerRun.headers_received")) + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + f"Download stopped for <GET http://localhost:{self.run.portno}/> from signal" + " handler HeadersReceivedCrawlerRun.headers_received")) + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + f"Download stopped for <GET http://localhost:{self.run.portno}/numbers> from" + " signal handler HeadersReceivedCrawlerRun.headers_received")) + self._assert_visited_urls() + self._assert_downloaded_responses(count=6) + self._assert_signals_caught() + self._assert_bytes_received() + self._assert_headers_received() + + def _assert_bytes_received(self): + self.assertEqual(0, len(self.run.bytes)) + + def _assert_visited_urls(self): + must_be_visited = ["/", "/redirect", "/redirected"] + urls_visited = {rp[0].url for rp in self.run.respplug} + urls_expected = {self.run.geturl(p) for p in must_be_visited} + assert urls_expected <= urls_visited, f"URLs not visited: {list(urls_expected - urls_visited)}" diff --git a/tests/test_exporters.py b/tests/test_exporters.py index b27380309..04bae31d3 100644 --- a/tests/test_exporters.py +++ b/tests/test_exporters.py @@ -6,11 +6,14 @@ import tempfile import unittest from io import BytesIO from datetime import datetime +from warnings import catch_warnings, filterwarnings import lxml.etree +from itemadapter import ItemAdapter from scrapy.item import Item, Field from scrapy.utils.python import to_unicode +from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.exporters import ( BaseItemExporter, PprintItemExporter, PickleItemExporter, CsvItemExporter, XmlItemExporter, JsonLinesItemExporter, JsonItemExporter, @@ -23,10 +26,37 @@ class TestItem(Item): age = Field() +def custom_serializer(value): + return str(int(value) + 2) + + +class CustomFieldItem(Item): + name = Field() + age = Field(serializer=custom_serializer) + + +try: + from dataclasses import make_dataclass, field +except ImportError: + TestDataClass = None + CustomFieldDataclass = None +else: + TestDataClass = make_dataclass("TestDataClass", [("name", str), ("age", int)]) + CustomFieldDataclass = make_dataclass( + "CustomFieldDataclass", + [("name", str), ("age", int, field(metadata={"serializer": custom_serializer}))] + ) + + class BaseItemExporterTest(unittest.TestCase): + item_class = TestItem + custom_field_item_class = CustomFieldItem + def setUp(self): - self.i = TestItem(name=u'John\xa3', age=u'22') + if self.item_class is None: + raise unittest.SkipTest("item class is None") + self.i = self.item_class(name='John\xa3', age='22') self.output = BytesIO() self.ie = self._get_exporter() @@ -39,7 +69,7 @@ class BaseItemExporterTest(unittest.TestCase): def _assert_expected_item(self, exported_dict): for k, v in exported_dict.items(): exported_dict[k] = to_unicode(v) - self.assertEqual(self.i, exported_dict) + self.assertEqual(self.i, self.item_class(**exported_dict)) def _get_nonstring_types_item(self): return { @@ -63,37 +93,36 @@ class BaseItemExporterTest(unittest.TestCase): self.assertItemExportWorks(self.i) def test_export_dict_item(self): - self.assertItemExportWorks(dict(self.i)) + self.assertItemExportWorks(ItemAdapter(self.i).asdict()) def test_serialize_field(self): - res = self.ie.serialize_field(self.i.fields['name'], 'name', self.i['name']) - self.assertEqual(res, u'John\xa3') + a = ItemAdapter(self.i) + res = self.ie.serialize_field(a.get_field_meta('name'), 'name', a['name']) + self.assertEqual(res, 'John\xa3') - res = self.ie.serialize_field(self.i.fields['age'], 'age', self.i['age']) - self.assertEqual(res, u'22') + res = self.ie.serialize_field(a.get_field_meta('age'), 'age', a['age']) + self.assertEqual(res, '22') def test_fields_to_export(self): ie = self._get_exporter(fields_to_export=['name']) - self.assertEqual(list(ie._get_serialized_fields(self.i)), [('name', u'John\xa3')]) + self.assertEqual(list(ie._get_serialized_fields(self.i)), [('name', 'John\xa3')]) ie = self._get_exporter(fields_to_export=['name'], encoding='latin-1') _, name = list(ie._get_serialized_fields(self.i))[0] assert isinstance(name, str) - self.assertEqual(name, u'John\xa3') + self.assertEqual(name, 'John\xa3') def test_field_custom_serializer(self): - def custom_serializer(value): - return str(int(value) + 2) - - class CustomFieldItem(Item): - name = Field() - age = Field(serializer=custom_serializer) - - i = CustomFieldItem(name=u'John\xa3', age=u'22') - + i = self.custom_field_item_class(name='John\xa3', age='22') + a = ItemAdapter(i) ie = self._get_exporter() - self.assertEqual(ie.serialize_field(i.fields['name'], 'name', i['name']), u'John\xa3') - self.assertEqual(ie.serialize_field(i.fields['age'], 'age', i['age']), '24') + self.assertEqual(ie.serialize_field(a.get_field_meta('name'), 'name', a['name']), 'John\xa3') + self.assertEqual(ie.serialize_field(a.get_field_meta('age'), 'age', a['age']), '24') + + +class BaseItemExporterDataclassTest(BaseItemExporterTest): + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass class PythonItemExporterTest(BaseItemExporterTest): @@ -105,50 +134,52 @@ class PythonItemExporterTest(BaseItemExporterTest): PythonItemExporter(invalid_option='something') def test_nested_item(self): - i1 = TestItem(name=u'Joseph', age='22') - i2 = dict(name=u'Maria', age=i1) - i3 = TestItem(name=u'Jesus', age=i2) + i1 = self.item_class(name='Joseph', age='22') + i2 = dict(name='Maria', age=i1) + i3 = self.item_class(name='Jesus', age=i2) ie = self._get_exporter() exported = ie.export_item(i3) self.assertEqual(type(exported), dict) self.assertEqual( exported, - {'age': {'age': {'age': '22', 'name': u'Joseph'}, 'name': u'Maria'}, 'name': 'Jesus'} + {'age': {'age': {'age': '22', 'name': 'Joseph'}, 'name': 'Maria'}, 'name': 'Jesus'} ) self.assertEqual(type(exported['age']), dict) self.assertEqual(type(exported['age']['age']), dict) def test_export_list(self): - i1 = TestItem(name=u'Joseph', age='22') - i2 = TestItem(name=u'Maria', age=[i1]) - i3 = TestItem(name=u'Jesus', age=[i2]) + i1 = self.item_class(name='Joseph', age='22') + i2 = self.item_class(name='Maria', age=[i1]) + i3 = self.item_class(name='Jesus', age=[i2]) ie = self._get_exporter() exported = ie.export_item(i3) self.assertEqual( exported, - {'age': [{'age': [{'age': '22', 'name': u'Joseph'}], 'name': u'Maria'}], 'name': 'Jesus'} + {'age': [{'age': [{'age': '22', 'name': 'Joseph'}], 'name': 'Maria'}], 'name': 'Jesus'} ) self.assertEqual(type(exported['age'][0]), dict) self.assertEqual(type(exported['age'][0]['age'][0]), dict) def test_export_item_dict_list(self): - i1 = TestItem(name=u'Joseph', age='22') - i2 = dict(name=u'Maria', age=[i1]) - i3 = TestItem(name=u'Jesus', age=[i2]) + i1 = self.item_class(name='Joseph', age='22') + i2 = dict(name='Maria', age=[i1]) + i3 = self.item_class(name='Jesus', age=[i2]) ie = self._get_exporter() exported = ie.export_item(i3) self.assertEqual( exported, - {'age': [{'age': [{'age': '22', 'name': u'Joseph'}], 'name': u'Maria'}], 'name': 'Jesus'} + {'age': [{'age': [{'age': '22', 'name': 'Joseph'}], 'name': 'Maria'}], 'name': 'Jesus'} ) self.assertEqual(type(exported['age'][0]), dict) self.assertEqual(type(exported['age'][0]['age'][0]), dict) def test_export_binary(self): - exporter = PythonItemExporter(binary=True) - value = TestItem(name=u'John\xa3', age=u'22') - expected = {b'name': b'John\xc2\xa3', b'age': b'22'} - self.assertEqual(expected, exporter.export_item(value)) + with catch_warnings(): + filterwarnings('ignore', category=ScrapyDeprecationWarning) + exporter = PythonItemExporter(binary=True) + value = self.item_class(name='John\xa3', age='22') + expected = {b'name': b'John\xc2\xa3', b'age': b'22'} + self.assertEqual(expected, exporter.export_item(value)) def test_nonstring_types_item(self): item = self._get_nonstring_types_item() @@ -157,6 +188,11 @@ class PythonItemExporterTest(BaseItemExporterTest): self.assertEqual(exported, item) +class PythonItemExporterDataclassTest(PythonItemExporterTest): + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass + + class PprintItemExporterTest(BaseItemExporterTest): def _get_exporter(self, **kwargs): @@ -166,6 +202,11 @@ class PprintItemExporterTest(BaseItemExporterTest): self._assert_expected_item(eval(self.output.getvalue())) +class PprintItemExporterDataclassTest(PprintItemExporterTest): + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass + + class PickleItemExporterTest(BaseItemExporterTest): def _get_exporter(self, **kwargs): @@ -175,8 +216,8 @@ class PickleItemExporterTest(BaseItemExporterTest): self._assert_expected_item(pickle.loads(self.output.getvalue())) def test_export_multiple_items(self): - i1 = TestItem(name='hello', age='world') - i2 = TestItem(name='bye', age='world') + i1 = self.item_class(name='hello', age='world') + i2 = self.item_class(name='bye', age='world') f = BytesIO() ie = PickleItemExporter(f) ie.start_exporting() @@ -184,8 +225,8 @@ class PickleItemExporterTest(BaseItemExporterTest): ie.export_item(i2) ie.finish_exporting() f.seek(0) - self.assertEqual(pickle.load(f), i1) - self.assertEqual(pickle.load(f), i2) + self.assertEqual(self.item_class(**pickle.load(f)), i1) + self.assertEqual(self.item_class(**pickle.load(f)), i2) def test_nonstring_types_item(self): item = self._get_nonstring_types_item() @@ -197,6 +238,11 @@ class PickleItemExporterTest(BaseItemExporterTest): self.assertEqual(pickle.loads(fp.getvalue()), item) +class PickleItemExporterDataclassTest(PickleItemExporterTest): + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass + + class MarshalItemExporterTest(BaseItemExporterTest): def _get_exporter(self, **kwargs): @@ -219,6 +265,11 @@ class MarshalItemExporterTest(BaseItemExporterTest): self.assertEqual(marshal.load(fp), item) +class MarshalItemExporterDataclassTest(MarshalItemExporterTest): + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass + + class CsvItemExporterTest(BaseItemExporterTest): def _get_exporter(self, **kwargs): return CsvItemExporter(self.output, **kwargs) @@ -232,7 +283,7 @@ class CsvItemExporterTest(BaseItemExporterTest): return self.assertEqual(split_csv(first), split_csv(second), msg=msg) def _check_output(self): - self.assertCsvEqual(to_unicode(self.output.getvalue()), u'age,name\r\n22,John\xa3\r\n') + self.assertCsvEqual(to_unicode(self.output.getvalue()), 'age,name\r\n22,John\xa3\r\n') def assertExportResult(self, item, expected, **kwargs): fp = BytesIO() @@ -245,18 +296,18 @@ class CsvItemExporterTest(BaseItemExporterTest): def test_header_export_all(self): self.assertExportResult( item=self.i, - fields_to_export=self.i.fields.keys(), + fields_to_export=ItemAdapter(self.i).field_names(), expected=b'age,name\r\n22,John\xc2\xa3\r\n', ) def test_header_export_all_dict(self): self.assertExportResult( - item=dict(self.i), + item=ItemAdapter(self.i).asdict(), expected=b'age,name\r\n22,John\xc2\xa3\r\n', ) def test_header_export_single_field(self): - for item in [self.i, dict(self.i)]: + for item in [self.i, ItemAdapter(self.i).asdict()]: self.assertExportResult( item=item, fields_to_export=['age'], @@ -264,7 +315,7 @@ class CsvItemExporterTest(BaseItemExporterTest): ) def test_header_export_two_items(self): - for item in [self.i, dict(self.i)]: + for item in [self.i, ItemAdapter(self.i).asdict()]: output = BytesIO() ie = CsvItemExporter(output) ie.start_exporting() @@ -275,7 +326,7 @@ class CsvItemExporterTest(BaseItemExporterTest): b'age,name\r\n22,John\xc2\xa3\r\n22,John\xc2\xa3\r\n') def test_header_no_header_line(self): - for item in [self.i, dict(self.i)]: + for item in [self.i, ItemAdapter(self.i).asdict()]: self.assertExportResult( item=item, include_headers_line=False, @@ -308,6 +359,28 @@ class CsvItemExporterTest(BaseItemExporterTest): expected='22,False,3.14,2015-01-01 01:01:01\r\n' ) + def test_errors_default(self): + with self.assertRaises(UnicodeEncodeError): + self.assertExportResult( + item=dict(text=u'W\u0275\u200Brd'), + expected=None, + encoding='windows-1251', + ) + + def test_errors_xmlcharrefreplace(self): + self.assertExportResult( + item=dict(text=u'W\u0275\u200Brd'), + include_headers_line=False, + expected='Wɵ​rd\r\n', + encoding='windows-1251', + errors='xmlcharrefreplace', + ) + + +class CsvItemExporterDataclassTest(CsvItemExporterTest): + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass + class XmlItemExporterTest(BaseItemExporterTest): @@ -318,8 +391,7 @@ class XmlItemExporterTest(BaseItemExporterTest): def xmltuple(elem): children = list(elem.iterchildren()) if children: - return [(child.tag, sorted(xmltuple(child))) - for child in children] + return [(child.tag, sorted(xmltuple(child))) for child in children] else: return [(elem.tag, [(elem.text, ())])] @@ -345,17 +417,21 @@ class XmlItemExporterTest(BaseItemExporterTest): def test_multivalued_fields(self): self.assertExportResult( - TestItem(name=[u'John\xa3', u'Doe']), - ( - b'<?xml version="1.0" encoding="utf-8"?>\n' - b'<items><item><name><value>John\xc2\xa3</value><value>Doe</value></name></item></items>' - ) + self.item_class(name=['John\xa3', 'Doe'], age=[1, 2, 3]), + b"""<?xml version="1.0" encoding="utf-8"?>\n + <items> + <item> + <name><value>John\xc2\xa3</value><value>Doe</value></name> + <age><value>1</value><value>2</value><value>3</value></age> + </item> + </items> + """ ) def test_nested_item(self): - i1 = TestItem(name=u'foo\xa3hoo', age='22') - i2 = dict(name=u'bar', age=i1) - i3 = TestItem(name=u'buz', age=i2) + i1 = dict(name='foo\xa3hoo', age='22') + i2 = dict(name='bar', age=i1) + i3 = self.item_class(name='buz', age=i2) self.assertExportResult( i3, @@ -376,9 +452,9 @@ class XmlItemExporterTest(BaseItemExporterTest): ) def test_nested_list_item(self): - i1 = TestItem(name=u'foo') - i2 = dict(name=u'bar', v2={"egg": ["spam"]}) - i3 = TestItem(name=u'buz', age=[i1, i2]) + i1 = dict(name='foo') + i2 = dict(name='bar', v2={"egg": ["spam"]}) + i3 = self.item_class(name='buz', age=[i1, i2]) self.assertExportResult( i3, @@ -412,21 +488,27 @@ class XmlItemExporterTest(BaseItemExporterTest): ) +class XmlItemExporterDataclassTest(XmlItemExporterTest): + + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass + + class JsonLinesItemExporterTest(BaseItemExporterTest): - _expected_nested = {'name': u'Jesus', 'age': {'name': 'Maria', 'age': {'name': 'Joseph', 'age': '22'}}} + _expected_nested = {'name': 'Jesus', 'age': {'name': 'Maria', 'age': {'name': 'Joseph', 'age': '22'}}} def _get_exporter(self, **kwargs): return JsonLinesItemExporter(self.output, **kwargs) def _check_output(self): exported = json.loads(to_unicode(self.output.getvalue().strip())) - self.assertEqual(exported, dict(self.i)) + self.assertEqual(exported, ItemAdapter(self.i).asdict()) def test_nested_item(self): - i1 = TestItem(name=u'Joseph', age='22') - i2 = dict(name=u'Maria', age=i1) - i3 = TestItem(name=u'Jesus', age=i2) + i1 = self.item_class(name='Joseph', age='22') + i2 = dict(name='Maria', age=i1) + i3 = self.item_class(name='Jesus', age=i2) self.ie.start_exporting() self.ie.export_item(i3) self.ie.finish_exporting() @@ -449,6 +531,12 @@ class JsonLinesItemExporterTest(BaseItemExporterTest): self.assertEqual(exported, item) +class JsonLinesItemExporterDataclassTest(JsonLinesItemExporterTest): + + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass + + class JsonItemExporterTest(JsonLinesItemExporterTest): _expected_nested = [JsonLinesItemExporterTest._expected_nested] @@ -458,7 +546,7 @@ class JsonItemExporterTest(JsonLinesItemExporterTest): def _check_output(self): exported = json.loads(to_unicode(self.output.getvalue().strip())) - self.assertEqual(exported, [dict(self.i)]) + self.assertEqual(exported, [ItemAdapter(self.i).asdict()]) def assertTwoItemsExported(self, item): self.ie.start_exporting() @@ -466,34 +554,34 @@ class JsonItemExporterTest(JsonLinesItemExporterTest): self.ie.export_item(item) self.ie.finish_exporting() exported = json.loads(to_unicode(self.output.getvalue())) - self.assertEqual(exported, [dict(item), dict(item)]) + self.assertEqual(exported, [ItemAdapter(item).asdict(), ItemAdapter(item).asdict()]) def test_two_items(self): self.assertTwoItemsExported(self.i) def test_two_dict_items(self): - self.assertTwoItemsExported(dict(self.i)) + self.assertTwoItemsExported(ItemAdapter(self.i).asdict()) def test_nested_item(self): - i1 = TestItem(name=u'Joseph\xa3', age='22') - i2 = TestItem(name=u'Maria', age=i1) - i3 = TestItem(name=u'Jesus', age=i2) + i1 = self.item_class(name='Joseph\xa3', age='22') + i2 = self.item_class(name='Maria', age=i1) + i3 = self.item_class(name='Jesus', age=i2) self.ie.start_exporting() self.ie.export_item(i3) self.ie.finish_exporting() exported = json.loads(to_unicode(self.output.getvalue())) - expected = {'name': u'Jesus', 'age': {'name': 'Maria', 'age': dict(i1)}} + expected = {'name': 'Jesus', 'age': {'name': 'Maria', 'age': ItemAdapter(i1).asdict()}} self.assertEqual(exported, [expected]) def test_nested_dict_item(self): - i1 = dict(name=u'Joseph\xa3', age='22') - i2 = TestItem(name=u'Maria', age=i1) - i3 = dict(name=u'Jesus', age=i2) + i1 = dict(name='Joseph\xa3', age='22') + i2 = self.item_class(name='Maria', age=i1) + i3 = dict(name='Jesus', age=i2) self.ie.start_exporting() self.ie.export_item(i3) self.ie.finish_exporting() exported = json.loads(to_unicode(self.output.getvalue())) - expected = {'name': u'Jesus', 'age': {'name': 'Maria', 'age': i1}} + expected = {'name': 'Jesus', 'age': {'name': 'Maria', 'age': i1}} self.assertEqual(exported, [expected]) def test_nonstring_types_item(self): @@ -506,7 +594,19 @@ class JsonItemExporterTest(JsonLinesItemExporterTest): self.assertEqual(exported, [item]) -class CustomItemExporterTest(unittest.TestCase): +class JsonItemExporterDataclassTest(JsonItemExporterTest): + + item_class = TestDataClass + custom_field_item_class = CustomFieldDataclass + + +class CustomExporterItemTest(unittest.TestCase): + + item_class = TestItem + + def setUp(self): + if self.item_class is None: + raise unittest.SkipTest("item class is None") def test_exporter_custom_serializer(self): class CustomItemExporter(BaseItemExporter): @@ -514,18 +614,24 @@ class CustomItemExporterTest(unittest.TestCase): if name == 'age': return str(int(value) + 1) else: - return super(CustomItemExporter, self).serialize_field(field, name, value) + return super().serialize_field(field, name, value) - i = TestItem(name=u'John', age='22') + i = self.item_class(name='John', age='22') + a = ItemAdapter(i) ie = CustomItemExporter() - self.assertEqual(ie.serialize_field(i.fields['name'], 'name', i['name']), 'John') - self.assertEqual(ie.serialize_field(i.fields['age'], 'age', i['age']), '23') + self.assertEqual(ie.serialize_field(a.get_field_meta('name'), 'name', a['name']), 'John') + self.assertEqual(ie.serialize_field(a.get_field_meta('age'), 'age', a['age']), '23') - i2 = {'name': u'John', 'age': '22'} + i2 = {'name': 'John', 'age': '22'} self.assertEqual(ie.serialize_field({}, 'name', i2['name']), 'John') self.assertEqual(ie.serialize_field({}, 'age', i2['age']), '23') +class CustomExporterDataclassTest(CustomExporterItemTest): + + item_class = TestDataClass + + if __name__ == '__main__': unittest.main() diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 8eeb29b6d..da0b2c786 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -6,29 +6,63 @@ import shutil import string import tempfile import warnings +from abc import ABC, abstractmethod +from collections import defaultdict +from contextlib import ExitStack from io import BytesIO +from logging import getLogger from pathlib import Path from string import ascii_letters, digits from unittest import mock -from urllib.parse import urljoin, urlparse, quote +from urllib.parse import urljoin, quote from urllib.request import pathname2url import lxml.etree +from testfixtures import LogCapture from twisted.internet import defer from twisted.trial import unittest -from w3lib.url import path_to_file_uri +from w3lib.url import file_uri_to_path, path_to_file_uri +from zope.interface import implementer from zope.interface.verify import verifyObject import scrapy from scrapy.crawler import CrawlerRunner +from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning from scrapy.exporters import CsvItemExporter -from scrapy.extensions.feedexport import (BlockingFeedStorage, FileFeedStorage, FTPFeedStorage, - IFeedStorage, S3FeedStorage, StdoutFeedStorage) +from scrapy.extensions.feedexport import ( + BlockingFeedStorage, + FeedExporter, + FileFeedStorage, + FTPFeedStorage, + GCSFeedStorage, + IFeedStorage, + S3FeedStorage, + StdoutFeedStorage, +) from scrapy.settings import Settings from scrapy.utils.python import to_unicode -from scrapy.utils.test import assert_aws_environ, get_crawler, get_s3_content_and_delete +from scrapy.utils.test import ( + get_crawler, + mock_google_cloud_storage, + skip_if_no_boto, +) -from tests.mockserver import MockServer +from tests.mockserver import MockFTPServer, MockServer +from tests.spiders import ItemSpider + + +def path_to_url(path): + return urljoin('file:', pathname2url(str(path))) + + +def printf_escape(string): + return string.replace('%', '%%') + + +def build_url(path): + if path[0] != '/': + path = '/' + path + return urljoin('file:', path) class FileFeedStorageTest(unittest.TestCase): @@ -57,8 +91,28 @@ class FileFeedStorageTest(unittest.TestCase): st = FileFeedStorage(path) verifyObject(IFeedStorage, st) + def _store(self, feed_options=None): + path = os.path.abspath(self.mktemp()) + storage = FileFeedStorage(path, feed_options=feed_options) + spider = scrapy.Spider("default") + file = storage.open(spider) + file.write(b"content") + storage.store(file) + return path + + def test_append(self): + path = self._store() + return self._assert_stores(FileFeedStorage(path), path, b"contentcontent") + + def test_overwrite(self): + path = self._store({"overwrite": True}) + return self._assert_stores( + FileFeedStorage(path, feed_options={"overwrite": True}), + path + ) + @defer.inlineCallbacks - def _assert_stores(self, storage, path): + def _assert_stores(self, storage, path, expected_content=b"content"): spider = scrapy.Spider("default") file = storage.open(spider) file.write(b"content") @@ -66,7 +120,7 @@ class FileFeedStorageTest(unittest.TestCase): self.assertTrue(os.path.exists(path)) try: with open(path, 'rb') as fp: - self.assertEqual(fp.read(), b"content") + self.assertEqual(fp.read(), expected_content) finally: os.unlink(path) @@ -76,59 +130,85 @@ class FTPFeedStorageTest(unittest.TestCase): def get_test_spider(self, settings=None): class TestSpider(scrapy.Spider): name = 'test_spider' + crawler = get_crawler(settings_dict=settings) spider = TestSpider.from_crawler(crawler) return spider - def test_store(self): - uri = os.environ.get('FEEDTEST_FTP_URI') - path = os.environ.get('FEEDTEST_FTP_PATH') - if not (uri and path): - raise unittest.SkipTest("No FTP server available for testing") - st = FTPFeedStorage(uri) - verifyObject(IFeedStorage, st) - return self._assert_stores(st, path) + def _store(self, uri, content, feed_options=None, settings=None): + crawler = get_crawler(settings_dict=settings or {}) + storage = FTPFeedStorage.from_crawler( + crawler, + uri, + feed_options=feed_options, + ) + verifyObject(IFeedStorage, storage) + spider = self.get_test_spider() + file = storage.open(spider) + file.write(content) + return storage.store(file) - def test_store_active_mode(self): - uri = os.environ.get('FEEDTEST_FTP_URI') - path = os.environ.get('FEEDTEST_FTP_PATH') - if not (uri and path): - raise unittest.SkipTest("No FTP server available for testing") - use_active_mode = {'FEED_STORAGE_FTP_ACTIVE': True} - crawler = get_crawler(settings_dict=use_active_mode) - st = FTPFeedStorage.from_crawler(crawler, uri) - verifyObject(IFeedStorage, st) - return self._assert_stores(st, path) + def _assert_stored(self, path, content): + self.assertTrue(path.exists()) + try: + with path.open('rb') as fp: + self.assertEqual(fp.read(), content) + finally: + os.unlink(str(path)) + + @defer.inlineCallbacks + def test_append(self): + with MockFTPServer() as ftp_server: + filename = 'file' + url = ftp_server.url(filename) + feed_options = {'overwrite': False} + yield self._store(url, b"foo", feed_options=feed_options) + yield self._store(url, b"bar", feed_options=feed_options) + self._assert_stored(ftp_server.path / filename, b"foobar") + + @defer.inlineCallbacks + def test_overwrite(self): + with MockFTPServer() as ftp_server: + filename = 'file' + url = ftp_server.url(filename) + yield self._store(url, b"foo") + yield self._store(url, b"bar") + self._assert_stored(ftp_server.path / filename, b"bar") + + @defer.inlineCallbacks + def test_append_active_mode(self): + with MockFTPServer() as ftp_server: + settings = {'FEED_STORAGE_FTP_ACTIVE': True} + filename = 'file' + url = ftp_server.url(filename) + feed_options = {'overwrite': False} + yield self._store(url, b"foo", feed_options=feed_options, settings=settings) + yield self._store(url, b"bar", feed_options=feed_options, settings=settings) + self._assert_stored(ftp_server.path / filename, b"foobar") + + @defer.inlineCallbacks + def test_overwrite_active_mode(self): + with MockFTPServer() as ftp_server: + settings = {'FEED_STORAGE_FTP_ACTIVE': True} + filename = 'file' + url = ftp_server.url(filename) + yield self._store(url, b"foo", settings=settings) + yield self._store(url, b"bar", settings=settings) + self._assert_stored(ftp_server.path / filename, b"bar") def test_uri_auth_quote(self): # RFC3986: 3.2.1. User Information pw_quoted = quote(string.punctuation, safe='') - st = FTPFeedStorage('ftp://foo:%s@example.com/some_path' % pw_quoted) + st = FTPFeedStorage(f'ftp://foo:{pw_quoted}@example.com/some_path', {}) self.assertEqual(st.password, string.punctuation) - @defer.inlineCallbacks - def _assert_stores(self, storage, path): - spider = self.get_test_spider() - file = storage.open(spider) - file.write(b"content") - yield storage.store(file) - self.assertTrue(os.path.exists(path)) - try: - with open(path, 'rb') as fp: - self.assertEqual(fp.read(), b"content") - # again, to check s3 objects are overwritten - yield storage.store(BytesIO(b"new content")) - with open(path, 'rb') as fp: - self.assertEqual(fp.read(), b"new content") - finally: - os.unlink(path) - class BlockingFeedStorageTest(unittest.TestCase): def get_test_spider(self, settings=None): class TestSpider(scrapy.Spider): name = 'test_spider' + crawler = get_crawler(settings_dict=settings) spider = TestSpider.from_crawler(crawler) return spider @@ -161,21 +241,16 @@ class BlockingFeedStorageTest(unittest.TestCase): class S3FeedStorageTest(unittest.TestCase): - @mock.patch('scrapy.utils.project.get_project_settings', - new=mock.MagicMock(return_value={'AWS_ACCESS_KEY_ID': 'conf_key', - 'AWS_SECRET_ACCESS_KEY': 'conf_secret'}), - create=True) def test_parse_credentials(self): - try: - import boto # noqa: F401 - except ImportError: - raise unittest.SkipTest("S3FeedStorage requires boto") + skip_if_no_boto() aws_credentials = {'AWS_ACCESS_KEY_ID': 'settings_key', 'AWS_SECRET_ACCESS_KEY': 'settings_secret'} crawler = get_crawler(settings_dict=aws_credentials) # Instantiate with crawler - storage = S3FeedStorage.from_crawler(crawler, - 's3://mybucket/export.csv') + storage = S3FeedStorage.from_crawler( + crawler, + 's3://mybucket/export.csv', + ) self.assertEqual(storage.access_key, 'settings_key') self.assertEqual(storage.secret_key, 'settings_secret') # Instantiate directly @@ -190,30 +265,45 @@ class S3FeedStorageTest(unittest.TestCase): aws_credentials['AWS_SECRET_ACCESS_KEY']) self.assertEqual(storage.access_key, 'uri_key') self.assertEqual(storage.secret_key, 'uri_secret') - # Backward compatibility for initialising without settings - with warnings.catch_warnings(record=True) as w: - storage = S3FeedStorage('s3://mybucket/export.csv') - self.assertEqual(storage.access_key, 'conf_key') - self.assertEqual(storage.secret_key, 'conf_secret') - self.assertTrue('without AWS keys' in str(w[-1].message)) @defer.inlineCallbacks def test_store(self): - assert_aws_environ() - uri = os.environ.get('S3_TEST_FILE_URI') - if not uri: - raise unittest.SkipTest("No S3 URI available for testing") - access_key = os.environ.get('AWS_ACCESS_KEY_ID') - secret_key = os.environ.get('AWS_SECRET_ACCESS_KEY') - storage = S3FeedStorage(uri, access_key, secret_key) + skip_if_no_boto() + + settings = { + 'AWS_ACCESS_KEY_ID': 'access_key', + 'AWS_SECRET_ACCESS_KEY': 'secret_key', + } + crawler = get_crawler(settings_dict=settings) + bucket = 'mybucket' + key = 'export.csv' + storage = S3FeedStorage.from_crawler(crawler, f's3://{bucket}/{key}') verifyObject(IFeedStorage, storage) - file = storage.open(scrapy.Spider("default")) - expected_content = b"content: \xe2\x98\x83" - file.write(expected_content) - yield storage.store(file) - u = urlparse(uri) - content = get_s3_content_and_delete(u.hostname, u.path[1:]) - self.assertEqual(content, expected_content) + + file = mock.MagicMock() + from botocore.stub import Stubber + with Stubber(storage.s3_client) as stub: + stub.add_response( + 'put_object', + expected_params={ + 'Body': file, + 'Bucket': bucket, + 'Key': key, + }, + service_response={}, + ) + + yield storage.store(file) + + stub.assert_no_pending_responses() + self.assertEqual( + file.method_calls, + [ + mock.call.seek(0), + # The call to read does not happen with Stubber + mock.call.close(), + ] + ) def test_init_without_acl(self): storage = S3FeedStorage( @@ -236,6 +326,17 @@ class S3FeedStorageTest(unittest.TestCase): self.assertEqual(storage.secret_key, 'secret_key') self.assertEqual(storage.acl, 'custom-acl') + def test_init_with_endpoint_url(self): + storage = S3FeedStorage( + 's3://mybucket/export.csv', + 'access_key', + 'secret_key', + endpoint_url='https://example.com' + ) + self.assertEqual(storage.access_key, 'access_key') + self.assertEqual(storage.secret_key, 'secret_key') + self.assertEqual(storage.endpoint_url, 'https://example.com') + def test_from_crawler_without_acl(self): settings = { 'AWS_ACCESS_KEY_ID': 'access_key', @@ -244,12 +345,26 @@ class S3FeedStorageTest(unittest.TestCase): crawler = get_crawler(settings_dict=settings) storage = S3FeedStorage.from_crawler( crawler, - 's3://mybucket/export.csv' + 's3://mybucket/export.csv', ) self.assertEqual(storage.access_key, 'access_key') self.assertEqual(storage.secret_key, 'secret_key') self.assertEqual(storage.acl, None) + def test_without_endpoint_url(self): + settings = { + 'AWS_ACCESS_KEY_ID': 'access_key', + 'AWS_SECRET_ACCESS_KEY': 'secret_key', + } + crawler = get_crawler(settings_dict=settings) + storage = S3FeedStorage.from_crawler( + crawler, + 's3://mybucket/export.csv', + ) + self.assertEqual(storage.access_key, 'access_key') + self.assertEqual(storage.secret_key, 'secret_key') + self.assertEqual(storage.endpoint_url, None) + def test_from_crawler_with_acl(self): settings = { 'AWS_ACCESS_KEY_ID': 'access_key', @@ -259,19 +374,30 @@ class S3FeedStorageTest(unittest.TestCase): crawler = get_crawler(settings_dict=settings) storage = S3FeedStorage.from_crawler( crawler, - 's3://mybucket/export.csv' + 's3://mybucket/export.csv', ) self.assertEqual(storage.access_key, 'access_key') self.assertEqual(storage.secret_key, 'secret_key') self.assertEqual(storage.acl, 'custom-acl') + def test_from_crawler_with_endpoint_url(self): + settings = { + 'AWS_ACCESS_KEY_ID': 'access_key', + 'AWS_SECRET_ACCESS_KEY': 'secret_key', + 'AWS_ENDPOINT_URL': 'https://example.com', + } + crawler = get_crawler(settings_dict=settings) + storage = S3FeedStorage.from_crawler( + crawler, + 's3://mybucket/export.csv' + ) + self.assertEqual(storage.access_key, 'access_key') + self.assertEqual(storage.secret_key, 'secret_key') + self.assertEqual(storage.endpoint_url, 'https://example.com') + @defer.inlineCallbacks def test_store_botocore_without_acl(self): - try: - import botocore # noqa: F401 - except ImportError: - raise unittest.SkipTest('botocore is required') - + skip_if_no_boto() storage = S3FeedStorage( 's3://mybucket/export.csv', 'access_key', @@ -287,11 +413,7 @@ class S3FeedStorageTest(unittest.TestCase): @defer.inlineCallbacks def test_store_botocore_with_acl(self): - try: - import botocore # noqa: F401 - except ImportError: - raise unittest.SkipTest('botocore is required') - + skip_if_no_boto() storage = S3FeedStorage( 's3://mybucket/export.csv', 'access_key', @@ -309,56 +431,83 @@ class S3FeedStorageTest(unittest.TestCase): 'custom-acl' ) - @defer.inlineCallbacks - def test_store_not_botocore_without_acl(self): - storage = S3FeedStorage( - 's3://mybucket/export.csv', - 'access_key', - 'secret_key', - ) - self.assertEqual(storage.access_key, 'access_key') - self.assertEqual(storage.secret_key, 'secret_key') - self.assertEqual(storage.acl, None) + def test_overwrite_default(self): + with LogCapture() as log: + S3FeedStorage( + 's3://mybucket/export.csv', + 'access_key', + 'secret_key', + 'custom-acl' + ) + self.assertNotIn('S3 does not support appending to files', str(log)) - storage.is_botocore = False - storage.connect_s3 = mock.MagicMock() - self.assertFalse(storage.is_botocore) + def test_overwrite_false(self): + with LogCapture() as log: + S3FeedStorage( + 's3://mybucket/export.csv', + 'access_key', + 'secret_key', + 'custom-acl', + feed_options={'overwrite': False}, + ) + self.assertIn('S3 does not support appending to files', str(log)) - yield storage.store(BytesIO(b'test file')) - conn = storage.connect_s3(*storage.connect_s3.call_args) - bucket = conn.get_bucket(*conn.get_bucket.call_args) - key = bucket.new_key(*bucket.new_key.call_args) - self.assertNotIn( - dict(policy='custom-acl'), - key.set_contents_from_file.call_args - ) +class GCSFeedStorageTest(unittest.TestCase): + + def test_parse_settings(self): + try: + from google.cloud.storage import Client # noqa + except ImportError: + raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") + + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': 'publicRead'} + crawler = get_crawler(settings_dict=settings) + storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') + assert storage.project_id == '123' + assert storage.acl == 'publicRead' + assert storage.bucket_name == 'mybucket' + assert storage.blob_name == 'export.csv' + + def test_parse_empty_acl(self): + try: + from google.cloud.storage import Client # noqa + except ImportError: + raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") + + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': ''} + crawler = get_crawler(settings_dict=settings) + storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') + assert storage.acl is None + + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': None} + crawler = get_crawler(settings_dict=settings) + storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') + assert storage.acl is None @defer.inlineCallbacks - def test_store_not_botocore_with_acl(self): - storage = S3FeedStorage( - 's3://mybucket/export.csv', - 'access_key', - 'secret_key', - 'custom-acl' - ) - self.assertEqual(storage.access_key, 'access_key') - self.assertEqual(storage.secret_key, 'secret_key') - self.assertEqual(storage.acl, 'custom-acl') + def test_store(self): + try: + from google.cloud.storage import Client # noqa + except ImportError: + raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") - storage.is_botocore = False - storage.connect_s3 = mock.MagicMock() - self.assertFalse(storage.is_botocore) + uri = 'gs://mybucket/export.csv' + project_id = 'myproject-123' + acl = 'publicRead' + (client_mock, bucket_mock, blob_mock) = mock_google_cloud_storage() + with mock.patch('google.cloud.storage.Client') as m: + m.return_value = client_mock - yield storage.store(BytesIO(b'test file')) + f = mock.Mock() + storage = GCSFeedStorage(uri, project_id, acl) + yield storage.store(f) - conn = storage.connect_s3(*storage.connect_s3.call_args) - bucket = conn.get_bucket(*conn.get_bucket.call_args) - key = bucket.new_key(*bucket.new_key.call_args) - self.assertIn( - dict(policy='custom-acl'), - key.set_contents_from_file.call_args - ) + f.seek.assert_called_once_with(0) + m.assert_called_once_with(project=project_id) + client_mock.get_bucket.assert_called_once_with('mybucket') + bucket_mock.blob.assert_called_once_with('export.csv') + blob_mock.upload_from_file.assert_called_once_with(f, predefined_acl=acl) class StdoutFeedStorageTest(unittest.TestCase): @@ -372,12 +521,22 @@ class StdoutFeedStorageTest(unittest.TestCase): yield storage.store(file) self.assertEqual(out.getvalue(), b"content") + def test_overwrite_default(self): + with LogCapture() as log: + StdoutFeedStorage('stdout:') + self.assertNotIn('Standard output (stdout) storage does not support overwriting', str(log)) + + def test_overwrite_true(self): + with LogCapture() as log: + StdoutFeedStorage('stdout:', feed_options={'overwrite': True}) + self.assertIn('Standard output (stdout) storage does not support overwriting', str(log)) + class FromCrawlerMixin: init_with_crawler = False @classmethod - def from_crawler(cls, crawler, *args, **kwargs): + def from_crawler(cls, crawler, *args, feed_options=None, **kwargs): cls.init_with_crawler = True return cls(*args, **kwargs) @@ -387,59 +546,82 @@ class FromCrawlerCsvItemExporter(CsvItemExporter, FromCrawlerMixin): class FromCrawlerFileFeedStorage(FileFeedStorage, FromCrawlerMixin): - pass + + @classmethod + def from_crawler(cls, crawler, *args, feed_options=None, **kwargs): + cls.init_with_crawler = True + return cls(*args, feed_options=feed_options, **kwargs) -class FeedExportTest(unittest.TestCase): +class DummyBlockingFeedStorage(BlockingFeedStorage): + + def __init__(self, uri, *args, feed_options=None): + self.path = file_uri_to_path(uri) + + def _store_in_thread(self, file): + dirname = os.path.dirname(self.path) + if dirname and not os.path.exists(dirname): + os.makedirs(dirname) + with open(self.path, 'ab') as output_file: + output_file.write(file.read()) + + file.close() + + +class FailingBlockingFeedStorage(DummyBlockingFeedStorage): + + def _store_in_thread(self, file): + raise OSError('Cannot store') + + +@implementer(IFeedStorage) +class LogOnStoreFileStorage: + """ + This storage logs inside `store` method. + It can be used to make sure `store` method is invoked. + """ + + def __init__(self, uri, feed_options=None): + self.path = file_uri_to_path(uri) + self.logger = getLogger() + + def open(self, spider): + return tempfile.NamedTemporaryFile(prefix='feed-') + + def store(self, file): + self.logger.info('Storage.store is called') + file.close() + + +class FeedExportTestBase(ABC, unittest.TestCase): + __test__ = False class MyItem(scrapy.Item): foo = scrapy.Field() egg = scrapy.Field() baz = scrapy.Field() + class MyItem2(scrapy.Item): + foo = scrapy.Field() + hello = scrapy.Field() + + def _random_temp_filename(self, inter_dir=''): + chars = [random.choice(ascii_letters + digits) for _ in range(15)] + filename = ''.join(chars) + return os.path.join(self.temp_dir, inter_dir, filename) + def setUp(self): self.temp_dir = tempfile.mkdtemp() def tearDown(self): shutil.rmtree(self.temp_dir, ignore_errors=True) - def _random_temp_filename(self): - chars = [random.choice(ascii_letters + digits) for _ in range(15)] - filename = ''.join(chars) - return os.path.join(self.temp_dir, filename) - - @defer.inlineCallbacks - def run_and_export(self, spider_cls, settings): - """ Run spider with specified settings; return exported data. """ - - FEEDS = settings.get('FEEDS') or {} - settings['FEEDS'] = { - urljoin('file:', pathname2url(str(file_path))): feed - for file_path, feed in FEEDS.items() - } - - content = {} - try: - with MockServer() as s: - runner = CrawlerRunner(Settings(settings)) - spider_cls.start_urls = [s.url('/')] - yield runner.crawl(spider_cls) - - for file_path, feed in FEEDS.items(): - with open(str(file_path), 'rb') as f: - content[feed['format']] = f.read() - - finally: - for file_path in FEEDS.keys(): - os.remove(str(file_path)) - - return content - @defer.inlineCallbacks def exported_data(self, items, settings): """ Return exported data which a spider yielding ``items`` would return. """ + class TestSpider(scrapy.Spider): name = 'testspider' @@ -455,6 +637,7 @@ class FeedExportTest(unittest.TestCase): """ Return exported data which a spider yielding no ``items`` would return. """ + class TestSpider(scrapy.Spider): name = 'testspider' @@ -464,6 +647,68 @@ class FeedExportTest(unittest.TestCase): data = yield self.run_and_export(TestSpider, settings) return data + @defer.inlineCallbacks + def assertExported(self, items, header, rows, settings=None, ordered=True): + yield self.assertExportedCsv(items, header, rows, settings, ordered) + yield self.assertExportedJsonLines(items, rows, settings) + yield self.assertExportedXml(items, rows, settings) + yield self.assertExportedPickle(items, rows, settings) + yield self.assertExportedMarshal(items, rows, settings) + yield self.assertExportedMultiple(items, rows, settings) + + @abstractmethod + def run_and_export(self, spider_cls, settings): + pass + + def _load_until_eof(self, data, load_func): + result = [] + with tempfile.TemporaryFile() as temp: + temp.write(data) + temp.seek(0) + while True: + try: + result.append(load_func(temp)) + except EOFError: + break + return result + + +class FeedExportTest(FeedExportTestBase): + __test__ = True + + @defer.inlineCallbacks + def run_and_export(self, spider_cls, settings): + """ Run spider with specified settings; return exported data. """ + + FEEDS = settings.get('FEEDS') or {} + settings['FEEDS'] = { + printf_escape(path_to_url(file_path)): feed_options + for file_path, feed_options in FEEDS.items() + } + + content = {} + try: + with MockServer() as s: + runner = CrawlerRunner(Settings(settings)) + spider_cls.start_urls = [s.url('/')] + yield runner.crawl(spider_cls) + + for file_path, feed_options in FEEDS.items(): + if not os.path.exists(str(file_path)): + continue + + with open(str(file_path), 'rb') as f: + content[feed_options['format']] = f.read() + + finally: + for file_path in FEEDS.keys(): + if not os.path.exists(str(file_path)): + continue + + os.remove(str(file_path)) + + return content + @defer.inlineCallbacks def assertExportedCsv(self, items, header, rows, settings=None, ordered=True): settings = settings or {} @@ -529,18 +774,6 @@ class FeedExportTest(unittest.TestCase): json_rows = json.loads(to_unicode(data['json'])) self.assertEqual(rows, json_rows) - def _load_until_eof(self, data, load_func): - result = [] - with tempfile.TemporaryFile() as temp: - temp.write(data) - temp.seek(0) - while True: - try: - result.append(load_func(temp)) - except EOFError: - break - return result - @defer.inlineCallbacks def assertExportedPickle(self, items, rows, settings=None): settings = settings or {} @@ -570,13 +803,67 @@ class FeedExportTest(unittest.TestCase): self.assertEqual(expected, result) @defer.inlineCallbacks - def assertExported(self, items, header, rows, settings=None, ordered=True): - yield self.assertExportedCsv(items, header, rows, settings, ordered) - yield self.assertExportedJsonLines(items, rows, settings) - yield self.assertExportedXml(items, rows, settings) - yield self.assertExportedPickle(items, rows, settings) - yield self.assertExportedMarshal(items, rows, settings) - yield self.assertExportedMultiple(items, rows, settings) + def test_stats_file_success(self): + settings = { + "FEEDS": { + printf_escape(path_to_url(self._random_temp_filename())): { + "format": "json", + } + }, + } + crawler = get_crawler(ItemSpider, settings) + with MockServer() as mockserver: + yield crawler.crawl(mockserver=mockserver) + self.assertIn("feedexport/success_count/FileFeedStorage", crawler.stats.get_stats()) + self.assertEqual(crawler.stats.get_value("feedexport/success_count/FileFeedStorage"), 1) + + @defer.inlineCallbacks + def test_stats_file_failed(self): + settings = { + "FEEDS": { + printf_escape(path_to_url(self._random_temp_filename())): { + "format": "json", + } + }, + } + crawler = get_crawler(ItemSpider, settings) + with ExitStack() as stack: + mockserver = stack.enter_context(MockServer()) + stack.enter_context( + mock.patch( + "scrapy.extensions.feedexport.FileFeedStorage.store", + side_effect=KeyError("foo")) + ) + yield crawler.crawl(mockserver=mockserver) + self.assertIn("feedexport/failed_count/FileFeedStorage", crawler.stats.get_stats()) + self.assertEqual(crawler.stats.get_value("feedexport/failed_count/FileFeedStorage"), 1) + + @defer.inlineCallbacks + def test_stats_multiple_file(self): + settings = { + 'AWS_ACCESS_KEY_ID': 'access_key', + 'AWS_SECRET_ACCESS_KEY': 'secret_key', + "FEEDS": { + printf_escape(path_to_url(self._random_temp_filename())): { + "format": "json", + }, + "s3://bucket/key/foo.csv": { + "format": "csv", + }, + "stdout:": { + "format": "xml", + } + }, + } + crawler = get_crawler(ItemSpider, settings) + with MockServer() as mockserver, mock.patch.object(S3FeedStorage, "store"): + yield crawler.crawl(mockserver=mockserver) + self.assertIn("feedexport/success_count/FileFeedStorage", crawler.stats.get_stats()) + self.assertIn("feedexport/success_count/S3FeedStorage", crawler.stats.get_stats()) + self.assertIn("feedexport/success_count/StdoutFeedStorage", crawler.stats.get_stats()) + self.assertEqual(crawler.stats.get_value("feedexport/success_count/FileFeedStorage"), 1) + self.assertEqual(crawler.stats.get_value("feedexport/success_count/S3FeedStorage"), 1) + self.assertEqual(crawler.stats.get_value("feedexport/success_count/StdoutFeedStorage"), 1) @defer.inlineCallbacks def test_export_items(self): @@ -601,7 +888,7 @@ class FeedExportTest(unittest.TestCase): }, } data = yield self.exported_no_data(settings) - self.assertEqual(data[fmt], b'') + self.assertEqual(b'', data[fmt]) @defer.inlineCallbacks def test_export_no_items_store_empty(self): @@ -621,18 +908,33 @@ class FeedExportTest(unittest.TestCase): 'FEED_EXPORT_INDENT': None, } data = yield self.exported_no_data(settings) - self.assertEqual(data[fmt], expctd) + self.assertEqual(expctd, data[fmt]) + + @defer.inlineCallbacks + def test_export_no_items_multiple_feeds(self): + """ Make sure that `storage.store` is called for every feed. """ + settings = { + 'FEEDS': { + self._random_temp_filename(): {'format': 'json'}, + self._random_temp_filename(): {'format': 'xml'}, + self._random_temp_filename(): {'format': 'csv'}, + }, + 'FEED_STORAGES': {'file': LogOnStoreFileStorage}, + 'FEED_STORE_EMPTY': False + } + + with LogCapture() as log: + yield self.exported_no_data(settings) + + print(log) + self.assertEqual(str(log).count('Storage.store is called'), 3) @defer.inlineCallbacks def test_export_multiple_item_classes(self): - class MyItem2(scrapy.Item): - foo = scrapy.Field() - hello = scrapy.Field() - items = [ self.MyItem({'foo': 'bar1', 'egg': 'spam1'}), - MyItem2({'hello': 'world2', 'foo': 'bar2'}), + self.MyItem2({'hello': 'world2', 'foo': 'bar2'}), self.MyItem({'foo': 'bar3', 'egg': 'spam3', 'baz': 'quux3'}), {'hello': 'world4', 'egg': 'spam4'}, ] @@ -667,6 +969,114 @@ class FeedExportTest(unittest.TestCase): yield self.assertExported(items, header, rows, settings=settings, ordered=True) + @defer.inlineCallbacks + def test_export_based_on_item_classes(self): + items = [ + self.MyItem({'foo': 'bar1', 'egg': 'spam1'}), + self.MyItem2({'hello': 'world2', 'foo': 'bar2'}), + {'hello': 'world3', 'egg': 'spam3'}, + ] + + formats = { + 'csv': b'baz,egg,foo\r\n,spam1,bar1\r\n', + 'json': b'[\n{"hello": "world2", "foo": "bar2"}\n]', + 'jsonlines': ( + b'{"foo": "bar1", "egg": "spam1"}\n' + b'{"hello": "world2", "foo": "bar2"}\n' + ), + 'xml': ( + b'<?xml version="1.0" encoding="utf-8"?>\n<items>\n<item>' + b'<foo>bar1</foo><egg>spam1</egg></item>\n<item><hello>' + b'world2</hello><foo>bar2</foo></item>\n<item><hello>world3' + b'</hello><egg>spam3</egg></item>\n</items>' + ), + } + + settings = { + 'FEEDS': { + self._random_temp_filename(): { + 'format': 'csv', + 'item_classes': [self.MyItem], + }, + self._random_temp_filename(): { + 'format': 'json', + 'item_classes': [self.MyItem2], + }, + self._random_temp_filename(): { + 'format': 'jsonlines', + 'item_classes': [self.MyItem, self.MyItem2], + }, + self._random_temp_filename(): { + 'format': 'xml', + }, + }, + } + + data = yield self.exported_data(items, settings) + for fmt, expected in formats.items(): + self.assertEqual(expected, data[fmt]) + + @defer.inlineCallbacks + def test_export_based_on_custom_filters(self): + items = [ + self.MyItem({'foo': 'bar1', 'egg': 'spam1'}), + self.MyItem2({'hello': 'world2', 'foo': 'bar2'}), + {'hello': 'world3', 'egg': 'spam3'}, + ] + + MyItem = self.MyItem + + class CustomFilter1: + def __init__(self, feed_options): + pass + + def accepts(self, item): + return isinstance(item, MyItem) + + class CustomFilter2(scrapy.extensions.feedexport.ItemFilter): + def accepts(self, item): + if 'foo' not in item.fields: + return False + return True + + class CustomFilter3(scrapy.extensions.feedexport.ItemFilter): + def accepts(self, item): + if isinstance(item, tuple(self.item_classes)) and item['foo'] == "bar1": + return True + return False + + formats = { + 'json': b'[\n{"foo": "bar1", "egg": "spam1"}\n]', + 'xml': ( + b'<?xml version="1.0" encoding="utf-8"?>\n<items>\n<item>' + b'<foo>bar1</foo><egg>spam1</egg></item>\n<item><hello>' + b'world2</hello><foo>bar2</foo></item>\n</items>' + ), + 'jsonlines': b'{"foo": "bar1", "egg": "spam1"}\n', + } + + settings = { + 'FEEDS': { + self._random_temp_filename(): { + 'format': 'json', + 'item_filter': CustomFilter1, + }, + self._random_temp_filename(): { + 'format': 'xml', + 'item_filter': CustomFilter2, + }, + self._random_temp_filename(): { + 'format': 'jsonlines', + 'item_classes': [self.MyItem, self.MyItem2], + 'item_filter': CustomFilter3, + }, + }, + } + + data = yield self.exported_data(items, settings) + for fmt, expected in formats.items(): + self.assertEqual(expected, data[fmt]) + @defer.inlineCallbacks def test_export_dicts(self): # When dicts are used, only keys from the first row are used as @@ -714,7 +1124,7 @@ class FeedExportTest(unittest.TestCase): @defer.inlineCallbacks def test_export_encoding(self): - items = [dict({'foo': u'Test\xd6'})] + items = [dict({'foo': 'Test\xd6'})] formats = { 'json': '[{"foo": "Test\\u00d6"}]'.encode('utf-8'), @@ -759,7 +1169,7 @@ class FeedExportTest(unittest.TestCase): @defer.inlineCallbacks def test_export_multiple_configs(self): - items = [dict({'foo': u'FOO', 'bar': u'BAR'})] + items = [dict({'foo': 'FOO', 'bar': 'BAR'})] formats = { 'json': '[\n{"bar": "BAR"}\n]'.encode('utf-8'), @@ -957,8 +1367,8 @@ class FeedExportTest(unittest.TestCase): @defer.inlineCallbacks def test_init_exporters_storages_with_crawler(self): settings = { - 'FEED_EXPORTERS': {'csv': 'tests.test_feedexport.FromCrawlerCsvItemExporter'}, - 'FEED_STORAGES': {'file': 'tests.test_feedexport.FromCrawlerFileFeedStorage'}, + 'FEED_EXPORTERS': {'csv': FromCrawlerCsvItemExporter}, + 'FEED_STORAGES': {'file': FromCrawlerFileFeedStorage}, 'FEEDS': { self._random_temp_filename(): {'format': 'csv'}, }, @@ -978,3 +1388,722 @@ class FeedExportTest(unittest.TestCase): } data = yield self.exported_no_data(settings) self.assertEqual(data['csv'], b'') + + @defer.inlineCallbacks + def test_multiple_feeds_success_logs_blocking_feed_storage(self): + settings = { + 'FEEDS': { + self._random_temp_filename(): {'format': 'json'}, + self._random_temp_filename(): {'format': 'xml'}, + self._random_temp_filename(): {'format': 'csv'}, + }, + 'FEED_STORAGES': {'file': DummyBlockingFeedStorage}, + } + items = [ + {'foo': 'bar1', 'baz': ''}, + {'foo': 'bar2', 'baz': 'quux'}, + ] + with LogCapture() as log: + yield self.exported_data(items, settings) + + print(log) + for fmt in ['json', 'xml', 'csv']: + self.assertIn(f'Stored {fmt} feed (2 items)', str(log)) + + @defer.inlineCallbacks + def test_multiple_feeds_failing_logs_blocking_feed_storage(self): + settings = { + 'FEEDS': { + self._random_temp_filename(): {'format': 'json'}, + self._random_temp_filename(): {'format': 'xml'}, + self._random_temp_filename(): {'format': 'csv'}, + }, + 'FEED_STORAGES': {'file': FailingBlockingFeedStorage}, + } + items = [ + {'foo': 'bar1', 'baz': ''}, + {'foo': 'bar2', 'baz': 'quux'}, + ] + with LogCapture() as log: + yield self.exported_data(items, settings) + + print(log) + for fmt in ['json', 'xml', 'csv']: + self.assertIn(f'Error storing {fmt} feed (2 items)', str(log)) + + @defer.inlineCallbacks + def test_extend_kwargs(self): + items = [{'foo': 'FOO', 'bar': 'BAR'}] + + expected_with_title_csv = 'foo,bar\r\nFOO,BAR\r\n'.encode('utf-8') + expected_without_title_csv = 'FOO,BAR\r\n'.encode('utf-8') + test_cases = [ + # with title + { + 'options': { + 'format': 'csv', + 'item_export_kwargs': {'include_headers_line': True}, + }, + 'expected': expected_with_title_csv, + }, + # without title + { + 'options': { + 'format': 'csv', + 'item_export_kwargs': {'include_headers_line': False}, + }, + 'expected': expected_without_title_csv, + }, + ] + + for row in test_cases: + feed_options = row['options'] + settings = { + 'FEEDS': { + self._random_temp_filename(): feed_options, + }, + 'FEED_EXPORT_INDENT': None, + } + + data = yield self.exported_data(items, settings) + self.assertEqual(row['expected'], data[feed_options['format']]) + + +class BatchDeliveriesTest(FeedExportTestBase): + __test__ = True + _file_mark = '_%(batch_time)s_#%(batch_id)02d_' + + @defer.inlineCallbacks + def run_and_export(self, spider_cls, settings): + """ Run spider with specified settings; return exported data. """ + + FEEDS = settings.get('FEEDS') or {} + settings['FEEDS'] = { + build_url(file_path): feed + for file_path, feed in FEEDS.items() + } + content = defaultdict(list) + try: + with MockServer() as s: + runner = CrawlerRunner(Settings(settings)) + spider_cls.start_urls = [s.url('/')] + yield runner.crawl(spider_cls) + + for path, feed in FEEDS.items(): + dir_name = os.path.dirname(path) + for file in sorted(os.listdir(dir_name)): + with open(os.path.join(dir_name, file), 'rb') as f: + data = f.read() + content[feed['format']].append(data) + finally: + self.tearDown() + defer.returnValue(content) + + @defer.inlineCallbacks + def assertExportedJsonLines(self, items, rows, settings=None): + settings = settings or {} + settings.update({ + 'FEEDS': { + os.path.join(self._random_temp_filename(), 'jl', self._file_mark): {'format': 'jl'}, + }, + }) + batch_size = settings.getint('FEED_EXPORT_BATCH_ITEM_COUNT') + rows = [{k: v for k, v in row.items() if v} for row in rows] + data = yield self.exported_data(items, settings) + for batch in data['jl']: + got_batch = [json.loads(to_unicode(batch_item)) for batch_item in batch.splitlines()] + expected_batch, rows = rows[:batch_size], rows[batch_size:] + self.assertEqual(expected_batch, got_batch) + + @defer.inlineCallbacks + def assertExportedCsv(self, items, header, rows, settings=None, ordered=True): + settings = settings or {} + settings.update({ + 'FEEDS': { + os.path.join(self._random_temp_filename(), 'csv', self._file_mark): {'format': 'csv'}, + }, + }) + batch_size = settings.getint('FEED_EXPORT_BATCH_ITEM_COUNT') + data = yield self.exported_data(items, settings) + for batch in data['csv']: + got_batch = csv.DictReader(to_unicode(batch).splitlines()) + self.assertEqual(list(header), got_batch.fieldnames) + expected_batch, rows = rows[:batch_size], rows[batch_size:] + self.assertEqual(expected_batch, list(got_batch)) + + @defer.inlineCallbacks + def assertExportedXml(self, items, rows, settings=None): + settings = settings or {} + settings.update({ + 'FEEDS': { + os.path.join(self._random_temp_filename(), 'xml', self._file_mark): {'format': 'xml'}, + }, + }) + batch_size = settings.getint('FEED_EXPORT_BATCH_ITEM_COUNT') + rows = [{k: v for k, v in row.items() if v} for row in rows] + data = yield self.exported_data(items, settings) + for batch in data['xml']: + root = lxml.etree.fromstring(batch) + got_batch = [{e.tag: e.text for e in it} for it in root.findall('item')] + expected_batch, rows = rows[:batch_size], rows[batch_size:] + self.assertEqual(expected_batch, got_batch) + + @defer.inlineCallbacks + def assertExportedMultiple(self, items, rows, settings=None): + settings = settings or {} + settings.update({ + 'FEEDS': { + os.path.join(self._random_temp_filename(), 'xml', self._file_mark): {'format': 'xml'}, + os.path.join(self._random_temp_filename(), 'json', self._file_mark): {'format': 'json'}, + }, + }) + batch_size = settings.getint('FEED_EXPORT_BATCH_ITEM_COUNT') + rows = [{k: v for k, v in row.items() if v} for row in rows] + data = yield self.exported_data(items, settings) + # XML + xml_rows = rows.copy() + for batch in data['xml']: + root = lxml.etree.fromstring(batch) + got_batch = [{e.tag: e.text for e in it} for it in root.findall('item')] + expected_batch, xml_rows = xml_rows[:batch_size], xml_rows[batch_size:] + self.assertEqual(expected_batch, got_batch) + # JSON + json_rows = rows.copy() + for batch in data['json']: + got_batch = json.loads(batch.decode('utf-8')) + expected_batch, json_rows = json_rows[:batch_size], json_rows[batch_size:] + self.assertEqual(expected_batch, got_batch) + + @defer.inlineCallbacks + def assertExportedPickle(self, items, rows, settings=None): + settings = settings or {} + settings.update({ + 'FEEDS': { + os.path.join(self._random_temp_filename(), 'pickle', self._file_mark): {'format': 'pickle'}, + }, + }) + batch_size = settings.getint('FEED_EXPORT_BATCH_ITEM_COUNT') + rows = [{k: v for k, v in row.items() if v} for row in rows] + data = yield self.exported_data(items, settings) + import pickle + for batch in data['pickle']: + got_batch = self._load_until_eof(batch, load_func=pickle.load) + expected_batch, rows = rows[:batch_size], rows[batch_size:] + self.assertEqual(expected_batch, got_batch) + + @defer.inlineCallbacks + def assertExportedMarshal(self, items, rows, settings=None): + settings = settings or {} + settings.update({ + 'FEEDS': { + os.path.join(self._random_temp_filename(), 'marshal', self._file_mark): {'format': 'marshal'}, + }, + }) + batch_size = settings.getint('FEED_EXPORT_BATCH_ITEM_COUNT') + rows = [{k: v for k, v in row.items() if v} for row in rows] + data = yield self.exported_data(items, settings) + import marshal + for batch in data['marshal']: + got_batch = self._load_until_eof(batch, load_func=marshal.load) + expected_batch, rows = rows[:batch_size], rows[batch_size:] + self.assertEqual(expected_batch, got_batch) + + @defer.inlineCallbacks + def test_export_items(self): + """ Test partial deliveries in all supported formats """ + items = [ + self.MyItem({'foo': 'bar1', 'egg': 'spam1'}), + self.MyItem({'foo': 'bar2', 'egg': 'spam2', 'baz': 'quux2'}), + self.MyItem({'foo': 'bar3', 'baz': 'quux3'}), + ] + rows = [ + {'egg': 'spam1', 'foo': 'bar1', 'baz': ''}, + {'egg': 'spam2', 'foo': 'bar2', 'baz': 'quux2'}, + {'foo': 'bar3', 'baz': 'quux3', 'egg': ''} + ] + settings = { + 'FEED_EXPORT_BATCH_ITEM_COUNT': 2 + } + header = self.MyItem.fields.keys() + yield self.assertExported(items, header, rows, settings=Settings(settings)) + + def test_wrong_path(self): + """ If path is without %(batch_time)s and %(batch_id) an exception must be raised """ + settings = { + 'FEEDS': { + self._random_temp_filename(): {'format': 'xml'}, + }, + 'FEED_EXPORT_BATCH_ITEM_COUNT': 1 + } + crawler = get_crawler(settings_dict=settings) + self.assertRaises(NotConfigured, FeedExporter, crawler) + + @defer.inlineCallbacks + def test_export_no_items_not_store_empty(self): + for fmt in ('json', 'jsonlines', 'xml', 'csv'): + settings = { + 'FEEDS': { + os.path.join(self._random_temp_filename(), fmt, self._file_mark): {'format': fmt}, + }, + 'FEED_EXPORT_BATCH_ITEM_COUNT': 1 + } + data = yield self.exported_no_data(settings) + data = dict(data) + self.assertEqual(b'', data[fmt][0]) + + @defer.inlineCallbacks + def test_export_no_items_store_empty(self): + formats = ( + ('json', b'[]'), + ('jsonlines', b''), + ('xml', b'<?xml version="1.0" encoding="utf-8"?>\n<items></items>'), + ('csv', b''), + ) + + for fmt, expctd in formats: + settings = { + 'FEEDS': { + os.path.join(self._random_temp_filename(), fmt, self._file_mark): {'format': fmt}, + }, + 'FEED_STORE_EMPTY': True, + 'FEED_EXPORT_INDENT': None, + 'FEED_EXPORT_BATCH_ITEM_COUNT': 1, + } + data = yield self.exported_no_data(settings) + data = dict(data) + self.assertEqual(expctd, data[fmt][0]) + + @defer.inlineCallbacks + def test_export_multiple_configs(self): + items = [dict({'foo': 'FOO', 'bar': 'BAR'}), dict({'foo': 'FOO1', 'bar': 'BAR1'})] + + formats = { + 'json': ['[\n{"bar": "BAR"}\n]'.encode('utf-8'), + '[\n{"bar": "BAR1"}\n]'.encode('utf-8')], + 'xml': [ + ( + '<?xml version="1.0" encoding="latin-1"?>\n' + '<items>\n <item>\n <foo>FOO</foo>\n </item>\n</items>' + ).encode('latin-1'), + ( + '<?xml version="1.0" encoding="latin-1"?>\n' + '<items>\n <item>\n <foo>FOO1</foo>\n </item>\n</items>' + ).encode('latin-1') + ], + 'csv': ['foo,bar\r\nFOO,BAR\r\n'.encode('utf-8'), + 'foo,bar\r\nFOO1,BAR1\r\n'.encode('utf-8')], + } + + settings = { + 'FEEDS': { + os.path.join(self._random_temp_filename(), 'json', self._file_mark): { + 'format': 'json', + 'indent': 0, + 'fields': ['bar'], + 'encoding': 'utf-8', + }, + os.path.join(self._random_temp_filename(), 'xml', self._file_mark): { + 'format': 'xml', + 'indent': 2, + 'fields': ['foo'], + 'encoding': 'latin-1', + }, + os.path.join(self._random_temp_filename(), 'csv', self._file_mark): { + 'format': 'csv', + 'indent': None, + 'fields': ['foo', 'bar'], + 'encoding': 'utf-8', + }, + }, + 'FEED_EXPORT_BATCH_ITEM_COUNT': 1, + } + data = yield self.exported_data(items, settings) + for fmt, expected in formats.items(): + for expected_batch, got_batch in zip(expected, data[fmt]): + self.assertEqual(expected_batch, got_batch) + + @defer.inlineCallbacks + def test_batch_item_count_feeds_setting(self): + items = [dict({'foo': 'FOO'}), dict({'foo': 'FOO1'})] + formats = { + 'json': ['[{"foo": "FOO"}]'.encode('utf-8'), + '[{"foo": "FOO1"}]'.encode('utf-8')], + } + settings = { + 'FEEDS': { + os.path.join(self._random_temp_filename(), 'json', self._file_mark): { + 'format': 'json', + 'indent': None, + 'encoding': 'utf-8', + 'batch_item_count': 1, + }, + }, + } + data = yield self.exported_data(items, settings) + for fmt, expected in formats.items(): + for expected_batch, got_batch in zip(expected, data[fmt]): + self.assertEqual(expected_batch, got_batch) + + @defer.inlineCallbacks + def test_batch_path_differ(self): + """ + Test that the name of all batch files differ from each other. + So %(batch_time)s replaced with the current date. + """ + items = [ + self.MyItem({'foo': 'bar1', 'egg': 'spam1'}), + self.MyItem({'foo': 'bar2', 'egg': 'spam2', 'baz': 'quux2'}), + self.MyItem({'foo': 'bar3', 'baz': 'quux3'}), + ] + settings = { + 'FEEDS': { + os.path.join(self._random_temp_filename(), '%(batch_time)s'): { + 'format': 'json', + }, + }, + 'FEED_EXPORT_BATCH_ITEM_COUNT': 1, + } + data = yield self.exported_data(items, settings) + self.assertEqual(len(items) + 1, len(data['json'])) + + @defer.inlineCallbacks + def test_stats_batch_file_success(self): + settings = { + "FEEDS": { + build_url(os.path.join(self._random_temp_filename(), "json", self._file_mark)): { + "format": "json", + } + }, + "FEED_EXPORT_BATCH_ITEM_COUNT": 1, + } + crawler = get_crawler(ItemSpider, settings) + with MockServer() as mockserver: + yield crawler.crawl(total=2, mockserver=mockserver) + self.assertIn("feedexport/success_count/FileFeedStorage", crawler.stats.get_stats()) + self.assertEqual(crawler.stats.get_value("feedexport/success_count/FileFeedStorage"), 12) + + @defer.inlineCallbacks + def test_s3_export(self): + skip_if_no_boto() + + bucket = 'mybucket' + items = [ + self.MyItem({'foo': 'bar1', 'egg': 'spam1'}), + self.MyItem({'foo': 'bar2', 'egg': 'spam2', 'baz': 'quux2'}), + self.MyItem({'foo': 'bar3', 'baz': 'quux3'}), + ] + + class CustomS3FeedStorage(S3FeedStorage): + + stubs = [] + + def open(self, *args, **kwargs): + from botocore.stub import ANY, Stubber + stub = Stubber(self.s3_client) + stub.activate() + CustomS3FeedStorage.stubs.append(stub) + stub.add_response( + 'put_object', + expected_params={ + 'Body': ANY, + 'Bucket': bucket, + 'Key': ANY, + }, + service_response={}, + ) + return super().open(*args, **kwargs) + + key = 'export.csv' + uri = f's3://{bucket}/{key}/%(batch_time)s.json' + batch_item_count = 1 + settings = { + 'AWS_ACCESS_KEY_ID': 'access_key', + 'AWS_SECRET_ACCESS_KEY': 'secret_key', + 'FEED_EXPORT_BATCH_ITEM_COUNT': batch_item_count, + 'FEED_STORAGES': { + 's3': CustomS3FeedStorage, + }, + 'FEEDS': { + uri: { + 'format': 'json', + }, + }, + } + crawler = get_crawler(settings_dict=settings) + storage = S3FeedStorage.from_crawler(crawler, uri) + verifyObject(IFeedStorage, storage) + + class TestSpider(scrapy.Spider): + name = 'testspider' + + def parse(self, response): + for item in items: + yield item + + with MockServer() as server: + runner = CrawlerRunner(Settings(settings)) + TestSpider.start_urls = [server.url('/')] + yield runner.crawl(TestSpider) + + self.assertEqual(len(CustomS3FeedStorage.stubs), len(items) + 1) + for stub in CustomS3FeedStorage.stubs[:-1]: + stub.assert_no_pending_responses() + + +class FeedExportInitTest(unittest.TestCase): + + def test_unsupported_storage(self): + settings = { + 'FEEDS': { + 'unsupported://uri': {}, + }, + } + crawler = get_crawler(settings_dict=settings) + with self.assertRaises(NotConfigured): + FeedExporter.from_crawler(crawler) + + def test_unsupported_format(self): + settings = { + 'FEEDS': { + 'file://path': { + 'format': 'unsupported_format', + }, + }, + } + crawler = get_crawler(settings_dict=settings) + with self.assertRaises(NotConfigured): + FeedExporter.from_crawler(crawler) + + +class StdoutFeedStorageWithoutFeedOptions(StdoutFeedStorage): + + def __init__(self, uri): + super().__init__(uri) + + +class StdoutFeedStoragePreFeedOptionsTest(unittest.TestCase): + """Make sure that any feed exporter created by users before the + introduction of the ``feed_options`` parameter continues to work as + expected, and simply issues a warning.""" + + def test_init(self): + settings_dict = { + 'FEED_URI': 'file:///tmp/foobar', + 'FEED_STORAGES': { + 'file': StdoutFeedStorageWithoutFeedOptions + }, + } + crawler = get_crawler(settings_dict=settings_dict) + feed_exporter = FeedExporter.from_crawler(crawler) + spider = scrapy.Spider("default") + with warnings.catch_warnings(record=True) as w: + feed_exporter.open_spider(spider) + messages = tuple(str(item.message) for item in w + if item.category is ScrapyDeprecationWarning) + self.assertEqual( + messages, + ( + ( + "StdoutFeedStorageWithoutFeedOptions does not support " + "the 'feed_options' keyword argument. Add a " + "'feed_options' parameter to its signature to remove " + "this warning. This parameter will become mandatory " + "in a future version of Scrapy." + ), + ) + ) + + +class FileFeedStorageWithoutFeedOptions(FileFeedStorage): + + def __init__(self, uri): + super().__init__(uri) + + +class FileFeedStoragePreFeedOptionsTest(unittest.TestCase): + """Make sure that any feed exporter created by users before the + introduction of the ``feed_options`` parameter continues to work as + expected, and simply issues a warning.""" + + maxDiff = None + + def test_init(self): + settings_dict = { + 'FEED_URI': 'file:///tmp/foobar', + 'FEED_STORAGES': { + 'file': FileFeedStorageWithoutFeedOptions + }, + } + crawler = get_crawler(settings_dict=settings_dict) + feed_exporter = FeedExporter.from_crawler(crawler) + spider = scrapy.Spider("default") + with warnings.catch_warnings(record=True) as w: + feed_exporter.open_spider(spider) + messages = tuple(str(item.message) for item in w + if item.category is ScrapyDeprecationWarning) + self.assertEqual( + messages, + ( + ( + "FileFeedStorageWithoutFeedOptions does not support " + "the 'feed_options' keyword argument. Add a " + "'feed_options' parameter to its signature to remove " + "this warning. This parameter will become mandatory " + "in a future version of Scrapy." + ), + ) + ) + + +class S3FeedStorageWithoutFeedOptions(S3FeedStorage): + + def __init__(self, uri, access_key, secret_key, acl, endpoint_url): + super().__init__(uri, access_key, secret_key, acl, endpoint_url) + + +class S3FeedStorageWithoutFeedOptionsWithFromCrawler(S3FeedStorage): + + @classmethod + def from_crawler(cls, crawler, uri): + return super().from_crawler(crawler, uri) + + +class S3FeedStoragePreFeedOptionsTest(unittest.TestCase): + """Make sure that any feed exporter created by users before the + introduction of the ``feed_options`` parameter continues to work as + expected, and simply issues a warning.""" + + maxDiff = None + + def test_init(self): + settings_dict = { + 'FEED_URI': 'file:///tmp/foobar', + 'FEED_STORAGES': { + 'file': S3FeedStorageWithoutFeedOptions + }, + } + crawler = get_crawler(settings_dict=settings_dict) + feed_exporter = FeedExporter.from_crawler(crawler) + spider = scrapy.Spider("default") + spider.crawler = crawler + with warnings.catch_warnings(record=True) as w: + feed_exporter.open_spider(spider) + messages = tuple(str(item.message) for item in w + if item.category is ScrapyDeprecationWarning) + self.assertEqual( + messages, + ( + ( + "S3FeedStorageWithoutFeedOptions does not support " + "the 'feed_options' keyword argument. Add a " + "'feed_options' parameter to its signature to remove " + "this warning. This parameter will become mandatory " + "in a future version of Scrapy." + ), + ) + ) + + def test_from_crawler(self): + settings_dict = { + 'FEED_URI': 'file:///tmp/foobar', + 'FEED_STORAGES': { + 'file': S3FeedStorageWithoutFeedOptionsWithFromCrawler + }, + } + crawler = get_crawler(settings_dict=settings_dict) + feed_exporter = FeedExporter.from_crawler(crawler) + spider = scrapy.Spider("default") + spider.crawler = crawler + with warnings.catch_warnings(record=True) as w: + feed_exporter.open_spider(spider) + messages = tuple(str(item.message) for item in w + if item.category is ScrapyDeprecationWarning) + self.assertEqual( + messages, + ( + ( + "S3FeedStorageWithoutFeedOptionsWithFromCrawler.from_crawler " + "does not support the 'feed_options' keyword argument. Add a " + "'feed_options' parameter to its signature to remove " + "this warning. This parameter will become mandatory " + "in a future version of Scrapy." + ), + ) + ) + + +class FTPFeedStorageWithoutFeedOptions(FTPFeedStorage): + + def __init__(self, uri, use_active_mode=False): + super().__init__(uri) + + +class FTPFeedStorageWithoutFeedOptionsWithFromCrawler(FTPFeedStorage): + + @classmethod + def from_crawler(cls, crawler, uri): + return super().from_crawler(crawler, uri) + + +class FTPFeedStoragePreFeedOptionsTest(unittest.TestCase): + """Make sure that any feed exporter created by users before the + introduction of the ``feed_options`` parameter continues to work as + expected, and simply issues a warning.""" + + maxDiff = None + + def test_init(self): + settings_dict = { + 'FEED_URI': 'file:///tmp/foobar', + 'FEED_STORAGES': { + 'file': FTPFeedStorageWithoutFeedOptions + }, + } + crawler = get_crawler(settings_dict=settings_dict) + feed_exporter = FeedExporter.from_crawler(crawler) + spider = scrapy.Spider("default") + spider.crawler = crawler + with warnings.catch_warnings(record=True) as w: + feed_exporter.open_spider(spider) + messages = tuple(str(item.message) for item in w + if item.category is ScrapyDeprecationWarning) + self.assertEqual( + messages, + ( + ( + "FTPFeedStorageWithoutFeedOptions does not support " + "the 'feed_options' keyword argument. Add a " + "'feed_options' parameter to its signature to remove " + "this warning. This parameter will become mandatory " + "in a future version of Scrapy." + ), + ) + ) + + def test_from_crawler(self): + settings_dict = { + 'FEED_URI': 'file:///tmp/foobar', + 'FEED_STORAGES': { + 'file': FTPFeedStorageWithoutFeedOptionsWithFromCrawler + }, + } + crawler = get_crawler(settings_dict=settings_dict) + feed_exporter = FeedExporter.from_crawler(crawler) + spider = scrapy.Spider("default") + spider.crawler = crawler + with warnings.catch_warnings(record=True) as w: + feed_exporter.open_spider(spider) + messages = tuple(str(item.message) for item in w + if item.category is ScrapyDeprecationWarning) + self.assertEqual( + messages, + ( + ( + "FTPFeedStorageWithoutFeedOptionsWithFromCrawler.from_crawler " + "does not support the 'feed_options' keyword argument. Add a " + "'feed_options' parameter to its signature to remove " + "this warning. This parameter will become mandatory " + "in a future version of Scrapy." + ), + ) + ) diff --git a/tests/test_http2_client_protocol.py b/tests/test_http2_client_protocol.py new file mode 100644 index 000000000..677ede92b --- /dev/null +++ b/tests/test_http2_client_protocol.py @@ -0,0 +1,669 @@ +import json +import os +import random +import re +import shutil +import string +from ipaddress import IPv4Address +from unittest import mock, skipIf +from urllib.parse import urlencode + +from twisted.internet import reactor +from twisted.internet.defer import CancelledError, Deferred, DeferredList, inlineCallbacks +from twisted.internet.endpoints import SSL4ClientEndpoint, SSL4ServerEndpoint +from twisted.internet.error import TimeoutError +from twisted.internet.ssl import optionsForClientTLS, PrivateCertificate, Certificate +from twisted.python.failure import Failure +from twisted.trial.unittest import TestCase +from twisted.web.client import ResponseFailed, URI +from twisted.web.http import H2_ENABLED, Request as TxRequest +from twisted.web.server import Site, NOT_DONE_YET +from twisted.web.static import File + +from scrapy.http import Request, Response, JsonRequest +from scrapy.settings import Settings +from scrapy.spiders import Spider +from tests.mockserver import ssl_context_factory, LeafResource, Status + + +def generate_random_string(size): + return ''.join(random.choices( + string.ascii_uppercase + string.digits, + k=size + )) + + +def make_html_body(val): + response = f'''<html> +<h1>Hello from HTTP2<h1> +<p>{val}</p> +</html>''' + return bytes(response, 'utf-8') + + +class DummySpider(Spider): + name = 'dummy' + start_urls: list = [] + + def parse(self, response): + print(response) + + +class Data: + SMALL_SIZE = 1024 # 1 KB + LARGE_SIZE = 1024 ** 2 # 1 MB + + STR_SMALL = generate_random_string(SMALL_SIZE) + STR_LARGE = generate_random_string(LARGE_SIZE) + + EXTRA_SMALL = generate_random_string(1024 * 15) + EXTRA_LARGE = generate_random_string((1024 ** 2) * 15) + + HTML_SMALL = make_html_body(STR_SMALL) + HTML_LARGE = make_html_body(STR_LARGE) + + JSON_SMALL = {'data': STR_SMALL} + JSON_LARGE = {'data': STR_LARGE} + + DATALOSS = b'Dataloss Content' + NO_CONTENT_LENGTH = b'This response do not have any content-length header' + + +class GetDataHtmlSmall(LeafResource): + def render_GET(self, request: TxRequest): + request.setHeader('Content-Type', 'text/html; charset=UTF-8') + return Data.HTML_SMALL + + +class GetDataHtmlLarge(LeafResource): + def render_GET(self, request: TxRequest): + request.setHeader('Content-Type', 'text/html; charset=UTF-8') + return Data.HTML_LARGE + + +class PostDataJsonMixin: + @staticmethod + def make_response(request: TxRequest, extra_data: str): + response = { + 'request-headers': {}, + 'request-body': json.loads(request.content.read()), + 'extra-data': extra_data + } + for k, v in request.requestHeaders.getAllRawHeaders(): + response['request-headers'][str(k, 'utf-8')] = str(v[0], 'utf-8') + + response_bytes = bytes(json.dumps(response), 'utf-8') + request.setHeader('Content-Type', 'application/json; charset=UTF-8') + request.setHeader('Content-Encoding', 'UTF-8') + return response_bytes + + +class PostDataJsonSmall(LeafResource, PostDataJsonMixin): + def render_POST(self, request: TxRequest): + return self.make_response(request, Data.EXTRA_SMALL) + + +class PostDataJsonLarge(LeafResource, PostDataJsonMixin): + def render_POST(self, request: TxRequest): + return self.make_response(request, Data.EXTRA_LARGE) + + +class Dataloss(LeafResource): + + def render_GET(self, request: TxRequest): + request.setHeader(b"Content-Length", b"1024") + self.deferRequest(request, 0, self._delayed_render, request) + return NOT_DONE_YET + + @staticmethod + def _delayed_render(request: TxRequest): + request.write(Data.DATALOSS) + request.finish() + + +class NoContentLengthHeader(LeafResource): + def render_GET(self, request: TxRequest): + request.requestHeaders.removeHeader('Content-Length') + self.deferRequest(request, 0, self._delayed_render, request) + return NOT_DONE_YET + + @staticmethod + def _delayed_render(request: TxRequest): + request.write(Data.NO_CONTENT_LENGTH) + request.finish() + + +class TimeoutResponse(LeafResource): + def render_GET(self, request: TxRequest): + return NOT_DONE_YET + + +class QueryParams(LeafResource): + def render_GET(self, request: TxRequest): + request.setHeader('Content-Type', 'application/json; charset=UTF-8') + request.setHeader('Content-Encoding', 'UTF-8') + + query_params = {} + for k, v in request.args.items(): + query_params[str(k, 'utf-8')] = str(v[0], 'utf-8') + + return bytes(json.dumps(query_params), 'utf-8') + + +class RequestHeaders(LeafResource): + """Sends all the headers received as a response""" + + def render_GET(self, request: TxRequest): + request.setHeader('Content-Type', 'application/json; charset=UTF-8') + request.setHeader('Content-Encoding', 'UTF-8') + headers = {} + for k, v in request.requestHeaders.getAllRawHeaders(): + headers[str(k, 'utf-8')] = str(v[0], 'utf-8') + + return bytes(json.dumps(headers), 'utf-8') + + +def get_client_certificate(key_file, certificate_file) -> PrivateCertificate: + with open(key_file, 'r') as key, open(certificate_file, 'r') as certificate: + pem = ''.join(key.readlines()) + ''.join(certificate.readlines()) + + return PrivateCertificate.loadPEM(pem) + + +@skipIf(not H2_ENABLED, "HTTP/2 support in Twisted is not enabled") +class Https2ClientProtocolTestCase(TestCase): + scheme = 'https' + key_file = os.path.join(os.path.dirname(__file__), 'keys', 'localhost.key') + certificate_file = os.path.join(os.path.dirname(__file__), 'keys', 'localhost.crt') + + def _init_resource(self): + self.temp_directory = self.mktemp() + os.mkdir(self.temp_directory) + r = File(self.temp_directory) + r.putChild(b'get-data-html-small', GetDataHtmlSmall()) + r.putChild(b'get-data-html-large', GetDataHtmlLarge()) + + r.putChild(b'post-data-json-small', PostDataJsonSmall()) + r.putChild(b'post-data-json-large', PostDataJsonLarge()) + + r.putChild(b'dataloss', Dataloss()) + r.putChild(b'no-content-length-header', NoContentLengthHeader()) + r.putChild(b'status', Status()) + r.putChild(b'query-params', QueryParams()) + r.putChild(b'timeout', TimeoutResponse()) + r.putChild(b'request-headers', RequestHeaders()) + return r + + @inlineCallbacks + def setUp(self): + # Initialize resource tree + root = self._init_resource() + self.site = Site(root, timeout=None) + + # Start server for testing + self.hostname = u'localhost' + context_factory = ssl_context_factory(self.key_file, self.certificate_file) + + server_endpoint = SSL4ServerEndpoint(reactor, 0, context_factory, interface=self.hostname) + self.server = yield server_endpoint.listen(self.site) + self.port_number = self.server.getHost().port + + # Connect H2 client with server + self.client_certificate = get_client_certificate(self.key_file, self.certificate_file) + client_options = optionsForClientTLS( + hostname=self.hostname, + trustRoot=self.client_certificate, + acceptableProtocols=[b'h2'] + ) + uri = URI.fromBytes(bytes(self.get_url('/'), 'utf-8')) + + self.conn_closed_deferred = Deferred() + from scrapy.core.http2.protocol import H2ClientFactory + h2_client_factory = H2ClientFactory(uri, Settings(), self.conn_closed_deferred) + client_endpoint = SSL4ClientEndpoint(reactor, self.hostname, self.port_number, client_options) + self.client = yield client_endpoint.connect(h2_client_factory) + + @inlineCallbacks + def tearDown(self): + if self.client.connected: + yield self.client.transport.loseConnection() + yield self.client.transport.abortConnection() + yield self.server.stopListening() + shutil.rmtree(self.temp_directory) + self.conn_closed_deferred = None + + def get_url(self, path): + """ + :param path: Should have / at the starting compulsorily if not empty + :return: Complete url + """ + assert len(path) > 0 and (path[0] == '/' or path[0] == '&') + return f'{self.scheme}://{self.hostname}:{self.port_number}{path}' + + def make_request(self, request: Request) -> Deferred: + return self.client.request(request, DummySpider()) + + @staticmethod + def _check_repeat(get_deferred, count): + d_list = [] + for _ in range(count): + d = get_deferred() + d_list.append(d) + + return DeferredList(d_list, fireOnOneErrback=True) + + def _check_GET( + self, + request: Request, + expected_body, + expected_status + ): + def check_response(response: Response): + self.assertEqual(response.status, expected_status) + self.assertEqual(response.body, expected_body) + self.assertEqual(response.request, request) + + content_length = int(response.headers.get('Content-Length')) + self.assertEqual(len(response.body), content_length) + + d = self.make_request(request) + d.addCallback(check_response) + d.addErrback(self.fail) + return d + + def test_GET_small_body(self): + request = Request(self.get_url('/get-data-html-small')) + return self._check_GET(request, Data.HTML_SMALL, 200) + + def test_GET_large_body(self): + request = Request(self.get_url('/get-data-html-large')) + return self._check_GET(request, Data.HTML_LARGE, 200) + + def _check_GET_x10(self, *args, **kwargs): + def get_deferred(): + return self._check_GET(*args, **kwargs) + + return self._check_repeat(get_deferred, 10) + + def test_GET_small_body_x10(self): + return self._check_GET_x10( + Request(self.get_url('/get-data-html-small')), + Data.HTML_SMALL, + 200 + ) + + def test_GET_large_body_x10(self): + return self._check_GET_x10( + Request(self.get_url('/get-data-html-large')), + Data.HTML_LARGE, + 200 + ) + + def _check_POST_json( + self, + request: Request, + expected_request_body, + expected_extra_data, + expected_status: int + ): + d = self.make_request(request) + + def assert_response(response: Response): + self.assertEqual(response.status, expected_status) + self.assertEqual(response.request, request) + + content_length = int(response.headers.get('Content-Length')) + self.assertEqual(len(response.body), content_length) + + # Parse the body + content_encoding = str(response.headers[b'Content-Encoding'], 'utf-8') + body = json.loads(str(response.body, content_encoding)) + self.assertIn('request-body', body) + self.assertIn('extra-data', body) + self.assertIn('request-headers', body) + + request_body = body['request-body'] + self.assertEqual(request_body, expected_request_body) + + extra_data = body['extra-data'] + self.assertEqual(extra_data, expected_extra_data) + + # Check if headers were sent successfully + request_headers = body['request-headers'] + for k, v in request.headers.items(): + k_str = str(k, 'utf-8') + self.assertIn(k_str, request_headers) + self.assertEqual(request_headers[k_str], str(v[0], 'utf-8')) + + d.addCallback(assert_response) + d.addErrback(self.fail) + return d + + def test_POST_small_json(self): + request = JsonRequest(url=self.get_url('/post-data-json-small'), method='POST', data=Data.JSON_SMALL) + return self._check_POST_json( + request, + Data.JSON_SMALL, + Data.EXTRA_SMALL, + 200 + ) + + def test_POST_large_json(self): + request = JsonRequest(url=self.get_url('/post-data-json-large'), method='POST', data=Data.JSON_LARGE) + return self._check_POST_json( + request, + Data.JSON_LARGE, + Data.EXTRA_LARGE, + 200 + ) + + def _check_POST_json_x10(self, *args, **kwargs): + def get_deferred(): + return self._check_POST_json(*args, **kwargs) + + return self._check_repeat(get_deferred, 10) + + def test_POST_small_json_x10(self): + request = JsonRequest(url=self.get_url('/post-data-json-small'), method='POST', data=Data.JSON_SMALL) + return self._check_POST_json_x10( + request, + Data.JSON_SMALL, + Data.EXTRA_SMALL, + 200 + ) + + def test_POST_large_json_x10(self): + request = JsonRequest(url=self.get_url('/post-data-json-large'), method='POST', data=Data.JSON_LARGE) + return self._check_POST_json_x10( + request, + Data.JSON_LARGE, + Data.EXTRA_LARGE, + 200 + ) + + @inlineCallbacks + def test_invalid_negotiated_protocol(self): + with mock.patch("scrapy.core.http2.protocol.PROTOCOL_NAME", return_value=b"not-h2"): + request = Request(url=self.get_url('/status?n=200')) + with self.assertRaises(ResponseFailed): + yield self.make_request(request) + + def test_cancel_request(self): + request = Request(url=self.get_url('/get-data-html-large')) + + def assert_response(response: Response): + self.assertEqual(response.status, 499) + self.assertEqual(response.request, request) + + d = self.make_request(request) + d.addCallback(assert_response) + d.addErrback(self.fail) + d.cancel() + + return d + + def test_download_maxsize_exceeded(self): + request = Request(url=self.get_url('/get-data-html-large'), meta={'download_maxsize': 1000}) + + def assert_cancelled_error(failure): + self.assertIsInstance(failure.value, CancelledError) + error_pattern = re.compile( + rf'Cancelling download of {request.url}: received response ' + rf'size \(\d*\) larger than download max size \(1000\)' + ) + self.assertEqual(len(re.findall(error_pattern, str(failure.value))), 1) + + d = self.make_request(request) + d.addCallback(self.fail) + d.addErrback(assert_cancelled_error) + return d + + def test_received_dataloss_response(self): + """In case when value of Header Content-Length != len(Received Data) + ProtocolError is raised""" + request = Request(url=self.get_url('/dataloss')) + + def assert_failure(failure: Failure): + self.assertTrue(len(failure.value.reasons) > 0) + from h2.exceptions import InvalidBodyLengthError + self.assertTrue(any( + isinstance(error, InvalidBodyLengthError) + for error in failure.value.reasons + )) + + d = self.make_request(request) + d.addCallback(self.fail) + d.addErrback(assert_failure) + return d + + def test_missing_content_length_header(self): + request = Request(url=self.get_url('/no-content-length-header')) + + def assert_content_length(response: Response): + self.assertEqual(response.status, 200) + self.assertEqual(response.body, Data.NO_CONTENT_LENGTH) + self.assertEqual(response.request, request) + self.assertNotIn('Content-Length', response.headers) + + d = self.make_request(request) + d.addCallback(assert_content_length) + d.addErrback(self.fail) + return d + + @inlineCallbacks + def _check_log_warnsize( + self, + request, + warn_pattern, + expected_body + ): + with self.assertLogs('scrapy.core.http2.stream', level='WARNING') as cm: + response = yield self.make_request(request) + self.assertEqual(response.status, 200) + self.assertEqual(response.request, request) + self.assertEqual(response.body, expected_body) + + # Check the warning is raised only once for this request + self.assertEqual(sum( + len(re.findall(warn_pattern, log)) + for log in cm.output + ), 1) + + @inlineCallbacks + def test_log_expected_warnsize(self): + request = Request(url=self.get_url('/get-data-html-large'), meta={'download_warnsize': 1000}) + warn_pattern = re.compile( + rf'Expected response size \(\d*\) larger than ' + rf'download warn size \(1000\) in request {request}' + ) + + yield self._check_log_warnsize(request, warn_pattern, Data.HTML_LARGE) + + @inlineCallbacks + def test_log_received_warnsize(self): + request = Request(url=self.get_url('/no-content-length-header'), meta={'download_warnsize': 10}) + warn_pattern = re.compile( + rf'Received more \(\d*\) bytes than download ' + rf'warn size \(10\) in request {request}' + ) + + yield self._check_log_warnsize(request, warn_pattern, Data.NO_CONTENT_LENGTH) + + def test_max_concurrent_streams(self): + """Send 500 requests at one to check if we can handle + very large number of request. + """ + + def get_deferred(): + return self._check_GET( + Request(self.get_url('/get-data-html-small')), + Data.HTML_SMALL, + 200 + ) + + return self._check_repeat(get_deferred, 500) + + def test_inactive_stream(self): + """Here we send 110 requests considering the MAX_CONCURRENT_STREAMS + by default is 100. After sending the first 100 requests we close the + connection.""" + d_list = [] + + def assert_inactive_stream(failure): + self.assertIsNotNone(failure.check(ResponseFailed)) + from scrapy.core.http2.stream import InactiveStreamClosed + self.assertTrue(any( + isinstance(e, InactiveStreamClosed) + for e in failure.value.reasons + )) + + # Send 100 request (we do not check the result) + for _ in range(100): + d = self.make_request(Request(self.get_url('/get-data-html-small'))) + d.addBoth(lambda _: None) + d_list.append(d) + + # Now send 10 extra request and save the response deferred in a list + for _ in range(10): + d = self.make_request(Request(self.get_url('/get-data-html-small'))) + d.addCallback(self.fail) + d.addErrback(assert_inactive_stream) + d_list.append(d) + + # Close the connection now to fire all the extra 10 requests errback + # with InactiveStreamClosed + self.client.transport.loseConnection() + + return DeferredList(d_list, consumeErrors=True, fireOnOneErrback=True) + + def test_invalid_request_type(self): + with self.assertRaises(TypeError): + self.make_request('https://InvalidDataTypePassed.com') + + def test_query_parameters(self): + params = { + 'a': generate_random_string(20), + 'b': generate_random_string(20), + 'c': generate_random_string(20), + 'd': generate_random_string(20) + } + request = Request(self.get_url(f'/query-params?{urlencode(params)}')) + + def assert_query_params(response: Response): + content_encoding = str(response.headers[b'Content-Encoding'], 'utf-8') + data = json.loads(str(response.body, content_encoding)) + self.assertEqual(data, params) + + d = self.make_request(request) + d.addCallback(assert_query_params) + d.addErrback(self.fail) + + return d + + def test_status_codes(self): + def assert_response_status(response: Response, expected_status: int): + self.assertEqual(response.status, expected_status) + + d_list = [] + for status in [200, 404]: + request = Request(self.get_url(f'/status?n={status}')) + d = self.make_request(request) + d.addCallback(assert_response_status, status) + d.addErrback(self.fail) + d_list.append(d) + + return DeferredList(d_list, fireOnOneErrback=True) + + def test_response_has_correct_certificate_ip_address(self): + request = Request(self.get_url('/status?n=200')) + + def assert_metadata(response: Response): + self.assertEqual(response.request, request) + self.assertIsInstance(response.certificate, Certificate) + self.assertIsNotNone(response.certificate.original) + self.assertEqual(response.certificate.getIssuer(), self.client_certificate.getIssuer()) + self.assertTrue(response.certificate.getPublicKey().matches(self.client_certificate.getPublicKey())) + + self.assertIsInstance(response.ip_address, IPv4Address) + self.assertEqual(str(response.ip_address), '127.0.0.1') + + d = self.make_request(request) + d.addCallback(assert_metadata) + d.addErrback(self.fail) + + return d + + def _check_invalid_netloc(self, url): + request = Request(url) + + def assert_invalid_hostname(failure: Failure): + from scrapy.core.http2.stream import InvalidHostname + self.assertIsNotNone(failure.check(InvalidHostname)) + error_msg = str(failure.value) + self.assertIn('localhost', error_msg) + self.assertIn('127.0.0.1', error_msg) + self.assertIn(str(request), error_msg) + + d = self.make_request(request) + d.addCallback(self.fail) + d.addErrback(assert_invalid_hostname) + return d + + def test_invalid_hostname(self): + return self._check_invalid_netloc('https://notlocalhost.notlocalhostdomain') + + def test_invalid_host_port(self): + port = self.port_number + 1 + return self._check_invalid_netloc(f'https://127.0.0.1:{port}') + + def test_connection_stays_with_invalid_requests(self): + d_list = [ + self.test_invalid_hostname(), + self.test_invalid_host_port(), + self.test_GET_small_body(), + self.test_POST_small_json() + ] + + return DeferredList(d_list, fireOnOneErrback=True) + + def test_connection_timeout(self): + request = Request(self.get_url('/timeout')) + d = self.make_request(request) + + # Update the timer to 1s to test connection timeout + self.client.setTimeout(1) + + def assert_timeout_error(failure: Failure): + for err in failure.value.reasons: + from scrapy.core.http2.protocol import H2ClientProtocol + if isinstance(err, TimeoutError): + self.assertIn(f"Connection was IDLE for more than {H2ClientProtocol.IDLE_TIMEOUT}s", str(err)) + break + else: + self.fail() + + d.addCallback(self.fail) + d.addErrback(assert_timeout_error) + return d + + def test_request_headers_received(self): + request = Request(self.get_url('/request-headers'), headers={ + 'header-1': 'header value 1', + 'header-2': 'header value 2' + }) + d = self.make_request(request) + + def assert_request_headers(response: Response): + self.assertEqual(response.status, 200) + self.assertEqual(response.request, request) + + response_headers = json.loads(str(response.body, 'utf-8')) + self.assertIsInstance(response_headers, dict) + for k, v in request.headers.items(): + k, v = str(k, 'utf-8'), str(v[0], 'utf-8') + self.assertIn(k, response_headers) + self.assertEqual(v, response_headers[k]) + + d.addErrback(self.fail) + d.addCallback(assert_request_headers) + return d diff --git a/tests/test_http_cookies.py b/tests/test_http_cookies.py index 45ddb42ba..540e27907 100644 --- a/tests/test_http_cookies.py +++ b/tests/test_http_cookies.py @@ -64,9 +64,6 @@ class WrappedResponseTest(TestCase): def test_info(self): self.assertIs(self.wrapped.info(), self.wrapped) - def test_getheaders(self): - self.assertEqual(self.wrapped.getheaders('content-type'), ['text/html']) - def test_get_all(self): # get_all result must be native string self.assertEqual(self.wrapped.get_all('content-type'), ['text/html']) diff --git a/tests/test_http_headers.py b/tests/test_http_headers.py index cf3fc8496..64ff7a73d 100644 --- a/tests/test_http_headers.py +++ b/tests/test_http_headers.py @@ -39,19 +39,19 @@ class HeadersTest(unittest.TestCase): assert h.getlist('X-Forwarded-For') is not hlist def test_encode_utf8(self): - h = Headers({u'key': u'\xa3'}, encoding='utf-8') + h = Headers({'key': '\xa3'}, encoding='utf-8') key, val = dict(h).popitem() assert isinstance(key, bytes), key assert isinstance(val[0], bytes), val[0] self.assertEqual(val[0], b'\xc2\xa3') def test_encode_latin1(self): - h = Headers({u'key': u'\xa3'}, encoding='latin1') + h = Headers({'key': '\xa3'}, encoding='latin1') key, val = dict(h).popitem() self.assertEqual(val[0], b'\xa3') def test_encode_multiple(self): - h = Headers({u'key': [u'\xa3']}, encoding='utf-8') + h = Headers({'key': ['\xa3']}, encoding='utf-8') key, val = dict(h).popitem() self.assertEqual(val[0], b'\xc2\xa3') diff --git a/tests/test_http_request.py b/tests/test_http_request.py index 63014b22d..b610087bd 100644 --- a/tests/test_http_request.py +++ b/tests/test_http_request.py @@ -43,6 +43,15 @@ class RequestTest(unittest.TestCase): assert r.headers is not headers self.assertEqual(r.headers[b"caca"], b"coco") + def test_url_scheme(self): + # This test passes by not raising any (ValueError) exception + self.request_class('http://example.org') + self.request_class('https://example.org') + self.request_class('s3://example.org') + self.request_class('ftp://example.org') + self.request_class('about:config') + self.request_class('data:,Hello%2C%20World!') + def test_url_no_scheme(self): self.assertRaises(ValueError, self.request_class, 'foo') self.assertRaises(ValueError, self.request_class, '/foo/') @@ -60,8 +69,8 @@ class RequestTest(unittest.TestCase): self.assertFalse(p.headers is r.headers) # headers must not be unicode - h = Headers({'key1': u'val1', u'key2': 'val2'}) - h[u'newkey'] = u'newval' + h = Headers({'key1': 'val1', 'key2': 'val2'}) + h['newkey'] = 'newval' for k, v in h.items(): self.assertIsInstance(k, bytes) for s in v: @@ -89,30 +98,30 @@ class RequestTest(unittest.TestCase): self.assertEqual(r.url, "http://www.scrapy.org/blank%20space") def test_url_encoding(self): - r = self.request_class(url=u"http://www.scrapy.org/price/£") + r = self.request_class(url="http://www.scrapy.org/price/£") self.assertEqual(r.url, "http://www.scrapy.org/price/%C2%A3") def test_url_encoding_other(self): # encoding affects only query part of URI, not path # path part should always be UTF-8 encoded before percent-escaping - r = self.request_class(url=u"http://www.scrapy.org/price/£", encoding="utf-8") + r = self.request_class(url="http://www.scrapy.org/price/£", encoding="utf-8") self.assertEqual(r.url, "http://www.scrapy.org/price/%C2%A3") - r = self.request_class(url=u"http://www.scrapy.org/price/£", encoding="latin1") + r = self.request_class(url="http://www.scrapy.org/price/£", encoding="latin1") self.assertEqual(r.url, "http://www.scrapy.org/price/%C2%A3") def test_url_encoding_query(self): - r1 = self.request_class(url=u"http://www.scrapy.org/price/£?unit=µ") + r1 = self.request_class(url="http://www.scrapy.org/price/£?unit=µ") self.assertEqual(r1.url, "http://www.scrapy.org/price/%C2%A3?unit=%C2%B5") # should be same as above - r2 = self.request_class(url=u"http://www.scrapy.org/price/£?unit=µ", encoding="utf-8") + r2 = self.request_class(url="http://www.scrapy.org/price/£?unit=µ", encoding="utf-8") self.assertEqual(r2.url, "http://www.scrapy.org/price/%C2%A3?unit=%C2%B5") def test_url_encoding_query_latin1(self): # encoding is used for encoding query-string before percent-escaping; # path is still UTF-8 encoded before percent-escaping - r3 = self.request_class(url=u"http://www.scrapy.org/price/µ?currency=£", encoding="latin1") + r3 = self.request_class(url="http://www.scrapy.org/price/µ?currency=£", encoding="latin1") self.assertEqual(r3.url, "http://www.scrapy.org/price/%C2%B5?currency=%A3") def test_url_encoding_nonutf8_untouched(self): @@ -131,16 +140,16 @@ class RequestTest(unittest.TestCase): # characters. Otherwise, in the future the IRI will be mapped to # "http://www.example.org/r%C3%A9sum%C3%A9.html", which is a different # URI from "http://www.example.org/r%E9sum%E9.html". - r1 = self.request_class(url=u"http://www.scrapy.org/price/%a3") + r1 = self.request_class(url="http://www.scrapy.org/price/%a3") self.assertEqual(r1.url, "http://www.scrapy.org/price/%a3") - r2 = self.request_class(url=u"http://www.scrapy.org/r%C3%A9sum%C3%A9/%a3") + r2 = self.request_class(url="http://www.scrapy.org/r%C3%A9sum%C3%A9/%a3") self.assertEqual(r2.url, "http://www.scrapy.org/r%C3%A9sum%C3%A9/%a3") - r3 = self.request_class(url=u"http://www.scrapy.org/résumé/%a3") + r3 = self.request_class(url="http://www.scrapy.org/résumé/%a3") self.assertEqual(r3.url, "http://www.scrapy.org/r%C3%A9sum%C3%A9/%a3") - r4 = self.request_class(url=u"http://www.example.org/r%E9sum%E9.html") + r4 = self.request_class(url="http://www.example.org/r%E9sum%E9.html") self.assertEqual(r4.url, "http://www.example.org/r%E9sum%E9.html") def test_body(self): @@ -151,11 +160,11 @@ class RequestTest(unittest.TestCase): assert isinstance(r2.body, bytes) self.assertEqual(r2.encoding, 'utf-8') # default encoding - r3 = self.request_class(url="http://www.example.com/", body=u"Price: \xa3100", encoding='utf-8') + r3 = self.request_class(url="http://www.example.com/", body="Price: \xa3100", encoding='utf-8') assert isinstance(r3.body, bytes) self.assertEqual(r3.body, b"Price: \xc2\xa3100") - r4 = self.request_class(url="http://www.example.com/", body=u"Price: \xa3100", encoding='latin1') + r4 = self.request_class(url="http://www.example.com/", body="Price: \xa3100", encoding='latin1') assert isinstance(r4.body, bytes) self.assertEqual(r4.body, b"Price: \xa3100") @@ -164,7 +173,7 @@ class RequestTest(unittest.TestCase): r = self.request_class(url="http://www.example.com/ajax.html#!key=value") self.assertEqual(r.url, "http://www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue") # unicode url - r = self.request_class(url=u"http://www.example.com/ajax.html#!key=value") + r = self.request_class(url="http://www.example.com/ajax.html#!key=value") self.assertEqual(r.url, "http://www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue") def test_copy(self): @@ -236,7 +245,7 @@ class RequestTest(unittest.TestCase): assert r4.dont_filter is False def test_method_always_str(self): - r = self.request_class("http://www.example.com", method=u"POST") + r = self.request_class("http://www.example.com", method="POST") assert isinstance(r.method, str) def test_immutable_attributes(self): @@ -370,6 +379,20 @@ class FormRequestTest(RequestTest): r1 = self.request_class("http://www.example.com", formdata={}) self.assertEqual(r1.body, b'') + def test_formdata_overrides_querystring(self): + data = (('a', 'one'), ('a', 'two'), ('b', '2')) + url = self.request_class('http://www.example.com/?a=0&b=1&c=3#fragment', + method='GET', formdata=data).url.split('#')[0] + fs = _qs(self.request_class(url, method='GET', formdata=data)) + self.assertEqual(set(fs[b'a']), {b'one', b'two'}) + self.assertEqual(fs[b'b'], [b'2']) + self.assertIsNone(fs.get(b'c')) + + data = {'a': '1', 'b': '2'} + fs = _qs(self.request_class('http://www.example.com/', method='GET', formdata=data)) + self.assertEqual(fs[b'a'], [b'1']) + self.assertEqual(fs[b'b'], [b'2']) + def test_default_encoding_bytes(self): # using default encoding (utf-8) data = {b'one': b'two', b'price': b'\xc2\xa3 100'} @@ -381,7 +404,7 @@ class FormRequestTest(RequestTest): def test_default_encoding_textual_data(self): # using default encoding (utf-8) - data = {u'µ one': u'two', u'price': u'£ 100'} + data = {'µ one': 'two', 'price': '£ 100'} r2 = self.request_class("http://www.example.com", formdata=data) self.assertEqual(r2.method, 'POST') self.assertEqual(r2.encoding, 'utf-8') @@ -390,7 +413,7 @@ class FormRequestTest(RequestTest): def test_default_encoding_mixed_data(self): # using default encoding (utf-8) - data = {u'\u00b5one': b'two', b'price\xc2\xa3': u'\u00a3 100'} + data = {'\u00b5one': b'two', b'price\xc2\xa3': '\u00a3 100'} r2 = self.request_class("http://www.example.com", formdata=data) self.assertEqual(r2.method, 'POST') self.assertEqual(r2.encoding, 'utf-8') @@ -406,14 +429,14 @@ class FormRequestTest(RequestTest): self.assertEqual(r2.headers[b'Content-Type'], b'application/x-www-form-urlencoded') def test_custom_encoding_textual_data(self): - data = {'price': u'£ 100'} + data = {'price': '£ 100'} r3 = self.request_class("http://www.example.com", formdata=data, encoding='latin1') self.assertEqual(r3.encoding, 'latin1') self.assertEqual(r3.body, b'price=%A3+100') def test_multi_key_values(self): # using multiples values for a single key - data = {'price': u'\xa3 100', 'colours': ['red', 'blue', 'green']} + data = {'price': '\xa3 100', 'colours': ['red', 'blue', 'green']} r3 = self.request_class("http://www.example.com", formdata=data) self.assertQueryEqual(r3.body, b'colours=red&colours=blue&colours=green&price=%C2%A3+100') @@ -450,10 +473,10 @@ class FormRequestTest(RequestTest): self.assertEqual(req.headers[b'Content-type'], b'application/x-www-form-urlencoded') self.assertEqual(req.url, "http://www.example.com/this/post.php") fs = _qs(req, to_unicode=True) - self.assertEqual(set(fs[u'test £']), {u'val1', u'val2'}) - self.assertEqual(set(fs[u'one']), {u'two', u'three'}) - self.assertEqual(fs[u'test2'], [u'xxx µ']) - self.assertEqual(fs[u'six'], [u'seven']) + self.assertEqual(set(fs['test £']), {'val1', 'val2'}) + self.assertEqual(set(fs['one']), {'two', 'three'}) + self.assertEqual(fs['test2'], ['xxx µ']) + self.assertEqual(fs['six'], ['seven']) def test_from_response_post_nonascii_bytes_latin1(self): response = _buildresponse( @@ -471,14 +494,14 @@ class FormRequestTest(RequestTest): self.assertEqual(req.headers[b'Content-type'], b'application/x-www-form-urlencoded') self.assertEqual(req.url, "http://www.example.com/this/post.php") fs = _qs(req, to_unicode=True, encoding='latin1') - self.assertEqual(set(fs[u'test £']), {u'val1', u'val2'}) - self.assertEqual(set(fs[u'one']), {u'two', u'three'}) - self.assertEqual(fs[u'test2'], [u'xxx µ']) - self.assertEqual(fs[u'six'], [u'seven']) + self.assertEqual(set(fs['test £']), {'val1', 'val2'}) + self.assertEqual(set(fs['one']), {'two', 'three'}) + self.assertEqual(fs['test2'], ['xxx µ']) + self.assertEqual(fs['six'], ['seven']) def test_from_response_post_nonascii_unicode(self): response = _buildresponse( - u"""<form action="post.php" method="POST"> + """<form action="post.php" method="POST"> <input type="hidden" name="test £" value="val1"> <input type="hidden" name="test £" value="val2"> <input type="hidden" name="test2" value="xxx µ"> @@ -490,10 +513,10 @@ class FormRequestTest(RequestTest): self.assertEqual(req.headers[b'Content-type'], b'application/x-www-form-urlencoded') self.assertEqual(req.url, "http://www.example.com/this/post.php") fs = _qs(req, to_unicode=True) - self.assertEqual(set(fs[u'test £']), {u'val1', u'val2'}) - self.assertEqual(set(fs[u'one']), {u'two', u'three'}) - self.assertEqual(fs[u'test2'], [u'xxx µ']) - self.assertEqual(fs[u'six'], [u'seven']) + self.assertEqual(set(fs['test £']), {'val1', 'val2'}) + self.assertEqual(set(fs['one']), {'two', 'three'}) + self.assertEqual(fs['test2'], ['xxx µ']) + self.assertEqual(fs['six'], ['seven']) def test_from_response_duplicate_form_key(self): response = _buildresponse( @@ -685,7 +708,7 @@ class FormRequestTest(RequestTest): <input type="hidden" name="two" value="clicked2"> </form>""") req = self.request_class.from_response( - response, clickdata={u'name': u'clickable', u'value': u'clicked2'} + response, clickdata={'name': 'clickable', 'value': 'clicked2'} ) fs = _qs(req) self.assertEqual(fs[b'clickable'], [b'clicked2']) @@ -694,21 +717,21 @@ class FormRequestTest(RequestTest): def test_from_response_unicode_clickdata(self): response = _buildresponse( - u"""<form action="get.php" method="GET"> + """<form action="get.php" method="GET"> <input type="submit" name="price in \u00a3" value="\u00a3 1000"> <input type="submit" name="price in \u20ac" value="\u20ac 2000"> <input type="hidden" name="poundsign" value="\u00a3"> <input type="hidden" name="eurosign" value="\u20ac"> </form>""") req = self.request_class.from_response( - response, clickdata={u'name': u'price in \u00a3'} + response, clickdata={'name': 'price in \u00a3'} ) fs = _qs(req, to_unicode=True) - self.assertTrue(fs[u'price in \u00a3']) + self.assertTrue(fs['price in \u00a3']) def test_from_response_unicode_clickdata_latin1(self): response = _buildresponse( - u"""<form action="get.php" method="GET"> + """<form action="get.php" method="GET"> <input type="submit" name="price in \u00a3" value="\u00a3 1000"> <input type="submit" name="price in \u00a5" value="\u00a5 2000"> <input type="hidden" name="poundsign" value="\u00a3"> @@ -716,10 +739,10 @@ class FormRequestTest(RequestTest): </form>""", encoding='latin1') req = self.request_class.from_response( - response, clickdata={u'name': u'price in \u00a5'} + response, clickdata={'name': 'price in \u00a5'} ) fs = _qs(req, to_unicode=True, encoding='latin1') - self.assertTrue(fs[u'price in \u00a5']) + self.assertTrue(fs['price in \u00a5']) def test_from_response_multiple_forms_clickdata(self): response = _buildresponse( @@ -733,7 +756,7 @@ class FormRequestTest(RequestTest): </form> """) req = self.request_class.from_response( - response, formname='form2', clickdata={u'name': u'clickable'} + response, formname='form2', clickdata={'name': 'clickable'} ) fs = _qs(req) self.assertEqual(fs[b'clickable'], [b'clicked2']) @@ -1072,11 +1095,11 @@ class FormRequestTest(RequestTest): def test_from_response_unicode_xpath(self): response = _buildresponse(b'<form name="\xd1\x8a"></form>') - r = self.request_class.from_response(response, formxpath=u"//form[@name='\u044a']") + r = self.request_class.from_response(response, formxpath="//form[@name='\u044a']") fs = _qs(r) self.assertEqual(fs, {}) - xpath = u"//form[@name='\u03b1']" + xpath = "//form[@name='\u03b1']" self.assertRaisesRegex(ValueError, re.escape(xpath), self.request_class.from_response, response, formxpath=xpath) @@ -1246,13 +1269,13 @@ class XmlRpcRequestTest(RequestTest): self._test_request(params=('value',)) self._test_request(params=('username', 'password'), methodname='login') self._test_request(params=('response', ), methodresponse='login') - self._test_request(params=(u'pas£',), encoding='utf-8') + self._test_request(params=('pas£',), encoding='utf-8') self._test_request(params=(None,), allow_none=1) self.assertRaises(TypeError, self._test_request) self.assertRaises(TypeError, self._test_request, params=(None,)) def test_latin1(self): - self._test_request(params=(u'pas£',), encoding='latin1') + self._test_request(params=('pas£',), encoding='latin1') class JsonRequestTest(RequestTest): @@ -1265,7 +1288,7 @@ class JsonRequestTest(RequestTest): def setUp(self): warnings.simplefilter("always") - super(JsonRequestTest, self).setUp() + super().setUp() def test_data(self): r1 = self.request_class(url="http://www.example.com/") @@ -1419,7 +1442,7 @@ class JsonRequestTest(RequestTest): def tearDown(self): warnings.resetwarnings() - super(JsonRequestTest, self).tearDown() + super().tearDown() if __name__ == "__main__": diff --git a/tests/test_http_response.py b/tests/test_http_response.py index e0ca3c0e6..04a594d03 100644 --- a/tests/test_http_response.py +++ b/tests/test_http_response.py @@ -1,6 +1,6 @@ import unittest from unittest import mock -from warnings import catch_warnings +from warnings import catch_warnings, filterwarnings from w3lib.encoding import resolve_encoding @@ -134,7 +134,9 @@ class BaseResponseTest(unittest.TestCase): assert isinstance(response.text, str) self._assert_response_encoding(response, encoding) self.assertEqual(response.body, body_bytes) - self.assertEqual(response.body_as_unicode(), body_unicode) + with catch_warnings(): + filterwarnings("ignore", category=ScrapyDeprecationWarning) + self.assertEqual(response.body_as_unicode(), body_unicode) self.assertEqual(response.text, body_unicode) def _assert_response_encoding(self, response, encoding): @@ -305,7 +307,7 @@ class TextResponseTest(BaseResponseTest): response_class = TextResponse def test_replace(self): - super(TextResponseTest, self).test_replace() + super().test_replace() r1 = self.response_class("http://www.example.com", body="hello", encoding="cp852") r2 = r1.replace(url="http://www.example.com/other") r3 = r1.replace(url="http://www.example.com/other", encoding="latin1") @@ -318,35 +320,37 @@ class TextResponseTest(BaseResponseTest): def test_unicode_url(self): # instantiate with unicode url without encoding (should set default encoding) - resp = self.response_class(u"http://www.example.com/") + resp = self.response_class("http://www.example.com/") self._assert_response_encoding(resp, self.response_class._DEFAULT_ENCODING) # make sure urls are converted to str - resp = self.response_class(url=u"http://www.example.com/", encoding='utf-8') + resp = self.response_class(url="http://www.example.com/", encoding='utf-8') assert isinstance(resp.url, str) - resp = self.response_class(url=u"http://www.example.com/price/\xa3", encoding='utf-8') + resp = self.response_class(url="http://www.example.com/price/\xa3", encoding='utf-8') self.assertEqual(resp.url, to_unicode(b'http://www.example.com/price/\xc2\xa3')) - resp = self.response_class(url=u"http://www.example.com/price/\xa3", encoding='latin-1') + resp = self.response_class(url="http://www.example.com/price/\xa3", encoding='latin-1') self.assertEqual(resp.url, 'http://www.example.com/price/\xa3') - resp = self.response_class(u"http://www.example.com/price/\xa3", + resp = self.response_class("http://www.example.com/price/\xa3", headers={"Content-type": ["text/html; charset=utf-8"]}) self.assertEqual(resp.url, to_unicode(b'http://www.example.com/price/\xc2\xa3')) - resp = self.response_class(u"http://www.example.com/price/\xa3", + resp = self.response_class("http://www.example.com/price/\xa3", headers={"Content-type": ["text/html; charset=iso-8859-1"]}) self.assertEqual(resp.url, 'http://www.example.com/price/\xa3') def test_unicode_body(self): unicode_string = ('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0447\u0435\u0441\u043a\u0438\u0439 ' '\u0442\u0435\u043a\u0441\u0442') - self.assertRaises(TypeError, self.response_class, 'http://www.example.com', body=u'unicode body') + self.assertRaises(TypeError, self.response_class, 'http://www.example.com', body='unicode body') original_string = unicode_string.encode('cp1251') r1 = self.response_class('http://www.example.com', body=original_string, encoding='cp1251') # check body_as_unicode - self.assertTrue(isinstance(r1.body_as_unicode(), str)) - self.assertEqual(r1.body_as_unicode(), unicode_string) + with catch_warnings(): + filterwarnings("ignore", category=ScrapyDeprecationWarning) + self.assertTrue(isinstance(r1.body_as_unicode(), str)) + self.assertEqual(r1.body_as_unicode(), unicode_string) # check response.text self.assertTrue(isinstance(r1.text, str)) @@ -355,7 +359,7 @@ class TextResponseTest(BaseResponseTest): def test_encoding(self): r1 = self.response_class("http://www.example.com", body=b"\xc2\xa3", headers={"Content-type": ["text/html; charset=utf-8"]}) - r2 = self.response_class("http://www.example.com", encoding='utf-8', body=u"\xa3") + r2 = self.response_class("http://www.example.com", encoding='utf-8', body="\xa3") r3 = self.response_class("http://www.example.com", body=b"\xa3", headers={"Content-type": ["text/html; charset=iso-8859-1"]}) r4 = self.response_class("http://www.example.com", body=b"\xa2\xa3") @@ -376,14 +380,14 @@ class TextResponseTest(BaseResponseTest): self.assertEqual(r5._headers_encoding(), None) self._assert_response_encoding(r5, "utf-8") assert r4._body_inferred_encoding() is not None and r4._body_inferred_encoding() != 'ascii' - self._assert_response_values(r1, 'utf-8', u"\xa3") - self._assert_response_values(r2, 'utf-8', u"\xa3") - self._assert_response_values(r3, 'iso-8859-1', u"\xa3") - self._assert_response_values(r6, 'gb18030', u"\u2015") - self._assert_response_values(r7, 'gb18030', u"\u2015") + self._assert_response_values(r1, 'utf-8', "\xa3") + self._assert_response_values(r2, 'utf-8', "\xa3") + self._assert_response_values(r3, 'iso-8859-1', "\xa3") + self._assert_response_values(r6, 'gb18030', "\u2015") + self._assert_response_values(r7, 'gb18030', "\u2015") # TextResponse (and subclasses) must be passed a encoding when instantiating with unicode bodies - self.assertRaises(TypeError, self.response_class, "http://www.example.com", body=u"\xa3") + self.assertRaises(TypeError, self.response_class, "http://www.example.com", body="\xa3") def test_declared_encoding_invalid(self): """Check that unknown declared encodings are ignored""" @@ -391,14 +395,14 @@ class TextResponseTest(BaseResponseTest): headers={"Content-type": ["text/html; charset=UKNOWN"]}, body=b"\xc2\xa3") self.assertEqual(r._declared_encoding(), None) - self._assert_response_values(r, 'utf-8', u"\xa3") + self._assert_response_values(r, 'utf-8', "\xa3") def test_utf16(self): """Test utf-16 because UnicodeDammit is known to have problems with""" r = self.response_class("http://www.example.com", body=b'\xff\xfeh\x00i\x00', encoding='utf-16') - self._assert_response_values(r, 'utf-16', u"hi") + self._assert_response_values(r, 'utf-16', "hi") def test_invalid_utf8_encoded_body_with_valid_utf8_BOM(self): r6 = self.response_class("http://www.example.com", @@ -406,8 +410,8 @@ class TextResponseTest(BaseResponseTest): body=b"\xef\xbb\xbfWORD\xe3\xab") self.assertEqual(r6.encoding, 'utf-8') self.assertIn(r6.text, { - u'WORD\ufffd\ufffd', # w3lib < 1.19.0 - u'WORD\ufffd', # w3lib >= 1.19.0 + 'WORD\ufffd\ufffd', # w3lib < 1.19.0 + 'WORD\ufffd', # w3lib >= 1.19.0 }) def test_bom_is_removed_from_body(self): @@ -422,9 +426,9 @@ class TextResponseTest(BaseResponseTest): # Test response without content-type and BOM encoding response = self.response_class(url, body=body) self.assertEqual(response.encoding, 'utf-8') - self.assertEqual(response.text, u'WORD') + self.assertEqual(response.text, 'WORD') response = self.response_class(url, body=body) - self.assertEqual(response.text, u'WORD') + self.assertEqual(response.text, 'WORD') self.assertEqual(response.encoding, 'utf-8') # Body caching sideeffect isn't triggered when encoding is declared in @@ -432,28 +436,28 @@ class TextResponseTest(BaseResponseTest): # body response = self.response_class(url, headers=headers, body=body) self.assertEqual(response.encoding, 'utf-8') - self.assertEqual(response.text, u'WORD') + self.assertEqual(response.text, 'WORD') response = self.response_class(url, headers=headers, body=body) - self.assertEqual(response.text, u'WORD') + self.assertEqual(response.text, 'WORD') self.assertEqual(response.encoding, 'utf-8') def test_replace_wrong_encoding(self): """Test invalid chars are replaced properly""" r = self.response_class("http://www.example.com", encoding='utf-8', body=b'PREFIX\xe3\xabSUFFIX') # XXX: Policy for replacing invalid chars may suffer minor variations - # but it should always contain the unicode replacement char (u'\ufffd') - assert u'\ufffd' in r.text, repr(r.text) - assert u'PREFIX' in r.text, repr(r.text) - assert u'SUFFIX' in r.text, repr(r.text) + # but it should always contain the unicode replacement char ('\ufffd') + assert '\ufffd' in r.text, repr(r.text) + assert 'PREFIX' in r.text, repr(r.text) + assert 'SUFFIX' in r.text, repr(r.text) # Do not destroy html tags due to encoding bugs r = self.response_class("http://example.com", encoding='utf-8', body=b'\xf0<span>value</span>') - assert u'<span>value</span>' in r.text, repr(r.text) + assert '<span>value</span>' in r.text, repr(r.text) # FIXME: This test should pass once we stop using BeautifulSoup's UnicodeDammit in TextResponse # r = self.response_class("http://www.example.com", body=b'PREFIX\xe3\xabSUFFIX') - # assert u'\ufffd' in r.text, repr(r.text) + # assert '\ufffd' in r.text, repr(r.text) def test_selector(self): body = b"<html><head><title>Some page" @@ -466,15 +470,15 @@ class TextResponseTest(BaseResponseTest): self.assertEqual( response.selector.xpath("//title/text()").getall(), - [u'Some page'] + ['Some page'] ) self.assertEqual( response.selector.css("title::text").getall(), - [u'Some page'] + ['Some page'] ) self.assertEqual( response.selector.re("Some (.*)"), - [u'page'] + ['page'] ) def test_selector_shortcuts(self): @@ -595,7 +599,7 @@ class TextResponseTest(BaseResponseTest): resp1 = self.response_class( 'http://example.com', encoding='utf8', - body=u'click me'.encode('utf8') + body='click me'.encode('utf8') ) req = self._assert_followed_url( resp1.css('a')[0], @@ -607,7 +611,7 @@ class TextResponseTest(BaseResponseTest): resp2 = self.response_class( 'http://example.com', encoding='cp1251', - body=u'click me'.encode('cp1251') + body='click me'.encode('cp1251') ) req = self._assert_followed_url( resp2.css('a')[0], @@ -681,8 +685,8 @@ class TextResponseTest(BaseResponseTest): def test_body_as_unicode_deprecation_warning(self): with catch_warnings(record=True) as warnings: - r1 = self.response_class("http://www.example.com", body=u'Hello', encoding='utf-8') - self.assertEqual(r1.body_as_unicode(), u'Hello') + r1 = self.response_class("http://www.example.com", body='Hello', encoding='utf-8') + self.assertEqual(r1.body_as_unicode(), 'Hello') self.assertEqual(len(warnings), 1) self.assertEqual(warnings[0].category, ScrapyDeprecationWarning) @@ -787,7 +791,7 @@ class XmlResponseTest(TextResponseTest): self.assertEqual( response.selector.xpath("//elem/text()").getall(), - [u'value'] + ['value'] ) def test_selector_shortcuts(self): diff --git a/tests/test_item.py b/tests/test_item.py index 60468971c..c94bb44af 100644 --- a/tests/test_item.py +++ b/tests/test_item.py @@ -1,15 +1,11 @@ -import sys import unittest from unittest import mock -from warnings import catch_warnings +from warnings import catch_warnings, filterwarnings from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.item import ABCMeta, _BaseItem, BaseItem, DictItem, Field, Item, ItemMeta -PY36_PLUS = (sys.version_info.major >= 3) and (sys.version_info.minor >= 6) - - class ItemTest(unittest.TestCase): def assertSortedEqual(self, first, second, msg=None): @@ -20,8 +16,8 @@ class ItemTest(unittest.TestCase): name = Field() i = TestItem() - i['name'] = u'name' - self.assertEqual(i['name'], u'name') + i['name'] = 'name' + self.assertEqual(i['name'], 'name') def test_init(self): class TestItem(Item): @@ -30,17 +26,17 @@ class ItemTest(unittest.TestCase): i = TestItem() self.assertRaises(KeyError, i.__getitem__, 'name') - i2 = TestItem(name=u'john doe') - self.assertEqual(i2['name'], u'john doe') + i2 = TestItem(name='john doe') + self.assertEqual(i2['name'], 'john doe') - i3 = TestItem({'name': u'john doe'}) - self.assertEqual(i3['name'], u'john doe') + i3 = TestItem({'name': 'john doe'}) + self.assertEqual(i3['name'], 'john doe') i4 = TestItem(i3) - self.assertEqual(i4['name'], u'john doe') + self.assertEqual(i4['name'], 'john doe') - self.assertRaises(KeyError, TestItem, {'name': u'john doe', - 'other': u'foo'}) + self.assertRaises(KeyError, TestItem, {'name': 'john doe', + 'other': 'foo'}) def test_invalid_field(self): class TestItem(Item): @@ -56,7 +52,7 @@ class ItemTest(unittest.TestCase): number = Field() i = TestItem() - i['name'] = u'John Doe' + i['name'] = 'John Doe' i['number'] = 123 itemrepr = repr(i) @@ -101,9 +97,9 @@ class ItemTest(unittest.TestCase): i = TestItem() self.assertRaises(KeyError, i.get_name) - i['name'] = u'lala' - self.assertEqual(i.get_name(), u'lala') - i.change_name(u'other') + i['name'] = 'lala' + self.assertEqual(i.get_name(), 'lala') + i.change_name('other') self.assertEqual(i.get_name(), 'other') def test_metaclass(self): @@ -113,22 +109,22 @@ class ItemTest(unittest.TestCase): values = Field() i = TestItem() - i['name'] = u'John' + i['name'] = 'John' self.assertEqual(list(i.keys()), ['name']) self.assertEqual(list(i.values()), ['John']) - i['keys'] = u'Keys' - i['values'] = u'Values' + i['keys'] = 'Keys' + i['values'] = 'Values' self.assertSortedEqual(list(i.keys()), ['keys', 'values', 'name']) - self.assertSortedEqual(list(i.values()), [u'Keys', u'Values', u'John']) + self.assertSortedEqual(list(i.values()), ['Keys', 'Values', 'John']) def test_metaclass_with_fields_attribute(self): class TestItem(Item): fields = {'new': Field(default='X')} - item = TestItem(new=u'New') + item = TestItem(new='New') self.assertSortedEqual(list(item.keys()), ['new']) - self.assertSortedEqual(list(item.values()), [u'New']) + self.assertSortedEqual(list(item.values()), ['New']) def test_metaclass_inheritance(self): class ParentItem(Item): @@ -238,8 +234,8 @@ class ItemTest(unittest.TestCase): name = Field() i = TestItem() - i['name'] = u'John' - self.assertEqual(dict(i), {'name': u'John'}) + i['name'] = 'John' + self.assertEqual(dict(i), {'name': 'John'}) def test_copy(self): class TestItem(Item): @@ -280,14 +276,6 @@ class ItemMetaTest(unittest.TestCase): with mock.patch.object(base, '__new__', new_mock): class MyItem(Item): - if not PY36_PLUS: - # This attribute is an internal attribute in Python 3.6+ - # and must be propagated properly. See - # https://docs.python.org/3.6/reference/datamodel.html#creating-the-class-object - # In <3.6, we add a dummy attribute just to ensure the - # __new__ method propagates it correctly. - __classcell__ = object() - def f(self): # For rationale of this see: # https://github.com/python/cpython/blob/ee1a81b77444c6715cbe610e951c655b6adab88b/Lib/test/test_super.py#L222 @@ -312,7 +300,7 @@ class ItemMetaClassCellRegression(unittest.TestCase): # requirement. When not done properly raises an error: # TypeError: __class__ set to # defining 'MyItem' as - super(MyItem, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) class DictItemTest(unittest.TestCase): @@ -340,16 +328,18 @@ class BaseItemTest(unittest.TestCase): class SubclassedItem(Item): pass - self.assertTrue(isinstance(BaseItem(), BaseItem)) - self.assertTrue(isinstance(SubclassedBaseItem(), BaseItem)) - self.assertTrue(isinstance(Item(), BaseItem)) - self.assertTrue(isinstance(SubclassedItem(), BaseItem)) + with catch_warnings(): + filterwarnings("ignore", category=ScrapyDeprecationWarning) + self.assertTrue(isinstance(BaseItem(), BaseItem)) + self.assertTrue(isinstance(SubclassedBaseItem(), BaseItem)) + self.assertTrue(isinstance(Item(), BaseItem)) + self.assertTrue(isinstance(SubclassedItem(), BaseItem)) - # make sure internal checks using private _BaseItem class succeed - self.assertTrue(isinstance(BaseItem(), _BaseItem)) - self.assertTrue(isinstance(SubclassedBaseItem(), _BaseItem)) - self.assertTrue(isinstance(Item(), _BaseItem)) - self.assertTrue(isinstance(SubclassedItem(), _BaseItem)) + # make sure internal checks using private _BaseItem class succeed + self.assertTrue(isinstance(BaseItem(), _BaseItem)) + self.assertTrue(isinstance(SubclassedBaseItem(), _BaseItem)) + self.assertTrue(isinstance(Item(), _BaseItem)) + self.assertTrue(isinstance(SubclassedItem(), _BaseItem)) def test_deprecation_warning(self): """ diff --git a/tests/test_linkextractors.py b/tests/test_linkextractors.py index 8d4538eed..6f133d77a 100644 --- a/tests/test_linkextractors.py +++ b/tests/test_linkextractors.py @@ -31,31 +31,31 @@ class Base: page4_url = 'http://example.com/page%204.html' self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample3.html', text='sample 3 text'), Link(url='http://example.com/sample3.html#foo', text='sample 3 repetition with fragment'), - Link(url='http://www.google.com/something', text=u''), - Link(url='http://example.com/innertag.html', text=u'inner tag'), - Link(url=page4_url, text=u'href with whitespaces'), + Link(url='http://www.google.com/something', text=''), + Link(url='http://example.com/innertag.html', text='inner tag'), + Link(url=page4_url, text='href with whitespaces'), ]) def test_extract_filter_allow(self): lx = self.extractor_cls(allow=('sample', )) self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample3.html', text='sample 3 text'), Link(url='http://example.com/sample3.html#foo', text='sample 3 repetition with fragment') ]) def test_extract_filter_allow_with_duplicates(self): lx = self.extractor_cls(allow=('sample', ), unique=False) self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), - Link(url='http://example.com/sample3.html', text=u'sample 3 repetition'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample3.html', text='sample 3 text'), + Link(url='http://example.com/sample3.html', text='sample 3 repetition'), Link(url='http://example.com/sample3.html#foo', text='sample 3 repetition with fragment') ]) @@ -63,10 +63,10 @@ class Base: lx = self.extractor_cls(allow=('sample', ), unique=False, canonicalize=True) self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), - Link(url='http://example.com/sample3.html', text=u'sample 3 repetition'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample3.html', text='sample 3 text'), + Link(url='http://example.com/sample3.html', text='sample 3 repetition'), Link(url='http://example.com/sample3.html', text='sample 3 repetition with fragment') ]) @@ -74,22 +74,22 @@ class Base: lx = self.extractor_cls(allow=('sample',), unique=True, canonicalize=True) self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample3.html', text='sample 3 text'), ]) def test_extract_filter_allow_and_deny(self): lx = self.extractor_cls(allow=('sample', ), deny=('3', )) self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), ]) def test_extract_filter_allowed_domains(self): lx = self.extractor_cls(allow_domains=('google.com', )) self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://www.google.com/something', text=u''), + Link(url='http://www.google.com/something', text=''), ]) def test_extraction_using_single_values(self): @@ -97,27 +97,27 @@ class Base: lx = self.extractor_cls(allow='sample') self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample3.html', text='sample 3 text'), Link(url='http://example.com/sample3.html#foo', text='sample 3 repetition with fragment') ]) lx = self.extractor_cls(allow='sample', deny='3') self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), ]) lx = self.extractor_cls(allow_domains='google.com') self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://www.google.com/something', text=u''), + Link(url='http://www.google.com/something', text=''), ]) lx = self.extractor_cls(deny_domains='example.com') self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://www.google.com/something', text=u''), + Link(url='http://www.google.com/something', text=''), ]) def test_nofollow(self): @@ -145,11 +145,11 @@ class Base: lx = self.extractor_cls() self.assertEqual(lx.extract_links(response), [ - Link(url='http://example.org/about.html', text=u'About us'), - Link(url='http://example.org/follow.html', text=u'Follow this link'), - Link(url='http://example.org/nofollow.html', text=u'Dont follow this one', nofollow=True), - Link(url='http://example.org/nofollow2.html', text=u'Choose to follow or not'), - Link(url='http://google.com/something', text=u'External link not to follow', nofollow=True), + Link(url='http://example.org/about.html', text='About us'), + Link(url='http://example.org/follow.html', text='Follow this link'), + Link(url='http://example.org/nofollow.html', text='Dont follow this one', nofollow=True), + Link(url='http://example.org/nofollow2.html', text='Choose to follow or not'), + Link(url='http://google.com/something', text='External link not to follow', nofollow=True), ]) def test_matches(self): @@ -183,8 +183,8 @@ class Base: def test_restrict_xpaths(self): lx = self.extractor_cls(restrict_xpaths=('//div[@id="subwrapper"]', )) self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), ]) def test_restrict_xpaths_encoding(self): @@ -202,14 +202,14 @@ class Base: lx = self.extractor_cls(restrict_xpaths="//div[@class='links']") self.assertEqual(lx.extract_links(response), - [Link(url='http://example.org/about.html', text=u'About us\xa3')]) + [Link(url='http://example.org/about.html', text='About us\xa3')]) def test_restrict_xpaths_with_html_entities(self): html = b'

    text

    ' response = HtmlResponse("http://example.org/somepage/index.html", body=html, encoding='iso8859-15') links = self.extractor_cls(restrict_xpaths='//p').extract_links(response) self.assertEqual(links, - [Link(url='http://example.org/%E2%99%A5/you?c=%A4', text=u'text')]) + [Link(url='http://example.org/%E2%99%A5/you?c=%A4', text='text')]) def test_restrict_xpaths_concat_in_handle_data(self): """html entities cause SGMLParser to call handle_data hook twice""" @@ -217,22 +217,22 @@ class Base: response = HtmlResponse("http://example.org", body=body, encoding='gb18030') lx = self.extractor_cls(restrict_xpaths="//div") self.assertEqual(lx.extract_links(response), - [Link(url='http://example.org/foo', text=u'>\u4eac<\u4e1c', + [Link(url='http://example.org/foo', text='>\u4eac<\u4e1c', fragment='', nofollow=False)]) def test_restrict_css(self): lx = self.extractor_cls(restrict_css=('#subwrapper a',)) self.assertEqual(lx.extract_links(self.response), [ - Link(url='http://example.com/sample2.html', text=u'sample 2') + Link(url='http://example.com/sample2.html', text='sample 2') ]) def test_restrict_css_and_restrict_xpaths_together(self): lx = self.extractor_cls(restrict_xpaths=('//div[@id="subwrapper"]', ), restrict_css=('#subwrapper + a', )) self.assertEqual([link for link in lx.extract_links(self.response)], [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample3.html', text='sample 3 text'), ]) def test_area_tag_with_unicode_present(self): @@ -243,7 +243,7 @@ class Base: lx.extract_links(response) lx.extract_links(response) self.assertEqual(lx.extract_links(response), - [Link(url='http://example.org/foo', text=u'', + [Link(url='http://example.org/foo', text='', fragment='', nofollow=False)]) def test_encoded_url(self): @@ -251,7 +251,7 @@ class Base: response = HtmlResponse("http://known.fm/AC%2FDC/", body=body, encoding='utf8') lx = self.extractor_cls() self.assertEqual(lx.extract_links(response), [ - Link(url='http://known.fm/AC%2FDC/?page=2', text=u'BinB', fragment='', nofollow=False), + Link(url='http://known.fm/AC%2FDC/?page=2', text='BinB', fragment='', nofollow=False), ]) def test_encoded_url_in_restricted_xpath(self): @@ -259,7 +259,7 @@ class Base: response = HtmlResponse("http://known.fm/AC%2FDC/", body=body, encoding='utf8') lx = self.extractor_cls(restrict_xpaths="//div") self.assertEqual(lx.extract_links(response), [ - Link(url='http://known.fm/AC%2FDC/?page=2', text=u'BinB', fragment='', nofollow=False), + Link(url='http://known.fm/AC%2FDC/?page=2', text='BinB', fragment='', nofollow=False), ]) def test_ignored_extensions(self): @@ -268,7 +268,7 @@ class Base: response = HtmlResponse("http://example.org/", body=html) lx = self.extractor_cls() self.assertEqual(lx.extract_links(response), [ - Link(url='http://example.org/page.html', text=u'asd'), + Link(url='http://example.org/page.html', text='asd'), ]) # override denied extensions @@ -308,25 +308,25 @@ class Base: page4_url = 'http://example.com/page%204.html' self.assertEqual(lx.extract_links(self.response), [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample3.html', text='sample 3 text'), Link(url='http://example.com/sample3.html#foo', text='sample 3 repetition with fragment'), - Link(url='http://www.google.com/something', text=u''), - Link(url='http://example.com/innertag.html', text=u'inner tag'), - Link(url=page4_url, text=u'href with whitespaces'), + Link(url='http://www.google.com/something', text=''), + Link(url='http://example.com/innertag.html', text='inner tag'), + Link(url=page4_url, text='href with whitespaces'), ]) lx = self.extractor_cls(attrs=("href", "src"), tags=("a", "area", "img"), deny_extensions=()) self.assertEqual(lx.extract_links(self.response), [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample2.jpg', text=u''), - Link(url='http://example.com/sample3.html', text=u'sample 3 text'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample2.jpg', text=''), + Link(url='http://example.com/sample3.html', text='sample 3 text'), Link(url='http://example.com/sample3.html#foo', text='sample 3 repetition with fragment'), - Link(url='http://www.google.com/something', text=u''), - Link(url='http://example.com/innertag.html', text=u'inner tag'), - Link(url=page4_url, text=u'href with whitespaces'), + Link(url='http://www.google.com/something', text=''), + Link(url='http://example.com/innertag.html', text='inner tag'), + Link(url=page4_url, text='href with whitespaces'), ]) lx = self.extractor_cls(attrs=None) @@ -344,24 +344,24 @@ class Base: lx = self.extractor_cls() self.assertEqual(lx.extract_links(response), [ - Link(url='http://example.com/sample1.html', text=u''), - Link(url='http://example.com/sample2.html', text=u'sample 2'), + Link(url='http://example.com/sample1.html', text=''), + Link(url='http://example.com/sample2.html', text='sample 2'), ]) lx = self.extractor_cls(tags="area") self.assertEqual(lx.extract_links(response), [ - Link(url='http://example.com/sample1.html', text=u''), + Link(url='http://example.com/sample1.html', text=''), ]) lx = self.extractor_cls(tags="a") self.assertEqual(lx.extract_links(response), [ - Link(url='http://example.com/sample2.html', text=u'sample 2'), + Link(url='http://example.com/sample2.html', text='sample 2'), ]) lx = self.extractor_cls(tags=("a", "img"), attrs=("href", "src"), deny_extensions=()) self.assertEqual(lx.extract_links(response), [ - Link(url='http://example.com/sample2.html', text=u'sample 2'), - Link(url='http://example.com/sample2.jpg', text=u''), + Link(url='http://example.com/sample2.html', text='sample 2'), + Link(url='http://example.com/sample2.jpg', text=''), ]) def test_tags_attrs(self): @@ -375,14 +375,14 @@ class Base: lx = self.extractor_cls(tags='div', attrs='data-url') self.assertEqual(lx.extract_links(response), [ - Link(url='http://example.com/get?id=1', text=u'Item 1', fragment='', nofollow=False), - Link(url='http://example.com/get?id=2', text=u'Item 2', fragment='', nofollow=False) + Link(url='http://example.com/get?id=1', text='Item 1', fragment='', nofollow=False), + Link(url='http://example.com/get?id=2', text='Item 2', fragment='', nofollow=False) ]) lx = self.extractor_cls(tags=('div',), attrs=('data-url',)) self.assertEqual(lx.extract_links(response), [ - Link(url='http://example.com/get?id=1', text=u'Item 1', fragment='', nofollow=False), - Link(url='http://example.com/get?id=2', text=u'Item 2', fragment='', nofollow=False) + Link(url='http://example.com/get?id=1', text='Item 1', fragment='', nofollow=False), + Link(url='http://example.com/get?id=2', text='Item 2', fragment='', nofollow=False) ]) def test_xhtml(self): @@ -420,13 +420,13 @@ class Base: self.assertEqual( lx.extract_links(response), [ - Link(url='http://example.com/about.html', text=u'About us', fragment='', nofollow=False), - Link(url='http://example.com/follow.html', text=u'Follow this link', fragment='', nofollow=False), - Link(url='http://example.com/nofollow.html', text=u'Dont follow this one', + Link(url='http://example.com/about.html', text='About us', fragment='', nofollow=False), + Link(url='http://example.com/follow.html', text='Follow this link', fragment='', nofollow=False), + Link(url='http://example.com/nofollow.html', text='Dont follow this one', fragment='', nofollow=True), - Link(url='http://example.com/nofollow2.html', text=u'Choose to follow or not', + Link(url='http://example.com/nofollow2.html', text='Choose to follow or not', fragment='', nofollow=False), - Link(url='http://google.com/something', text=u'External link not to follow', nofollow=True), + Link(url='http://google.com/something', text='External link not to follow', nofollow=True), ] ) @@ -436,13 +436,13 @@ class Base: self.assertEqual( lx.extract_links(response), [ - Link(url='http://example.com/about.html', text=u'About us', fragment='', nofollow=False), - Link(url='http://example.com/follow.html', text=u'Follow this link', fragment='', nofollow=False), - Link(url='http://example.com/nofollow.html', text=u'Dont follow this one', + Link(url='http://example.com/about.html', text='About us', fragment='', nofollow=False), + Link(url='http://example.com/follow.html', text='Follow this link', fragment='', nofollow=False), + Link(url='http://example.com/nofollow.html', text='Dont follow this one', fragment='', nofollow=True), - Link(url='http://example.com/nofollow2.html', text=u'Choose to follow or not', + Link(url='http://example.com/nofollow2.html', text='Choose to follow or not', fragment='', nofollow=False), - Link(url='http://google.com/something', text=u'External link not to follow', nofollow=True), + Link(url='http://google.com/something', text='External link not to follow', nofollow=True), ] ) @@ -455,8 +455,8 @@ class Base: response = HtmlResponse("http://example.org/index.html", body=html) lx = self.extractor_cls() self.assertEqual([link for link in lx.extract_links(response)], [ - Link(url='http://example.org/item1.html', text=u'Item 1', nofollow=False), - Link(url='http://example.org/item3.html', text=u'Item 3', nofollow=False), + Link(url='http://example.org/item1.html', text='Item 1', nofollow=False), + Link(url='http://example.org/item3.html', text='Item 3', nofollow=False), ]) def test_ftp_links(self): @@ -467,7 +467,7 @@ class Base: response = HtmlResponse("http://www.example.com/index.html", body=body, encoding='utf8') lx = self.extractor_cls() self.assertEqual(lx.extract_links(response), [ - Link(url='ftp://www.external.com/', text=u'An Item', fragment='', nofollow=False), + Link(url='ftp://www.external.com/', text='An Item', fragment='', nofollow=False), ]) def test_pickle_extractor(self): @@ -487,8 +487,8 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): response = HtmlResponse("http://example.org/index.html", body=html) lx = self.extractor_cls() self.assertEqual([link for link in lx.extract_links(response)], [ - Link(url='http://example.org/item1.html', text=u'Item 1', nofollow=False), - Link(url='http://example.org/item3.html', text=u'Item 3', nofollow=False), + Link(url='http://example.org/item1.html', text='Item 1', nofollow=False), + Link(url='http://example.org/item3.html', text='Item 3', nofollow=False), ]) def test_link_restrict_text(self): @@ -501,22 +501,22 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): # Simple text inclusion test lx = self.extractor_cls(restrict_text='dog') self.assertEqual([link for link in lx.extract_links(response)], [ - Link(url='http://example.org/item2.html', text=u'Pic of a dog', nofollow=False), + Link(url='http://example.org/item2.html', text='Pic of a dog', nofollow=False), ]) # Unique regex test lx = self.extractor_cls(restrict_text=r'of.*dog') self.assertEqual([link for link in lx.extract_links(response)], [ - Link(url='http://example.org/item2.html', text=u'Pic of a dog', nofollow=False), + Link(url='http://example.org/item2.html', text='Pic of a dog', nofollow=False), ]) # Multiple regex test lx = self.extractor_cls(restrict_text=[r'of.*dog', r'of.*cat']) self.assertEqual([link for link in lx.extract_links(response)], [ - Link(url='http://example.org/item1.html', text=u'Pic of a cat', nofollow=False), - Link(url='http://example.org/item2.html', text=u'Pic of a dog', nofollow=False), + Link(url='http://example.org/item1.html', text='Pic of a cat', nofollow=False), + Link(url='http://example.org/item2.html', text='Pic of a dog', nofollow=False), ]) def test_restrict_xpaths_with_html_entities(self): - super(LxmlLinkExtractorTestCase, self).test_restrict_xpaths_with_html_entities() + super().test_restrict_xpaths_with_html_entities() def test_filteringlinkextractor_deprecation_warning(self): """Make sure the FilteringLinkExtractor deprecation warning is not diff --git a/tests/test_loader.py b/tests/test_loader.py index f14714c75..b0bc82f4e 100644 --- a/tests/test_loader.py +++ b/tests/test_loader.py @@ -1,14 +1,22 @@ -from functools import partial import unittest +import attr +from itemadapter import ItemAdapter +from itemloaders.processors import Compose, Identity, MapCompose, TakeFirst + from scrapy.http import HtmlResponse from scrapy.item import Item, Field from scrapy.loader import ItemLoader -from scrapy.loader.processors import (Compose, Identity, Join, - MapCompose, SelectJmes, TakeFirst) from scrapy.selector import Selector +try: + from dataclasses import make_dataclass, field as dataclass_field +except ImportError: + make_dataclass = None + dataclass_field = None + + # test items class NameItem(Item): name = Field() @@ -28,6 +36,11 @@ class TestNestedItem(Item): image = Field() +@attr.s +class AttrsNameItem: + name = attr.ib(default="") + + # test item loaders class NameItemLoader(ItemLoader): default_item_class = TestItem @@ -54,406 +67,25 @@ def processor_with_args(value, other=None, loader_context=None): class BasicItemLoaderTest(unittest.TestCase): + def test_add_value_on_unknown_field(self): + il = TestItemLoader() + self.assertRaises(KeyError, il.add_value, 'wrong_field', ['lala', 'lolo']) + def test_load_item_using_default_loader(self): i = TestItem() - i['summary'] = u'lala' + i['summary'] = 'lala' il = ItemLoader(item=i) - il.add_value('name', u'marta') + il.add_value('name', 'marta') item = il.load_item() assert item is i - self.assertEqual(item['summary'], [u'lala']) - self.assertEqual(item['name'], [u'marta']) + self.assertEqual(item['summary'], ['lala']) + self.assertEqual(item['name'], ['marta']) def test_load_item_using_custom_loader(self): il = TestItemLoader() - il.add_value('name', u'marta') + il.add_value('name', 'marta') item = il.load_item() - self.assertEqual(item['name'], [u'Marta']) - - def test_load_item_ignore_none_field_values(self): - def validate_sku(value): - # Let's assume a SKU is only digits. - if value.isdigit(): - return value - - class MyLoader(ItemLoader): - name_out = Compose(lambda vs: vs[0]) # take first which allows empty values - price_out = Compose(TakeFirst(), float) - sku_out = Compose(TakeFirst(), validate_sku) - - valid_fragment = u'SKU: 1234' - invalid_fragment = u'SKU: not available' - sku_re = 'SKU: (.+)' - - il = MyLoader(item={}) - # Should not return "sku: None". - il.add_value('sku', [invalid_fragment], re=sku_re) - # Should not ignore empty values. - il.add_value('name', u'') - il.add_value('price', [u'0']) - self.assertEqual(il.load_item(), { - 'name': u'', - 'price': 0.0, - }) - - il.replace_value('sku', [valid_fragment], re=sku_re) - self.assertEqual(il.load_item()['sku'], u'1234') - - def test_self_referencing_loader(self): - class MyLoader(ItemLoader): - url_out = TakeFirst() - - def img_url_out(self, values): - return (self.get_output_value('url') or '') + values[0] - - il = MyLoader(item={}) - il.add_value('url', 'http://example.com/') - il.add_value('img_url', '1234.png') - self.assertEqual(il.load_item(), { - 'url': 'http://example.com/', - 'img_url': 'http://example.com/1234.png', - }) - - il = MyLoader(item={}) - il.add_value('img_url', '1234.png') - self.assertEqual(il.load_item(), { - 'img_url': '1234.png', - }) - - def test_add_value(self): - il = TestItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_collected_values('name'), [u'Marta']) - self.assertEqual(il.get_output_value('name'), [u'Marta']) - il.add_value('name', u'pepe') - self.assertEqual(il.get_collected_values('name'), [u'Marta', u'Pepe']) - self.assertEqual(il.get_output_value('name'), [u'Marta', u'Pepe']) - - # test add object value - il.add_value('summary', {'key': 1}) - self.assertEqual(il.get_collected_values('summary'), [{'key': 1}]) - - il.add_value(None, u'Jim', lambda x: {'name': x}) - self.assertEqual(il.get_collected_values('name'), [u'Marta', u'Pepe', u'Jim']) - - def test_add_zero(self): - il = NameItemLoader() - il.add_value('name', 0) - self.assertEqual(il.get_collected_values('name'), [0]) - - def test_replace_value(self): - il = TestItemLoader() - il.replace_value('name', u'marta') - self.assertEqual(il.get_collected_values('name'), [u'Marta']) - self.assertEqual(il.get_output_value('name'), [u'Marta']) - il.replace_value('name', u'pepe') - self.assertEqual(il.get_collected_values('name'), [u'Pepe']) - self.assertEqual(il.get_output_value('name'), [u'Pepe']) - - il.replace_value(None, u'Jim', lambda x: {'name': x}) - self.assertEqual(il.get_collected_values('name'), [u'Jim']) - - def test_get_value(self): - il = NameItemLoader() - self.assertEqual(u'FOO', il.get_value([u'foo', u'bar'], TakeFirst(), str.upper)) - self.assertEqual([u'foo', u'bar'], il.get_value([u'name:foo', u'name:bar'], re=u'name:(.*)$')) - self.assertEqual(u'foo', il.get_value([u'name:foo', u'name:bar'], TakeFirst(), re=u'name:(.*)$')) - - il.add_value('name', [u'name:foo', u'name:bar'], TakeFirst(), re=u'name:(.*)$') - self.assertEqual([u'foo'], il.get_collected_values('name')) - il.replace_value('name', u'name:bar', re=u'name:(.*)$') - self.assertEqual([u'bar'], il.get_collected_values('name')) - - def test_iter_on_input_processor_input(self): - class NameFirstItemLoader(NameItemLoader): - name_in = TakeFirst() - - il = NameFirstItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_collected_values('name'), [u'marta']) - il = NameFirstItemLoader() - il.add_value('name', [u'marta', u'jose']) - self.assertEqual(il.get_collected_values('name'), [u'marta']) - - il = NameFirstItemLoader() - il.replace_value('name', u'marta') - self.assertEqual(il.get_collected_values('name'), [u'marta']) - il = NameFirstItemLoader() - il.replace_value('name', [u'marta', u'jose']) - self.assertEqual(il.get_collected_values('name'), [u'marta']) - - il = NameFirstItemLoader() - il.add_value('name', u'marta') - il.add_value('name', [u'jose', u'pedro']) - self.assertEqual(il.get_collected_values('name'), [u'marta', u'jose']) - - def test_map_compose_filter(self): - def filter_world(x): - return None if x == 'world' else x - - proc = MapCompose(filter_world, str.upper) - self.assertEqual(proc(['hello', 'world', 'this', 'is', 'scrapy']), - ['HELLO', 'THIS', 'IS', 'SCRAPY']) - - def test_map_compose_filter_multil(self): - class TestItemLoader(NameItemLoader): - name_in = MapCompose(lambda v: v.title(), lambda v: v[:-1]) - - il = TestItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'Mart']) - item = il.load_item() - self.assertEqual(item['name'], [u'Mart']) - - def test_default_input_processor(self): - il = DefaultedItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'mart']) - - def test_inherited_default_input_processor(self): - class InheritDefaultedItemLoader(DefaultedItemLoader): - pass - - il = InheritDefaultedItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'mart']) - - def test_input_processor_inheritance(self): - class ChildItemLoader(TestItemLoader): - url_in = MapCompose(lambda v: v.lower()) - - il = ChildItemLoader() - il.add_value('url', u'HTTP://scrapy.ORG') - self.assertEqual(il.get_output_value('url'), [u'http://scrapy.org']) - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'Marta']) - - class ChildChildItemLoader(ChildItemLoader): - url_in = MapCompose(lambda v: v.upper()) - summary_in = MapCompose(lambda v: v) - - il = ChildChildItemLoader() - il.add_value('url', u'http://scrapy.org') - self.assertEqual(il.get_output_value('url'), [u'HTTP://SCRAPY.ORG']) - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'Marta']) - - def test_empty_map_compose(self): - class IdentityDefaultedItemLoader(DefaultedItemLoader): - name_in = MapCompose() - - il = IdentityDefaultedItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'marta']) - - def test_identity_input_processor(self): - class IdentityDefaultedItemLoader(DefaultedItemLoader): - name_in = Identity() - - il = IdentityDefaultedItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'marta']) - - def test_extend_custom_input_processors(self): - class ChildItemLoader(TestItemLoader): - name_in = MapCompose(TestItemLoader.name_in, str.swapcase) - - il = ChildItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'mARTA']) - - def test_extend_default_input_processors(self): - class ChildDefaultedItemLoader(DefaultedItemLoader): - name_in = MapCompose(DefaultedItemLoader.default_input_processor, str.swapcase) - - il = ChildDefaultedItemLoader() - il.add_value('name', u'marta') - self.assertEqual(il.get_output_value('name'), [u'MART']) - - def test_output_processor_using_function(self): - il = TestItemLoader() - il.add_value('name', [u'mar', u'ta']) - self.assertEqual(il.get_output_value('name'), [u'Mar', u'Ta']) - - class TakeFirstItemLoader(TestItemLoader): - name_out = u" ".join - - il = TakeFirstItemLoader() - il.add_value('name', [u'mar', u'ta']) - self.assertEqual(il.get_output_value('name'), u'Mar Ta') - - def test_output_processor_error(self): - class TestItemLoader(ItemLoader): - default_item_class = TestItem - name_out = MapCompose(float) - - il = TestItemLoader() - il.add_value('name', [u'$10']) - try: - float(u'$10') - except Exception as e: - expected_exc_str = str(e) - - exc = None - try: - il.load_item() - except Exception as e: - exc = e - assert isinstance(exc, ValueError) - s = str(exc) - assert 'name' in s, s - assert '$10' in s, s - assert 'ValueError' in s, s - assert expected_exc_str in s, s - - def test_output_processor_using_classes(self): - il = TestItemLoader() - il.add_value('name', [u'mar', u'ta']) - self.assertEqual(il.get_output_value('name'), [u'Mar', u'Ta']) - - class TakeFirstItemLoader(TestItemLoader): - name_out = Join() - - il = TakeFirstItemLoader() - il.add_value('name', [u'mar', u'ta']) - self.assertEqual(il.get_output_value('name'), u'Mar Ta') - - class TakeFirstItemLoader(TestItemLoader): - name_out = Join("
    ") - - il = TakeFirstItemLoader() - il.add_value('name', [u'mar', u'ta']) - self.assertEqual(il.get_output_value('name'), u'Mar
    Ta') - - def test_default_output_processor(self): - il = TestItemLoader() - il.add_value('name', [u'mar', u'ta']) - self.assertEqual(il.get_output_value('name'), [u'Mar', u'Ta']) - - class LalaItemLoader(TestItemLoader): - default_output_processor = Identity() - - il = LalaItemLoader() - il.add_value('name', [u'mar', u'ta']) - self.assertEqual(il.get_output_value('name'), [u'Mar', u'Ta']) - - def test_loader_context_on_declaration(self): - class ChildItemLoader(TestItemLoader): - url_in = MapCompose(processor_with_args, key=u'val') - - il = ChildItemLoader() - il.add_value('url', u'text') - self.assertEqual(il.get_output_value('url'), ['val']) - il.replace_value('url', u'text2') - self.assertEqual(il.get_output_value('url'), ['val']) - - def test_loader_context_on_instantiation(self): - class ChildItemLoader(TestItemLoader): - url_in = MapCompose(processor_with_args) - - il = ChildItemLoader(key=u'val') - il.add_value('url', u'text') - self.assertEqual(il.get_output_value('url'), ['val']) - il.replace_value('url', u'text2') - self.assertEqual(il.get_output_value('url'), ['val']) - - def test_loader_context_on_assign(self): - class ChildItemLoader(TestItemLoader): - url_in = MapCompose(processor_with_args) - - il = ChildItemLoader() - il.context['key'] = u'val' - il.add_value('url', u'text') - self.assertEqual(il.get_output_value('url'), ['val']) - il.replace_value('url', u'text2') - self.assertEqual(il.get_output_value('url'), ['val']) - - def test_item_passed_to_input_processor_functions(self): - def processor(value, loader_context): - return loader_context['item']['name'] - - class ChildItemLoader(TestItemLoader): - url_in = MapCompose(processor) - - it = TestItem(name='marta') - il = ChildItemLoader(item=it) - il.add_value('url', u'text') - self.assertEqual(il.get_output_value('url'), ['marta']) - il.replace_value('url', u'text2') - self.assertEqual(il.get_output_value('url'), ['marta']) - - def test_add_value_on_unknown_field(self): - il = TestItemLoader() - self.assertRaises(KeyError, il.add_value, 'wrong_field', [u'lala', u'lolo']) - - def test_compose_processor(self): - class TestItemLoader(NameItemLoader): - name_out = Compose(lambda v: v[0], lambda v: v.title(), lambda v: v[:-1]) - - il = TestItemLoader() - il.add_value('name', [u'marta', u'other']) - self.assertEqual(il.get_output_value('name'), u'Mart') - item = il.load_item() - self.assertEqual(item['name'], u'Mart') - - def test_partial_processor(self): - def join(values, sep=None, loader_context=None, ignored=None): - if sep is not None: - return sep.join(values) - elif loader_context and 'sep' in loader_context: - return loader_context['sep'].join(values) - else: - return ''.join(values) - - class TestItemLoader(NameItemLoader): - name_out = Compose(partial(join, sep='+')) - url_out = Compose(partial(join, loader_context={'sep': '.'})) - summary_out = Compose(partial(join, ignored='foo')) - - il = TestItemLoader() - il.add_value('name', [u'rabbit', u'hole']) - il.add_value('url', [u'rabbit', u'hole']) - il.add_value('summary', [u'rabbit', u'hole']) - item = il.load_item() - self.assertEqual(item['name'], u'rabbit+hole') - self.assertEqual(item['url'], u'rabbit.hole') - self.assertEqual(item['summary'], u'rabbithole') - - def test_error_input_processor(self): - class TestItem(Item): - name = Field() - - class TestItemLoader(ItemLoader): - default_item_class = TestItem - name_in = MapCompose(float) - - il = TestItemLoader() - self.assertRaises(ValueError, il.add_value, 'name', - [u'marta', u'other']) - - def test_error_output_processor(self): - class TestItem(Item): - name = Field() - - class TestItemLoader(ItemLoader): - default_item_class = TestItem - name_out = Compose(Join(), float) - - il = TestItemLoader() - il.add_value('name', u'marta') - with self.assertRaises(ValueError): - il.load_item() - - def test_error_processor_as_argument(self): - class TestItem(Item): - name = Field() - - class TestItemLoader(ItemLoader): - default_item_class = TestItem - - il = TestItemLoader() - self.assertRaises(ValueError, il.add_value, 'name', - [u'marta', u'other'], Compose(float)) + self.assertEqual(item['name'], ['Marta']) class InitializationTestMixin: @@ -466,7 +98,7 @@ class InitializationTestMixin: il = ItemLoader(item=input_item) loaded_item = il.load_item() self.assertIsInstance(loaded_item, self.item_class) - self.assertEqual(dict(loaded_item), {'name': ['foo']}) + self.assertEqual(ItemAdapter(loaded_item).asdict(), {'name': ['foo']}) def test_keep_list(self): """Loaded item should contain values from the initial item""" @@ -474,7 +106,7 @@ class InitializationTestMixin: il = ItemLoader(item=input_item) loaded_item = il.load_item() self.assertIsInstance(loaded_item, self.item_class) - self.assertEqual(dict(loaded_item), {'name': ['foo', 'bar']}) + self.assertEqual(ItemAdapter(loaded_item).asdict(), {'name': ['foo', 'bar']}) def test_add_value_singlevalue_singlevalue(self): """Values added after initialization should be appended""" @@ -483,7 +115,7 @@ class InitializationTestMixin: il.add_value('name', 'bar') loaded_item = il.load_item() self.assertIsInstance(loaded_item, self.item_class) - self.assertEqual(dict(loaded_item), {'name': ['foo', 'bar']}) + self.assertEqual(ItemAdapter(loaded_item).asdict(), {'name': ['foo', 'bar']}) def test_add_value_singlevalue_list(self): """Values added after initialization should be appended""" @@ -492,7 +124,7 @@ class InitializationTestMixin: il.add_value('name', ['item', 'loader']) loaded_item = il.load_item() self.assertIsInstance(loaded_item, self.item_class) - self.assertEqual(dict(loaded_item), {'name': ['foo', 'item', 'loader']}) + self.assertEqual(ItemAdapter(loaded_item).asdict(), {'name': ['foo', 'item', 'loader']}) def test_add_value_list_singlevalue(self): """Values added after initialization should be appended""" @@ -501,7 +133,7 @@ class InitializationTestMixin: il.add_value('name', 'qwerty') loaded_item = il.load_item() self.assertIsInstance(loaded_item, self.item_class) - self.assertEqual(dict(loaded_item), {'name': ['foo', 'bar', 'qwerty']}) + self.assertEqual(ItemAdapter(loaded_item).asdict(), {'name': ['foo', 'bar', 'qwerty']}) def test_add_value_list_list(self): """Values added after initialization should be appended""" @@ -510,7 +142,7 @@ class InitializationTestMixin: il.add_value('name', ['item', 'loader']) loaded_item = il.load_item() self.assertIsInstance(loaded_item, self.item_class) - self.assertEqual(dict(loaded_item), {'name': ['foo', 'bar', 'item', 'loader']}) + self.assertEqual(ItemAdapter(loaded_item).asdict(), {'name': ['foo', 'bar', 'item', 'loader']}) def test_get_output_value_singlevalue(self): """Getting output value must not remove value from item""" @@ -519,7 +151,7 @@ class InitializationTestMixin: self.assertEqual(il.get_output_value('name'), ['foo']) loaded_item = il.load_item() self.assertIsInstance(loaded_item, self.item_class) - self.assertEqual(loaded_item, dict({'name': ['foo']})) + self.assertEqual(ItemAdapter(loaded_item).asdict(), dict({'name': ['foo']})) def test_get_output_value_list(self): """Getting output value must not remove value from item""" @@ -528,7 +160,7 @@ class InitializationTestMixin: self.assertEqual(il.get_output_value('name'), ['foo', 'bar']) loaded_item = il.load_item() self.assertIsInstance(loaded_item, self.item_class) - self.assertEqual(loaded_item, dict({'name': ['foo', 'bar']})) + self.assertEqual(ItemAdapter(loaded_item).asdict(), dict({'name': ['foo', 'bar']})) def test_values_single(self): """Values from initial item must be added to loader._values""" @@ -551,46 +183,27 @@ class InitializationFromItemTest(InitializationTestMixin, unittest.TestCase): item_class = NameItem +class InitializationFromAttrsItemTest(InitializationTestMixin, unittest.TestCase): + item_class = AttrsNameItem + + +@unittest.skipIf(not make_dataclass, "dataclasses module is not available") +class InitializationFromDataClassTest(InitializationTestMixin, unittest.TestCase): + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + if make_dataclass: + self.item_class = make_dataclass( + "TestDataClass", + [("name", list, dataclass_field(default_factory=list))], + ) + + class BaseNoInputReprocessingLoader(ItemLoader): title_in = MapCompose(str.upper) title_out = TakeFirst() -class NoInputReprocessingDictLoader(BaseNoInputReprocessingLoader): - default_item_class = dict - - -class NoInputReprocessingFromDictTest(unittest.TestCase): - """ - Loaders initialized from loaded items must not reprocess fields (dict instances) - """ - def test_avoid_reprocessing_with_initial_values_single(self): - il = NoInputReprocessingDictLoader(item=dict(title='foo')) - il_loaded = il.load_item() - self.assertEqual(il_loaded, dict(title='foo')) - self.assertEqual(NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title='foo')) - - def test_avoid_reprocessing_with_initial_values_list(self): - il = NoInputReprocessingDictLoader(item=dict(title=['foo', 'bar'])) - il_loaded = il.load_item() - self.assertEqual(il_loaded, dict(title='foo')) - self.assertEqual(NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title='foo')) - - def test_avoid_reprocessing_without_initial_values_single(self): - il = NoInputReprocessingDictLoader() - il.add_value('title', 'foo') - il_loaded = il.load_item() - self.assertEqual(il_loaded, dict(title='FOO')) - self.assertEqual(NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title='FOO')) - - def test_avoid_reprocessing_without_initial_values_list(self): - il = NoInputReprocessingDictLoader() - il.add_value('title', ['foo', 'bar']) - il_loaded = il.load_item() - self.assertEqual(il_loaded, dict(title='FOO')) - self.assertEqual(NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title='FOO')) - - class NoInputReprocessingItem(Item): title = Field() @@ -630,25 +243,6 @@ class NoInputReprocessingFromItemTest(unittest.TestCase): self.assertEqual(NoInputReprocessingItemLoader(item=il_loaded).load_item(), {'title': 'FOO'}) -class TestOutputProcessorDict(unittest.TestCase): - def test_output_processor(self): - - class TempDict(dict): - def __init__(self, *args, **kwargs): - super(TempDict, self).__init__(self, *args, **kwargs) - self.setdefault('temp', 0.3) - - class TempLoader(ItemLoader): - default_item_class = TempDict - default_input_processor = Identity() - default_output_processor = Compose(TakeFirst()) - - loader = TempLoader() - item = loader.load_item() - self.assertIsInstance(item, TempDict) - self.assertEqual(dict(item), {'temp': 0.3}) - - class TestOutputProcessorItem(unittest.TestCase): def test_output_processor(self): @@ -656,7 +250,7 @@ class TestOutputProcessorItem(unittest.TestCase): temp = Field() def __init__(self, *args, **kwargs): - super(TempItem, self).__init__(self, *args, **kwargs) + super().__init__(self, *args, **kwargs) self.setdefault('temp', 0.3) class TempLoader(ItemLoader): @@ -670,49 +264,6 @@ class TestOutputProcessorItem(unittest.TestCase): self.assertEqual(dict(item), {'temp': 0.3}) -class ProcessorsTest(unittest.TestCase): - - def test_take_first(self): - proc = TakeFirst() - self.assertEqual(proc([None, '', 'hello', 'world']), 'hello') - self.assertEqual(proc([None, '', 0, 'hello', 'world']), 0) - - def test_identity(self): - proc = Identity() - self.assertEqual(proc([None, '', 'hello', 'world']), - [None, '', 'hello', 'world']) - - def test_join(self): - proc = Join() - self.assertRaises(TypeError, proc, [None, '', 'hello', 'world']) - self.assertEqual(proc(['', 'hello', 'world']), u' hello world') - self.assertEqual(proc(['hello', 'world']), u'hello world') - self.assertIsInstance(proc(['hello', 'world']), str) - - def test_compose(self): - proc = Compose(lambda v: v[0], str.upper) - self.assertEqual(proc(['hello', 'world']), 'HELLO') - proc = Compose(str.upper) - self.assertEqual(proc(None), None) - proc = Compose(str.upper, stop_on_none=False) - self.assertRaises(ValueError, proc, None) - proc = Compose(str.upper, lambda x: x + 1) - self.assertRaises(ValueError, proc, 'hello') - - def test_mapcompose(self): - def filter_world(x): - return None if x == 'world' else x - proc = MapCompose(filter_world, str.upper) - self.assertEqual(proc([u'hello', u'world', u'this', u'is', u'scrapy']), - [u'HELLO', u'THIS', u'IS', u'SCRAPY']) - proc = MapCompose(filter_world, str.upper) - self.assertEqual(proc(None), []) - proc = MapCompose(filter_world, str.upper) - self.assertRaises(ValueError, proc, [1]) - proc = MapCompose(filter_world, lambda x: x + 1) - self.assertRaises(ValueError, proc, 'hello') - - class SelectortemLoaderTest(unittest.TestCase): response = HtmlResponse(url="", encoding='utf-8', body=b""" @@ -739,137 +290,137 @@ class SelectortemLoaderTest(unittest.TestCase): self.assertRaises(RuntimeError, l.get_css, '#name::text') def test_init_method_with_selector(self): - sel = Selector(text=u"
    marta
    ") + sel = Selector(text="
    marta
    ") l = TestItemLoader(selector=sel) self.assertIs(l.selector, sel) l.add_xpath('name', '//div/text()') - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) def test_init_method_with_selector_css(self): - sel = Selector(text=u"
    marta
    ") + sel = Selector(text="
    marta
    ") l = TestItemLoader(selector=sel) self.assertIs(l.selector, sel) l.add_css('name', 'div::text') - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) def test_init_method_with_response(self): l = TestItemLoader(response=self.response) self.assertTrue(l.selector) l.add_xpath('name', '//div/text()') - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) def test_init_method_with_response_css(self): l = TestItemLoader(response=self.response) self.assertTrue(l.selector) l.add_css('name', 'div::text') - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) l.add_css('url', 'a::attr(href)') - self.assertEqual(l.get_output_value('url'), [u'http://www.scrapy.org']) + self.assertEqual(l.get_output_value('url'), ['http://www.scrapy.org']) # combining/accumulating CSS selectors and XPath expressions l.add_xpath('name', '//div/text()') - self.assertEqual(l.get_output_value('name'), [u'Marta', u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta', 'Marta']) l.add_xpath('url', '//img/@src') - self.assertEqual(l.get_output_value('url'), [u'http://www.scrapy.org', u'/images/logo.png']) + self.assertEqual(l.get_output_value('url'), ['http://www.scrapy.org', '/images/logo.png']) def test_add_xpath_re(self): l = TestItemLoader(response=self.response) l.add_xpath('name', '//div/text()', re='ma') - self.assertEqual(l.get_output_value('name'), [u'Ma']) + self.assertEqual(l.get_output_value('name'), ['Ma']) def test_replace_xpath(self): l = TestItemLoader(response=self.response) self.assertTrue(l.selector) l.add_xpath('name', '//div/text()') - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) l.replace_xpath('name', '//p/text()') - self.assertEqual(l.get_output_value('name'), [u'Paragraph']) + self.assertEqual(l.get_output_value('name'), ['Paragraph']) l.replace_xpath('name', ['//p/text()', '//div/text()']) - self.assertEqual(l.get_output_value('name'), [u'Paragraph', 'Marta']) + self.assertEqual(l.get_output_value('name'), ['Paragraph', 'Marta']) def test_get_xpath(self): l = TestItemLoader(response=self.response) - self.assertEqual(l.get_xpath('//p/text()'), [u'paragraph']) - self.assertEqual(l.get_xpath('//p/text()', TakeFirst()), u'paragraph') - self.assertEqual(l.get_xpath('//p/text()', TakeFirst(), re='pa'), u'pa') + self.assertEqual(l.get_xpath('//p/text()'), ['paragraph']) + self.assertEqual(l.get_xpath('//p/text()', TakeFirst()), 'paragraph') + self.assertEqual(l.get_xpath('//p/text()', TakeFirst(), re='pa'), 'pa') - self.assertEqual(l.get_xpath(['//p/text()', '//div/text()']), [u'paragraph', 'marta']) + self.assertEqual(l.get_xpath(['//p/text()', '//div/text()']), ['paragraph', 'marta']) def test_replace_xpath_multi_fields(self): l = TestItemLoader(response=self.response) l.add_xpath(None, '//div/text()', TakeFirst(), lambda x: {'name': x}) - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) l.replace_xpath(None, '//p/text()', TakeFirst(), lambda x: {'name': x}) - self.assertEqual(l.get_output_value('name'), [u'Paragraph']) + self.assertEqual(l.get_output_value('name'), ['Paragraph']) def test_replace_xpath_re(self): l = TestItemLoader(response=self.response) self.assertTrue(l.selector) l.add_xpath('name', '//div/text()') - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) l.replace_xpath('name', '//div/text()', re='ma') - self.assertEqual(l.get_output_value('name'), [u'Ma']) + self.assertEqual(l.get_output_value('name'), ['Ma']) def test_add_css_re(self): l = TestItemLoader(response=self.response) l.add_css('name', 'div::text', re='ma') - self.assertEqual(l.get_output_value('name'), [u'Ma']) + self.assertEqual(l.get_output_value('name'), ['Ma']) l.add_css('url', 'a::attr(href)', re='http://(.+)') - self.assertEqual(l.get_output_value('url'), [u'www.scrapy.org']) + self.assertEqual(l.get_output_value('url'), ['www.scrapy.org']) def test_replace_css(self): l = TestItemLoader(response=self.response) self.assertTrue(l.selector) l.add_css('name', 'div::text') - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) l.replace_css('name', 'p::text') - self.assertEqual(l.get_output_value('name'), [u'Paragraph']) + self.assertEqual(l.get_output_value('name'), ['Paragraph']) l.replace_css('name', ['p::text', 'div::text']) - self.assertEqual(l.get_output_value('name'), [u'Paragraph', 'Marta']) + self.assertEqual(l.get_output_value('name'), ['Paragraph', 'Marta']) l.add_css('url', 'a::attr(href)', re='http://(.+)') - self.assertEqual(l.get_output_value('url'), [u'www.scrapy.org']) + self.assertEqual(l.get_output_value('url'), ['www.scrapy.org']) l.replace_css('url', 'img::attr(src)') - self.assertEqual(l.get_output_value('url'), [u'/images/logo.png']) + self.assertEqual(l.get_output_value('url'), ['/images/logo.png']) def test_get_css(self): l = TestItemLoader(response=self.response) - self.assertEqual(l.get_css('p::text'), [u'paragraph']) - self.assertEqual(l.get_css('p::text', TakeFirst()), u'paragraph') - self.assertEqual(l.get_css('p::text', TakeFirst(), re='pa'), u'pa') + self.assertEqual(l.get_css('p::text'), ['paragraph']) + self.assertEqual(l.get_css('p::text', TakeFirst()), 'paragraph') + self.assertEqual(l.get_css('p::text', TakeFirst(), re='pa'), 'pa') - self.assertEqual(l.get_css(['p::text', 'div::text']), [u'paragraph', 'marta']) + self.assertEqual(l.get_css(['p::text', 'div::text']), ['paragraph', 'marta']) self.assertEqual(l.get_css(['a::attr(href)', 'img::attr(src)']), - [u'http://www.scrapy.org', u'/images/logo.png']) + ['http://www.scrapy.org', '/images/logo.png']) def test_replace_css_multi_fields(self): l = TestItemLoader(response=self.response) l.add_css(None, 'div::text', TakeFirst(), lambda x: {'name': x}) - self.assertEqual(l.get_output_value('name'), [u'Marta']) + self.assertEqual(l.get_output_value('name'), ['Marta']) l.replace_css(None, 'p::text', TakeFirst(), lambda x: {'name': x}) - self.assertEqual(l.get_output_value('name'), [u'Paragraph']) + self.assertEqual(l.get_output_value('name'), ['Paragraph']) l.add_css(None, 'a::attr(href)', TakeFirst(), lambda x: {'url': x}) - self.assertEqual(l.get_output_value('url'), [u'http://www.scrapy.org']) + self.assertEqual(l.get_output_value('url'), ['http://www.scrapy.org']) l.replace_css(None, 'img::attr(src)', TakeFirst(), lambda x: {'url': x}) - self.assertEqual(l.get_output_value('url'), [u'/images/logo.png']) + self.assertEqual(l.get_output_value('url'), ['/images/logo.png']) def test_replace_css_re(self): l = TestItemLoader(response=self.response) self.assertTrue(l.selector) l.add_css('url', 'a::attr(href)') - self.assertEqual(l.get_output_value('url'), [u'http://www.scrapy.org']) + self.assertEqual(l.get_output_value('url'), ['http://www.scrapy.org']) l.replace_css('url', 'a::attr(href)', re=r'http://www\.(.+)') - self.assertEqual(l.get_output_value('url'), [u'scrapy.org']) + self.assertEqual(l.get_output_value('url'), ['scrapy.org']) class SubselectorLoaderTest(unittest.TestCase): @@ -890,14 +441,15 @@ class SubselectorLoaderTest(unittest.TestCase): def test_nested_xpath(self): l = NestedItemLoader(response=self.response) + nl = l.nested_xpath("//header") nl.add_xpath('name', 'div/text()') nl.add_css('name_div', '#id') nl.add_value('name_value', nl.selector.xpath('div[@id = "id"]/text()').getall()) - self.assertEqual(l.get_output_value('name'), [u'marta']) - self.assertEqual(l.get_output_value('name_div'), [u'
    marta
    ']) - self.assertEqual(l.get_output_value('name_value'), [u'marta']) + self.assertEqual(l.get_output_value('name'), ['marta']) + self.assertEqual(l.get_output_value('name_div'), ['
    marta
    ']) + self.assertEqual(l.get_output_value('name_value'), ['marta']) self.assertEqual(l.get_output_value('name'), nl.get_output_value('name')) self.assertEqual(l.get_output_value('name_div'), nl.get_output_value('name_div')) @@ -910,9 +462,9 @@ class SubselectorLoaderTest(unittest.TestCase): nl.add_css('name_div', '#id') nl.add_value('name_value', nl.selector.xpath('div[@id = "id"]/text()').getall()) - self.assertEqual(l.get_output_value('name'), [u'marta']) - self.assertEqual(l.get_output_value('name_div'), [u'
    marta
    ']) - self.assertEqual(l.get_output_value('name_value'), [u'marta']) + self.assertEqual(l.get_output_value('name'), ['marta']) + self.assertEqual(l.get_output_value('name_div'), ['
    marta
    ']) + self.assertEqual(l.get_output_value('name_value'), ['marta']) self.assertEqual(l.get_output_value('name'), nl.get_output_value('name')) self.assertEqual(l.get_output_value('name_div'), nl.get_output_value('name_div')) @@ -924,11 +476,11 @@ class SubselectorLoaderTest(unittest.TestCase): nl2 = nl1.nested_xpath('a') l.add_xpath('url', '//footer/a/@href') - self.assertEqual(l.get_output_value('url'), [u'http://www.scrapy.org']) + self.assertEqual(l.get_output_value('url'), ['http://www.scrapy.org']) nl1.replace_xpath('url', 'img/@src') - self.assertEqual(l.get_output_value('url'), [u'/images/logo.png']) + self.assertEqual(l.get_output_value('url'), ['/images/logo.png']) nl2.replace_xpath('url', '@href') - self.assertEqual(l.get_output_value('url'), [u'http://www.scrapy.org']) + self.assertEqual(l.get_output_value('url'), ['http://www.scrapy.org']) def test_nested_ordering(self): l = NestedItemLoader(response=self.response) @@ -941,10 +493,10 @@ class SubselectorLoaderTest(unittest.TestCase): l.add_xpath('url', '//footer/a/@href') self.assertEqual(l.get_output_value('url'), [ - u'/images/logo.png', - u'http://www.scrapy.org', - u'homepage', - u'http://www.scrapy.org', + '/images/logo.png', + 'http://www.scrapy.org', + 'homepage', + 'http://www.scrapy.org', ]) def test_nested_load_item(self): @@ -962,34 +514,9 @@ class SubselectorLoaderTest(unittest.TestCase): assert item is nl1.item assert item is nl2.item - self.assertEqual(item['name'], [u'marta']) - self.assertEqual(item['url'], [u'http://www.scrapy.org']) - self.assertEqual(item['image'], [u'/images/logo.png']) - - -class SelectJmesTestCase(unittest.TestCase): - test_list_equals = { - 'simple': ('foo.bar', {"foo": {"bar": "baz"}}, "baz"), - 'invalid': ('foo.bar.baz', {"foo": {"bar": "baz"}}, None), - 'top_level': ('foo', {"foo": {"bar": "baz"}}, {"bar": "baz"}), - 'double_vs_single_quote_string': ('foo.bar', {"foo": {"bar": "baz"}}, "baz"), - 'dict': ( - 'foo.bar[*].name', - {"foo": {"bar": [{"name": "one"}, {"name": "two"}]}}, - ['one', 'two'] - ), - 'list': ('[1]', [1, 2], 2) - } - - def test_output(self): - for l in self.test_list_equals: - expr, test_list, expected = self.test_list_equals[l] - test = SelectJmes(expr)(test_list) - self.assertEqual( - test, - expected, - msg='test "{}" got {} expected {}'.format(l, test, expected) - ) + self.assertEqual(item['name'], ['marta']) + self.assertEqual(item['url'], ['http://www.scrapy.org']) + self.assertEqual(item['image'], ['/images/logo.png']) # Functions as processors @@ -1013,12 +540,6 @@ class FunctionProcessorItemLoader(ItemLoader): default_item_class = FunctionProcessorItem -class FunctionProcessorDictLoader(ItemLoader): - default_item_class = dict - foo_in = function_processor_strip - foo_out = function_processor_upper - - class FunctionProcessorTestCase(unittest.TestCase): def test_processor_defined_in_item(self): @@ -1030,15 +551,6 @@ class FunctionProcessorTestCase(unittest.TestCase): {'foo': ['BAR', 'ASDF', 'QWERTY']} ) - def test_processor_defined_in_item_loader(self): - lo = FunctionProcessorDictLoader() - lo.add_value('foo', ' bar ') - lo.add_value('foo', [' asdf ', ' qwerty ']) - self.assertEqual( - dict(lo.load_item()), - {'foo': ['BAR', 'ASDF', 'QWERTY']} - ) - if __name__ == "__main__": unittest.main() diff --git a/tests/test_loader_deprecated.py b/tests/test_loader_deprecated.py new file mode 100644 index 000000000..41afa2896 --- /dev/null +++ b/tests/test_loader_deprecated.py @@ -0,0 +1,720 @@ +""" +These tests are kept as references from the ones that were ported to a itemloaders library. +Once we remove the references from scrapy, we can remove these tests. +""" + +import unittest +import warnings +from functools import partial + +from itemloaders.processors import (Compose, Identity, Join, + MapCompose, SelectJmes, TakeFirst) + +from scrapy.item import Item, Field +from scrapy.loader import ItemLoader +from scrapy.loader.common import wrap_loader_context +from scrapy.utils.deprecate import ScrapyDeprecationWarning +from scrapy.utils.misc import extract_regex + + +# test items +class NameItem(Item): + name = Field() + + +class TestItem(NameItem): + url = Field() + summary = Field() + + +# test item loaders +class NameItemLoader(ItemLoader): + default_item_class = TestItem + + +class TestItemLoader(NameItemLoader): + name_in = MapCompose(lambda v: v.title()) + + +class DefaultedItemLoader(NameItemLoader): + default_input_processor = MapCompose(lambda v: v[:-1]) + + +# test processors +def processor_with_args(value, other=None, loader_context=None): + if 'key' in loader_context: + return loader_context['key'] + return value + + +class BasicItemLoaderTest(unittest.TestCase): + + def test_load_item_using_default_loader(self): + i = TestItem() + i['summary'] = 'lala' + il = ItemLoader(item=i) + il.add_value('name', 'marta') + item = il.load_item() + assert item is i + self.assertEqual(item['summary'], ['lala']) + self.assertEqual(item['name'], ['marta']) + + def test_load_item_using_custom_loader(self): + il = TestItemLoader() + il.add_value('name', 'marta') + item = il.load_item() + self.assertEqual(item['name'], ['Marta']) + + def test_load_item_ignore_none_field_values(self): + def validate_sku(value): + # Let's assume a SKU is only digits. + if value.isdigit(): + return value + + class MyLoader(ItemLoader): + name_out = Compose(lambda vs: vs[0]) # take first which allows empty values + price_out = Compose(TakeFirst(), float) + sku_out = Compose(TakeFirst(), validate_sku) + + valid_fragment = 'SKU: 1234' + invalid_fragment = 'SKU: not available' + sku_re = 'SKU: (.+)' + + il = MyLoader(item={}) + # Should not return "sku: None". + il.add_value('sku', [invalid_fragment], re=sku_re) + # Should not ignore empty values. + il.add_value('name', '') + il.add_value('price', ['0']) + self.assertEqual(il.load_item(), { + 'name': '', + 'price': 0.0, + }) + + il.replace_value('sku', [valid_fragment], re=sku_re) + self.assertEqual(il.load_item()['sku'], '1234') + + def test_self_referencing_loader(self): + class MyLoader(ItemLoader): + url_out = TakeFirst() + + def img_url_out(self, values): + return (self.get_output_value('url') or '') + values[0] + + il = MyLoader(item={}) + il.add_value('url', 'http://example.com/') + il.add_value('img_url', '1234.png') + self.assertEqual(il.load_item(), { + 'url': 'http://example.com/', + 'img_url': 'http://example.com/1234.png', + }) + + il = MyLoader(item={}) + il.add_value('img_url', '1234.png') + self.assertEqual(il.load_item(), { + 'img_url': '1234.png', + }) + + def test_add_value(self): + il = TestItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_collected_values('name'), ['Marta']) + self.assertEqual(il.get_output_value('name'), ['Marta']) + il.add_value('name', 'pepe') + self.assertEqual(il.get_collected_values('name'), ['Marta', 'Pepe']) + self.assertEqual(il.get_output_value('name'), ['Marta', 'Pepe']) + + # test add object value + il.add_value('summary', {'key': 1}) + self.assertEqual(il.get_collected_values('summary'), [{'key': 1}]) + + il.add_value(None, 'Jim', lambda x: {'name': x}) + self.assertEqual(il.get_collected_values('name'), ['Marta', 'Pepe', 'Jim']) + + def test_add_zero(self): + il = NameItemLoader() + il.add_value('name', 0) + self.assertEqual(il.get_collected_values('name'), [0]) + + def test_replace_value(self): + il = TestItemLoader() + il.replace_value('name', 'marta') + self.assertEqual(il.get_collected_values('name'), ['Marta']) + self.assertEqual(il.get_output_value('name'), ['Marta']) + il.replace_value('name', 'pepe') + self.assertEqual(il.get_collected_values('name'), ['Pepe']) + self.assertEqual(il.get_output_value('name'), ['Pepe']) + + il.replace_value(None, 'Jim', lambda x: {'name': x}) + self.assertEqual(il.get_collected_values('name'), ['Jim']) + + def test_get_value(self): + il = NameItemLoader() + self.assertEqual('FOO', il.get_value(['foo', 'bar'], TakeFirst(), str.upper)) + self.assertEqual(['foo', 'bar'], il.get_value(['name:foo', 'name:bar'], re='name:(.*)$')) + self.assertEqual('foo', il.get_value(['name:foo', 'name:bar'], TakeFirst(), re='name:(.*)$')) + + il.add_value('name', ['name:foo', 'name:bar'], TakeFirst(), re='name:(.*)$') + self.assertEqual(['foo'], il.get_collected_values('name')) + il.replace_value('name', 'name:bar', re='name:(.*)$') + self.assertEqual(['bar'], il.get_collected_values('name')) + + def test_iter_on_input_processor_input(self): + class NameFirstItemLoader(NameItemLoader): + name_in = TakeFirst() + + il = NameFirstItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_collected_values('name'), ['marta']) + il = NameFirstItemLoader() + il.add_value('name', ['marta', 'jose']) + self.assertEqual(il.get_collected_values('name'), ['marta']) + + il = NameFirstItemLoader() + il.replace_value('name', 'marta') + self.assertEqual(il.get_collected_values('name'), ['marta']) + il = NameFirstItemLoader() + il.replace_value('name', ['marta', 'jose']) + self.assertEqual(il.get_collected_values('name'), ['marta']) + + il = NameFirstItemLoader() + il.add_value('name', 'marta') + il.add_value('name', ['jose', 'pedro']) + self.assertEqual(il.get_collected_values('name'), ['marta', 'jose']) + + def test_map_compose_filter(self): + def filter_world(x): + return None if x == 'world' else x + + proc = MapCompose(filter_world, str.upper) + self.assertEqual(proc(['hello', 'world', 'this', 'is', 'scrapy']), + ['HELLO', 'THIS', 'IS', 'SCRAPY']) + + def test_map_compose_filter_multil(self): + class TestItemLoader(NameItemLoader): + name_in = MapCompose(lambda v: v.title(), lambda v: v[:-1]) + + il = TestItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['Mart']) + item = il.load_item() + self.assertEqual(item['name'], ['Mart']) + + def test_default_input_processor(self): + il = DefaultedItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['mart']) + + def test_inherited_default_input_processor(self): + class InheritDefaultedItemLoader(DefaultedItemLoader): + pass + + il = InheritDefaultedItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['mart']) + + def test_input_processor_inheritance(self): + class ChildItemLoader(TestItemLoader): + url_in = MapCompose(lambda v: v.lower()) + + il = ChildItemLoader() + il.add_value('url', 'HTTP://scrapy.ORG') + self.assertEqual(il.get_output_value('url'), ['http://scrapy.org']) + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['Marta']) + + class ChildChildItemLoader(ChildItemLoader): + url_in = MapCompose(lambda v: v.upper()) + summary_in = MapCompose(lambda v: v) + + il = ChildChildItemLoader() + il.add_value('url', 'http://scrapy.org') + self.assertEqual(il.get_output_value('url'), ['HTTP://SCRAPY.ORG']) + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['Marta']) + + def test_empty_map_compose(self): + class IdentityDefaultedItemLoader(DefaultedItemLoader): + name_in = MapCompose() + + il = IdentityDefaultedItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['marta']) + + def test_identity_input_processor(self): + class IdentityDefaultedItemLoader(DefaultedItemLoader): + name_in = Identity() + + il = IdentityDefaultedItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['marta']) + + def test_extend_custom_input_processors(self): + class ChildItemLoader(TestItemLoader): + name_in = MapCompose(TestItemLoader.name_in, str.swapcase) + + il = ChildItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['mARTA']) + + def test_extend_default_input_processors(self): + class ChildDefaultedItemLoader(DefaultedItemLoader): + name_in = MapCompose(DefaultedItemLoader.default_input_processor, str.swapcase) + + il = ChildDefaultedItemLoader() + il.add_value('name', 'marta') + self.assertEqual(il.get_output_value('name'), ['MART']) + + def test_output_processor_using_function(self): + il = TestItemLoader() + il.add_value('name', ['mar', 'ta']) + self.assertEqual(il.get_output_value('name'), ['Mar', 'Ta']) + + class TakeFirstItemLoader(TestItemLoader): + name_out = " ".join + + il = TakeFirstItemLoader() + il.add_value('name', ['mar', 'ta']) + self.assertEqual(il.get_output_value('name'), 'Mar Ta') + + def test_output_processor_error(self): + class TestItemLoader(ItemLoader): + default_item_class = TestItem + name_out = MapCompose(float) + + il = TestItemLoader() + il.add_value('name', ['$10']) + try: + float('$10') + except Exception as e: + expected_exc_str = str(e) + + exc = None + try: + il.load_item() + except Exception as e: + exc = e + assert isinstance(exc, ValueError) + s = str(exc) + assert 'name' in s, s + assert '$10' in s, s + assert 'ValueError' in s, s + assert expected_exc_str in s, s + + def test_output_processor_using_classes(self): + il = TestItemLoader() + il.add_value('name', ['mar', 'ta']) + self.assertEqual(il.get_output_value('name'), ['Mar', 'Ta']) + + class TakeFirstItemLoader(TestItemLoader): + name_out = Join() + + il = TakeFirstItemLoader() + il.add_value('name', ['mar', 'ta']) + self.assertEqual(il.get_output_value('name'), 'Mar Ta') + + class TakeFirstItemLoader(TestItemLoader): + name_out = Join("
    ") + + il = TakeFirstItemLoader() + il.add_value('name', ['mar', 'ta']) + self.assertEqual(il.get_output_value('name'), 'Mar
    Ta') + + def test_default_output_processor(self): + il = TestItemLoader() + il.add_value('name', ['mar', 'ta']) + self.assertEqual(il.get_output_value('name'), ['Mar', 'Ta']) + + class LalaItemLoader(TestItemLoader): + default_output_processor = Identity() + + il = LalaItemLoader() + il.add_value('name', ['mar', 'ta']) + self.assertEqual(il.get_output_value('name'), ['Mar', 'Ta']) + + def test_loader_context_on_declaration(self): + class ChildItemLoader(TestItemLoader): + url_in = MapCompose(processor_with_args, key='val') + + il = ChildItemLoader() + il.add_value('url', 'text') + self.assertEqual(il.get_output_value('url'), ['val']) + il.replace_value('url', 'text2') + self.assertEqual(il.get_output_value('url'), ['val']) + + def test_loader_context_on_instantiation(self): + class ChildItemLoader(TestItemLoader): + url_in = MapCompose(processor_with_args) + + il = ChildItemLoader(key='val') + il.add_value('url', 'text') + self.assertEqual(il.get_output_value('url'), ['val']) + il.replace_value('url', 'text2') + self.assertEqual(il.get_output_value('url'), ['val']) + + def test_loader_context_on_assign(self): + class ChildItemLoader(TestItemLoader): + url_in = MapCompose(processor_with_args) + + il = ChildItemLoader() + il.context['key'] = 'val' + il.add_value('url', 'text') + self.assertEqual(il.get_output_value('url'), ['val']) + il.replace_value('url', 'text2') + self.assertEqual(il.get_output_value('url'), ['val']) + + def test_item_passed_to_input_processor_functions(self): + def processor(value, loader_context): + return loader_context['item']['name'] + + class ChildItemLoader(TestItemLoader): + url_in = MapCompose(processor) + + it = TestItem(name='marta') + il = ChildItemLoader(item=it) + il.add_value('url', 'text') + self.assertEqual(il.get_output_value('url'), ['marta']) + il.replace_value('url', 'text2') + self.assertEqual(il.get_output_value('url'), ['marta']) + + def test_compose_processor(self): + class TestItemLoader(NameItemLoader): + name_out = Compose(lambda v: v[0], lambda v: v.title(), lambda v: v[:-1]) + + il = TestItemLoader() + il.add_value('name', ['marta', 'other']) + self.assertEqual(il.get_output_value('name'), 'Mart') + item = il.load_item() + self.assertEqual(item['name'], 'Mart') + + def test_partial_processor(self): + def join(values, sep=None, loader_context=None, ignored=None): + if sep is not None: + return sep.join(values) + elif loader_context and 'sep' in loader_context: + return loader_context['sep'].join(values) + else: + return ''.join(values) + + class TestItemLoader(NameItemLoader): + name_out = Compose(partial(join, sep='+')) + url_out = Compose(partial(join, loader_context={'sep': '.'})) + summary_out = Compose(partial(join, ignored='foo')) + + il = TestItemLoader() + il.add_value('name', ['rabbit', 'hole']) + il.add_value('url', ['rabbit', 'hole']) + il.add_value('summary', ['rabbit', 'hole']) + item = il.load_item() + self.assertEqual(item['name'], 'rabbit+hole') + self.assertEqual(item['url'], 'rabbit.hole') + self.assertEqual(item['summary'], 'rabbithole') + + def test_error_input_processor(self): + class TestItem(Item): + name = Field() + + class TestItemLoader(ItemLoader): + default_item_class = TestItem + name_in = MapCompose(float) + + il = TestItemLoader() + self.assertRaises(ValueError, il.add_value, 'name', + ['marta', 'other']) + + def test_error_output_processor(self): + class TestItem(Item): + name = Field() + + class TestItemLoader(ItemLoader): + default_item_class = TestItem + name_out = Compose(Join(), float) + + il = TestItemLoader() + il.add_value('name', 'marta') + with self.assertRaises(ValueError): + il.load_item() + + def test_error_processor_as_argument(self): + class TestItem(Item): + name = Field() + + class TestItemLoader(ItemLoader): + default_item_class = TestItem + + il = TestItemLoader() + self.assertRaises(ValueError, il.add_value, 'name', + ['marta', 'other'], Compose(float)) + + +class InitializationFromDictTest(unittest.TestCase): + + item_class = dict + + def test_keep_single_value(self): + """Loaded item should contain values from the initial item""" + input_item = self.item_class(name='foo') + il = ItemLoader(item=input_item) + loaded_item = il.load_item() + self.assertIsInstance(loaded_item, self.item_class) + self.assertEqual(dict(loaded_item), {'name': ['foo']}) + + def test_keep_list(self): + """Loaded item should contain values from the initial item""" + input_item = self.item_class(name=['foo', 'bar']) + il = ItemLoader(item=input_item) + loaded_item = il.load_item() + self.assertIsInstance(loaded_item, self.item_class) + self.assertEqual(dict(loaded_item), {'name': ['foo', 'bar']}) + + def test_add_value_singlevalue_singlevalue(self): + """Values added after initialization should be appended""" + input_item = self.item_class(name='foo') + il = ItemLoader(item=input_item) + il.add_value('name', 'bar') + loaded_item = il.load_item() + self.assertIsInstance(loaded_item, self.item_class) + self.assertEqual(dict(loaded_item), {'name': ['foo', 'bar']}) + + def test_add_value_singlevalue_list(self): + """Values added after initialization should be appended""" + input_item = self.item_class(name='foo') + il = ItemLoader(item=input_item) + il.add_value('name', ['item', 'loader']) + loaded_item = il.load_item() + self.assertIsInstance(loaded_item, self.item_class) + self.assertEqual(dict(loaded_item), {'name': ['foo', 'item', 'loader']}) + + def test_add_value_list_singlevalue(self): + """Values added after initialization should be appended""" + input_item = self.item_class(name=['foo', 'bar']) + il = ItemLoader(item=input_item) + il.add_value('name', 'qwerty') + loaded_item = il.load_item() + self.assertIsInstance(loaded_item, self.item_class) + self.assertEqual(dict(loaded_item), {'name': ['foo', 'bar', 'qwerty']}) + + def test_add_value_list_list(self): + """Values added after initialization should be appended""" + input_item = self.item_class(name=['foo', 'bar']) + il = ItemLoader(item=input_item) + il.add_value('name', ['item', 'loader']) + loaded_item = il.load_item() + self.assertIsInstance(loaded_item, self.item_class) + self.assertEqual(dict(loaded_item), {'name': ['foo', 'bar', 'item', 'loader']}) + + def test_get_output_value_singlevalue(self): + """Getting output value must not remove value from item""" + input_item = self.item_class(name='foo') + il = ItemLoader(item=input_item) + self.assertEqual(il.get_output_value('name'), ['foo']) + loaded_item = il.load_item() + self.assertIsInstance(loaded_item, self.item_class) + self.assertEqual(loaded_item, dict({'name': ['foo']})) + + def test_get_output_value_list(self): + """Getting output value must not remove value from item""" + input_item = self.item_class(name=['foo', 'bar']) + il = ItemLoader(item=input_item) + self.assertEqual(il.get_output_value('name'), ['foo', 'bar']) + loaded_item = il.load_item() + self.assertIsInstance(loaded_item, self.item_class) + self.assertEqual(loaded_item, dict({'name': ['foo', 'bar']})) + + def test_values_single(self): + """Values from initial item must be added to loader._values""" + input_item = self.item_class(name='foo') + il = ItemLoader(item=input_item) + self.assertEqual(il._values.get('name'), ['foo']) + + def test_values_list(self): + """Values from initial item must be added to loader._values""" + input_item = self.item_class(name=['foo', 'bar']) + il = ItemLoader(item=input_item) + self.assertEqual(il._values.get('name'), ['foo', 'bar']) + + +class BaseNoInputReprocessingLoader(ItemLoader): + title_in = MapCompose(str.upper) + title_out = TakeFirst() + + +class NoInputReprocessingDictLoader(BaseNoInputReprocessingLoader): + default_item_class = dict + + +class NoInputReprocessingFromDictTest(unittest.TestCase): + """ + Loaders initialized from loaded items must not reprocess fields (dict instances) + """ + def test_avoid_reprocessing_with_initial_values_single(self): + il = NoInputReprocessingDictLoader(item=dict(title='foo')) + il_loaded = il.load_item() + self.assertEqual(il_loaded, dict(title='foo')) + self.assertEqual(NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title='foo')) + + def test_avoid_reprocessing_with_initial_values_list(self): + il = NoInputReprocessingDictLoader(item=dict(title=['foo', 'bar'])) + il_loaded = il.load_item() + self.assertEqual(il_loaded, dict(title='foo')) + self.assertEqual(NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title='foo')) + + def test_avoid_reprocessing_without_initial_values_single(self): + il = NoInputReprocessingDictLoader() + il.add_value('title', 'foo') + il_loaded = il.load_item() + self.assertEqual(il_loaded, dict(title='FOO')) + self.assertEqual(NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title='FOO')) + + def test_avoid_reprocessing_without_initial_values_list(self): + il = NoInputReprocessingDictLoader() + il.add_value('title', ['foo', 'bar']) + il_loaded = il.load_item() + self.assertEqual(il_loaded, dict(title='FOO')) + self.assertEqual(NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title='FOO')) + + +class TestOutputProcessorDict(unittest.TestCase): + def test_output_processor(self): + + class TempDict(dict): + def __init__(self, *args, **kwargs): + super().__init__(self, *args, **kwargs) + self.setdefault('temp', 0.3) + + class TempLoader(ItemLoader): + default_item_class = TempDict + default_input_processor = Identity() + default_output_processor = Compose(TakeFirst()) + + loader = TempLoader() + item = loader.load_item() + self.assertIsInstance(item, TempDict) + self.assertEqual(dict(item), {'temp': 0.3}) + + +class ProcessorsTest(unittest.TestCase): + + def test_take_first(self): + proc = TakeFirst() + self.assertEqual(proc([None, '', 'hello', 'world']), 'hello') + self.assertEqual(proc([None, '', 0, 'hello', 'world']), 0) + + def test_identity(self): + proc = Identity() + self.assertEqual(proc([None, '', 'hello', 'world']), + [None, '', 'hello', 'world']) + + def test_join(self): + proc = Join() + self.assertRaises(TypeError, proc, [None, '', 'hello', 'world']) + self.assertEqual(proc(['', 'hello', 'world']), ' hello world') + self.assertEqual(proc(['hello', 'world']), 'hello world') + self.assertIsInstance(proc(['hello', 'world']), str) + + def test_compose(self): + proc = Compose(lambda v: v[0], str.upper) + self.assertEqual(proc(['hello', 'world']), 'HELLO') + proc = Compose(str.upper) + self.assertEqual(proc(None), None) + proc = Compose(str.upper, stop_on_none=False) + self.assertRaises(ValueError, proc, None) + proc = Compose(str.upper, lambda x: x + 1) + self.assertRaises(ValueError, proc, 'hello') + + def test_mapcompose(self): + def filter_world(x): + return None if x == 'world' else x + proc = MapCompose(filter_world, str.upper) + self.assertEqual(proc(['hello', 'world', 'this', 'is', 'scrapy']), + ['HELLO', 'THIS', 'IS', 'SCRAPY']) + proc = MapCompose(filter_world, str.upper) + self.assertEqual(proc(None), []) + proc = MapCompose(filter_world, str.upper) + self.assertRaises(ValueError, proc, [1]) + proc = MapCompose(filter_world, lambda x: x + 1) + self.assertRaises(ValueError, proc, 'hello') + + +class SelectJmesTestCase(unittest.TestCase): + test_list_equals = { + 'simple': ('foo.bar', {"foo": {"bar": "baz"}}, "baz"), + 'invalid': ('foo.bar.baz', {"foo": {"bar": "baz"}}, None), + 'top_level': ('foo', {"foo": {"bar": "baz"}}, {"bar": "baz"}), + 'double_vs_single_quote_string': ('foo.bar', {"foo": {"bar": "baz"}}, "baz"), + 'dict': ( + 'foo.bar[*].name', + {"foo": {"bar": [{"name": "one"}, {"name": "two"}]}}, + ['one', 'two'] + ), + 'list': ('[1]', [1, 2], 2) + } + + def test_output(self): + for tl in self.test_list_equals: + expr, test_list, expected = self.test_list_equals[tl] + test = SelectJmes(expr)(test_list) + self.assertEqual( + test, + expected, + msg=f'test "{tl}" got {test} expected {expected}' + ) + + +# Functions as processors + +def function_processor_strip(iterable): + return [x.strip() for x in iterable] + + +def function_processor_upper(iterable): + return [x.upper() for x in iterable] + + +class FunctionProcessorItem(Item): + foo = Field( + input_processor=function_processor_strip, + output_processor=function_processor_upper, + ) + + +class FunctionProcessorDictLoader(ItemLoader): + default_item_class = dict + foo_in = function_processor_strip + foo_out = function_processor_upper + + +class FunctionProcessorTestCase(unittest.TestCase): + + def test_processor_defined_in_item_loader(self): + lo = FunctionProcessorDictLoader() + lo.add_value('foo', ' bar ') + lo.add_value('foo', [' asdf ', ' qwerty ']) + self.assertEqual( + dict(lo.load_item()), + {'foo': ['BAR', 'ASDF', 'QWERTY']} + ) + + +class DeprecatedUtilityFunctionsTestCase(unittest.TestCase): + + def test_deprecated_wrap_loader_context(self): + def function(*args): + return None + + with warnings.catch_warnings(record=True) as w: + wrap_loader_context(function, context=dict()) + + assert len(w) == 1 + assert issubclass(w[0].category, ScrapyDeprecationWarning) + + def test_deprecated_extract_regex(self): + with warnings.catch_warnings(record=True) as w: + extract_regex(r'\w+', 'this is a test') + + assert len(w) == 1 + assert issubclass(w[0].category, ScrapyDeprecationWarning) + + +if __name__ == "__main__": + unittest.main() diff --git a/tests/test_logformatter.py b/tests/test_logformatter.py index 7064337ad..6381f895b 100644 --- a/tests/test_logformatter.py +++ b/tests/test_logformatter.py @@ -20,7 +20,7 @@ class CustomItem(Item): name = Field() def __str__(self): - return "name: %s" % self['name'] + return f"name: {self['name']}" class LogFormatterTestCase(unittest.TestCase): @@ -56,13 +56,13 @@ class LogFormatterTestCase(unittest.TestCase): def test_dropped(self): item = {} - exception = Exception(u"\u2018") + exception = Exception("\u2018") response = Response("http://www.example.com") logkws = self.formatter.dropped(item, exception, response, self.spider) logline = logkws['msg'] % logkws['args'] lines = logline.splitlines() assert all(isinstance(x, str) for x in lines) - self.assertEqual(lines, [u"Dropped: \u2018", '{}']) + self.assertEqual(lines, ["Dropped: \u2018", '{}']) def test_item_error(self): # In practice, the complete traceback is shown by passing the @@ -72,7 +72,7 @@ class LogFormatterTestCase(unittest.TestCase): response = Response("http://www.example.com") logkws = self.formatter.item_error(item, exception, response, self.spider) logline = logkws['msg'] % logkws['args'] - self.assertEqual(logline, u"Error processing {'key': 'value'}") + self.assertEqual(logline, "Error processing {'key': 'value'}") def test_spider_error(self): # In practice, the complete traceback is shown by passing the @@ -107,20 +107,20 @@ class LogFormatterTestCase(unittest.TestCase): def test_scraped(self): item = CustomItem() - item['name'] = u'\xa3' + item['name'] = '\xa3' response = Response("http://www.example.com") logkws = self.formatter.scraped(item, response, self.spider) logline = logkws['msg'] % logkws['args'] lines = logline.splitlines() assert all(isinstance(x, str) for x in lines) - self.assertEqual(lines, [u"Scraped from <200 http://www.example.com>", u'name: \xa3']) + self.assertEqual(lines, ["Scraped from <200 http://www.example.com>", 'name: \xa3']) class LogFormatterSubclass(LogFormatter): def crawled(self, request, response, spider): - kwargs = super(LogFormatterSubclass, self).crawled(request, response, spider) + kwargs = super().crawled(request, response, spider) CRAWLEDMSG = ( - u"Crawled (%(status)s) %(request)s (referer: %(referer)s) %(flags)s" + "Crawled (%(status)s) %(request)s (referer: %(referer)s) %(flags)s" ) log_args = kwargs['args'] log_args['flags'] = str(request.flags) @@ -193,7 +193,7 @@ class ShowOrSkipMessagesTestCase(TwistedTestCase): self.base_settings = { 'LOG_LEVEL': 'DEBUG', 'ITEM_PIPELINES': { - __name__ + '.DropSomeItemsPipeline': 300, + DropSomeItemsPipeline: 300, }, } @@ -212,7 +212,7 @@ class ShowOrSkipMessagesTestCase(TwistedTestCase): @defer.inlineCallbacks def test_skip_messages(self): settings = self.base_settings.copy() - settings['LOG_FORMATTER'] = __name__ + '.SkipMessagesLogFormatter' + settings['LOG_FORMATTER'] = SkipMessagesLogFormatter crawler = CrawlerRunner(settings).create_crawler(ItemSpider) with LogCapture() as lc: yield crawler.crawl(mockserver=self.mockserver) diff --git a/tests/test_mail.py b/tests/test_mail.py index 53dbc0686..9b248fbfa 100644 --- a/tests/test_mail.py +++ b/tests/test_mail.py @@ -73,8 +73,8 @@ class MailSenderTest(unittest.TestCase): self.catched_msg = dict(**kwargs) def test_send_utf8(self): - subject = u'sübjèçt' - body = u'bödÿ-àéïöñß' + subject = 'sübjèçt' + body = 'bödÿ-àéïöñß' mailsender = MailSender(debug=True) mailsender.send(to=['test@scrapy.org'], subject=subject, body=body, charset='utf-8', _callback=self._catch_mail_sent) @@ -90,8 +90,8 @@ class MailSenderTest(unittest.TestCase): self.assertEqual(msg.get('Content-Type'), 'text/plain; charset="utf-8"') def test_send_attach_utf8(self): - subject = u'sübjèçt' - body = u'bödÿ-àéïöñß' + subject = 'sübjèçt' + body = 'bödÿ-àéïöñß' attach = BytesIO() attach.write(body.encode('utf-8')) attach.seek(0) diff --git a/tests/test_middleware.py b/tests/test_middleware.py index 3364d2258..8651431b5 100644 --- a/tests/test_middleware.py +++ b/tests/test_middleware.py @@ -50,10 +50,10 @@ class TestMiddlewareManager(MiddlewareManager): @classmethod def _get_mwlist_from_settings(cls, settings): - return ['tests.test_middleware.%s' % x for x in ['M1', 'MOff', 'M3']] + return [M1, MOff, M3] def _add_middleware(self, mw): - super(TestMiddlewareManager, self)._add_middleware(mw) + super()._add_middleware(mw) if hasattr(mw, 'process'): self.methods['process'].append(mw.process) diff --git a/tests/test_pipeline_crawl.py b/tests/test_pipeline_crawl.py index 9af5affec..f49fda701 100644 --- a/tests/test_pipeline_crawl.py +++ b/tests/test_pipeline_crawl.py @@ -123,10 +123,10 @@ class FileDownloadCrawlTestCase(TestCase): self.assertEqual(crawler.stats.get_value('downloader/request_method_count/GET'), 4) self.assertEqual(crawler.stats.get_value('downloader/response_count'), 4) self.assertEqual(crawler.stats.get_value('downloader/response_status_count/200'), 1) - self.assertEqual(crawler.stats.get_value('downloader/response_status_count/%d' % code), 3) + self.assertEqual(crawler.stats.get_value(f'downloader/response_status_count/{code}'), 3) # check that logs do show the failure on the file downloads - file_dl_failure = 'File (code: %d): Error downloading file from' % code + file_dl_failure = f'File (code: {code}): Error downloading file from' self.assertEqual(logs.count(file_dl_failure), 3) # check that no files were written to the media store @@ -180,7 +180,18 @@ class FileDownloadCrawlTestCase(TestCase): self.assertEqual(crawler.stats.get_value('downloader/response_status_count/302'), 3) +try: + from PIL import Image # noqa: imported just to check for the import error +except ImportError: + skip_pillow = 'Missing Python Imaging Library, install https://pypi.python.org/pypi/Pillow' +else: + skip_pillow = None + + class ImageDownloadCrawlTestCase(FileDownloadCrawlTestCase): + + skip = skip_pillow + pipeline_class = 'scrapy.pipelines.images.ImagesPipeline' store_setting_key = 'IMAGES_STORE' media_key = 'images' diff --git a/tests/test_pipeline_files.py b/tests/test_pipeline_files.py index 6bbcbc2e9..4e1b90787 100644 --- a/tests/test_pipeline_files.py +++ b/tests/test_pipeline_files.py @@ -1,23 +1,41 @@ import os import random import time +from datetime import datetime from io import BytesIO -from tempfile import mkdtemp from shutil import rmtree -from unittest import mock +from tempfile import mkdtemp +from unittest import mock, skipIf from urllib.parse import urlparse -from twisted.trial import unittest +import attr +from itemadapter import ItemAdapter from twisted.internet import defer +from twisted.trial import unittest -from scrapy.pipelines.files import FilesPipeline, FSFilesStore, S3FilesStore, GCSFilesStore, FTPFilesStore -from scrapy.item import Item, Field from scrapy.http import Request, Response +from scrapy.item import Field, Item +from scrapy.pipelines.files import ( + FilesPipeline, + FSFilesStore, + FTPFilesStore, + GCSFilesStore, + S3FilesStore, +) from scrapy.settings import Settings -from scrapy.utils.test import assert_aws_environ, get_s3_content_and_delete -from scrapy.utils.test import assert_gcs_environ, get_gcs_content_and_delete -from scrapy.utils.test import get_ftp_content_and_delete -from scrapy.utils.boto import is_botocore +from scrapy.utils.test import ( + assert_gcs_environ, + get_ftp_content_and_delete, + get_gcs_content_and_delete, + skip_if_no_boto, +) + + +try: + from dataclasses import make_dataclass, field as dataclass_field +except ImportError: + make_dataclass = None + dataclass_field = None def _mocked_download_func(request, info): @@ -142,44 +160,102 @@ class FilesPipelineTestCase(unittest.TestCase): for p in patchers: p.stop() + def test_file_path_from_item(self): + """ + Custom file path based on item data, overriding default implementation + """ + class CustomFilesPipeline(FilesPipeline): + def file_path(self, request, response=None, info=None, item=None): + return f'full/{item.get("path")}' -class FilesPipelineTestCaseFields(unittest.TestCase): + file_path = CustomFilesPipeline.from_settings(Settings({'FILES_STORE': self.tempdir})).file_path + item = dict(path='path-to-store-file') + request = Request("http://example.com") + self.assertEqual(file_path(request, item=item), 'full/path-to-store-file') + + +class FilesPipelineTestCaseFieldsMixin: def test_item_fields_default(self): - class TestItem(Item): - name = Field() - file_urls = Field() - files = Field() - - for cls in TestItem, dict: - url = 'http://www.example.com/files/1.txt' - item = cls({'name': 'item1', 'file_urls': [url]}) - pipeline = FilesPipeline.from_settings(Settings({'FILES_STORE': 's3://example/files/'})) - requests = list(pipeline.get_media_requests(item, None)) - self.assertEqual(requests[0].url, url) - results = [(True, {'url': url})] - pipeline.item_completed(results, item, None) - self.assertEqual(item['files'], [results[0][1]]) + url = 'http://www.example.com/files/1.txt' + item = self.item_class(name='item1', file_urls=[url]) + pipeline = FilesPipeline.from_settings(Settings({'FILES_STORE': 's3://example/files/'})) + requests = list(pipeline.get_media_requests(item, None)) + self.assertEqual(requests[0].url, url) + results = [(True, {'url': url})] + item = pipeline.item_completed(results, item, None) + files = ItemAdapter(item).get("files") + self.assertEqual(files, [results[0][1]]) + self.assertIsInstance(item, self.item_class) def test_item_fields_override_settings(self): - class TestItem(Item): - name = Field() - files = Field() - stored_file = Field() + url = 'http://www.example.com/files/1.txt' + item = self.item_class(name='item1', custom_file_urls=[url]) + pipeline = FilesPipeline.from_settings(Settings({ + 'FILES_STORE': 's3://example/files/', + 'FILES_URLS_FIELD': 'custom_file_urls', + 'FILES_RESULT_FIELD': 'custom_files' + })) + requests = list(pipeline.get_media_requests(item, None)) + self.assertEqual(requests[0].url, url) + results = [(True, {'url': url})] + item = pipeline.item_completed(results, item, None) + custom_files = ItemAdapter(item).get("custom_files") + self.assertEqual(custom_files, [results[0][1]]) + self.assertIsInstance(item, self.item_class) - for cls in TestItem, dict: - url = 'http://www.example.com/files/1.txt' - item = cls({'name': 'item1', 'files': [url]}) - pipeline = FilesPipeline.from_settings(Settings({ - 'FILES_STORE': 's3://example/files/', - 'FILES_URLS_FIELD': 'files', - 'FILES_RESULT_FIELD': 'stored_file' - })) - requests = list(pipeline.get_media_requests(item, None)) - self.assertEqual(requests[0].url, url) - results = [(True, {'url': url})] - pipeline.item_completed(results, item, None) - self.assertEqual(item['stored_file'], [results[0][1]]) + +class FilesPipelineTestCaseFieldsDict(FilesPipelineTestCaseFieldsMixin, unittest.TestCase): + item_class = dict + + +class FilesPipelineTestItem(Item): + name = Field() + # default fields + file_urls = Field() + files = Field() + # overridden fields + custom_file_urls = Field() + custom_files = Field() + + +class FilesPipelineTestCaseFieldsItem(FilesPipelineTestCaseFieldsMixin, unittest.TestCase): + item_class = FilesPipelineTestItem + + +@skipIf(not make_dataclass, "dataclasses module is not available") +class FilesPipelineTestCaseFieldsDataClass(FilesPipelineTestCaseFieldsMixin, unittest.TestCase): + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + if make_dataclass: + self.item_class = make_dataclass( + "FilesPipelineTestDataClass", + [ + ("name", str), + # default fields + ("file_urls", list, dataclass_field(default_factory=list)), + ("files", list, dataclass_field(default_factory=list)), + # overridden fields + ("custom_file_urls", list, dataclass_field(default_factory=list)), + ("custom_files", list, dataclass_field(default_factory=list)), + ], + ) + + +@attr.s +class FilesPipelineTestAttrsItem: + name = attr.ib(default="") + # default fields + file_urls = attr.ib(default=lambda: []) + files = attr.ib(default=lambda: []) + # overridden fields + custom_file_urls = attr.ib(default=lambda: []) + custom_files = attr.ib(default=lambda: []) + + +class FilesPipelineTestCaseFieldsAttrsItem(FilesPipelineTestCaseFieldsMixin, unittest.TestCase): + item_class = FilesPipelineTestAttrsItem class FilesPipelineTestCaseCustomSettings(unittest.TestCase): @@ -338,38 +414,88 @@ class FilesPipelineTestCaseCustomSettings(unittest.TestCase): class TestS3FilesStore(unittest.TestCase): + @defer.inlineCallbacks def test_persist(self): - assert_aws_environ() - uri = os.environ.get('S3_TEST_FILE_URI') - if not uri: - raise unittest.SkipTest("No S3 URI available for testing") - data = b"TestS3FilesStore: \xe2\x98\x83" - buf = BytesIO(data) + skip_if_no_boto() + + bucket = 'mybucket' + key = 'export.csv' + uri = f's3://{bucket}/{key}' + buffer = mock.MagicMock() meta = {'foo': 'bar'} path = '' + content_type = 'image/png' + store = S3FilesStore(uri) - yield store.persist_file( - path, buf, info=None, meta=meta, - headers={'Content-Type': 'image/png'}) - s = yield store.stat_file(path, info=None) - self.assertIn('last_modified', s) - self.assertIn('checksum', s) - self.assertEqual(s['checksum'], '3187896a9657a28163abb31667df64c8') - u = urlparse(uri) - content, key = get_s3_content_and_delete( - u.hostname, u.path[1:], with_key=True) - self.assertEqual(content, data) - if is_botocore(): - self.assertEqual(key['Metadata'], {'foo': 'bar'}) + from botocore.stub import Stubber + with Stubber(store.s3_client) as stub: + stub.add_response( + 'put_object', + expected_params={ + 'ACL': S3FilesStore.POLICY, + 'Body': buffer, + 'Bucket': bucket, + 'CacheControl': S3FilesStore.HEADERS['Cache-Control'], + 'ContentType': content_type, + 'Key': key, + 'Metadata': meta, + }, + service_response={}, + ) + + yield store.persist_file( + path, + buffer, + info=None, + meta=meta, + headers={'Content-Type': content_type}, + ) + + stub.assert_no_pending_responses() self.assertEqual( - key['CacheControl'], S3FilesStore.HEADERS['Cache-Control']) - self.assertEqual(key['ContentType'], 'image/png') - else: - self.assertEqual(key.metadata, {'foo': 'bar'}) + buffer.method_calls, + [ + mock.call.seek(0), + # The call to read does not happen with Stubber + ] + ) + + @defer.inlineCallbacks + def test_stat(self): + skip_if_no_boto() + + bucket = 'mybucket' + key = 'export.csv' + uri = f's3://{bucket}/{key}' + checksum = '3187896a9657a28163abb31667df64c8' + last_modified = datetime(2019, 12, 1) + + store = S3FilesStore(uri) + from botocore.stub import Stubber + with Stubber(store.s3_client) as stub: + stub.add_response( + 'head_object', + expected_params={ + 'Bucket': bucket, + 'Key': key, + }, + service_response={ + 'ETag': f'"{checksum}"', + 'LastModified': last_modified, + }, + ) + + file_stats = yield store.stat_file('', info=None) self.assertEqual( - key.cache_control, S3FilesStore.HEADERS['Cache-Control']) - self.assertEqual(key.content_type, 'image/png') + file_stats, + { + 'checksum': checksum, + 'last_modified': last_modified.timestamp(), + }, + ) + + stub.assert_no_pending_responses() class TestGCSFilesStore(unittest.TestCase): @@ -418,7 +544,7 @@ class TestFTPFileStore(unittest.TestCase): self.assertIn('last_modified', stat) self.assertIn('checksum', stat) self.assertEqual(stat['checksum'], 'd113d66b2ec7258724a268bd88eef6b6') - path = '%s/%s' % (store.basedir, path) + path = f'{store.basedir}/{path}' content = get_ftp_content_and_delete( path, store.host, store.port, store.username, store.password, store.USE_ACTIVE_MODE) diff --git a/tests/test_pipeline_images.py b/tests/test_pipeline_images.py index 8ef27fce7..c69cd0e4a 100644 --- a/tests/test_pipeline_images.py +++ b/tests/test_pipeline_images.py @@ -1,26 +1,38 @@ -import io import hashlib +import io import random -from tempfile import mkdtemp from shutil import rmtree +from tempfile import mkdtemp +from unittest import skipIf +import attr +from itemadapter import ItemAdapter from twisted.trial import unittest -from scrapy.item import Item, Field from scrapy.http import Request, Response -from scrapy.settings import Settings +from scrapy.item import Field, Item from scrapy.pipelines.images import ImagesPipeline +from scrapy.settings import Settings from scrapy.utils.python import to_bytes -skip = False + +try: + from dataclasses import make_dataclass, field as dataclass_field +except ImportError: + make_dataclass = None + dataclass_field = None + + try: from PIL import Image except ImportError: - skip = 'Missing Python Imaging Library, install https://pypi.python.org/pypi/Pillow' + skip_pillow = 'Missing Python Imaging Library, install https://pypi.python.org/pypi/Pillow' else: encoders = {'jpeg_encoder', 'jpeg_decoder'} if not encoders.issubset(set(Image.core.__dict__)): - skip = 'Missing JPEG encoders' + skip_pillow = 'Missing JPEG encoders' + else: + skip_pillow = None def _mocked_download_func(request, info): @@ -30,7 +42,7 @@ def _mocked_download_func(request, info): class ImagesPipelineTestCase(unittest.TestCase): - skip = skip + skip = skip_pillow def setUp(self): self.tempdir = mkdtemp() @@ -117,53 +129,104 @@ class DeprecatedImagesPipeline(ImagesPipeline): def image_key(self, url): image_guid = hashlib.sha1(to_bytes(url)).hexdigest() - return 'empty/%s.jpg' % (image_guid) + return f'empty/{image_guid}.jpg' def thumb_key(self, url, thumb_id): thumb_guid = hashlib.sha1(to_bytes(url)).hexdigest() - return 'thumbsup/%s/%s.jpg' % (thumb_id, thumb_guid) + return f'thumbsup/{thumb_id}/{thumb_guid}.jpg' -class ImagesPipelineTestCaseFields(unittest.TestCase): +class ImagesPipelineTestCaseFieldsMixin: + + skip = skip_pillow def test_item_fields_default(self): - class TestItem(Item): - name = Field() - image_urls = Field() - images = Field() - - for cls in TestItem, dict: - url = 'http://www.example.com/images/1.jpg' - item = cls({'name': 'item1', 'image_urls': [url]}) - pipeline = ImagesPipeline.from_settings(Settings({'IMAGES_STORE': 's3://example/images/'})) - requests = list(pipeline.get_media_requests(item, None)) - self.assertEqual(requests[0].url, url) - results = [(True, {'url': url})] - pipeline.item_completed(results, item, None) - self.assertEqual(item['images'], [results[0][1]]) + url = 'http://www.example.com/images/1.jpg' + item = self.item_class(name='item1', image_urls=[url]) + pipeline = ImagesPipeline.from_settings(Settings({'IMAGES_STORE': 's3://example/images/'})) + requests = list(pipeline.get_media_requests(item, None)) + self.assertEqual(requests[0].url, url) + results = [(True, {'url': url})] + item = pipeline.item_completed(results, item, None) + images = ItemAdapter(item).get("images") + self.assertEqual(images, [results[0][1]]) + self.assertIsInstance(item, self.item_class) def test_item_fields_override_settings(self): - class TestItem(Item): - name = Field() - image = Field() - stored_image = Field() + url = 'http://www.example.com/images/1.jpg' + item = self.item_class(name='item1', custom_image_urls=[url]) + pipeline = ImagesPipeline.from_settings(Settings({ + 'IMAGES_STORE': 's3://example/images/', + 'IMAGES_URLS_FIELD': 'custom_image_urls', + 'IMAGES_RESULT_FIELD': 'custom_images' + })) + requests = list(pipeline.get_media_requests(item, None)) + self.assertEqual(requests[0].url, url) + results = [(True, {'url': url})] + item = pipeline.item_completed(results, item, None) + custom_images = ItemAdapter(item).get("custom_images") + self.assertEqual(custom_images, [results[0][1]]) + self.assertIsInstance(item, self.item_class) - for cls in TestItem, dict: - url = 'http://www.example.com/images/1.jpg' - item = cls({'name': 'item1', 'image': [url]}) - pipeline = ImagesPipeline.from_settings(Settings({ - 'IMAGES_STORE': 's3://example/images/', - 'IMAGES_URLS_FIELD': 'image', - 'IMAGES_RESULT_FIELD': 'stored_image' - })) - requests = list(pipeline.get_media_requests(item, None)) - self.assertEqual(requests[0].url, url) - results = [(True, {'url': url})] - pipeline.item_completed(results, item, None) - self.assertEqual(item['stored_image'], [results[0][1]]) + +class ImagesPipelineTestCaseFieldsDict(ImagesPipelineTestCaseFieldsMixin, unittest.TestCase): + item_class = dict + + +class ImagesPipelineTestItem(Item): + name = Field() + # default fields + image_urls = Field() + images = Field() + # overridden fields + custom_image_urls = Field() + custom_images = Field() + + +class ImagesPipelineTestCaseFieldsItem(ImagesPipelineTestCaseFieldsMixin, unittest.TestCase): + item_class = ImagesPipelineTestItem + + +@skipIf(not make_dataclass, "dataclasses module is not available") +class ImagesPipelineTestCaseFieldsDataClass(ImagesPipelineTestCaseFieldsMixin, unittest.TestCase): + item_class = None + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + if make_dataclass: + self.item_class = make_dataclass( + "FilesPipelineTestDataClass", + [ + ("name", str), + # default fields + ("image_urls", list, dataclass_field(default_factory=list)), + ("images", list, dataclass_field(default_factory=list)), + # overridden fields + ("custom_image_urls", list, dataclass_field(default_factory=list)), + ("custom_images", list, dataclass_field(default_factory=list)), + ], + ) + + +@attr.s +class ImagesPipelineTestAttrsItem: + name = attr.ib(default="") + # default fields + image_urls = attr.ib(default=lambda: []) + images = attr.ib(default=lambda: []) + # overridden fields + custom_image_urls = attr.ib(default=lambda: []) + custom_images = attr.ib(default=lambda: []) + + +class ImagesPipelineTestCaseFieldsAttrsItem(ImagesPipelineTestCaseFieldsMixin, unittest.TestCase): + item_class = ImagesPipelineTestAttrsItem class ImagesPipelineTestCaseCustomSettings(unittest.TestCase): + + skip = skip_pillow + img_cls_attribute_names = [ # Pipeline attribute names with corresponding setting names. ("EXPIRES", "IMAGES_EXPIRES"), diff --git a/tests/test_pipeline_media.py b/tests/test_pipeline_media.py index 19ff00350..893d43052 100644 --- a/tests/test_pipeline_media.py +++ b/tests/test_pipeline_media.py @@ -1,3 +1,5 @@ +from typing import Optional + from testfixtures import LogCapture from twisted.trial import unittest from twisted.python.failure import Failure @@ -7,7 +9,9 @@ from twisted.internet.defer import Deferred, inlineCallbacks from scrapy.http import Request, Response from scrapy.settings import Settings from scrapy.spiders import Spider +from scrapy.utils.deprecate import ScrapyDeprecationWarning from scrapy.utils.request import request_fingerprint +from scrapy.pipelines.images import ImagesPipeline from scrapy.pipelines.media import MediaPipeline from scrapy.pipelines.files import FileException from scrapy.utils.log import failure_to_exc_info @@ -15,6 +19,14 @@ from scrapy.utils.signal import disconnect_all from scrapy import signals +try: + from PIL import Image # noqa: imported just to check for the import error +except ImportError: + skip_pillow: Optional[str] = 'Missing Python Imaging Library, install https://pypi.python.org/pypi/Pillow' +else: + skip_pillow = None + + def _mocked_download_func(request, info): response = request.meta.get('response') return response() if callable(response) else response @@ -162,34 +174,34 @@ class BaseMediaPipelineTestCase(unittest.TestCase): class MockedMediaPipeline(MediaPipeline): def __init__(self, *args, **kwargs): - super(MockedMediaPipeline, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self._mockcalled = [] def download(self, request, info): self._mockcalled.append('download') - return super(MockedMediaPipeline, self).download(request, info) + return super().download(request, info) - def media_to_download(self, request, info): + def media_to_download(self, request, info, *, item=None): self._mockcalled.append('media_to_download') if 'result' in request.meta: return request.meta.get('result') - return super(MockedMediaPipeline, self).media_to_download(request, info) + return super().media_to_download(request, info) def get_media_requests(self, item, info): self._mockcalled.append('get_media_requests') return item.get('requests') - def media_downloaded(self, response, request, info): + def media_downloaded(self, response, request, info, *, item=None): self._mockcalled.append('media_downloaded') - return super(MockedMediaPipeline, self).media_downloaded(response, request, info) + return super().media_downloaded(response, request, info) def media_failed(self, failure, request, info): self._mockcalled.append('media_failed') - return super(MockedMediaPipeline, self).media_failed(failure, request, info) + return super().media_failed(failure, request, info) def item_completed(self, results, item, info): self._mockcalled.append('item_completed') - item = super(MockedMediaPipeline, self).item_completed(results, item, info) + item = super().item_completed(results, item, info) item['results'] = results return item @@ -335,6 +347,124 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): ['get_media_requests', 'media_to_download', 'item_completed']) +class MockedMediaPipelineDeprecatedMethods(ImagesPipeline): + + def __init__(self, *args, **kwargs): + super(MockedMediaPipelineDeprecatedMethods, self).__init__(*args, **kwargs) + self._mockcalled = [] + + def get_media_requests(self, item, info): + item_url = item['image_urls'][0] + return Request( + item_url, + meta={'response': Response(item_url, status=200, body=b'data')} + ) + + def inc_stats(self, *args, **kwargs): + return True + + def media_to_download(self, request, info): + self._mockcalled.append('media_to_download') + return super(MockedMediaPipelineDeprecatedMethods, self).media_to_download(request, info) + + def media_downloaded(self, response, request, info): + self._mockcalled.append('media_downloaded') + return super(MockedMediaPipelineDeprecatedMethods, self).media_downloaded(response, request, info) + + def file_downloaded(self, response, request, info): + self._mockcalled.append('file_downloaded') + return super(MockedMediaPipelineDeprecatedMethods, self).file_downloaded(response, request, info) + + def file_path(self, request, response=None, info=None): + self._mockcalled.append('file_path') + return super(MockedMediaPipelineDeprecatedMethods, self).file_path(request, response, info) + + def get_images(self, response, request, info): + self._mockcalled.append('get_images') + return [] + + def image_downloaded(self, response, request, info): + self._mockcalled.append('image_downloaded') + return super(MockedMediaPipelineDeprecatedMethods, self).image_downloaded(response, request, info) + + +class MediaPipelineDeprecatedMethodsTestCase(unittest.TestCase): + skip = skip_pillow + + def setUp(self): + self.pipe = MockedMediaPipelineDeprecatedMethods(store_uri='store-uri', download_func=_mocked_download_func) + self.pipe.open_spider(None) + self.item = dict(image_urls=['http://picsum.photos/id/1014/200/300'], images=[]) + + def _assert_method_called_with_warnings(self, method, message, warnings): + self.assertIn(method, self.pipe._mockcalled) + warningShown = False + for warning in warnings: + if warning['message'] == message and warning['category'] == ScrapyDeprecationWarning: + warningShown = True + self.assertTrue(warningShown) + + @inlineCallbacks + def test_media_to_download_called(self): + yield self.pipe.process_item(self.item, None) + warnings = self.flushWarnings([MediaPipeline._compatible]) + message = ( + 'media_to_download(self, request, info) is deprecated, ' + 'please use media_to_download(self, request, info, *, item=None)' + ) + self._assert_method_called_with_warnings('media_to_download', message, warnings) + + @inlineCallbacks + def test_media_downloaded_called(self): + yield self.pipe.process_item(self.item, None) + warnings = self.flushWarnings([MediaPipeline._compatible]) + message = ( + 'media_downloaded(self, response, request, info) is deprecated, ' + 'please use media_downloaded(self, response, request, info, *, item=None)' + ) + self._assert_method_called_with_warnings('media_downloaded', message, warnings) + + @inlineCallbacks + def test_file_downloaded_called(self): + yield self.pipe.process_item(self.item, None) + warnings = self.flushWarnings([MediaPipeline._compatible]) + message = ( + 'file_downloaded(self, response, request, info) is deprecated, ' + 'please use file_downloaded(self, response, request, info, *, item=None)' + ) + self._assert_method_called_with_warnings('file_downloaded', message, warnings) + + @inlineCallbacks + def test_file_path_called(self): + yield self.pipe.process_item(self.item, None) + warnings = self.flushWarnings([MediaPipeline._compatible]) + message = ( + 'file_path(self, request, response=None, info=None) is deprecated, ' + 'please use file_path(self, request, response=None, info=None, *, item=None)' + ) + self._assert_method_called_with_warnings('file_path', message, warnings) + + @inlineCallbacks + def test_get_images_called(self): + yield self.pipe.process_item(self.item, None) + warnings = self.flushWarnings([MediaPipeline._compatible]) + message = ( + 'get_images(self, response, request, info) is deprecated, ' + 'please use get_images(self, response, request, info, *, item=None)' + ) + self._assert_method_called_with_warnings('get_images', message, warnings) + + @inlineCallbacks + def test_image_downloaded_called(self): + yield self.pipe.process_item(self.item, None) + warnings = self.flushWarnings([MediaPipeline._compatible]) + message = ( + 'image_downloaded(self, response, request, info) is deprecated, ' + 'please use image_downloaded(self, response, request, info, *, item=None)' + ) + self._assert_method_called_with_warnings('image_downloaded', message, warnings) + + class MediaPipelineAllowRedirectSettingsTestCase(unittest.TestCase): def _assert_request_no3xx(self, pipeline_class, settings): diff --git a/tests/test_pipelines.py b/tests/test_pipelines.py index c72f1a338..ff3af9a74 100644 --- a/tests/test_pipelines.py +++ b/tests/test_pipelines.py @@ -68,7 +68,7 @@ class PipelineTestCase(unittest.TestCase): def _create_crawler(self, pipeline_class): settings = { - 'ITEM_PIPELINES': {__name__ + '.' + pipeline_class.__name__: 1}, + 'ITEM_PIPELINES': {pipeline_class: 1}, } crawler = get_crawler(ItemSpider, settings) crawler.signals.connect(self._on_item_scraped, signals.item_scraped) diff --git a/tests/test_pqueues.py b/tests/test_pqueues.py new file mode 100644 index 000000000..ec55033d1 --- /dev/null +++ b/tests/test_pqueues.py @@ -0,0 +1,144 @@ +import tempfile +import unittest + +import queuelib + +from scrapy.http.request import Request +from scrapy.pqueues import ScrapyPriorityQueue, DownloaderAwarePriorityQueue +from scrapy.spiders import Spider +from scrapy.squeues import FifoMemoryQueue +from scrapy.utils.test import get_crawler + +from tests.test_scheduler import MockDownloader, MockEngine + + +class PriorityQueueTest(unittest.TestCase): + def setUp(self): + self.crawler = get_crawler(Spider) + self.spider = self.crawler._create_spider("foo") + + def test_queue_push_pop_one(self): + temp_dir = tempfile.mkdtemp() + queue = ScrapyPriorityQueue.from_crawler(self.crawler, FifoMemoryQueue, temp_dir) + self.assertIsNone(queue.pop()) + self.assertEqual(len(queue), 0) + req1 = Request("https://example.org/1", priority=1) + queue.push(req1) + self.assertEqual(len(queue), 1) + dequeued = queue.pop() + self.assertEqual(len(queue), 0) + self.assertEqual(dequeued.url, req1.url) + self.assertEqual(dequeued.priority, req1.priority) + self.assertEqual(queue.close(), []) + + def test_no_peek_raises(self): + if hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("queuelib.queue.FifoMemoryQueue.peek is defined") + temp_dir = tempfile.mkdtemp() + queue = ScrapyPriorityQueue.from_crawler(self.crawler, FifoMemoryQueue, temp_dir) + queue.push(Request("https://example.org")) + with self.assertRaises(NotImplementedError, msg="The underlying queue class does not implement 'peek'"): + queue.peek() + queue.close() + + def test_peek(self): + if not hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("queuelib.queue.FifoMemoryQueue.peek is undefined") + temp_dir = tempfile.mkdtemp() + queue = ScrapyPriorityQueue.from_crawler(self.crawler, FifoMemoryQueue, temp_dir) + self.assertEqual(len(queue), 0) + self.assertIsNone(queue.peek()) + req1 = Request("https://example.org/1") + req2 = Request("https://example.org/2") + req3 = Request("https://example.org/3") + queue.push(req1) + queue.push(req2) + queue.push(req3) + self.assertEqual(len(queue), 3) + self.assertEqual(queue.peek().url, req1.url) + self.assertEqual(queue.pop().url, req1.url) + self.assertEqual(len(queue), 2) + self.assertEqual(queue.peek().url, req2.url) + self.assertEqual(queue.pop().url, req2.url) + self.assertEqual(len(queue), 1) + self.assertEqual(queue.peek().url, req3.url) + self.assertEqual(queue.pop().url, req3.url) + self.assertEqual(queue.close(), []) + + def test_queue_push_pop_priorities(self): + temp_dir = tempfile.mkdtemp() + queue = ScrapyPriorityQueue.from_crawler(self.crawler, FifoMemoryQueue, temp_dir, [-1, -2, -3]) + self.assertIsNone(queue.pop()) + self.assertEqual(len(queue), 0) + req1 = Request("https://example.org/1", priority=1) + req2 = Request("https://example.org/2", priority=2) + req3 = Request("https://example.org/3", priority=3) + queue.push(req1) + queue.push(req2) + queue.push(req3) + self.assertEqual(len(queue), 3) + dequeued = queue.pop() + self.assertEqual(len(queue), 2) + self.assertEqual(dequeued.url, req3.url) + self.assertEqual(dequeued.priority, req3.priority) + self.assertEqual(queue.close(), [-1, -2]) + + +class DownloaderAwarePriorityQueueTest(unittest.TestCase): + def setUp(self): + crawler = get_crawler(Spider) + crawler.engine = MockEngine(downloader=MockDownloader()) + self.queue = DownloaderAwarePriorityQueue.from_crawler( + crawler=crawler, + downstream_queue_cls=FifoMemoryQueue, + key="foo/bar", + ) + + def tearDown(self): + self.queue.close() + + def test_push_pop(self): + self.assertEqual(len(self.queue), 0) + self.assertIsNone(self.queue.pop()) + req1 = Request("http://www.example.com/1") + req2 = Request("http://www.example.com/2") + req3 = Request("http://www.example.com/3") + self.queue.push(req1) + self.queue.push(req2) + self.queue.push(req3) + self.assertEqual(len(self.queue), 3) + self.assertEqual(self.queue.pop().url, req1.url) + self.assertEqual(len(self.queue), 2) + self.assertEqual(self.queue.pop().url, req2.url) + self.assertEqual(len(self.queue), 1) + self.assertEqual(self.queue.pop().url, req3.url) + self.assertEqual(len(self.queue), 0) + self.assertIsNone(self.queue.pop()) + + def test_no_peek_raises(self): + if hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("queuelib.queue.FifoMemoryQueue.peek is defined") + self.queue.push(Request("https://example.org")) + with self.assertRaises(NotImplementedError, msg="The underlying queue class does not implement 'peek'"): + self.queue.peek() + + def test_peek(self): + if not hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("queuelib.queue.FifoMemoryQueue.peek is undefined") + self.assertEqual(len(self.queue), 0) + req1 = Request("https://example.org/1") + req2 = Request("https://example.org/2") + req3 = Request("https://example.org/3") + self.queue.push(req1) + self.queue.push(req2) + self.queue.push(req3) + self.assertEqual(len(self.queue), 3) + self.assertEqual(self.queue.peek().url, req1.url) + self.assertEqual(self.queue.pop().url, req1.url) + self.assertEqual(len(self.queue), 2) + self.assertEqual(self.queue.peek().url, req2.url) + self.assertEqual(self.queue.pop().url, req2.url) + self.assertEqual(len(self.queue), 1) + self.assertEqual(self.queue.peek().url, req3.url) + self.assertEqual(self.queue.pop().url, req3.url) + self.assertIsNone(self.queue.peek()) diff --git a/tests/test_proxy_connect.py b/tests/test_proxy_connect.py index eb4ecc91d..afdfb2578 100644 --- a/tests/test_proxy_connect.py +++ b/tests/test_proxy_connect.py @@ -4,9 +4,6 @@ import re import sys from subprocess import Popen, PIPE from urllib.parse import urlsplit, urlunsplit -from unittest import skipIf - -import pytest from testfixtures import LogCapture from twisted.internet import defer from twisted.trial.unittest import TestCase @@ -36,14 +33,14 @@ sys.exit(mitmdump()) '-c', script, '--listen-host', '127.0.0.1', '--listen-port', '0', - '--proxyauth', '%s:%s' % (self.auth_user, self.auth_pass), + '--proxyauth', f'{self.auth_user}:{self.auth_pass}', '--certs', cert_path, '--ssl-insecure', ], stdout=PIPE, env=get_testenv()) line = self.proc.stdout.readline().decode('utf-8') host_port = re.search(r'listening at http://([^:]+:\d+)', line).group(1) - address = 'http://%s:%s@%s' % (self.auth_user, self.auth_pass, host_port) + address = f'http://{self.auth_user}:{self.auth_pass}@{host_port}' return address def stop(self): @@ -57,11 +54,14 @@ def _wrong_credentials(proxy_url): return urlunsplit(bad_auth_proxy) -@skipIf(sys.version_info < (3, 5, 4), - "requires mitmproxy < 3.0.0, which these tests do not support") class ProxyConnectTestCase(TestCase): def setUp(self): + try: + import mitmproxy # noqa: F401 + except ImportError: + self.skipTest('mitmproxy is not installed') + self.mockserver = MockServer() self.mockserver.__enter__() self._oldenv = os.environ.copy() @@ -83,14 +83,6 @@ class ProxyConnectTestCase(TestCase): yield crawler.crawl(self.mockserver.url("/status?n=200", is_secure=True)) self._assert_got_response_code(200, log) - @pytest.mark.xfail(reason='Python 3.6+ fails this earlier', condition=sys.version_info >= (3, 6)) - @defer.inlineCallbacks - def test_https_connect_tunnel_error(self): - crawler = get_crawler(SimpleSpider) - with LogCapture() as log: - yield crawler.crawl("https://localhost:99999/status?n=200") - self._assert_got_tunnel_error(log) - @defer.inlineCallbacks def test_https_tunnel_auth_error(self): os.environ['https_proxy'] = _wrong_credentials(os.environ['https_proxy']) @@ -113,7 +105,7 @@ class ProxyConnectTestCase(TestCase): def _assert_got_response_code(self, code, log): print(log) - self.assertEqual(str(log).count('Crawled (%d)' % code), 1) + self.assertEqual(str(log).count(f'Crawled ({code})'), 1) def _assert_got_tunnel_error(self, log): print(log) diff --git a/tests/test_request_attribute_binding.py b/tests/test_request_attribute_binding.py new file mode 100644 index 000000000..00c532c41 --- /dev/null +++ b/tests/test_request_attribute_binding.py @@ -0,0 +1,202 @@ +from twisted.internet import defer +from twisted.trial.unittest import TestCase + +from scrapy import Request, signals +from scrapy.crawler import CrawlerRunner +from scrapy.http.response import Response + +from testfixtures import LogCapture + +from tests.mockserver import MockServer +from tests.spiders import SingleRequestSpider + + +OVERRIDEN_URL = "https://example.org" + + +class ProcessResponseMiddleware: + def process_response(self, request, response, spider): + return response.replace(request=Request(OVERRIDEN_URL)) + + +class RaiseExceptionRequestMiddleware: + def process_request(self, request, spider): + 1 / 0 + return request + + +class CatchExceptionOverrideRequestMiddleware: + def process_exception(self, request, exception, spider): + return Response( + url="http://localhost/", + body=b"Caught " + exception.__class__.__name__.encode("utf-8"), + request=Request(OVERRIDEN_URL), + ) + + +class CatchExceptionDoNotOverrideRequestMiddleware: + def process_exception(self, request, exception, spider): + return Response( + url="http://localhost/", + body=b"Caught " + exception.__class__.__name__.encode("utf-8"), + ) + + +class AlternativeCallbacksSpider(SingleRequestSpider): + name = "alternative_callbacks_spider" + + def alt_callback(self, response, foo=None): + self.logger.info("alt_callback was invoked with foo=%s", foo) + + +class AlternativeCallbacksMiddleware: + def process_response(self, request, response, spider): + new_request = request.replace( + url=OVERRIDEN_URL, + callback=spider.alt_callback, + cb_kwargs={"foo": "bar"}, + ) + return response.replace(request=new_request) + + +class CrawlTestCase(TestCase): + + def setUp(self): + self.mockserver = MockServer() + self.mockserver.__enter__() + + def tearDown(self): + self.mockserver.__exit__(None, None, None) + + @defer.inlineCallbacks + def test_response_200(self): + url = self.mockserver.url("/status?n=200") + crawler = CrawlerRunner().create_crawler(SingleRequestSpider) + yield crawler.crawl(seed=url, mockserver=self.mockserver) + response = crawler.spider.meta["responses"][0] + self.assertEqual(response.request.url, url) + + @defer.inlineCallbacks + def test_response_error(self): + for status in ("404", "500"): + url = self.mockserver.url(f"/status?n={status}") + crawler = CrawlerRunner().create_crawler(SingleRequestSpider) + yield crawler.crawl(seed=url, mockserver=self.mockserver) + failure = crawler.spider.meta["failure"] + response = failure.value.response + self.assertEqual(failure.request.url, url) + self.assertEqual(response.request.url, url) + + @defer.inlineCallbacks + def test_downloader_middleware_raise_exception(self): + url = self.mockserver.url("/status?n=200") + runner = CrawlerRunner(settings={ + "DOWNLOADER_MIDDLEWARES": { + RaiseExceptionRequestMiddleware: 590, + }, + }) + crawler = runner.create_crawler(SingleRequestSpider) + yield crawler.crawl(seed=url, mockserver=self.mockserver) + failure = crawler.spider.meta["failure"] + self.assertEqual(failure.request.url, url) + self.assertIsInstance(failure.value, ZeroDivisionError) + + @defer.inlineCallbacks + def test_downloader_middleware_override_request_in_process_response(self): + """ + Downloader middleware which returns a response with an specific 'request' attribute. + + * The spider callback should receive the overriden response.request + * Handlers listening to the response_received signal should receive the overriden response.request + * The "crawled" log message should show the overriden response.request + """ + signal_params = {} + + def signal_handler(response, request, spider): + signal_params["response"] = response + signal_params["request"] = request + + url = self.mockserver.url("/status?n=200") + runner = CrawlerRunner(settings={ + "DOWNLOADER_MIDDLEWARES": { + ProcessResponseMiddleware: 595, + } + }) + crawler = runner.create_crawler(SingleRequestSpider) + crawler.signals.connect(signal_handler, signal=signals.response_received) + + with LogCapture() as log: + yield crawler.crawl(seed=url, mockserver=self.mockserver) + + response = crawler.spider.meta["responses"][0] + self.assertEqual(response.request.url, OVERRIDEN_URL) + + self.assertEqual(signal_params["response"].url, url) + self.assertEqual(signal_params["request"].url, OVERRIDEN_URL) + + log.check_present( + ("scrapy.core.engine", "DEBUG", f"Crawled (200) (referer: None)"), + ) + + @defer.inlineCallbacks + def test_downloader_middleware_override_in_process_exception(self): + """ + An exception is raised but caught by the next middleware, which + returns a Response with a specific 'request' attribute. + + The spider callback should receive the overriden response.request + """ + url = self.mockserver.url("/status?n=200") + runner = CrawlerRunner(settings={ + "DOWNLOADER_MIDDLEWARES": { + RaiseExceptionRequestMiddleware: 590, + CatchExceptionOverrideRequestMiddleware: 595, + }, + }) + crawler = runner.create_crawler(SingleRequestSpider) + yield crawler.crawl(seed=url, mockserver=self.mockserver) + response = crawler.spider.meta["responses"][0] + self.assertEqual(response.body, b"Caught ZeroDivisionError") + self.assertEqual(response.request.url, OVERRIDEN_URL) + + @defer.inlineCallbacks + def test_downloader_middleware_do_not_override_in_process_exception(self): + """ + An exception is raised but caught by the next middleware, which + returns a Response without a specific 'request' attribute. + + The spider callback should receive the original response.request + """ + url = self.mockserver.url("/status?n=200") + runner = CrawlerRunner(settings={ + "DOWNLOADER_MIDDLEWARES": { + RaiseExceptionRequestMiddleware: 590, + CatchExceptionDoNotOverrideRequestMiddleware: 595, + }, + }) + crawler = runner.create_crawler(SingleRequestSpider) + yield crawler.crawl(seed=url, mockserver=self.mockserver) + response = crawler.spider.meta["responses"][0] + self.assertEqual(response.body, b"Caught ZeroDivisionError") + self.assertEqual(response.request.url, url) + + @defer.inlineCallbacks + def test_downloader_middleware_alternative_callback(self): + """ + Downloader middleware which returns a response with a + specific 'request' attribute, with an alternative callback + """ + runner = CrawlerRunner(settings={ + "DOWNLOADER_MIDDLEWARES": { + AlternativeCallbacksMiddleware: 595, + } + }) + crawler = runner.create_crawler(AlternativeCallbacksSpider) + + with LogCapture() as log: + url = self.mockserver.url("/status?n=200") + yield crawler.crawl(seed=url, mockserver=self.mockserver) + + log.check_present( + ("alternative_callbacks_spider", "INFO", "alt_callback was invoked with foo=bar"), + ) diff --git a/tests/test_request_cb_kwargs.py b/tests/test_request_cb_kwargs.py index bd49179aa..145a4e9b2 100644 --- a/tests/test_request_cb_kwargs.py +++ b/tests/test_request_cb_kwargs.py @@ -50,10 +50,10 @@ class KeywordArgumentsSpider(MockServerSpider): name = 'kwargs' custom_settings = { 'DOWNLOADER_MIDDLEWARES': { - __name__ + '.InjectArgumentsDownloaderMiddleware': 750, + InjectArgumentsDownloaderMiddleware: 750, }, 'SPIDER_MIDDLEWARES': { - __name__ + '.InjectArgumentsSpiderMiddleware': 750, + InjectArgumentsSpiderMiddleware: 750, }, } diff --git a/tests/test_utils_reqser.py b/tests/test_request_dict.py similarity index 63% rename from tests/test_utils_reqser.py rename to tests/test_request_dict.py index 450e4bdca..5bdcb975b 100644 --- a/tests/test_utils_reqser.py +++ b/tests/test_request_dict.py @@ -1,8 +1,16 @@ +import sys import unittest +import warnings +from contextlib import suppress -from scrapy.http import Request, FormRequest -from scrapy.spiders import Spider -from scrapy.utils.reqser import request_to_dict, request_from_dict +from scrapy import Spider, Request +from scrapy.exceptions import ScrapyDeprecationWarning +from scrapy.http import FormRequest, JsonRequest +from scrapy.utils.request import request_from_dict + + +class CustomRequest(Request): + pass class RequestSerializationTest(unittest.TestCase): @@ -22,12 +30,13 @@ class RequestSerializationTest(unittest.TestCase): method="POST", body=b"some body", headers={'content-encoding': 'text/html; charset=latin-1'}, - cookies={'currency': u'руб'}, + cookies={'currency': 'руб'}, encoding='latin-1', priority=20, meta={'a': 'b'}, cb_kwargs={'k': 'v'}, - flags=['testFlag']) + flags=['testFlag'], + ) self._assert_serializes_ok(r, spider=self.spider) def test_latin1_body(self): @@ -39,7 +48,7 @@ class RequestSerializationTest(unittest.TestCase): self._assert_serializes_ok(r) def _assert_serializes_ok(self, request, spider=None): - d = request_to_dict(request, spider=spider) + d = request.to_dict(spider=spider) request2 = request_from_dict(d, spider=spider) self._assert_same_request(request, request2) @@ -54,16 +63,21 @@ class RequestSerializationTest(unittest.TestCase): self.assertEqual(r1.cookies, r2.cookies) self.assertEqual(r1.meta, r2.meta) self.assertEqual(r1.cb_kwargs, r2.cb_kwargs) + self.assertEqual(r1.encoding, r2.encoding) self.assertEqual(r1._encoding, r2._encoding) self.assertEqual(r1.priority, r2.priority) self.assertEqual(r1.dont_filter, r2.dont_filter) self.assertEqual(r1.flags, r2.flags) + if isinstance(r1, JsonRequest): + self.assertEqual(r1.dumps_kwargs, r2.dumps_kwargs) def test_request_class(self): - r = FormRequest("http://www.example.com") - self._assert_serializes_ok(r, spider=self.spider) - r = CustomRequest("http://www.example.com") - self._assert_serializes_ok(r, spider=self.spider) + r1 = FormRequest("http://www.example.com") + self._assert_serializes_ok(r1, spider=self.spider) + r2 = CustomRequest("http://www.example.com") + self._assert_serializes_ok(r2, spider=self.spider) + r3 = JsonRequest("http://www.example.com", dumps_kwargs={"indent": 4}) + self._assert_serializes_ok(r3, spider=self.spider) def test_callback_serialization(self): r = Request("http://www.example.com", callback=self.spider.parse_item, @@ -75,7 +89,7 @@ class RequestSerializationTest(unittest.TestCase): callback=self.spider.parse_item_reference, errback=self.spider.handle_error_reference) self._assert_serializes_ok(r, spider=self.spider) - request_dict = request_to_dict(r, self.spider) + request_dict = r.to_dict(spider=self.spider) self.assertEqual(request_dict['callback'], 'parse_item_reference') self.assertEqual(request_dict['errback'], 'handle_error_reference') @@ -84,7 +98,7 @@ class RequestSerializationTest(unittest.TestCase): callback=self.spider._TestSpider__parse_item_reference, errback=self.spider._TestSpider__handle_error_reference) self._assert_serializes_ok(r, spider=self.spider) - request_dict = request_to_dict(r, self.spider) + request_dict = r.to_dict(spider=self.spider) self.assertEqual(request_dict['callback'], '_TestSpider__parse_item_reference') self.assertEqual(request_dict['errback'], @@ -102,20 +116,24 @@ class RequestSerializationTest(unittest.TestCase): errback=self.spider.handle_error) self._assert_serializes_ok(r, spider=self.spider) + def test_delegated_callback_serialization(self): + r = Request("http://www.example.com", + callback=self.spider.delegated_callback, + errback=self.spider.handle_error) + self._assert_serializes_ok(r, spider=self.spider) + def test_unserializable_callback1(self): r = Request("http://www.example.com", callback=lambda x: x) - self.assertRaises(ValueError, request_to_dict, r) - self.assertRaises(ValueError, request_to_dict, r, spider=self.spider) + self.assertRaises(ValueError, r.to_dict, spider=self.spider) def test_unserializable_callback2(self): r = Request("http://www.example.com", callback=self.spider.parse_item) - self.assertRaises(ValueError, request_to_dict, r) + self.assertRaises(ValueError, r.to_dict, spider=None) def test_unserializable_callback3(self): """Parser method is removed or replaced dynamically.""" class MySpider(Spider): - name = 'my_spider' def parse(self, response): @@ -124,7 +142,35 @@ class RequestSerializationTest(unittest.TestCase): spider = MySpider() r = Request("http://www.example.com", callback=spider.parse) setattr(spider, 'parse', None) - self.assertRaises(ValueError, request_to_dict, r, spider=spider) + self.assertRaises(ValueError, r.to_dict, spider=spider) + + def test_callback_not_available(self): + """Callback method is not available in the spider passed to from_dict""" + spider = TestSpiderDelegation() + r = Request("http://www.example.com", callback=spider.delegated_callback) + d = r.to_dict(spider=spider) + self.assertRaises(ValueError, request_from_dict, d, spider=Spider("foo")) + + +class DeprecatedMethodsRequestSerializationTest(RequestSerializationTest): + def _assert_serializes_ok(self, request, spider=None): + with warnings.catch_warnings(record=True) as caught: + warnings.simplefilter("always") + with suppress(KeyError): + del sys.modules["scrapy.utils.reqser"] # delete module to reset the deprecation warning + + from scrapy.utils.reqser import request_from_dict as _from_dict, request_to_dict as _to_dict + + request_copy = _from_dict(_to_dict(request, spider), spider) + self._assert_same_request(request, request_copy) + + self.assertEqual(len(caught), 1) + self.assertTrue(issubclass(caught[0].category, ScrapyDeprecationWarning)) + self.assertEqual( + "Module scrapy.utils.reqser is deprecated, please use request.to_dict method" + " and/or scrapy.utils.request.request_from_dict instead", + str(caught[0].message), + ) class TestSpiderMixin: @@ -132,6 +178,11 @@ class TestSpiderMixin: pass +class TestSpiderDelegation: + def delegated_callback(self, response): + pass + + def parse_item(response): pass @@ -155,6 +206,9 @@ class TestSpider(Spider, TestSpiderMixin): __parse_item_reference = private_parse_item __handle_error_reference = private_handle_error + def __init__(self): + self.delegated_callback = TestSpiderDelegation().delegated_callback + def parse_item(self, response): pass @@ -163,7 +217,3 @@ class TestSpider(Spider, TestSpiderMixin): def __parse_item_private(self, response): pass - - -class CustomRequest(Request): - pass diff --git a/tests/test_request_left.py b/tests/test_request_left.py index 5cfef8e7d..373b2e49c 100644 --- a/tests/test_request_left.py +++ b/tests/test_request_left.py @@ -10,7 +10,7 @@ class SignalCatcherSpider(Spider): name = 'signal_catcher' def __init__(self, crawler, url, *args, **kwargs): - super(SignalCatcherSpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) crawler.signals.connect(self.on_request_left, signal=request_left_downloader) self.caught_times = 0 diff --git a/tests/test_responsetypes.py b/tests/test_responsetypes.py index dd19a69d5..c07d3a99c 100644 --- a/tests/test_responsetypes.py +++ b/tests/test_responsetypes.py @@ -17,22 +17,22 @@ class ResponseTypesTest(unittest.TestCase): ] for source, cls in mappings: retcls = responsetypes.from_filename(source) - assert retcls is cls, "%s ==> %s != %s" % (source, retcls, cls) + assert retcls is cls, f"{source} ==> {retcls} != {cls}" def test_from_content_disposition(self): mappings = [ (b'attachment; filename="data.xml"', XmlResponse), (b'attachment; filename=data.xml', XmlResponse), - (u'attachment;filename=data£.tar.gz'.encode('utf-8'), Response), - (u'attachment;filename=dataµ.tar.gz'.encode('latin-1'), Response), - (u'attachment;filename=data高.doc'.encode('gbk'), Response), - (u'attachment;filename=دورهdata.html'.encode('cp720'), HtmlResponse), - (u'attachment;filename=日本語版Wikipedia.xml'.encode('iso2022_jp'), XmlResponse), + ('attachment;filename=data£.tar.gz'.encode('utf-8'), Response), + ('attachment;filename=dataµ.tar.gz'.encode('latin-1'), Response), + ('attachment;filename=data高.doc'.encode('gbk'), Response), + ('attachment;filename=دورهdata.html'.encode('cp720'), HtmlResponse), + ('attachment;filename=日本語版Wikipedia.xml'.encode('iso2022_jp'), XmlResponse), ] for source, cls in mappings: retcls = responsetypes.from_content_disposition(source) - assert retcls is cls, "%s ==> %s != %s" % (source, retcls, cls) + assert retcls is cls, f"{source} ==> {retcls} != {cls}" def test_from_content_type(self): mappings = [ @@ -47,7 +47,7 @@ class ResponseTypesTest(unittest.TestCase): ] for source, cls in mappings: retcls = responsetypes.from_content_type(source) - assert retcls is cls, "%s ==> %s != %s" % (source, retcls, cls) + assert retcls is cls, f"{source} ==> {retcls} != {cls}" def test_from_body(self): mappings = [ @@ -58,7 +58,7 @@ class ResponseTypesTest(unittest.TestCase): ] for source, cls in mappings: retcls = responsetypes.from_body(source) - assert retcls is cls, "%s ==> %s != %s" % (source, retcls, cls) + assert retcls is cls, f"{source} ==> {retcls} != {cls}" def test_from_headers(self): mappings = [ @@ -70,7 +70,7 @@ class ResponseTypesTest(unittest.TestCase): for source, cls in mappings: source = Headers(source) retcls = responsetypes.from_headers(source) - assert retcls is cls, "%s ==> %s != %s" % (source, retcls, cls) + assert retcls is cls, f"{source} ==> {retcls} != {cls}" def test_from_args(self): # TODO: add more tests that check precedence between the different arguments @@ -86,7 +86,7 @@ class ResponseTypesTest(unittest.TestCase): ] for source, cls in mappings: retcls = responsetypes.from_args(**source) - assert retcls is cls, "%s ==> %s != %s" % (source, retcls, cls) + assert retcls is cls, f"{source} ==> {retcls} != {cls}" def test_custom_mime_types_loaded(self): # check that mime.types files shipped with scrapy are loaded diff --git a/tests/test_robotstxt_interface.py b/tests/test_robotstxt_interface.py index 24aaaf7ec..4b15d0fab 100644 --- a/tests/test_robotstxt_interface.py +++ b/tests/test_robotstxt_interface.py @@ -93,7 +93,7 @@ class BaseRobotParserTest: self.assertTrue(rp.allowed("https://site.local/disallowed", "*")) def test_unicode_url_and_useragent(self): - robotstxt_robotstxt_body = u""" + robotstxt_robotstxt_body = """ User-Agent: * Disallow: /admin/ Disallow: /static/ @@ -107,17 +107,17 @@ class BaseRobotParserTest: self.assertTrue(rp.allowed("https://site.local/", "*")) self.assertFalse(rp.allowed("https://site.local/admin/", "*")) self.assertFalse(rp.allowed("https://site.local/static/", "*")) - self.assertTrue(rp.allowed("https://site.local/admin/", u"UnicödeBöt")) + self.assertTrue(rp.allowed("https://site.local/admin/", "UnicödeBöt")) self.assertFalse(rp.allowed("https://site.local/wiki/K%C3%A4ytt%C3%A4j%C3%A4:", "*")) - self.assertFalse(rp.allowed(u"https://site.local/wiki/Käyttäjä:", "*")) + self.assertFalse(rp.allowed("https://site.local/wiki/Käyttäjä:", "*")) self.assertTrue(rp.allowed("https://site.local/some/randome/page.html", "*")) - self.assertFalse(rp.allowed("https://site.local/some/randome/page.html", u"UnicödeBöt")) + self.assertFalse(rp.allowed("https://site.local/some/randome/page.html", "UnicödeBöt")) class PythonRobotParserTest(BaseRobotParserTest, unittest.TestCase): def setUp(self): from scrapy.robotstxt import PythonRobotParser - super(PythonRobotParserTest, self)._setUp(PythonRobotParser) + super()._setUp(PythonRobotParser) def test_length_based_precedence(self): raise unittest.SkipTest("RobotFileParser does not support length based directives precedence.") @@ -132,7 +132,7 @@ class ReppyRobotParserTest(BaseRobotParserTest, unittest.TestCase): def setUp(self): from scrapy.robotstxt import ReppyRobotParser - super(ReppyRobotParserTest, self)._setUp(ReppyRobotParser) + super()._setUp(ReppyRobotParser) def test_order_based_precedence(self): raise unittest.SkipTest("Reppy does not support order based directives precedence.") @@ -144,7 +144,7 @@ class RerpRobotParserTest(BaseRobotParserTest, unittest.TestCase): def setUp(self): from scrapy.robotstxt import RerpRobotParser - super(RerpRobotParserTest, self)._setUp(RerpRobotParser) + super()._setUp(RerpRobotParser) def test_length_based_precedence(self): raise unittest.SkipTest("Rerp does not support length based directives precedence.") @@ -156,7 +156,7 @@ class ProtegoRobotParserTest(BaseRobotParserTest, unittest.TestCase): def setUp(self): from scrapy.robotstxt import ProtegoRobotParser - super(ProtegoRobotParserTest, self)._setUp(ProtegoRobotParser) + super()._setUp(ProtegoRobotParser) def test_order_based_precedence(self): raise unittest.SkipTest("Protego does not support order based directives precedence.") diff --git a/tests/test_scheduler.py b/tests/test_scheduler.py index 930a5dd99..512a7460e 100644 --- a/tests/test_scheduler.py +++ b/tests/test_scheduler.py @@ -53,7 +53,7 @@ class MockCrawler(Crawler): JOBDIR=jobdir, DUPEFILTER_CLASS='scrapy.dupefilters.BaseDupeFilter', ) - super(MockCrawler, self).__init__(Spider, settings) + super().__init__(Spider, settings) self.engine = MockEngine(downloader=MockDownloader()) @@ -296,7 +296,7 @@ class StartUrlsSpider(Spider): def __init__(self, start_urls): self.start_urls = start_urls - super(StartUrlsSpider, self).__init__(start_urls) + super().__init__(name='StartUrlsSpider') def parse(self, response): pass diff --git a/tests/test_scheduler_base.py b/tests/test_scheduler_base.py new file mode 100644 index 000000000..bf90b4320 --- /dev/null +++ b/tests/test_scheduler_base.py @@ -0,0 +1,159 @@ +from typing import Dict, Optional +from unittest import TestCase +from urllib.parse import urljoin, urlparse + +from testfixtures import LogCapture +from twisted.internet import defer +from twisted.trial.unittest import TestCase as TwistedTestCase + +from scrapy.core.scheduler import BaseScheduler +from scrapy.crawler import CrawlerRunner +from scrapy.http import Request +from scrapy.spiders import Spider +from scrapy.utils.request import request_fingerprint + +from tests.mockserver import MockServer + + +PATHS = ["/a", "/b", "/c"] +URLS = [urljoin("https://example.org", p) for p in PATHS] + + +class MinimalScheduler: + def __init__(self) -> None: + self.requests: Dict[str, Request] = {} + + def has_pending_requests(self) -> bool: + return bool(self.requests) + + def enqueue_request(self, request: Request) -> bool: + fp = request_fingerprint(request) + if fp not in self.requests: + self.requests[fp] = request + return True + return False + + def next_request(self) -> Optional[Request]: + if self.has_pending_requests(): + fp, request = self.requests.popitem() + return request + return None + + +class SimpleScheduler(MinimalScheduler): + def open(self, spider: Spider) -> defer.Deferred: + return defer.succeed("open") + + def close(self, reason: str) -> defer.Deferred: + return defer.succeed("close") + + def __len__(self) -> int: + return len(self.requests) + + +class TestSpider(Spider): + name = "test" + + def __init__(self, mockserver, *args, **kwargs): + super().__init__(*args, **kwargs) + self.start_urls = map(mockserver.url, PATHS) + + def parse(self, response): + return {"path": urlparse(response.url).path} + + +class InterfaceCheckMixin: + def test_scheduler_class(self): + self.assertTrue(isinstance(self.scheduler, BaseScheduler)) + self.assertTrue(issubclass(self.scheduler.__class__, BaseScheduler)) + + +class BaseSchedulerTest(TestCase, InterfaceCheckMixin): + def setUp(self): + self.scheduler = BaseScheduler() + + def test_methods(self): + self.assertIsNone(self.scheduler.open(Spider("foo"))) + self.assertIsNone(self.scheduler.close("finished")) + self.assertRaises(NotImplementedError, self.scheduler.has_pending_requests) + self.assertRaises(NotImplementedError, self.scheduler.enqueue_request, Request("https://example.org")) + self.assertRaises(NotImplementedError, self.scheduler.next_request) + + +class MinimalSchedulerTest(TestCase, InterfaceCheckMixin): + def setUp(self): + self.scheduler = MinimalScheduler() + + def test_open_close(self): + with self.assertRaises(AttributeError): + self.scheduler.open(Spider("foo")) + with self.assertRaises(AttributeError): + self.scheduler.close("finished") + + def test_len(self): + with self.assertRaises(AttributeError): + self.scheduler.__len__() + with self.assertRaises(TypeError): + len(self.scheduler) + + def test_enqueue_dequeue(self): + self.assertFalse(self.scheduler.has_pending_requests()) + for url in URLS: + self.assertTrue(self.scheduler.enqueue_request(Request(url))) + self.assertFalse(self.scheduler.enqueue_request(Request(url))) + self.assertTrue(self.scheduler.has_pending_requests) + + dequeued = [] + while self.scheduler.has_pending_requests(): + request = self.scheduler.next_request() + dequeued.append(request.url) + self.assertEqual(set(dequeued), set(URLS)) + self.assertFalse(self.scheduler.has_pending_requests()) + + +class SimpleSchedulerTest(TwistedTestCase, InterfaceCheckMixin): + def setUp(self): + self.scheduler = SimpleScheduler() + + @defer.inlineCallbacks + def test_enqueue_dequeue(self): + open_result = yield self.scheduler.open(Spider("foo")) + self.assertEqual(open_result, "open") + self.assertFalse(self.scheduler.has_pending_requests()) + + for url in URLS: + self.assertTrue(self.scheduler.enqueue_request(Request(url))) + self.assertFalse(self.scheduler.enqueue_request(Request(url))) + + self.assertTrue(self.scheduler.has_pending_requests()) + self.assertEqual(len(self.scheduler), len(URLS)) + + dequeued = [] + while self.scheduler.has_pending_requests(): + request = self.scheduler.next_request() + dequeued.append(request.url) + self.assertEqual(set(dequeued), set(URLS)) + + self.assertFalse(self.scheduler.has_pending_requests()) + self.assertEqual(len(self.scheduler), 0) + + close_result = yield self.scheduler.close("") + self.assertEqual(close_result, "close") + + +class MinimalSchedulerCrawlTest(TwistedTestCase): + scheduler_cls = MinimalScheduler + + @defer.inlineCallbacks + def test_crawl(self): + with MockServer() as mockserver: + settings = {"SCHEDULER": self.scheduler_cls} + with LogCapture() as log: + yield CrawlerRunner(settings).crawl(TestSpider, mockserver) + for path in PATHS: + self.assertIn(f"{{'path': '{path}'}}", str(log)) + self.assertIn(f"'item_scraped_count': {len(PATHS)}", str(log)) + + +class SimpleSchedulerCrawlTest(MinimalSchedulerCrawlTest): + scheduler_cls = SimpleScheduler diff --git a/tests/test_selector.py b/tests/test_selector.py index bcf653444..cff8d0393 100644 --- a/tests/test_selector.py +++ b/tests/test_selector.py @@ -25,19 +25,19 @@ class SelectorTestCase(unittest.TestCase): ) self.assertEqual( [x.get() for x in sel.xpath("//input[@name='a']/@name")], - [u'a'] + ['a'] ) self.assertEqual( [x.get() for x in sel.xpath("number(concat(//input[@name='a']/@value, //input[@name='b']/@value))")], - [u'12.0'] + ['12.0'] ) self.assertEqual( sel.xpath("concat('xpath', 'rules')").getall(), - [u'xpathrules'] + ['xpathrules'] ) self.assertEqual( [x.get() for x in sel.xpath("concat(//input[@name='a']/@value, //input[@name='b']/@value)")], - [u'12'] + ['12'] ) def test_root_base_url(self): @@ -52,30 +52,30 @@ class SelectorTestCase(unittest.TestCase): sel = Selector(XmlResponse('http://example.com', body=text, encoding='utf-8')) self.assertEqual(sel.type, 'xml') self.assertEqual(sel.xpath("//div").getall(), - [u'

    Hello

    ']) + ['

    Hello

    ']) sel = Selector(HtmlResponse('http://example.com', body=text, encoding='utf-8')) self.assertEqual(sel.type, 'html') self.assertEqual(sel.xpath("//div").getall(), - [u'

    Hello

    ']) + ['

    Hello

    ']) def test_http_header_encoding_precedence(self): - # u'\xa3' = pound symbol in unicode - # u'\xc2\xa3' = pound symbol in utf-8 - # u'\xa3' = pound symbol in latin-1 (iso-8859-1) + # '\xa3' = pound symbol in unicode + # '\xc2\xa3' = pound symbol in utf-8 + # '\xa3' = pound symbol in latin-1 (iso-8859-1) - meta = u'' - head = u'' + meta + u'' - body_content = u'\xa3' - body = u'' + body_content + u'' - html = u'' + head + body + u'' + meta = '' + head = '' + meta + '' + body_content = '\xa3' + body = '' + body_content + '' + html = '' + head + body + '' encoding = 'utf-8' html_utf8 = html.encode(encoding) headers = {'Content-Type': ['text/html; charset=utf-8']} response = HtmlResponse(url="http://example.com", headers=headers, body=html_utf8) x = Selector(response) - self.assertEqual(x.xpath("//span[@id='blank']/text()").getall(), [u'\xa3']) + self.assertEqual(x.xpath("//span[@id='blank']/text()").getall(), ['\xa3']) def test_badly_encoded_body(self): # \xe9 alone isn't valid utf8 sequence @@ -88,9 +88,8 @@ class SelectorTestCase(unittest.TestCase): """Check that classes are using slots and are weak-referenceable""" x = Selector(text='') weakref.ref(x) - assert not hasattr(x, '__dict__'), "%s does not use __slots__" % \ - x.__class__.__name__ + assert not hasattr(x, '__dict__'), f"{x.__class__.__name__} does not use __slots__" def test_selector_bad_args(self): with self.assertRaisesRegex(ValueError, 'received both response and text'): - Selector(TextResponse(url='http://example.com', body=b''), text=u'') + Selector(TextResponse(url='http://example.com', body=b''), text='') diff --git a/tests/test_settings/__init__.py b/tests/test_settings/__init__.py index 2da6aa4b5..916fe012a 100644 --- a/tests/test_settings/__init__.py +++ b/tests/test_settings/__init__.py @@ -86,8 +86,7 @@ class BaseSettingsTest(unittest.TestCase): def test_set_calls_settings_attributes_methods_on_update(self): attr = SettingsAttribute('value', 10) - with mock.patch.object(attr, '__setattr__') as mock_setattr, \ - mock.patch.object(attr, 'set') as mock_set: + with mock.patch.object(attr, '__setattr__') as mock_setattr, mock.patch.object(attr, 'set') as mock_set: self.settings.attributes = {'TEST_OPTION': attr} @@ -386,6 +385,38 @@ class SettingsTest(unittest.TestCase): self.assertIn('key', mydict) self.assertEqual(mydict['key'], 'val') + def test_passing_objects_as_values(self): + from scrapy.core.downloader.handlers.file import FileDownloadHandler + from scrapy.utils.misc import create_instance + from scrapy.utils.test import get_crawler + + class TestPipeline(): + def process_item(self, i, s): + return i + + settings = Settings({ + 'ITEM_PIPELINES': { + TestPipeline: 800, + }, + 'DOWNLOAD_HANDLERS': { + 'ftp': FileDownloadHandler, + }, + }) + + self.assertIn('ITEM_PIPELINES', settings.attributes) + + mypipeline, priority = settings.getdict('ITEM_PIPELINES').popitem() + self.assertEqual(priority, 800) + self.assertEqual(mypipeline, TestPipeline) + self.assertIsInstance(mypipeline(), TestPipeline) + self.assertEqual(mypipeline().process_item('item', None), 'item') + + myhandler = settings.getdict('DOWNLOAD_HANDLERS').pop('ftp') + self.assertEqual(myhandler, FileDownloadHandler) + myhandler_instance = create_instance(myhandler, None, get_crawler()) + self.assertIsInstance(myhandler_instance, FileDownloadHandler) + self.assertTrue(hasattr(myhandler_instance, 'download_request')) + if __name__ == "__main__": unittest.main() diff --git a/tests/test_signals.py b/tests/test_signals.py index d6ae526be..a43f00b27 100644 --- a/tests/test_signals.py +++ b/tests/test_signals.py @@ -13,7 +13,7 @@ class ItemSpider(Spider): def start_requests(self): for index in range(10): - yield Request(self.mockserver.url('/status?n=200&id=%d' % index), + yield Request(self.mockserver.url(f'/status?n=200&id={index}'), meta={'index': index}) def parse(self, response): diff --git a/tests/test_spider.py b/tests/test_spider.py index 805d70459..d23543f6a 100644 --- a/tests/test_spider.py +++ b/tests/test_spider.py @@ -1,8 +1,8 @@ import gzip import inspect -from unittest import mock import warnings from io import BytesIO +from unittest import mock from testfixtures import LogCapture from twisted.trial import unittest @@ -11,10 +11,15 @@ from scrapy import signals from scrapy.settings import Settings from scrapy.http import Request, Response, TextResponse, XmlResponse, HtmlResponse from scrapy.spiders.init import InitSpider -from scrapy.spiders import Spider, CrawlSpider, Rule, XMLFeedSpider, \ - CSVFeedSpider, SitemapSpider +from scrapy.spiders import ( + CSVFeedSpider, + CrawlSpider, + Rule, + SitemapSpider, + Spider, + XMLFeedSpider, +) from scrapy.linkextractors import LinkExtractor -from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.utils.test import get_crawler @@ -144,16 +149,16 @@ class XMLFeedSpiderTest(SpiderTest): for iterator in ('iternodes', 'xml'): spider = _XMLSpider('example', iterator=iterator) - output = list(spider.parse(response)) + output = list(spider._parse(response)) self.assertEqual(len(output), 2, iterator) self.assertEqual(output, [ - {'loc': [u'http://www.example.com/Special-Offers.html'], - 'updated': [u'2009-08-16'], - 'custom': [u'fuu'], - 'other': [u'bar']}, + {'loc': ['http://www.example.com/Special-Offers.html'], + 'updated': ['2009-08-16'], + 'custom': ['fuu'], + 'other': ['bar']}, {'loc': [], - 'updated': [u'2009-08-16'], - 'other': [u'foo'], + 'updated': ['2009-08-16'], + 'other': ['foo'], 'custom': []}, ], iterator) @@ -274,7 +279,7 @@ class CrawlSpiderTest(SpiderTest): response = HtmlResponse("http://example.org/somepage/index.html", body=self.test_body) - def process_request_change_domain(request): + def process_request_change_domain(request, response): return request.replace(url=request.url.replace('.org', '.com')) class _CrawlSpider(self.spider_class): @@ -284,17 +289,14 @@ class CrawlSpiderTest(SpiderTest): Rule(LinkExtractor(), process_request=process_request_change_domain), ) - with warnings.catch_warnings(record=True) as cw: - spider = _CrawlSpider() - output = list(spider._requests_to_follow(response)) - self.assertEqual(len(output), 3) - self.assertTrue(all(map(lambda r: isinstance(r, Request), output))) - self.assertEqual([r.url for r in output], - ['http://example.com/somepage/item/12.html', - 'http://example.com/about.html', - 'http://example.com/nofollow.html']) - self.assertEqual(len(cw), 1) - self.assertEqual(cw[0].category, ScrapyDeprecationWarning) + spider = _CrawlSpider() + output = list(spider._requests_to_follow(response)) + self.assertEqual(len(output), 3) + self.assertTrue(all(map(lambda r: isinstance(r, Request), output))) + self.assertEqual([r.url for r in output], + ['http://example.com/somepage/item/12.html', + 'http://example.com/about.html', + 'http://example.com/nofollow.html']) def test_process_request_with_response(self): @@ -333,20 +335,17 @@ class CrawlSpiderTest(SpiderTest): Rule(LinkExtractor(), process_request='process_request_upper'), ) - def process_request_upper(self, request): + def process_request_upper(self, request, response): return request.replace(url=request.url.upper()) - with warnings.catch_warnings(record=True) as cw: - spider = _CrawlSpider() - output = list(spider._requests_to_follow(response)) - self.assertEqual(len(output), 3) - self.assertTrue(all(map(lambda r: isinstance(r, Request), output))) - self.assertEqual([r.url for r in output], - ['http://EXAMPLE.ORG/SOMEPAGE/ITEM/12.HTML', - 'http://EXAMPLE.ORG/ABOUT.HTML', - 'http://EXAMPLE.ORG/NOFOLLOW.HTML']) - self.assertEqual(len(cw), 1) - self.assertEqual(cw[0].category, ScrapyDeprecationWarning) + spider = _CrawlSpider() + output = list(spider._requests_to_follow(response)) + self.assertEqual(len(output), 3) + self.assertTrue(all(map(lambda r: isinstance(r, Request), output))) + self.assertEqual([r.url for r in output], + ['http://EXAMPLE.ORG/SOMEPAGE/ITEM/12.HTML', + 'http://EXAMPLE.ORG/ABOUT.HTML', + 'http://EXAMPLE.ORG/NOFOLLOW.HTML']) def test_process_request_instance_method_with_response(self): diff --git a/tests/test_spiderloader/__init__.py b/tests/test_spiderloader/__init__.py index d922c6059..4929f1e3e 100644 --- a/tests/test_spiderloader/__init__.py +++ b/tests/test_spiderloader/__init__.py @@ -20,13 +20,20 @@ from scrapy.crawler import CrawlerRunner module_dir = os.path.dirname(os.path.abspath(__file__)) +def _copytree(source, target): + try: + shutil.copytree(source, target) + except shutil.Error: + pass + + class SpiderLoaderTest(unittest.TestCase): def setUp(self): orig_spiders_dir = os.path.join(module_dir, 'test_spiders') self.tmpdir = tempfile.mkdtemp() self.spiders_dir = os.path.join(self.tmpdir, 'test_spiders_xxx') - shutil.copytree(orig_spiders_dir, self.spiders_dir) + _copytree(orig_spiders_dir, self.spiders_dir) sys.path.append(self.tmpdir) settings = Settings({'SPIDER_MODULES': ['test_spiders_xxx']}) self.spider_loader = SpiderLoader.from_settings(settings) @@ -124,7 +131,7 @@ class DuplicateSpiderNameLoaderTest(unittest.TestCase): self.tmpdir = self.mktemp() os.mkdir(self.tmpdir) self.spiders_dir = os.path.join(self.tmpdir, 'test_spiders_xxx') - shutil.copytree(orig_spiders_dir, self.spiders_dir) + _copytree(orig_spiders_dir, self.spiders_dir) sys.path.append(self.tmpdir) self.settings = Settings({'SPIDER_MODULES': ['test_spiders_xxx']}) @@ -134,8 +141,8 @@ class DuplicateSpiderNameLoaderTest(unittest.TestCase): def test_dupename_warning(self): # copy 1 spider module so as to have duplicate spider name - shutil.copyfile(os.path.join(self.tmpdir, 'test_spiders_xxx/spider3.py'), - os.path.join(self.tmpdir, 'test_spiders_xxx/spider3dupe.py')) + shutil.copyfile(os.path.join(self.tmpdir, 'test_spiders_xxx', 'spider3.py'), + os.path.join(self.tmpdir, 'test_spiders_xxx', 'spider3dupe.py')) with warnings.catch_warnings(record=True) as w: spider_loader = SpiderLoader.from_settings(self.settings) @@ -156,10 +163,10 @@ class DuplicateSpiderNameLoaderTest(unittest.TestCase): def test_multiple_dupename_warning(self): # copy 2 spider modules so as to have duplicate spider name # This should issue 2 warning, 1 for each duplicate spider name - shutil.copyfile(os.path.join(self.tmpdir, 'test_spiders_xxx/spider1.py'), - os.path.join(self.tmpdir, 'test_spiders_xxx/spider1dupe.py')) - shutil.copyfile(os.path.join(self.tmpdir, 'test_spiders_xxx/spider2.py'), - os.path.join(self.tmpdir, 'test_spiders_xxx/spider2dupe.py')) + shutil.copyfile(os.path.join(self.tmpdir, 'test_spiders_xxx', 'spider1.py'), + os.path.join(self.tmpdir, 'test_spiders_xxx', 'spider1dupe.py')) + shutil.copyfile(os.path.join(self.tmpdir, 'test_spiders_xxx', 'spider2.py'), + os.path.join(self.tmpdir, 'test_spiders_xxx', 'spider2dupe.py')) with warnings.catch_warnings(record=True) as w: spider_loader = SpiderLoader.from_settings(self.settings) diff --git a/tests/test_spidermiddleware_httperror.py b/tests/test_spidermiddleware_httperror.py index e032b247c..46f74ae52 100644 --- a/tests/test_spidermiddleware_httperror.py +++ b/tests/test_spidermiddleware_httperror.py @@ -19,7 +19,7 @@ class _HttpErrorSpider(MockServerSpider): bypass_status_codes = set() def __init__(self, *args, **kwargs): - super(_HttpErrorSpider, self).__init__(*args, **kwargs) + super().__init__(*args, **kwargs) self.start_urls = [ self.mockserver.url("/status?n=200"), self.mockserver.url("/status?n=404"), @@ -139,6 +139,19 @@ class TestHttpErrorMiddlewareHandleAll(TestCase): self.assertIsNone(self.mw.process_spider_input(res404, self.spider)) self.assertRaises(HttpError, self.mw.process_spider_input, res402, self.spider) + def test_httperror_allow_all_false(self): + crawler = get_crawler(_HttpErrorSpider) + mw = HttpErrorMiddleware.from_crawler(crawler) + request_httpstatus_false = Request('http://scrapytest.org', meta={'handle_httpstatus_all': False}) + request_httpstatus_true = Request('http://scrapytest.org', meta={'handle_httpstatus_all': True}) + res404 = self.res404.copy() + res404.request = request_httpstatus_false + res402 = self.res402.copy() + res402.request = request_httpstatus_true + + self.assertRaises(HttpError, mw.process_spider_input, res404, self.spider) + self.assertIsNone(mw.process_spider_input(res402, self.spider)) + class TestHttpErrorMiddlewareIntegrational(TrialTestCase): def setUp(self): diff --git a/tests/test_spidermiddleware_output_chain.py b/tests/test_spidermiddleware_output_chain.py index 79eda35b3..029bf8bd6 100644 --- a/tests/test_spidermiddleware_output_chain.py +++ b/tests/test_spidermiddleware_output_chain.py @@ -16,11 +16,20 @@ class LogExceptionMiddleware: # ================================================================================ # (0) recover from an exception on a spider callback +class RecoveryMiddleware: + def process_spider_exception(self, response, exception, spider): + spider.logger.info('Middleware: %s exception caught', exception.__class__.__name__) + return [ + {'from': 'process_spider_exception'}, + Request(response.url, meta={'dont_fail': True}, dont_filter=True), + ] + + class RecoverySpider(Spider): name = 'RecoverySpider' custom_settings = { 'SPIDER_MIDDLEWARES': { - __name__ + '.RecoveryMiddleware': 10, + RecoveryMiddleware: 10, }, } @@ -34,15 +43,6 @@ class RecoverySpider(Spider): raise TabError() -class RecoveryMiddleware: - def process_spider_exception(self, response, exception, spider): - spider.logger.info('Middleware: %s exception caught', exception.__class__.__name__) - return [ - {'from': 'process_spider_exception'}, - Request(response.url, meta={'dont_fail': True}, dont_filter=True), - ] - - # ================================================================================ # (1) exceptions from a spider middleware's process_spider_input method class FailProcessSpiderInputMiddleware: @@ -56,9 +56,8 @@ class ProcessSpiderInputSpiderWithoutErrback(Spider): custom_settings = { 'SPIDER_MIDDLEWARES': { # spider - __name__ + '.LogExceptionMiddleware': 10, - __name__ + '.FailProcessSpiderInputMiddleware': 8, - __name__ + '.LogExceptionMiddleware': 6, + FailProcessSpiderInputMiddleware: 8, + LogExceptionMiddleware: 6, # engine } } @@ -87,7 +86,7 @@ class GeneratorCallbackSpider(Spider): name = 'GeneratorCallbackSpider' custom_settings = { 'SPIDER_MIDDLEWARES': { - __name__ + '.LogExceptionMiddleware': 10, + LogExceptionMiddleware: 10, }, } @@ -106,7 +105,7 @@ class GeneratorCallbackSpiderMiddlewareRightAfterSpider(GeneratorCallbackSpider) name = 'GeneratorCallbackSpiderMiddlewareRightAfterSpider' custom_settings = { 'SPIDER_MIDDLEWARES': { - __name__ + '.LogExceptionMiddleware': 100000, + LogExceptionMiddleware: 100000, }, } @@ -117,7 +116,7 @@ class NotGeneratorCallbackSpider(Spider): name = 'NotGeneratorCallbackSpider' custom_settings = { 'SPIDER_MIDDLEWARES': { - __name__ + '.LogExceptionMiddleware': 10, + LogExceptionMiddleware: 10, }, } @@ -134,40 +133,21 @@ class NotGeneratorCallbackSpiderMiddlewareRightAfterSpider(NotGeneratorCallbackS name = 'NotGeneratorCallbackSpiderMiddlewareRightAfterSpider' custom_settings = { 'SPIDER_MIDDLEWARES': { - __name__ + '.LogExceptionMiddleware': 100000, + LogExceptionMiddleware: 100000, }, } # ================================================================================ # (4) exceptions from a middleware process_spider_output method (generator) -class GeneratorOutputChainSpider(Spider): - name = 'GeneratorOutputChainSpider' - custom_settings = { - 'SPIDER_MIDDLEWARES': { - __name__ + '.GeneratorFailMiddleware': 10, - __name__ + '.GeneratorDoNothingAfterFailureMiddleware': 8, - __name__ + '.GeneratorRecoverMiddleware': 5, - __name__ + '.GeneratorDoNothingAfterRecoveryMiddleware': 3, - }, - } - - def start_requests(self): - yield Request(self.mockserver.url('/status?n=200')) - - def parse(self, response): - yield {'processed': ['parse-first-item']} - yield {'processed': ['parse-second-item']} - - class _GeneratorDoNothingMiddleware: def process_spider_output(self, response, result, spider): for r in result: - r['processed'].append('{}.process_spider_output'.format(self.__class__.__name__)) + r['processed'].append(f'{self.__class__.__name__}.process_spider_output') yield r def process_spider_exception(self, response, exception, spider): - method = '{}.process_spider_exception'.format(self.__class__.__name__) + method = f'{self.__class__.__name__}.process_spider_exception' spider.logger.info('%s: %s caught', method, exception.__class__.__name__) return None @@ -175,12 +155,12 @@ class _GeneratorDoNothingMiddleware: class GeneratorFailMiddleware: def process_spider_output(self, response, result, spider): for r in result: - r['processed'].append('{}.process_spider_output'.format(self.__class__.__name__)) + r['processed'].append(f'{self.__class__.__name__}.process_spider_output') yield r raise LookupError() def process_spider_exception(self, response, exception, spider): - method = '{}.process_spider_exception'.format(self.__class__.__name__) + method = f'{self.__class__.__name__}.process_spider_exception' spider.logger.info('%s: %s caught', method, exception.__class__.__name__) yield {'processed': [method]} @@ -192,11 +172,11 @@ class GeneratorDoNothingAfterFailureMiddleware(_GeneratorDoNothingMiddleware): class GeneratorRecoverMiddleware: def process_spider_output(self, response, result, spider): for r in result: - r['processed'].append('{}.process_spider_output'.format(self.__class__.__name__)) + r['processed'].append(f'{self.__class__.__name__}.process_spider_output') yield r def process_spider_exception(self, response, exception, spider): - method = '{}.process_spider_exception'.format(self.__class__.__name__) + method = f'{self.__class__.__name__}.process_spider_exception' spider.logger.info('%s: %s caught', method, exception.__class__.__name__) yield {'processed': [method]} @@ -205,36 +185,38 @@ class GeneratorDoNothingAfterRecoveryMiddleware(_GeneratorDoNothingMiddleware): pass -# ================================================================================ -# (5) exceptions from a middleware process_spider_output method (not generator) -class NotGeneratorOutputChainSpider(Spider): - name = 'NotGeneratorOutputChainSpider' +class GeneratorOutputChainSpider(Spider): + name = 'GeneratorOutputChainSpider' custom_settings = { 'SPIDER_MIDDLEWARES': { - __name__ + '.NotGeneratorFailMiddleware': 10, - __name__ + '.NotGeneratorDoNothingAfterFailureMiddleware': 8, - __name__ + '.NotGeneratorRecoverMiddleware': 5, - __name__ + '.NotGeneratorDoNothingAfterRecoveryMiddleware': 3, + GeneratorFailMiddleware: 10, + GeneratorDoNothingAfterFailureMiddleware: 8, + GeneratorRecoverMiddleware: 5, + GeneratorDoNothingAfterRecoveryMiddleware: 3, }, } def start_requests(self): - return [Request(self.mockserver.url('/status?n=200'))] + yield Request(self.mockserver.url('/status?n=200')) def parse(self, response): - return [{'processed': ['parse-first-item']}, {'processed': ['parse-second-item']}] + yield {'processed': ['parse-first-item']} + yield {'processed': ['parse-second-item']} +# ================================================================================ +# (5) exceptions from a middleware process_spider_output method (not generator) + class _NotGeneratorDoNothingMiddleware: def process_spider_output(self, response, result, spider): out = [] for r in result: - r['processed'].append('{}.process_spider_output'.format(self.__class__.__name__)) + r['processed'].append(f'{self.__class__.__name__}.process_spider_output') out.append(r) return out def process_spider_exception(self, response, exception, spider): - method = '{}.process_spider_exception'.format(self.__class__.__name__) + method = f'{self.__class__.__name__}.process_spider_exception' spider.logger.info('%s: %s caught', method, exception.__class__.__name__) return None @@ -243,13 +225,13 @@ class NotGeneratorFailMiddleware: def process_spider_output(self, response, result, spider): out = [] for r in result: - r['processed'].append('{}.process_spider_output'.format(self.__class__.__name__)) + r['processed'].append(f'{self.__class__.__name__}.process_spider_output') out.append(r) raise ReferenceError() return out def process_spider_exception(self, response, exception, spider): - method = '{}.process_spider_exception'.format(self.__class__.__name__) + method = f'{self.__class__.__name__}.process_spider_exception' spider.logger.info('%s: %s caught', method, exception.__class__.__name__) return [{'processed': [method]}] @@ -262,12 +244,12 @@ class NotGeneratorRecoverMiddleware: def process_spider_output(self, response, result, spider): out = [] for r in result: - r['processed'].append('{}.process_spider_output'.format(self.__class__.__name__)) + r['processed'].append(f'{self.__class__.__name__}.process_spider_output') out.append(r) return out def process_spider_exception(self, response, exception, spider): - method = '{}.process_spider_exception'.format(self.__class__.__name__) + method = f'{self.__class__.__name__}.process_spider_exception' spider.logger.info('%s: %s caught', method, exception.__class__.__name__) return [{'processed': [method]}] @@ -276,6 +258,24 @@ class NotGeneratorDoNothingAfterRecoveryMiddleware(_NotGeneratorDoNothingMiddlew pass +class NotGeneratorOutputChainSpider(Spider): + name = 'NotGeneratorOutputChainSpider' + custom_settings = { + 'SPIDER_MIDDLEWARES': { + NotGeneratorFailMiddleware: 10, + NotGeneratorDoNothingAfterFailureMiddleware: 8, + NotGeneratorRecoverMiddleware: 5, + NotGeneratorDoNothingAfterRecoveryMiddleware: 3, + }, + } + + def start_requests(self): + return [Request(self.mockserver.url('/status?n=200'))] + + def parse(self, response): + return [{'processed': ['parse-first-item']}, {'processed': ['parse-second-item']}] + + # ================================================================================ class TestSpiderMiddleware(TestCase): @classmethod diff --git a/tests/test_spidermiddleware_referer.py b/tests/test_spidermiddleware_referer.py index 067118cf0..9456b01d4 100644 --- a/tests/test_spidermiddleware_referer.py +++ b/tests/test_spidermiddleware_referer.py @@ -6,16 +6,28 @@ from scrapy.http import Response, Request from scrapy.settings import Settings from scrapy.spiders import Spider from scrapy.downloadermiddlewares.redirect import RedirectMiddleware -from scrapy.spidermiddlewares.referer import RefererMiddleware, \ - POLICY_NO_REFERRER, POLICY_NO_REFERRER_WHEN_DOWNGRADE, \ - POLICY_SAME_ORIGIN, POLICY_ORIGIN, POLICY_ORIGIN_WHEN_CROSS_ORIGIN, \ - POLICY_SCRAPY_DEFAULT, POLICY_UNSAFE_URL, \ - POLICY_STRICT_ORIGIN, POLICY_STRICT_ORIGIN_WHEN_CROSS_ORIGIN, \ - DefaultReferrerPolicy, \ - NoReferrerPolicy, NoReferrerWhenDowngradePolicy, \ - OriginWhenCrossOriginPolicy, OriginPolicy, \ - StrictOriginWhenCrossOriginPolicy, StrictOriginPolicy, \ - SameOriginPolicy, UnsafeUrlPolicy, ReferrerPolicy +from scrapy.spidermiddlewares.referer import ( + DefaultReferrerPolicy, + NoReferrerPolicy, + NoReferrerWhenDowngradePolicy, + OriginPolicy, + OriginWhenCrossOriginPolicy, + POLICY_NO_REFERRER, + POLICY_NO_REFERRER_WHEN_DOWNGRADE, + POLICY_ORIGIN, + POLICY_ORIGIN_WHEN_CROSS_ORIGIN, + POLICY_SAME_ORIGIN, + POLICY_SCRAPY_DEFAULT, + POLICY_STRICT_ORIGIN, + POLICY_STRICT_ORIGIN_WHEN_CROSS_ORIGIN, + POLICY_UNSAFE_URL, + RefererMiddleware, + ReferrerPolicy, + SameOriginPolicy, + StrictOriginPolicy, + StrictOriginWhenCrossOriginPolicy, + UnsafeUrlPolicy, +) class TestRefererMiddleware(TestCase): @@ -373,7 +385,7 @@ class CustomPythonOrgPolicy(ReferrerPolicy): class TestSettingsCustomPolicy(TestRefererMiddleware): - settings = {'REFERRER_POLICY': 'tests.test_spidermiddleware_referer.CustomPythonOrgPolicy'} + settings = {'REFERRER_POLICY': CustomPythonOrgPolicy} scenarii = [ ('https://example.com/', 'https://scrapy.org/', b'https://python.org/'), ('http://example.com/', 'http://scrapy.org/', b'http://python.org/'), diff --git a/tests/test_spidermiddleware_urllength.py b/tests/test_spidermiddleware_urllength.py index 5ef2b23fd..171f4ddfd 100644 --- a/tests/test_spidermiddleware_urllength.py +++ b/tests/test_spidermiddleware_urllength.py @@ -1,20 +1,41 @@ from unittest import TestCase +from testfixtures import LogCapture + from scrapy.spidermiddlewares.urllength import UrlLengthMiddleware from scrapy.http import Response, Request from scrapy.spiders import Spider +from scrapy.utils.test import get_crawler +from scrapy.settings import Settings class TestUrlLengthMiddleware(TestCase): - def test_process_spider_output(self): - res = Response('http://scrapytest.org') + def setUp(self): + self.maxlength = 25 + settings = Settings({'URLLENGTH_LIMIT': self.maxlength}) - short_url_req = Request('http://scrapytest.org/') - long_url_req = Request('http://scrapytest.org/this_is_a_long_url') - reqs = [short_url_req, long_url_req] + crawler = get_crawler(Spider) + self.spider = crawler._create_spider('foo') + self.stats = crawler.stats + self.mw = UrlLengthMiddleware.from_settings(settings) - mw = UrlLengthMiddleware(maxlength=25) - spider = Spider('foo') - out = list(mw.process_spider_output(res, reqs, spider)) - self.assertEqual(out, [short_url_req]) + self.response = Response('http://scrapytest.org') + self.short_url_req = Request('http://scrapytest.org/') + self.long_url_req = Request('http://scrapytest.org/this_is_a_long_url') + self.reqs = [self.short_url_req, self.long_url_req] + + def process_spider_output(self): + return list(self.mw.process_spider_output(self.response, self.reqs, self.spider)) + + def test_middleware_works(self): + self.assertEqual(self.process_spider_output(), [self.short_url_req]) + + def test_logging(self): + with LogCapture() as log: + self.process_spider_output() + + ric = self.stats.get_value('urllength/request_ignored_count', spider=self.spider) + self.assertEqual(ric, 1) + + self.assertIn(f'Ignoring link (url length > {self.maxlength})', str(log)) diff --git a/tests/test_squeues.py b/tests/test_squeues.py index becacce62..acc821b83 100644 --- a/tests/test_squeues.py +++ b/tests/test_squeues.py @@ -3,10 +3,10 @@ import sys from queuelib.tests import test_queue as t from scrapy.squeues import ( - MarshalFifoDiskQueueNonRequest as MarshalFifoDiskQueue, - MarshalLifoDiskQueueNonRequest as MarshalLifoDiskQueue, - PickleFifoDiskQueueNonRequest as PickleFifoDiskQueue, - PickleLifoDiskQueueNonRequest as PickleLifoDiskQueue + _MarshalFifoSerializationDiskQueue, + _MarshalLifoSerializationDiskQueue, + _PickleFifoSerializationDiskQueue, + _PickleLifoSerializationDiskQueue, ) from scrapy.item import Item, Field from scrapy.http import Request @@ -53,7 +53,7 @@ class MarshalFifoDiskQueueTest(t.FifoDiskQueueTest, FifoDiskQueueTestMixin): chunksize = 100000 def queue(self): - return MarshalFifoDiskQueue(self.qpath, chunksize=self.chunksize) + return _MarshalFifoSerializationDiskQueue(self.qpath, chunksize=self.chunksize) class ChunkSize1MarshalFifoDiskQueueTest(MarshalFifoDiskQueueTest): @@ -77,7 +77,7 @@ class PickleFifoDiskQueueTest(t.FifoDiskQueueTest, FifoDiskQueueTestMixin): chunksize = 100000 def queue(self): - return PickleFifoDiskQueue(self.qpath, chunksize=self.chunksize) + return _PickleFifoSerializationDiskQueue(self.qpath, chunksize=self.chunksize) def test_serialize_item(self): q = self.queue() @@ -155,13 +155,13 @@ class LifoDiskQueueTestMixin: class MarshalLifoDiskQueueTest(t.LifoDiskQueueTest, LifoDiskQueueTestMixin): def queue(self): - return MarshalLifoDiskQueue(self.qpath) + return _MarshalLifoSerializationDiskQueue(self.qpath) class PickleLifoDiskQueueTest(t.LifoDiskQueueTest, LifoDiskQueueTestMixin): def queue(self): - return PickleLifoDiskQueue(self.qpath) + return _PickleLifoSerializationDiskQueue(self.qpath) def test_serialize_item(self): q = self.queue() diff --git a/tests/test_squeues_request.py b/tests/test_squeues_request.py new file mode 100644 index 000000000..c5fcc1853 --- /dev/null +++ b/tests/test_squeues_request.py @@ -0,0 +1,214 @@ +import shutil +import tempfile +import unittest + +import queuelib + +from scrapy.squeues import ( + PickleFifoDiskQueue, + PickleLifoDiskQueue, + MarshalFifoDiskQueue, + MarshalLifoDiskQueue, + FifoMemoryQueue, + LifoMemoryQueue, +) +from scrapy.http import Request +from scrapy.spiders import Spider +from scrapy.utils.test import get_crawler + + +""" +Queues that handle requests +""" + + +class BaseQueueTestCase(unittest.TestCase): + def setUp(self): + self.tmpdir = tempfile.mkdtemp(prefix="scrapy-queue-tests-") + self.qpath = self.tempfilename() + self.qdir = self.mkdtemp() + self.crawler = get_crawler(Spider) + + def tearDown(self): + shutil.rmtree(self.tmpdir) + + def tempfilename(self): + with tempfile.NamedTemporaryFile(dir=self.tmpdir) as nf: + return nf.name + + def mkdtemp(self): + return tempfile.mkdtemp(dir=self.tmpdir) + + +class RequestQueueTestMixin: + def queue(self): + raise NotImplementedError() + + def test_one_element_with_peek(self): + if not hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("The queuelib queues do not define peek") + q = self.queue() + self.assertEqual(len(q), 0) + self.assertIsNone(q.peek()) + self.assertIsNone(q.pop()) + req = Request("http://www.example.com") + q.push(req) + self.assertEqual(len(q), 1) + self.assertEqual(q.peek().url, req.url) + self.assertEqual(q.pop().url, req.url) + self.assertEqual(len(q), 0) + self.assertIsNone(q.peek()) + self.assertIsNone(q.pop()) + q.close() + + def test_one_element_without_peek(self): + if hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("The queuelib queues define peek") + q = self.queue() + self.assertEqual(len(q), 0) + self.assertIsNone(q.pop()) + req = Request("http://www.example.com") + q.push(req) + self.assertEqual(len(q), 1) + with self.assertRaises(NotImplementedError, msg="The underlying queue class does not implement 'peek'"): + q.peek() + self.assertEqual(q.pop().url, req.url) + self.assertEqual(len(q), 0) + self.assertIsNone(q.pop()) + q.close() + + +class FifoQueueMixin(RequestQueueTestMixin): + def test_fifo_with_peek(self): + if not hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("The queuelib queues do not define peek") + q = self.queue() + self.assertEqual(len(q), 0) + self.assertIsNone(q.peek()) + self.assertIsNone(q.pop()) + req1 = Request("http://www.example.com/1") + req2 = Request("http://www.example.com/2") + req3 = Request("http://www.example.com/3") + q.push(req1) + q.push(req2) + q.push(req3) + self.assertEqual(len(q), 3) + self.assertEqual(q.peek().url, req1.url) + self.assertEqual(q.pop().url, req1.url) + self.assertEqual(len(q), 2) + self.assertEqual(q.peek().url, req2.url) + self.assertEqual(q.pop().url, req2.url) + self.assertEqual(len(q), 1) + self.assertEqual(q.peek().url, req3.url) + self.assertEqual(q.pop().url, req3.url) + self.assertEqual(len(q), 0) + self.assertIsNone(q.peek()) + self.assertIsNone(q.pop()) + q.close() + + def test_fifo_without_peek(self): + if hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("The queuelib queues do not define peek") + q = self.queue() + self.assertEqual(len(q), 0) + self.assertIsNone(q.pop()) + req1 = Request("http://www.example.com/1") + req2 = Request("http://www.example.com/2") + req3 = Request("http://www.example.com/3") + q.push(req1) + q.push(req2) + q.push(req3) + with self.assertRaises(NotImplementedError, msg="The underlying queue class does not implement 'peek'"): + q.peek() + self.assertEqual(len(q), 3) + self.assertEqual(q.pop().url, req1.url) + self.assertEqual(len(q), 2) + self.assertEqual(q.pop().url, req2.url) + self.assertEqual(len(q), 1) + self.assertEqual(q.pop().url, req3.url) + self.assertEqual(len(q), 0) + self.assertIsNone(q.pop()) + q.close() + + +class LifoQueueMixin(RequestQueueTestMixin): + def test_lifo_with_peek(self): + if not hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("The queuelib queues do not define peek") + q = self.queue() + self.assertEqual(len(q), 0) + self.assertIsNone(q.peek()) + self.assertIsNone(q.pop()) + req1 = Request("http://www.example.com/1") + req2 = Request("http://www.example.com/2") + req3 = Request("http://www.example.com/3") + q.push(req1) + q.push(req2) + q.push(req3) + self.assertEqual(len(q), 3) + self.assertEqual(q.peek().url, req3.url) + self.assertEqual(q.pop().url, req3.url) + self.assertEqual(len(q), 2) + self.assertEqual(q.peek().url, req2.url) + self.assertEqual(q.pop().url, req2.url) + self.assertEqual(len(q), 1) + self.assertEqual(q.peek().url, req1.url) + self.assertEqual(q.pop().url, req1.url) + self.assertEqual(len(q), 0) + self.assertIsNone(q.peek()) + self.assertIsNone(q.pop()) + q.close() + + def test_lifo_without_peek(self): + if hasattr(queuelib.queue.FifoMemoryQueue, "peek"): + raise unittest.SkipTest("The queuelib queues do not define peek") + q = self.queue() + self.assertEqual(len(q), 0) + self.assertIsNone(q.pop()) + req1 = Request("http://www.example.com/1") + req2 = Request("http://www.example.com/2") + req3 = Request("http://www.example.com/3") + q.push(req1) + q.push(req2) + q.push(req3) + with self.assertRaises(NotImplementedError, msg="The underlying queue class does not implement 'peek'"): + q.peek() + self.assertEqual(len(q), 3) + self.assertEqual(q.pop().url, req3.url) + self.assertEqual(len(q), 2) + self.assertEqual(q.pop().url, req2.url) + self.assertEqual(len(q), 1) + self.assertEqual(q.pop().url, req1.url) + self.assertEqual(len(q), 0) + self.assertIsNone(q.pop()) + q.close() + + +class PickleFifoDiskQueueRequestTest(FifoQueueMixin, BaseQueueTestCase): + def queue(self): + return PickleFifoDiskQueue.from_crawler(crawler=self.crawler, key="pickle/fifo") + + +class PickleLifoDiskQueueRequestTest(LifoQueueMixin, BaseQueueTestCase): + def queue(self): + return PickleLifoDiskQueue.from_crawler(crawler=self.crawler, key="pickle/lifo") + + +class MarshalFifoDiskQueueRequestTest(FifoQueueMixin, BaseQueueTestCase): + def queue(self): + return MarshalFifoDiskQueue.from_crawler(crawler=self.crawler, key="marshal/fifo") + + +class MarshalLifoDiskQueueRequestTest(LifoQueueMixin, BaseQueueTestCase): + def queue(self): + return MarshalLifoDiskQueue.from_crawler(crawler=self.crawler, key="marshal/lifo") + + +class FifoMemoryQueueRequestTest(FifoQueueMixin, BaseQueueTestCase): + def queue(self): + return FifoMemoryQueue.from_crawler(crawler=self.crawler) + + +class LifoMemoryQueueRequestTest(LifoQueueMixin, BaseQueueTestCase): + def queue(self): + return LifoMemoryQueue.from_crawler(crawler=self.crawler) diff --git a/tests/test_utils_asyncio.py b/tests/test_utils_asyncio.py index 295323e4d..a2114bd18 100644 --- a/tests/test_utils_asyncio.py +++ b/tests/test_utils_asyncio.py @@ -1,4 +1,6 @@ -from unittest import TestCase +import platform +import sys +from unittest import skipIf, TestCase from pytest import mark @@ -12,6 +14,9 @@ class AsyncioTest(TestCase): # the result should depend only on the pytest --reactor argument self.assertEqual(is_asyncio_reactor_installed(), self.reactor_pytest == 'asyncio') + # https://twistedmatrix.com/trac/ticket/9766 + @skipIf(platform.system() == 'Windows' and sys.version_info >= (3, 8), + "the asyncio reactor is broken on Windows when running Python ≥ 3.8") def test_install_asyncio_reactor(self): # this should do nothing install_reactor("twisted.internet.asyncioreactor.AsyncioSelectorReactor") diff --git a/tests/test_utils_conf.py b/tests/test_utils_conf.py index e5d3ef582..dc2560add 100644 --- a/tests/test_utils_conf.py +++ b/tests/test_utils_conf.py @@ -50,8 +50,9 @@ class BuildComponentListTest(unittest.TestCase): def test_duplicate_components_in_list(self): duplicate_list = ['a', 'b', 'a'] - self.assertRaises(ValueError, build_component_list, None, - duplicate_list, convert=lambda x: x) + with self.assertRaises(ValueError) as cm: + build_component_list(None, duplicate_list, convert=lambda x: x) + self.assertIn(str(duplicate_list), str(cm.exception)) def test_duplicate_components_in_basesettings(self): # Higher priority takes precedence @@ -141,6 +142,22 @@ class FeedExportConfigTestCase(unittest.TestCase): feed_process_params_from_cli(settings, ['-:pickle']) ) + def test_feed_export_config_overwrite(self): + settings = Settings() + self.assertEqual( + {'output.json': {'format': 'json', 'overwrite': True}}, + feed_process_params_from_cli(settings, [], None, ['output.json']) + ) + + def test_output_and_overwrite_output(self): + with self.assertRaises(UsageError): + feed_process_params_from_cli( + Settings(), + ['output1.json'], + None, + ['output2.json'], + ) + def test_feed_complete_default_values_from_settings_empty(self): feed = {} settings = Settings({ @@ -149,6 +166,7 @@ class FeedExportConfigTestCase(unittest.TestCase): "FEED_EXPORT_INDENT": 42, "FEED_STORE_EMPTY": True, "FEED_URI_PARAMS": (1, 2, 3, 4), + "FEED_EXPORT_BATCH_ITEM_COUNT": 2, }) new_feed = feed_complete_default_values_from_settings(feed, settings) self.assertEqual(new_feed, { @@ -157,6 +175,8 @@ class FeedExportConfigTestCase(unittest.TestCase): "indent": 42, "store_empty": True, "uri_params": (1, 2, 3, 4), + "batch_item_count": 2, + "item_export_kwargs": dict(), }) def test_feed_complete_default_values_from_settings_non_empty(self): @@ -169,6 +189,7 @@ class FeedExportConfigTestCase(unittest.TestCase): "FEED_EXPORT_FIELDS": ["f1", "f2", "f3"], "FEED_EXPORT_INDENT": 42, "FEED_STORE_EMPTY": True, + "FEED_EXPORT_BATCH_ITEM_COUNT": 2, }) new_feed = feed_complete_default_values_from_settings(feed, settings) self.assertEqual(new_feed, { @@ -177,6 +198,8 @@ class FeedExportConfigTestCase(unittest.TestCase): "indent": 42, "store_empty": True, "uri_params": None, + "batch_item_count": 2, + "item_export_kwargs": dict(), }) diff --git a/tests/test_utils_curl.py b/tests/test_utils_curl.py index 50e1bfd5f..f5d684d3f 100644 --- a/tests/test_utils_curl.py +++ b/tests/test_utils_curl.py @@ -16,7 +16,7 @@ class CurlToRequestKwargsTest(unittest.TestCase): try: Request(**result) except TypeError as e: - self.fail("Request kwargs are not correct {}".format(e)) + self.fail(f"Request kwargs are not correct {e}") def test_get(self): curl_command = "curl http://example.org/" @@ -29,8 +29,7 @@ class CurlToRequestKwargsTest(unittest.TestCase): self._test_command(curl_command, expected_result) def test_get_basic_auth(self): - curl_command = 'curl "https://api.test.com/" -u ' \ - '"some_username:some_password"' + curl_command = 'curl "https://api.test.com/" -u "some_username:some_password"' expected_result = { "method": "GET", "url": "https://api.test.com/", @@ -141,6 +140,31 @@ class CurlToRequestKwargsTest(unittest.TestCase): } self._test_command(curl_command, expected_result) + def test_post_data_raw(self): + curl_command = ( + "curl 'https://www.example.org/' --data-raw 'excerptLength=200&ena" + "bleDidYouMean=true&sortCriteria=ffirstz32xnamez32x201740686%20asc" + "ending&queryFunctions=%5B%5D&rankingFunctions=%5B%5D'" + ) + expected_result = { + "method": "POST", + "url": "https://www.example.org/", + "body": ( + "excerptLength=200&enableDidYouMean=true&sortCriteria=ffirstz3" + "2xnamez32x201740686%20ascending&queryFunctions=%5B%5D&ranking" + "Functions=%5B%5D") + } + self._test_command(curl_command, expected_result) + + def test_explicit_get_with_data(self): + curl_command = 'curl httpbin.org/anything -X GET --data asdf' + expected_result = { + "method": "GET", + "url": "http://httpbin.org/anything", + "body": "asdf" + } + self._test_command(curl_command, expected_result) + def test_patch(self): curl_command = ( 'curl "https://example.com/api/fake" -u "username:password" -H "Ac' @@ -187,8 +211,7 @@ class CurlToRequestKwargsTest(unittest.TestCase): with warnings.catch_warnings(): # avoid warning when executing tests warnings.simplefilter('ignore') curl_command = 'curl --bar --baz http://www.example.com' - expected_result = \ - {"method": "GET", "url": "http://www.example.com"} + expected_result = {"method": "GET", "url": "http://www.example.com"} self.assertEqual(curl_to_request_kwargs(curl_command), expected_result) # case 2: ignore_unknown_options=False (raise exception): diff --git a/tests/test_utils_datatypes.py b/tests/test_utils_datatypes.py index aa18ef1f3..e4bccf30e 100644 --- a/tests/test_utils_datatypes.py +++ b/tests/test_utils_datatypes.py @@ -299,7 +299,7 @@ class LocalWeakReferencedCacheTest(unittest.TestCase): cache = LocalWeakReferencedCache() refs = [] for x in range(max): - refs.append(Request('https://example.org/{}'.format(x))) + refs.append(Request(f'https://example.org/{x}')) cache[refs[-1]] = x self.assertEqual(len(cache), max) for i, r in enumerate(refs): diff --git a/tests/test_utils_defer.py b/tests/test_utils_defer.py index 2d4b88121..7a5f458c7 100644 --- a/tests/test_utils_defer.py +++ b/tests/test_utils_defer.py @@ -1,9 +1,16 @@ +from pytest import mark from twisted.trial import unittest from twisted.internet import reactor, defer from twisted.python.failure import Failure -from scrapy.utils.defer import mustbe_deferred, process_chain, \ - process_chain_both, process_parallel, iter_errback +from scrapy.utils.defer import ( + deferred_f_from_coro_f, + iter_errback, + mustbe_deferred, + process_chain, + process_chain_both, + process_parallel, +) class MustbeDeferredTest(unittest.TestCase): @@ -35,15 +42,15 @@ class MustbeDeferredTest(unittest.TestCase): def cb1(value, arg1, arg2): - return "(cb1 %s %s %s)" % (value, arg1, arg2) + return f"(cb1 {value} {arg1} {arg2})" def cb2(value, arg1, arg2): - return defer.succeed("(cb2 %s %s %s)" % (value, arg1, arg2)) + return defer.succeed(f"(cb2 {value} {arg1} {arg2})") def cb3(value, arg1, arg2): - return "(cb3 %s %s %s)" % (value, arg1, arg2) + return f"(cb3 {value} {arg1} {arg2})" def cb_fail(value, arg1, arg2): @@ -51,7 +58,7 @@ def cb_fail(value, arg1, arg2): def eb1(failure, arg1, arg2): - return "(eb1 %s %s %s)" % (failure.value.__class__.__name__, arg1, arg2) + return f"(eb1 {failure.value.__class__.__name__} {arg1} {arg2})" class DeferUtilsTest(unittest.TestCase): @@ -112,3 +119,18 @@ class IterErrbackTest(unittest.TestCase): self.assertEqual(out, [0, 1, 2, 3, 4]) self.assertEqual(len(errors), 1) self.assertIsInstance(errors[0].value, ZeroDivisionError) + + +class AsyncDefTestsuiteTest(unittest.TestCase): + @deferred_f_from_coro_f + async def test_deferred_f_from_coro_f(self): + pass + + @deferred_f_from_coro_f + async def test_deferred_f_from_coro_f_generator(self): + yield + + @mark.xfail(reason="Checks that the test is actually executed", strict=True) + @deferred_f_from_coro_f + async def test_deferred_f_from_coro_f_xfail(self): + raise Exception("This is expected to be raised") diff --git a/tests/test_utils_deprecate.py b/tests/test_utils_deprecate.py index 35d35b45d..e47afa266 100644 --- a/tests/test_utils_deprecate.py +++ b/tests/test_utils_deprecate.py @@ -108,7 +108,7 @@ class WarnWhenSubclassedTest(unittest.TestCase): # ignore subclassing warnings with warnings.catch_warnings(): - warnings.simplefilter('ignore', ScrapyDeprecationWarning) + warnings.simplefilter('ignore', MyWarning) class UserClass(Deprecated): pass diff --git a/tests/test_utils_display.py b/tests/test_utils_display.py new file mode 100644 index 000000000..9ec8311d9 --- /dev/null +++ b/tests/test_utils_display.py @@ -0,0 +1,78 @@ +from io import StringIO + +from unittest import mock, TestCase + +from scrapy.utils.display import pformat, pprint + + +class TestDisplay(TestCase): + object = {'a': 1} + colorized_string = ( + "{\x1b[33m'\x1b[39;49;00m\x1b[33ma\x1b[39;49;00m\x1b[33m'" + "\x1b[39;49;00m: \x1b[34m1\x1b[39;49;00m}\n" + ) + plain_string = "{'a': 1}" + + @mock.patch('sys.platform', 'linux') + @mock.patch("sys.stdout.isatty") + def test_pformat(self, isatty): + isatty.return_value = True + self.assertEqual(pformat(self.object), self.colorized_string) + + @mock.patch("sys.stdout.isatty") + def test_pformat_dont_colorize(self, isatty): + isatty.return_value = True + self.assertEqual(pformat(self.object, colorize=False), self.plain_string) + + def test_pformat_not_tty(self): + self.assertEqual(pformat(self.object), self.plain_string) + + @mock.patch('sys.platform', 'win32') + @mock.patch('platform.version') + @mock.patch("sys.stdout.isatty") + def test_pformat_old_windows(self, isatty, version): + isatty.return_value = True + version.return_value = '10.0.14392' + self.assertEqual(pformat(self.object), self.colorized_string) + + @mock.patch('sys.platform', 'win32') + @mock.patch('scrapy.utils.display._enable_windows_terminal_processing') + @mock.patch('platform.version') + @mock.patch("sys.stdout.isatty") + def test_pformat_windows_no_terminal_processing(self, isatty, version, terminal_processing): + isatty.return_value = True + version.return_value = '10.0.14393' + terminal_processing.return_value = False + self.assertEqual(pformat(self.object), self.plain_string) + + @mock.patch('sys.platform', 'win32') + @mock.patch('scrapy.utils.display._enable_windows_terminal_processing') + @mock.patch('platform.version') + @mock.patch("sys.stdout.isatty") + def test_pformat_windows(self, isatty, version, terminal_processing): + isatty.return_value = True + version.return_value = '10.0.14393' + terminal_processing.return_value = True + self.assertEqual(pformat(self.object), self.colorized_string) + + @mock.patch('sys.platform', 'linux') + @mock.patch("sys.stdout.isatty") + def test_pformat_no_pygments(self, isatty): + isatty.return_value = True + + import builtins + real_import = builtins.__import__ + + def mock_import(name, globals, locals, fromlist, level): + if 'pygments' in name: + raise ImportError + return real_import(name, globals, locals, fromlist, level) + + builtins.__import__ = mock_import + self.assertEqual(pformat(self.object), self.plain_string) + builtins.__import__ = real_import + + def test_pprint(self): + with mock.patch('sys.stdout', new=StringIO()) as mock_out: + pprint(self.object) + self.assertEqual(mock_out.getvalue(), "{'a': 1}\n") diff --git a/tests/test_utils_gz.py b/tests/test_utils_gz.py index 7148185f4..4943731cb 100644 --- a/tests/test_utils_gz.py +++ b/tests/test_utils_gz.py @@ -3,10 +3,11 @@ from os.path import join from w3lib.encoding import html_to_unicode -from scrapy.utils.gz import gunzip, is_gzipped -from scrapy.http import Response, Headers +from scrapy.utils.gz import gunzip, gzip_magic_number +from scrapy.http import Response from tests import tests_datadir + SAMPLEDIR = join(tests_datadir, 'compressed') @@ -14,8 +15,12 @@ class GunzipTest(unittest.TestCase): def test_gunzip_basic(self): with open(join(SAMPLEDIR, 'feed-sample1.xml.gz'), 'rb') as f: - text = gunzip(f.read()) - self.assertEqual(len(text), 9950) + r1 = Response("http://www.example.com", body=f.read()) + self.assertTrue(gzip_magic_number(r1)) + + r2 = Response("http://www.example.com", body=gunzip(r1.body)) + self.assertFalse(gzip_magic_number(r2)) + self.assertEqual(len(r2.body), 9950) def test_gunzip_truncated(self): with open(join(SAMPLEDIR, 'truncated-crc-error.gz'), 'rb') as f: @@ -28,46 +33,16 @@ class GunzipTest(unittest.TestCase): def test_gunzip_truncated_short(self): with open(join(SAMPLEDIR, 'truncated-crc-error-short.gz'), 'rb') as f: - text = gunzip(f.read()) - assert text.endswith(b'') + r1 = Response("http://www.example.com", body=f.read()) + self.assertTrue(gzip_magic_number(r1)) - def test_is_x_gzipped_right(self): - hdrs = Headers({"Content-Type": "application/x-gzip"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) - - def test_is_gzipped_right(self): - hdrs = Headers({"Content-Type": "application/gzip"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) - - def test_is_gzipped_not_quite(self): - hdrs = Headers({"Content-Type": "application/gzippppp"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertFalse(is_gzipped(r1)) - - def test_is_gzipped_case_insensitive(self): - hdrs = Headers({"Content-Type": "Application/X-Gzip"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) - - hdrs = Headers({"Content-Type": "application/X-GZIP ; charset=utf-8"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) + r2 = Response("http://www.example.com", body=gunzip(r1.body)) + assert r2.body.endswith(b'') + self.assertFalse(gzip_magic_number(r2)) def test_is_gzipped_empty(self): r1 = Response("http://www.example.com") - self.assertFalse(is_gzipped(r1)) - - def test_is_gzipped_wrong(self): - hdrs = Headers({"Content-Type": "application/javascript"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertFalse(is_gzipped(r1)) - - def test_is_gzipped_with_charset(self): - hdrs = Headers({"Content-Type": "application/x-gzip;charset=utf-8"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) + self.assertFalse(gzip_magic_number(r1)) def test_gunzip_illegal_eof(self): with open(join(SAMPLEDIR, 'unexpected-eof.gz'), 'rb') as f: diff --git a/tests/test_utils_http.py b/tests/test_utils_http.py deleted file mode 100644 index 363b015a8..000000000 --- a/tests/test_utils_http.py +++ /dev/null @@ -1,19 +0,0 @@ -import unittest - -from scrapy.utils.http import decode_chunked_transfer - - -class ChunkedTest(unittest.TestCase): - - def test_decode_chunked_transfer(self): - """Example taken from: http://en.wikipedia.org/wiki/Chunked_transfer_encoding""" - chunked_body = "25\r\n" + "This is the data in the first chunk\r\n\r\n" - chunked_body += "1C\r\n" + "and this is the second one\r\n\r\n" - chunked_body += "3\r\n" + "con\r\n" - chunked_body += "8\r\n" + "sequence\r\n" - chunked_body += "0\r\n\r\n" - body = decode_chunked_transfer(chunked_body) - self.assertEqual( - body, - "This is the data in the first chunk\r\nand this is the second one\r\nconsequence" - ) diff --git a/tests/test_utils_iterators.py b/tests/test_utils_iterators.py index 8344c6701..f84cb2956 100644 --- a/tests/test_utils_iterators.py +++ b/tests/test_utils_iterators.py @@ -1,5 +1,6 @@ import os +from pytest import mark from twisted.trial import unittest from scrapy.utils.iterators import csviter, xmliter, _body_or_str, xmliter_lxml @@ -7,26 +8,25 @@ from scrapy.http import XmlResponse, TextResponse, Response from tests import get_testdata -FOOBAR_NL = u"foo\nbar" - - class XmliterTestCase(unittest.TestCase): xmliter = staticmethod(xmliter) def test_xmliter(self): - body = b"""\ + body = b""" + \ - \ - Type 1\ - Name 1\ - \ - \ - Type 2\ - Name 2\ - \ - """ + xsi:noNamespaceSchemaLocation="someschmea.xsd"> + + Type 1 + Name 1 + + + Type 2 + Name 2 + + + """ response = XmlResponse(url="http://example.com", body=body) attrs = [] @@ -52,7 +52,7 @@ class XmliterTestCase(unittest.TestCase): def test_xmliter_unicode(self): # example taken from https://github.com/scrapy/scrapy/issues/1665 - body = u""" + body = """ <þingflokkar> <þingflokkur id="26"> @@ -95,15 +95,15 @@ class XmliterTestCase(unittest.TestCase): XmlResponse(url="http://example.com", body=body, encoding='utf-8'), ): attrs = [] - for x in self.xmliter(r, u'þingflokkur'): + for x in self.xmliter(r, 'þingflokkur'): attrs.append((x.attrib['id'], - x.xpath(u'./skammstafanir/stuttskammstöfun/text()').getall(), - x.xpath(u'./tímabil/fyrstaþing/text()').getall())) + x.xpath('./skammstafanir/stuttskammstöfun/text()').getall(), + x.xpath('./tímabil/fyrstaþing/text()').getall())) self.assertEqual(attrs, - [(u'26', [u'-'], [u'80']), - (u'21', [u'Ab'], [u'76']), - (u'27', [u'A'], [u'27'])]) + [('26', ['-'], ['80']), + ('21', ['Ab'], ['76']), + ('27', ['A'], ['27'])]) def test_xmliter_text(self): body = ( @@ -112,10 +112,10 @@ class XmliterTestCase(unittest.TestCase): ) self.assertEqual([x.xpath("text()").getall() for x in self.xmliter(body, 'product')], - [[u'one'], [u'two']]) + [['one'], ['two']]) def test_xmliter_namespaces(self): - body = b"""\ + body = b""" @@ -135,7 +135,6 @@ class XmliterTestCase(unittest.TestCase): """ response = XmlResponse(url='http://mydummycompany.com', body=body) my_iter = self.xmliter(response, 'item') - node = next(my_iter) node.register_namespace('g', 'http://base.google.com/ns/1.0') self.assertEqual(node.xpath('title/text()').getall(), ['Item 1']) @@ -151,6 +150,55 @@ class XmliterTestCase(unittest.TestCase): self.assertEqual(node.xpath('id/text()').getall(), []) self.assertEqual(node.xpath('price/text()').getall(), []) + def test_xmliter_namespaced_nodename(self): + body = b""" + + + + My Dummy Company + http://www.mydummycompany.com + This is a dummy company. We do nothing. + + Item 1 + This is item 1 + http://www.mydummycompany.com/items/1 + http://www.mydummycompany.com/images/item1.jpg + ITEM_1 + 400 + + + + """ + response = XmlResponse(url='http://mydummycompany.com', body=body) + my_iter = self.xmliter(response, 'g:image_link') + node = next(my_iter) + node.register_namespace('g', 'http://base.google.com/ns/1.0') + self.assertEqual(node.xpath('text()').extract(), ['http://www.mydummycompany.com/images/item1.jpg']) + + def test_xmliter_namespaced_nodename_missing(self): + body = b""" + + + + My Dummy Company + http://www.mydummycompany.com + This is a dummy company. We do nothing. + + Item 1 + This is item 1 + http://www.mydummycompany.com/items/1 + http://www.mydummycompany.com/images/item1.jpg + ITEM_1 + 400 + + + + """ + response = XmlResponse(url='http://mydummycompany.com', body=body) + my_iter = self.xmliter(response, 'g:link_image') + with self.assertRaises(StopIteration): + next(my_iter) + def test_xmliter_exception(self): body = ( '' @@ -177,15 +225,19 @@ class XmliterTestCase(unittest.TestCase): response = XmlResponse('http://www.example.com', body=body) self.assertEqual( next(self.xmliter(response, 'item')).get(), - u'Some Turkish Characters \xd6\xc7\u015e\u0130\u011e\xdc \xfc\u011f\u0131\u015f\xe7\xf6' + 'Some Turkish Characters \xd6\xc7\u015e\u0130\u011e\xdc \xfc\u011f\u0131\u015f\xe7\xf6' ) class LxmlXmliterTestCase(XmliterTestCase): xmliter = staticmethod(xmliter_lxml) + @mark.xfail(reason='known bug of the current implementation') + def test_xmliter_namespaced_nodename(self): + super().test_xmliter_namespaced_nodename() + def test_xmliter_iterate_namespace(self): - body = b"""\ + body = b""" @@ -214,7 +266,7 @@ class LxmlXmliterTestCase(XmliterTestCase): self.assertEqual(node.xpath('text()').getall(), ['http://www.mydummycompany.com/images/item2.jpg']) def test_xmliter_namespaces_prefix(self): - body = b"""\ + body = b""" @@ -263,10 +315,10 @@ class UtilsCsvTestCase(unittest.TestCase): result = [row for row in csv] self.assertEqual(result, - [{u'id': u'1', u'name': u'alpha', u'value': u'foobar'}, - {u'id': u'2', u'name': u'unicode', u'value': u'\xfan\xedc\xf3d\xe9\u203d'}, - {u'id': u'3', u'name': u'multi', u'value': FOOBAR_NL}, - {u'id': u'4', u'name': u'empty', u'value': u''}]) + [{'id': '1', 'name': 'alpha', 'value': 'foobar'}, + {'id': '2', 'name': 'unicode', 'value': '\xfan\xedc\xf3d\xe9\u203d'}, + {'id': '3', 'name': 'multi', 'value': "foo\nbar"}, + {'id': '4', 'name': 'empty', 'value': ''}]) # explicit type check cuz' we no like stinkin' autocasting! yarrr for result_row in result: @@ -279,10 +331,10 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response, delimiter='\t') self.assertEqual([row for row in csv], - [{u'id': u'1', u'name': u'alpha', u'value': u'foobar'}, - {u'id': u'2', u'name': u'unicode', u'value': u'\xfan\xedc\xf3d\xe9\u203d'}, - {u'id': u'3', u'name': u'multi', u'value': FOOBAR_NL}, - {u'id': u'4', u'name': u'empty', u'value': u''}]) + [{'id': '1', 'name': 'alpha', 'value': 'foobar'}, + {'id': '2', 'name': 'unicode', 'value': '\xfan\xedc\xf3d\xe9\u203d'}, + {'id': '3', 'name': 'multi', 'value': "foo\nbar"}, + {'id': '4', 'name': 'empty', 'value': ''}]) def test_csviter_quotechar(self): body1 = get_testdata('feeds', 'feed-sample6.csv') @@ -292,19 +344,19 @@ class UtilsCsvTestCase(unittest.TestCase): csv1 = csviter(response1, quotechar="'") self.assertEqual([row for row in csv1], - [{u'id': u'1', u'name': u'alpha', u'value': u'foobar'}, - {u'id': u'2', u'name': u'unicode', u'value': u'\xfan\xedc\xf3d\xe9\u203d'}, - {u'id': u'3', u'name': u'multi', u'value': FOOBAR_NL}, - {u'id': u'4', u'name': u'empty', u'value': u''}]) + [{'id': '1', 'name': 'alpha', 'value': 'foobar'}, + {'id': '2', 'name': 'unicode', 'value': '\xfan\xedc\xf3d\xe9\u203d'}, + {'id': '3', 'name': 'multi', 'value': "foo\nbar"}, + {'id': '4', 'name': 'empty', 'value': ''}]) response2 = TextResponse(url="http://example.com/", body=body2) csv2 = csviter(response2, delimiter="|", quotechar="'") self.assertEqual([row for row in csv2], - [{u'id': u'1', u'name': u'alpha', u'value': u'foobar'}, - {u'id': u'2', u'name': u'unicode', u'value': u'\xfan\xedc\xf3d\xe9\u203d'}, - {u'id': u'3', u'name': u'multi', u'value': FOOBAR_NL}, - {u'id': u'4', u'name': u'empty', u'value': u''}]) + [{'id': '1', 'name': 'alpha', 'value': 'foobar'}, + {'id': '2', 'name': 'unicode', 'value': '\xfan\xedc\xf3d\xe9\u203d'}, + {'id': '3', 'name': 'multi', 'value': "foo\nbar"}, + {'id': '4', 'name': 'empty', 'value': ''}]) def test_csviter_wrong_quotechar(self): body = get_testdata('feeds', 'feed-sample6.csv') @@ -312,10 +364,10 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response) self.assertEqual([row for row in csv], - [{u"'id'": u"1", u"'name'": u"'alpha'", u"'value'": u"'foobar'"}, - {u"'id'": u"2", u"'name'": u"'unicode'", u"'value'": u"'\xfan\xedc\xf3d\xe9\u203d'"}, - {u"'id'": u"'3'", u"'name'": u"'multi'", u"'value'": u"'foo"}, - {u"'id'": u"4", u"'name'": u"'empty'", u"'value'": u""}]) + [{"'id'": "1", "'name'": "'alpha'", "'value'": "'foobar'"}, + {"'id'": "2", "'name'": "'unicode'", "'value'": "'\xfan\xedc\xf3d\xe9\u203d'"}, + {"'id'": "'3'", "'name'": "'multi'", "'value'": "'foo"}, + {"'id'": "4", "'name'": "'empty'", "'value'": ""}]) def test_csviter_delimiter_binary_response_assume_utf8_encoding(self): body = get_testdata('feeds', 'feed-sample3.csv').replace(b',', b'\t') @@ -323,10 +375,10 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response, delimiter='\t') self.assertEqual([row for row in csv], - [{u'id': u'1', u'name': u'alpha', u'value': u'foobar'}, - {u'id': u'2', u'name': u'unicode', u'value': u'\xfan\xedc\xf3d\xe9\u203d'}, - {u'id': u'3', u'name': u'multi', u'value': FOOBAR_NL}, - {u'id': u'4', u'name': u'empty', u'value': u''}]) + [{'id': '1', 'name': 'alpha', 'value': 'foobar'}, + {'id': '2', 'name': 'unicode', 'value': '\xfan\xedc\xf3d\xe9\u203d'}, + {'id': '3', 'name': 'multi', 'value': "foo\nbar"}, + {'id': '4', 'name': 'empty', 'value': ''}]) def test_csviter_headers(self): sample = get_testdata('feeds', 'feed-sample3.csv').splitlines() @@ -336,10 +388,10 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response, headers=[h.decode('utf-8') for h in headers]) self.assertEqual([row for row in csv], - [{u'id': u'1', u'name': u'alpha', u'value': u'foobar'}, - {u'id': u'2', u'name': u'unicode', u'value': u'\xfan\xedc\xf3d\xe9\u203d'}, - {u'id': u'3', u'name': u'multi', u'value': u'foo\nbar'}, - {u'id': u'4', u'name': u'empty', u'value': u''}]) + [{'id': '1', 'name': 'alpha', 'value': 'foobar'}, + {'id': '2', 'name': 'unicode', 'value': '\xfan\xedc\xf3d\xe9\u203d'}, + {'id': '3', 'name': 'multi', 'value': 'foo\nbar'}, + {'id': '4', 'name': 'empty', 'value': ''}]) def test_csviter_falserow(self): body = get_testdata('feeds', 'feed-sample3.csv') @@ -349,10 +401,10 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response) self.assertEqual([row for row in csv], - [{u'id': u'1', u'name': u'alpha', u'value': u'foobar'}, - {u'id': u'2', u'name': u'unicode', u'value': u'\xfan\xedc\xf3d\xe9\u203d'}, - {u'id': u'3', u'name': u'multi', u'value': FOOBAR_NL}, - {u'id': u'4', u'name': u'empty', u'value': u''}]) + [{'id': '1', 'name': 'alpha', 'value': 'foobar'}, + {'id': '2', 'name': 'unicode', 'value': '\xfan\xedc\xf3d\xe9\u203d'}, + {'id': '3', 'name': 'multi', 'value': "foo\nbar"}, + {'id': '4', 'name': 'empty', 'value': ''}]) def test_csviter_exception(self): body = get_testdata('feeds', 'feed-sample3.csv') @@ -375,8 +427,8 @@ class UtilsCsvTestCase(unittest.TestCase): self.assertEqual( list(csv), [ - {u'id': u'1', u'name': u'latin1', u'value': u'test'}, - {u'id': u'2', u'name': u'something', u'value': u'\xf1\xe1\xe9\xf3'}, + {'id': '1', 'name': 'latin1', 'value': 'test'}, + {'id': '2', 'name': 'something', 'value': '\xf1\xe1\xe9\xf3'}, ] ) @@ -385,8 +437,8 @@ class UtilsCsvTestCase(unittest.TestCase): self.assertEqual( list(csv), [ - {u'id': u'1', u'name': u'cp852', u'value': u'test'}, - {u'id': u'2', u'name': u'something', u'value': u'\u255a\u2569\u2569\u2569\u2550\u2550\u2557'}, + {'id': '1', 'name': 'cp852', 'value': 'test'}, + {'id': '2', 'name': 'something', 'value': '\u255a\u2569\u2569\u2569\u2550\u2550\u2557'}, ] ) @@ -410,7 +462,7 @@ class TestHelper(unittest.TestCase): def _assert_type_and_value(self, a, b, obj): self.assertTrue(type(a) is type(b), - 'Got {}, expected {} for {!r}'.format(type(a), type(b), obj)) + f'Got {type(a)}, expected {type(b)} for { obj!r}') self.assertEqual(a, b) diff --git a/tests/test_utils_misc/__init__.py b/tests/test_utils_misc/__init__.py index 9bb996d27..e95a3a316 100644 --- a/tests/test_utils_misc/__init__.py +++ b/tests/test_utils_misc/__init__.py @@ -12,11 +12,22 @@ __doctests__ = ['scrapy.utils.misc'] class UtilsMiscTestCase(unittest.TestCase): - def test_load_object(self): + def test_load_object_class(self): + obj = load_object(Field) + self.assertIs(obj, Field) + obj = load_object('scrapy.item.Field') + self.assertIs(obj, Field) + + def test_load_object_function(self): + obj = load_object(load_object) + self.assertIs(obj, load_object) obj = load_object('scrapy.utils.misc.load_object') - assert obj is load_object + self.assertIs(obj, load_object) + + def test_load_object_exceptions(self): self.assertRaises(ImportError, load_object, 'nomodule999.mod.function') self.assertRaises(NameError, load_object, 'scrapy.utils.misc.load_object999') + self.assertRaises(TypeError, load_object, dict()) def test_walk_modules(self): mods = walk_modules('tests.test_utils_misc.test_walk_modules') diff --git a/tests/test_utils_misc/test_return_with_argument_inside_generator.py b/tests/test_utils_misc/test_return_with_argument_inside_generator.py index bdbec1beb..1c85ca353 100644 --- a/tests/test_utils_misc/test_return_with_argument_inside_generator.py +++ b/tests/test_utils_misc/test_return_with_argument_inside_generator.py @@ -1,37 +1,173 @@ import unittest +import warnings +from unittest import mock -from scrapy.utils.misc import is_generator_with_return_value +from scrapy.utils.misc import is_generator_with_return_value, warn_on_generator_with_return_value + + +def _indentation_error(*args, **kwargs): + raise IndentationError() + + +def top_level_return_something(): + """ +docstring + """ + url = """ +https://example.org +""" + yield url + return 1 + + +def top_level_return_none(): + """ +docstring + """ + url = """ +https://example.org +""" + yield url + return + + +def generator_that_returns_stuff(): + yield 1 + yield 2 + return 3 class UtilsMiscPy3TestCase(unittest.TestCase): - def test_generators_with_return_statements(self): - def f(): + def test_generators_return_something(self): + def f1(): yield 1 return 2 - def g(): + def g1(): yield 1 - return 'asdf' + return "asdf" - def h(): + def h1(): + yield 1 + + def helper(): + return 0 + + yield helper() + return 2 + + def i1(): + """ +docstring + """ + url = """ +https://example.org + """ + yield url + return 1 + + assert is_generator_with_return_value(top_level_return_something) + assert is_generator_with_return_value(f1) + assert is_generator_with_return_value(g1) + assert is_generator_with_return_value(h1) + assert is_generator_with_return_value(i1) + + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, top_level_return_something) + self.assertEqual(len(w), 1) + self.assertIn('The "NoneType.top_level_return_something" method is a generator', str(w[0].message)) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, f1) + self.assertEqual(len(w), 1) + self.assertIn('The "NoneType.f1" method is a generator', str(w[0].message)) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, g1) + self.assertEqual(len(w), 1) + self.assertIn('The "NoneType.g1" method is a generator', str(w[0].message)) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, h1) + self.assertEqual(len(w), 1) + self.assertIn('The "NoneType.h1" method is a generator', str(w[0].message)) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, i1) + self.assertEqual(len(w), 1) + self.assertIn('The "NoneType.i1" method is a generator', str(w[0].message)) + + def test_generators_return_none(self): + def f2(): yield 1 return None - def i(): + def g2(): yield 1 return - def j(): + def h2(): yield 1 - def k(): + def i2(): yield 1 - yield from g() + yield from generator_that_returns_stuff() - assert is_generator_with_return_value(f) - assert is_generator_with_return_value(g) - assert not is_generator_with_return_value(h) - assert not is_generator_with_return_value(i) - assert not is_generator_with_return_value(j) - assert not is_generator_with_return_value(k) # not recursive + def j2(): + yield 1 + + def helper(): + return 0 + + yield helper() + + def k2(): + """ +docstring + """ + url = """ +https://example.org + """ + yield url + return + + def l2(): + return + + assert not is_generator_with_return_value(top_level_return_none) + assert not is_generator_with_return_value(f2) + assert not is_generator_with_return_value(g2) + assert not is_generator_with_return_value(h2) + assert not is_generator_with_return_value(i2) + assert not is_generator_with_return_value(j2) # not recursive + assert not is_generator_with_return_value(k2) # not recursive + assert not is_generator_with_return_value(l2) + + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, top_level_return_none) + self.assertEqual(len(w), 0) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, f2) + self.assertEqual(len(w), 0) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, g2) + self.assertEqual(len(w), 0) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, h2) + self.assertEqual(len(w), 0) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, i2) + self.assertEqual(len(w), 0) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, j2) + self.assertEqual(len(w), 0) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, k2) + self.assertEqual(len(w), 0) + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, l2) + self.assertEqual(len(w), 0) + + @mock.patch("scrapy.utils.misc.is_generator_with_return_value", new=_indentation_error) + def test_indentation_error(self): + with warnings.catch_warnings(record=True) as w: + warn_on_generator_with_return_value(None, top_level_return_none) + self.assertEqual(len(w), 1) + self.assertIn('Unable to determine', str(w[0].message)) diff --git a/tests/test_utils_python.py b/tests/test_utils_python.py index 65e6ba876..4b3964154 100644 --- a/tests/test_utils_python.py +++ b/tests/test_utils_python.py @@ -3,9 +3,11 @@ import gc import operator import platform import unittest +from datetime import datetime from itertools import count -from warnings import catch_warnings +from warnings import catch_warnings, filterwarnings +from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.utils.python import ( memoizemethod_noargs, binary_is_text, equal_attributes, WeakKeyCache, get_func_args, to_bytes, to_unicode, @@ -33,13 +35,13 @@ class MutableChainTest(unittest.TestCase): class ToUnicodeTest(unittest.TestCase): def test_converting_an_utf8_encoded_string_to_unicode(self): - self.assertEqual(to_unicode(b'lel\xc3\xb1e'), u'lel\xf1e') + self.assertEqual(to_unicode(b'lel\xc3\xb1e'), 'lel\xf1e') def test_converting_a_latin_1_encoded_string_to_unicode(self): - self.assertEqual(to_unicode(b'lel\xf1e', 'latin-1'), u'lel\xf1e') + self.assertEqual(to_unicode(b'lel\xf1e', 'latin-1'), 'lel\xf1e') def test_converting_a_unicode_to_unicode_should_return_the_same_object(self): - self.assertEqual(to_unicode(u'\xf1e\xf1e\xf1e'), u'\xf1e\xf1e\xf1e') + self.assertEqual(to_unicode('\xf1e\xf1e\xf1e'), '\xf1e\xf1e\xf1e') def test_converting_a_strange_object_should_raise_TypeError(self): self.assertRaises(TypeError, to_unicode, 423) @@ -47,16 +49,16 @@ class ToUnicodeTest(unittest.TestCase): def test_errors_argument(self): self.assertEqual( to_unicode(b'a\xedb', 'utf-8', errors='replace'), - u'a\ufffdb' + 'a\ufffdb' ) class ToBytesTest(unittest.TestCase): def test_converting_a_unicode_object_to_an_utf_8_encoded_string(self): - self.assertEqual(to_bytes(u'\xa3 49'), b'\xc2\xa3 49') + self.assertEqual(to_bytes('\xa3 49'), b'\xc2\xa3 49') def test_converting_a_unicode_object_to_a_latin_1_encoded_string(self): - self.assertEqual(to_bytes(u'\xa3 49', 'latin-1'), b'\xa3 49') + self.assertEqual(to_bytes('\xa3 49', 'latin-1'), b'\xa3 49') def test_converting_a_regular_bytes_to_bytes_should_return_the_same_object(self): self.assertEqual(to_bytes(b'lel\xf1e'), b'lel\xf1e') @@ -66,7 +68,7 @@ class ToBytesTest(unittest.TestCase): def test_errors_argument(self): self.assertEqual( - to_bytes(u'a\ufffdb', 'latin-1', errors='replace'), + to_bytes('a\ufffdb', 'latin-1', errors='replace'), b'a?b' ) @@ -95,7 +97,7 @@ class BinaryIsTextTest(unittest.TestCase): assert binary_is_text(b"hello") def test_utf_16_strings_contain_null_bytes(self): - assert binary_is_text(u"hello".encode('utf-16')) + assert binary_is_text("hello".encode('utf-16')) def test_one_with_encoding(self): assert binary_is_text(b"
    Price \xa3
    ") @@ -159,7 +161,11 @@ class UtilsPythonTestCase(unittest.TestCase): pass _values = count() - wk = WeakKeyCache(lambda k: next(_values)) + + with catch_warnings(): + filterwarnings("ignore", category=ScrapyDeprecationWarning) + wk = WeakKeyCache(lambda k: next(_values)) + k = _Weakme() v = wk[k] self.assertEqual(v, wk[k]) @@ -178,6 +184,9 @@ class UtilsPythonTestCase(unittest.TestCase): def f2(a, b=None, c=None): pass + def f3(a, b=None, *, c=None): + pass + class A: def __init__(self, a, b, c): pass @@ -198,6 +207,7 @@ class UtilsPythonTestCase(unittest.TestCase): self.assertEqual(get_func_args(f1), ['a', 'b', 'c']) self.assertEqual(get_func_args(f2), ['a', 'b', 'c']) + self.assertEqual(get_func_args(f3), ['a', 'b', 'c']) self.assertEqual(get_func_args(A), ['a', 'b', 'c']) self.assertEqual(get_func_args(a.method), ['a', 'b', 'c']) self.assertEqual(get_func_args(partial_f1), ['b', 'c']) @@ -211,12 +221,15 @@ class UtilsPythonTestCase(unittest.TestCase): self.assertEqual(get_func_args(str.split), []) self.assertEqual(get_func_args(" ".join), []) self.assertEqual(get_func_args(operator.itemgetter(2)), []) - else: - self.assertEqual( - get_func_args(str.split, stripself=True), ['sep', 'maxsplit']) - self.assertEqual(get_func_args(" ".join, stripself=True), ['list']) - self.assertEqual( - get_func_args(operator.itemgetter(2), stripself=True), ['obj']) + elif platform.python_implementation() == 'PyPy': + self.assertEqual(get_func_args(str.split, stripself=True), ['sep', 'maxsplit']) + self.assertEqual(get_func_args(operator.itemgetter(2), stripself=True), ['obj']) + + build_date = datetime.strptime(platform.python_build()[1], '%b %d %Y') + if build_date >= datetime(2020, 4, 7): # PyPy 3.6-v7.3.1 + self.assertEqual(get_func_args(" ".join, stripself=True), ['iterable']) + else: + self.assertEqual(get_func_args(" ".join, stripself=True), ['list']) def test_without_none_values(self): self.assertEqual(without_none_values([1, None, 3, 4]), [1, 3, 4]) diff --git a/tests/test_utils_request.py b/tests/test_utils_request.py index 4cd4b7010..7e0049b1d 100644 --- a/tests/test_utils_request.py +++ b/tests/test_utils_request.py @@ -1,7 +1,11 @@ import unittest from scrapy.http import Request -from scrapy.utils.request import request_fingerprint, _fingerprint_cache, \ - request_authenticate, request_httprepr +from scrapy.utils.request import ( + _fingerprint_cache, + request_authenticate, + request_fingerprint, + request_httprepr, +) class UtilsRequestTest(unittest.TestCase): diff --git a/tests/test_utils_response.py b/tests/test_utils_response.py index 6ebf290c0..d6f4c0bb5 100644 --- a/tests/test_utils_response.py +++ b/tests/test_utils_response.py @@ -37,8 +37,7 @@ class ResponseUtilsTest(unittest.TestCase): self.assertIn(b'', bbody) return True response = HtmlResponse(url, body=body) - assert open_in_browser(response, _openfunc=browser_open), \ - "Browser not called" + assert open_in_browser(response, _openfunc=browser_open), "Browser not called" resp = Response(url, body=body) self.assertRaises(TypeError, open_in_browser, resp, debug=True) diff --git a/tests/test_utils_serialize.py b/tests/test_utils_serialize.py index 6dc117779..daf022aee 100644 --- a/tests/test_utils_serialize.py +++ b/tests/test_utils_serialize.py @@ -1,18 +1,25 @@ +import datetime import json import unittest -import datetime from decimal import Decimal +import attr from twisted.internet import defer -from scrapy.utils.serialize import ScrapyJSONEncoder from scrapy.http import Request, Response +from scrapy.utils.serialize import ScrapyJSONEncoder + + +try: + from dataclasses import make_dataclass +except ImportError: + make_dataclass = None class JsonEncoderTestCase(unittest.TestCase): def setUp(self): - self.encoder = ScrapyJSONEncoder() + self.encoder = ScrapyJSONEncoder(sort_keys=True) def test_encode_decode(self): dt = datetime.datetime(2010, 1, 2, 10, 11, 12) @@ -31,7 +38,8 @@ class JsonEncoderTestCase(unittest.TestCase): for input, output in [('foo', 'foo'), (d, ds), (t, ts), (dt, dts), (dec, decs), (['foo', d], ['foo', ds]), (s, ss), (dt_set, dt_sets)]: - self.assertEqual(self.encoder.encode(input), json.dumps(output)) + self.assertEqual(self.encoder.encode(input), + json.dumps(output, sort_keys=True)) def test_encode_deferred(self): self.assertIn('Deferred', self.encoder.encode(defer.Deferred())) @@ -47,3 +55,30 @@ class JsonEncoderTestCase(unittest.TestCase): rs = self.encoder.encode(r) self.assertIn(r.url, rs) self.assertIn(str(r.status), rs) + + @unittest.skipIf(not make_dataclass, "No dataclass support") + def test_encode_dataclass_item(self): + TestDataClass = make_dataclass( + "TestDataClass", + [("name", str), ("url", str), ("price", int)], + ) + item = TestDataClass(name="Product", url="http://product.org", price=1) + encoded = self.encoder.encode(item) + self.assertEqual( + encoded, + '{"name": "Product", "price": 1, "url": "http://product.org"}' + ) + + def test_encode_attrs_item(self): + @attr.s + class AttrsItem: + name = attr.ib(type=str) + url = attr.ib(type=str) + price = attr.ib(type=int) + + item = AttrsItem(name="Product", url="http://product.org", price=1) + encoded = self.encoder.encode(item) + self.assertEqual( + encoded, + '{"name": "Product", "price": 1, "url": "http://product.org"}' + ) diff --git a/tests/test_utils_signal.py b/tests/test_utils_signal.py index b66588efb..ad7394232 100644 --- a/tests/test_utils_signal.py +++ b/tests/test_utils_signal.py @@ -1,11 +1,14 @@ import asyncio +from unittest import SkipTest +from pydispatch import dispatcher from pytest import mark from testfixtures import LogCapture -from twisted.trial import unittest -from twisted.python.failure import Failure +from twisted import version as twisted_version from twisted.internet import defer, reactor -from pydispatch import dispatcher +from twisted.python.failure import Failure +from twisted.python.versions import Version +from twisted.trial import unittest from scrapy.utils.signal import send_catch_log, send_catch_log_deferred from scrapy.utils.test import get_from_asyncio_queue @@ -68,6 +71,7 @@ class SendCatchLogDeferredTest2(SendCatchLogDeferredTest): return d +@mark.usefixtures('reactor_pytest') class SendCatchLogDeferredAsyncDefTest(SendCatchLogDeferredTest): async def ok_handler(self, arg, handlers_called): @@ -76,6 +80,19 @@ class SendCatchLogDeferredAsyncDefTest(SendCatchLogDeferredTest): await defer.succeed(42) return "OK" + def test_send_catch_log(self): + if ( + self.reactor_pytest == 'asyncio' + and twisted_version < Version('twisted', 18, 4, 0) + ): + raise SkipTest( + 'Due to https://twistedmatrix.com/trac/ticket/9390, this test ' + 'fails due to a timeout when using AsyncIO and Twisted ' + 'versions lower than 18.4.0' + ) + + return super().test_send_catch_log() + @mark.only_asyncio() class SendCatchLogDeferredAsyncioTest(SendCatchLogDeferredTest): @@ -86,6 +103,16 @@ class SendCatchLogDeferredAsyncioTest(SendCatchLogDeferredTest): await asyncio.sleep(0.2) return await get_from_asyncio_queue("OK") + def test_send_catch_log(self): + if twisted_version < Version('twisted', 18, 4, 0): + raise SkipTest( + 'Due to https://twistedmatrix.com/trac/ticket/9390, this test ' + 'fails due to a timeout when using Twisted versions lower ' + 'than 18.4.0' + ) + + return super().test_send_catch_log() + class SendCatchLogTest2(unittest.TestCase): diff --git a/tests/test_utils_sitemap.py b/tests/test_utils_sitemap.py index bfbf9abb3..23eb261b7 100644 --- a/tests/test_utils_sitemap.py +++ b/tests/test_utils_sitemap.py @@ -156,8 +156,7 @@ Disallow: /forum/active/ def test_sitemap_blanklines(self): """Assert we can deal with starting blank lines before tag""" - s = Sitemap(b"""\ - + s = Sitemap(b""" diff --git a/tests/test_utils_template.py b/tests/test_utils_template.py index 5a52dd695..5ff2e41ef 100644 --- a/tests/test_utils_template.py +++ b/tests/test_utils_template.py @@ -19,8 +19,8 @@ class UtilsRenderTemplateFileTestCase(unittest.TestCase): def test_simple_render(self): context = dict(project_name='proj', name='spi', classname='TheSpider') - template = u'from ${project_name}.spiders.${name} import ${classname}' - rendered = u'from proj.spiders.spi import TheSpider' + template = 'from ${project_name}.spiders.${name} import ${classname}' + rendered = 'from proj.spiders.spi import TheSpider' template_path = os.path.join(self.tmp_path, 'templ.py.tmpl') render_path = os.path.join(self.tmp_path, 'templ.py') diff --git a/tests/test_utils_trackref.py b/tests/test_utils_trackref.py index 16e02f919..b8e8c3130 100644 --- a/tests/test_utils_trackref.py +++ b/tests/test_utils_trackref.py @@ -1,7 +1,10 @@ import unittest from io import StringIO +from time import sleep, time from unittest import mock +from twisted.trial.unittest import SkipTest + from scrapy.utils import trackref @@ -55,7 +58,18 @@ Foo 1 oldest: 0s ago\n\n''') def test_get_oldest(self): o1 = Foo() # NOQA + + o1_time = time() + o2 = Bar() # NOQA + + o3_time = time() + if o3_time <= o1_time: + sleep(0.01) + o3_time = time() + if o3_time <= o1_time: + raise SkipTest('time.time is not precise enough') + o3 = Foo() # NOQA self.assertIs(trackref.get_oldest('Foo'), o1) self.assertIs(trackref.get_oldest('Bar'), o2) diff --git a/tests/test_utils_url.py b/tests/test_utils_url.py index 09a6d6c70..144c7bd76 100644 --- a/tests/test_utils_url.py +++ b/tests/test_utils_url.py @@ -1,8 +1,14 @@ import unittest from scrapy.spiders import Spider -from scrapy.utils.url import (url_is_from_any_domain, url_is_from_spider, - add_http_if_no_scheme, guess_scheme, strip_url) +from scrapy.utils.url import ( + add_http_if_no_scheme, + guess_scheme, + _is_filesystem_path, + strip_url, + url_is_from_any_domain, + url_is_from_spider, +) __doctests__ = ['scrapy.utils.url'] @@ -207,8 +213,7 @@ def create_guess_scheme_t(args): def do_expected(self): url = guess_scheme(args[0]) assert url.startswith(args[1]), \ - 'Wrong scheme guessed: for `%s` got `%s`, expected `%s...`' % ( - args[0], url, args[1]) + f'Wrong scheme guessed: for `{args[0]}` got `{url}`, expected `{args[1]}...`' return do_expected @@ -249,7 +254,7 @@ for k, args in enumerate( start=1, ): t_method = create_guess_scheme_t(args) - t_method.__name__ = 'test_uri_%03d' % k + t_method.__name__ = f'test_uri_{k:03}' setattr(GuessSchemeTest, t_method.__name__, t_method) # TODO: the following tests do not pass with current implementation @@ -264,7 +269,7 @@ for k, args in enumerate( start=1, ): t_method = create_skipped_scheme_t(args) - t_method.__name__ = 'test_uri_skipped_%03d' % k + t_method.__name__ = f'test_uri_skipped_{k:03}' setattr(GuessSchemeTest, t_method.__name__, t_method) @@ -434,5 +439,28 @@ class StripUrl(unittest.TestCase): self.assertEqual(strip_url(i, origin_only=True), o) +class IsPathTestCase(unittest.TestCase): + + def test_path(self): + for input_value, output_value in ( + # https://en.wikipedia.org/wiki/Path_(computing)#Representations_of_paths_by_operating_system_and_shell + # Unix-like OS, Microsoft Windows / cmd.exe + ("/home/user/docs/Letter.txt", True), + ("./inthisdir", True), + ("../../greatgrandparent", True), + ("~/.rcinfo", True), + (r"C:\user\docs\Letter.txt", True), + ("/user/docs/Letter.txt", True), + (r"C:\Letter.txt", True), + (r"\\Server01\user\docs\Letter.txt", True), + (r"\\?\UNC\Server01\user\docs\Letter.txt", True), + (r"\\?\C:\user\docs\Letter.txt", True), + (r"C:\user\docs\somefile.ext:alternate_stream_name", True), + + (r"https://example.com", False), + ): + self.assertEqual(_is_filesystem_path(input_value), output_value, input_value) + + if __name__ == "__main__": unittest.main() diff --git a/tests/test_webclient.py b/tests/test_webclient.py index 188e54602..6e4cb9b6e 100644 --- a/tests/test_webclient.py +++ b/tests/test_webclient.py @@ -4,7 +4,10 @@ Tests borrowed from the twisted.web.client tests. """ import os import shutil +import sys +from pkg_resources import parse_version +import cryptography import OpenSSL.SSL from twisted.trial import unittest from twisted.web import server, static, util, resource @@ -253,7 +256,7 @@ class WebClientTestCase(unittest.TestCase): shutil.rmtree(self.tmpname) def getURL(self, path): - return "http://127.0.0.1:%d/%s" % (self.portno, path) + return f"http://127.0.0.1:{self.portno}/{path}" def testPayload(self): s = "0123456789" * 10 @@ -265,7 +268,7 @@ class WebClientTestCase(unittest.TestCase): # it should extract from url return defer.gatherResults([ getPage(self.getURL("host")).addCallback( - self.assertEqual, to_bytes("127.0.0.1:%d" % self.portno)), + self.assertEqual, to_bytes(f"127.0.0.1:{self.portno}")), getPage(self.getURL("host"), headers={"Host": "www.example.com"}).addCallback( self.assertEqual, to_bytes("www.example.com"))]) @@ -298,7 +301,7 @@ class WebClientTestCase(unittest.TestCase): """ d = getPage(self.getURL("host"), timeout=100) d.addCallback( - self.assertEqual, to_bytes("127.0.0.1:%d" % self.portno)) + self.assertEqual, to_bytes(f"127.0.0.1:{self.portno}")) return d def test_timeoutTriggering(self): @@ -356,9 +359,8 @@ class WebClientTestCase(unittest.TestCase): """ Test that non-standart body encoding matches Content-Encoding header """ body = b'\xd0\x81\xd1\x8e\xd0\xaf' - return getPage( - self.getURL('encoding'), body=body, response_transform=lambda r: r)\ - .addCallback(self._check_Encoding, body) + dfd = getPage(self.getURL('encoding'), body=body, response_transform=lambda r: r) + return dfd.addCallback(self._check_Encoding, body) def _check_Encoding(self, response, original_body): content_encoding = to_unicode(response.headers[b'Content-Encoding']) @@ -377,7 +379,7 @@ class WebClientSSLTestCase(unittest.TestCase): interface="127.0.0.1") def getURL(self, path): - return "https://127.0.0.1:%d/%s" % (self.portno, path) + return f"https://127.0.0.1:{self.portno}/{path}" def setUp(self): self.tmpname = self.mktemp() @@ -414,7 +416,11 @@ class WebClientCustomCiphersSSLTestCase(WebClientSSLTestCase): self.getURL("payload"), body=s, contextFactory=client_context_factory ).addCallback(self.assertEqual, to_bytes(s)) - def testPayloadDefaultCiphers(self): + def testPayloadDisabledCipher(self): + if sys.implementation.name == "pypy" and parse_version(cryptography.__version__) <= parse_version("2.3.1"): + self.skipTest("This test expects a failure, but the code does work in PyPy with cryptography<=2.3.1") s = "0123456789" * 10 - d = getPage(self.getURL("payload"), body=s, contextFactory=ScrapyClientContextFactory()) + settings = Settings({'DOWNLOADER_CLIENT_TLS_CIPHERS': 'ECDHE-RSA-AES256-GCM-SHA384'}) + client_context_factory = create_instance(ScrapyClientContextFactory, settings=settings, crawler=None) + d = getPage(self.getURL("payload"), body=s, contextFactory=client_context_factory) return self.assertFailure(d, OpenSSL.SSL.Error) diff --git a/tests/upper-constraints.txt b/tests/upper-constraints.txt new file mode 100644 index 000000000..2a335e533 --- /dev/null +++ b/tests/upper-constraints.txt @@ -0,0 +1,17 @@ +# Request the latest known version or newer of some dependencies to prevent the +# pip dependency resolver from spending too much time backtracking. +attrs>=20.2.0 +Automat>=0.8.0 +botocore>=1.20.30 +itemadapter>=0.1.1 +itemloaders>=1.0.3 +lxml>=4.6.1 +parsel>=1.5.2 +Pillow>=8.0.1 +pyOpenSSL>=17.5 # mitmproxy 4.0.4 +pytest>=6.2.1 +pytest-twisted>=1.13.1 +service_identity>=17.0.0 +six>=1.14.0 +sybil>=2.0.0 +Twisted>=19.10.0 diff --git a/tox.ini b/tox.ini index 69b1bdfdd..4c4bbff6e 100644 --- a/tox.ini +++ b/tox.ini @@ -9,19 +9,38 @@ minversion = 1.7.0 [testenv] deps = - -ctests/constraints.txt -rtests/requirements-py3.txt + # mitmproxy does not support PyPy + # mitmproxy does not support Windows when running Python < 3.7 + # Python 3.9+ requires https://github.com/mitmproxy/mitmproxy/commit/8e5e43de24c9bc93092b63efc67fbec029a9e7fe + # mitmproxy >= 5.3.0 requires h2 >= 4.0, Twisted 21.2 requires h2 < 4.0 + #mitmproxy >= 5.3.0; python_version >= '3.9' and implementation_name != 'pypy' + mitmproxy >= 4.0.4; python_version >= '3.7' and python_version < '3.9' and implementation_name != 'pypy' + mitmproxy >= 4.0.4, < 5; python_version >= '3.6' and python_version < '3.7' and platform_system != 'Windows' and implementation_name != 'pypy' # Extras - botocore>=1.3.23 - Pillow>=3.4.2 + botocore>=1.4.87 passenv = S3_TEST_FILE_URI AWS_ACCESS_KEY_ID AWS_SECRET_ACCESS_KEY GCS_TEST_FILE_URI GCS_PROJECT_ID +#allow tox virtualenv to upgrade pip/wheel/setuptools +download = true commands = - py.test --cov=scrapy --cov-report= {posargs:--durations=10 docs scrapy tests} + py.test --cov=scrapy --cov-report=xml --cov-report= {posargs:--durations=10 docs scrapy tests} +install_command = + pip install -U -ctests/upper-constraints.txt {opts} {packages} + +[testenv:typing] +basepython = python3 +deps = + lxml-stubs==0.2.0 + mypy==0.910 + types-pyOpenSSL==20.0.3 + types-setuptools==57.0.0 +commands = + mypy --show-error-codes {posargs: scrapy tests} [testenv:security] basepython = python3 @@ -34,54 +53,104 @@ commands = basepython = python3 deps = {[testenv]deps} + # Twisted[http2] is required to import some files + Twisted[http2]>=17.9.0 pytest-flake8 commands = py.test --flake8 {posargs:docs scrapy tests} - + [testenv:pylint] basepython = python3 deps = - {[testenv]deps} - # Optional dependencies - boto - reppy - robotexclusionrulesparser - # Test dependencies + {[testenv:extra-deps]deps} pylint commands = pylint conftest.py docs extras scrapy setup.py tests +[pinned] +deps = + cryptography==2.0 + cssselect==0.9.1 + h2==3.0 + itemadapter==0.1.0 + parsel==1.5.0 + Protego==0.1.15 + pyOpenSSL==16.2.0 + queuelib==1.4.2 + service_identity==16.0.0 + Twisted[http2]==17.9.0 + w3lib==1.17.0 + zope.interface==4.1.3 + -rtests/requirements-py3.txt + + # mitmproxy 4.0.4+ requires upgrading some of the pinned dependencies + # above, hence we do not install it in pinned environments at the moment + + # Extras + botocore==1.4.87 + google-cloud-storage==1.29.0 + Pillow==4.0.0 +setenv = + _SCRAPY_PINNED=true +install_command = + pip install -U {opts} {packages} + +[testenv:pinned] +deps = + {[pinned]deps} + lxml==3.5.0 + PyDispatcher==2.0.5 +install_command = {[pinned]install_command} +setenv = + {[pinned]setenv} + +[testenv:windows-pinned] +basepython = python3 +deps = + {[pinned]deps} + # First lxml version that includes a Windows wheel for Python 3.6, so we do + # not need to build lxml from sources in a CI Windows job: + lxml==3.8.0 + PyDispatcher==2.0.5 +install_command = {[pinned]install_command} +setenv = + {[pinned]setenv} + +[testenv:extra-deps] +deps = + {[testenv]deps} + boto + reppy + robotexclusionrulesparser + Pillow>=4.0.0 + Twisted[http2]>=17.9.0 + +[testenv:asyncio] +commands = + {[testenv]commands} --reactor=asyncio + +[testenv:asyncio-pinned] +deps = {[testenv:pinned]deps} +commands = {[testenv:asyncio]commands} +install_command = {[pinned]install_command} +setenv = + {[pinned]setenv} + [testenv:pypy3] basepython = pypy3 commands = py.test {posargs:--durations=10 docs scrapy tests} -[testenv:pinned] -basepython = python3 +[testenv:pypy3-pinned] +basepython = {[testenv:pypy3]basepython} deps = - -ctests/constraints.txt - cryptography==2.0 - cssselect==0.9.1 - lxml==3.5.0 - parsel==1.5.0 - Protego==0.1.15 - PyDispatcher==2.0.5 - pyOpenSSL==16.2.0 - queuelib==1.4.2 - service_identity==16.0.0 - Twisted==17.9.0 - w3lib==1.17.0 - zope.interface==4.1.3 - -rtests/requirements-py3.txt - # Extras - botocore==1.3.23 - Pillow==3.4.2 - -[testenv:extra-deps] -deps = - {[testenv]deps} - reppy - robotexclusionrulesparser + {[pinned]deps} + lxml==4.0.0 + PyPyDispatcher==2.1.0 +commands = {[testenv:pypy3]commands} +install_command = {[pinned]install_command} +setenv = + {[pinned]setenv} [docs] changedir = docs @@ -114,7 +183,3 @@ deps = {[docs]deps} setenv = {[docs]setenv} commands = sphinx-build -W -b linkcheck . {envtmpdir}/linkcheck - -[testenv:asyncio] -commands = - {[testenv]commands} --reactor=asyncio