diff --git a/.github/workflows/checks.yml b/.github/workflows/checks.yml new file mode 100644 index 000000000..2748bf5fe --- /dev/null +++ b/.github/workflows/checks.yml @@ -0,0 +1,38 @@ +name: Checks +on: [push, pull_request] + +jobs: + checks: + runs-on: ubuntu-18.04 + strategy: + matrix: + include: + - python-version: 3.8 + env: + TOXENV: security + - python-version: 3.8 + env: + TOXENV: flake8 + - python-version: 3.8 + env: + TOXENV: pylint + - python-version: 3.8 + env: + TOXENV: typing + - python-version: 3.7 # 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: | + pip install -U tox + tox diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml deleted file mode 100644 index 28771216c..000000000 --- a/.github/workflows/main.yml +++ /dev/null @@ -1,31 +0,0 @@ -name: Run test suite -on: [push, pull_request] - -jobs: - test-windows: - name: "Windows Tests" - runs-on: ${{ matrix.os }} - strategy: - matrix: - os: [windows-latest] - python-version: [3.7, 3.8] - env: [TOXENV: py] - include: - - os: windows-latest - python-version: 3.6 - env: - TOXENV: windows-pinned - - steps: - - uses: actions/checkout@v2 - - - name: Set up Python ${{ matrix.python-version }} - uses: actions/setup-python@v1 - with: - python-version: ${{ matrix.python-version }} - - - name: Run test suite - env: ${{ matrix.env }} - run: | - pip install -U tox twine wheel codecov - tox diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml new file mode 100644 index 000000000..aec6b8696 --- /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 3.8 + uses: actions/setup-python@v2 + with: + python-version: 3.8 + + - 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..51d27c405 --- /dev/null +++ b/.github/workflows/tests-macos.yml @@ -0,0 +1,25 @@ +name: macOS +on: [push, pull_request] + +jobs: + tests: + runs-on: macos-10.15 + strategy: + matrix: + python-version: [3.6, 3.7, 3.8] + + 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..89c0334e2 --- /dev/null +++ b/.github/workflows/tests-ubuntu.yml @@ -0,0 +1,69 @@ +name: Ubuntu +on: [push, pull_request] + +jobs: + tests: + runs-on: ubuntu-18.04 + strategy: + matrix: + include: + - python-version: 3.7 + env: + TOXENV: py + - python-version: 3.8 + 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 + - python-version: 3.8 + env: + TOXENV: extra-deps + - python-version: 3.8 + 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 + sudo apt-get install libxml2-dev 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 + 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..ed2e4075d --- /dev/null +++ b/.github/workflows/tests-windows.yml @@ -0,0 +1,32 @@ +name: Windows +on: [push, pull_request] + +jobs: + tests: + runs-on: windows-latest + strategy: + matrix: + include: + - python-version: 3.6 + env: + TOXENV: windows-pinned + - python-version: 3.7 + env: + TOXENV: py + - python-version: 3.8 + 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: ${{ matrix.env }} + run: | + pip install -U tox + tox diff --git a/.travis.yml b/.travis.yml deleted file mode 100644 index b883c5b78..000000000 --- a/.travis.yml +++ /dev/null @@ -1,75 +0,0 @@ -language: python -dist: xenial -branches: - only: - - master - - /^\d\.\d+$/ - - /^\d\.\d+\.\d+(rc\d+|\.dev\d+)?$/ -matrix: - include: - - env: TOXENV=security - python: 3.8 - - env: TOXENV=flake8 - python: 3.8 - - env: TOXENV=pylint - python: 3.8 - - env: TOXENV=docs - python: 3.7 # Keep in sync with .readthedocs.yml - - env: TOXENV=typing - python: 3.8 - - - env: TOXENV=pinned - python: 3.6.1 - - env: TOXENV=asyncio-pinned - python: 3.6.1 - - env: TOXENV=pypy3-pinned PYPY_VERSION=3.6-v7.2.0 - - - env: TOXENV=py - python: 3.6 - - env: TOXENV=pypy3 PYPY_VERSION=3.6-v7.3.1 - - - env: TOXENV=py - python: 3.7 - - - env: TOXENV=py PYPI_RELEASE_JOB=true - python: 3.8 - dist: bionic - - env: TOXENV=extra-deps - python: 3.8 - dist: bionic - - env: TOXENV=asyncio - python: 3.8 - dist: bionic -install: - - | - if [[ ! -z "$PYPY_VERSION" ]]; then - export PYPY_VERSION="pypy$PYPY_VERSION-linux64" - wget "https://downloads.python.org/pypy/${PYPY_VERSION}.tar.bz2" - tar -jxf ${PYPY_VERSION}.tar.bz2 - virtualenv --python="$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..652460383 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. diff --git a/README.rst b/README.rst index a8f2ba52b..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 @@ -34,9 +42,16 @@ 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 ============ @@ -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/conftest.py b/conftest.py index 68b855c08..e4dd80de0 100644 --- a/conftest.py +++ b/conftest.py @@ -2,6 +2,8 @@ from pathlib import Path import pytest +from scrapy.utils.reactor import install_reactor + from tests.keys import generate_keys @@ -40,6 +42,14 @@ 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: @@ -55,5 +65,10 @@ def only_asyncio(request, reactor_pytest): 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/conf.py b/docs/conf.py index 27d2b5dff..543507a46 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -283,6 +283,7 @@ 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), diff --git a/docs/intro/install.rst b/docs/intro/install.rst index 3bfd3bc3b..bf919ce25 100644 --- a/docs/intro/install.rst +++ b/docs/intro/install.rst @@ -69,10 +69,9 @@ 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: @@ -265,10 +264,8 @@ 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 .. _conda-forge: https://conda-forge.org/ diff --git a/docs/news.rst b/docs/news.rst index 0391506c4..d9fe897ad 100644 --- a/docs/news.rst +++ b/docs/news.rst @@ -2428,7 +2428,7 @@ 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 ~~~~~~~~~~~~~ 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/exporters.rst b/docs/topics/exporters.rst index ef50c9f5c..0a0a1765a 100644 --- a/docs/topics/exporters.rst +++ b/docs/topics/exporters.rst @@ -123,7 +123,7 @@ Example:: def serialize_field(self, field, name, value): if field == 'price': return f'$ {str(value)}' - return super(Product, self).serialize_field(field, name, value) + return super().serialize_field(field, name, value) .. _topics-exporters-reference: diff --git a/docs/topics/logging.rst b/docs/topics/logging.rst index 55065a1a3..c3445d40e 100644 --- a/docs/topics/logging.rst +++ b/docs/topics/logging.rst @@ -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) diff --git a/docs/topics/practices.rst b/docs/topics/practices.rst index cf1de1bd1..502fd5fcd 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 @@ -244,7 +244,7 @@ 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 +254,5 @@ 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 f3aaa2c8f..98906992d 100644 --- a/docs/topics/request-response.rst +++ b/docs/topics/request-response.rst @@ -693,9 +693,19 @@ 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" + :type protocol: :class:`str` + + .. versionadded:: 2.0.0 + The ``certificate`` parameter. + .. versionadded:: 2.1.0 The ``ip_address`` parameter. + .. versionadded:: VERSION + The ``protocol`` parameter. + .. attribute:: Response.url A string containing the URL of the response. @@ -780,6 +790,8 @@ Response objects .. attribute:: Response.certificate + .. versionadded:: 2.0.0 + A :class:`twisted.internet.ssl.Certificate` object representing the server's SSL certificate. @@ -795,6 +807,17 @@ Response objects handler, i.e. for ``http(s)`` responses. For other handlers, :attr:`ip_address` is always ``None``. + .. attribute:: Response.protocol + + .. versionadded:: VERSION + + 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. diff --git a/docs/topics/selectors.rst b/docs/topics/selectors.rst index b576fde91..c7ec2e0cc 100644 --- a/docs/topics/selectors.rst +++ b/docs/topics/selectors.rst @@ -464,10 +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: diff --git a/pytest.ini b/pytest.ini index 1c95f715a..0aae09ff5 100644 --- a/pytest.ini +++ b/pytest.ini @@ -18,7 +18,6 @@ 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 @@ -36,8 +35,5 @@ flake8-ignore = 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 diff --git a/scrapy/core/downloader/handlers/http11.py b/scrapy/core/downloader/handlers/http11.py index 1b041c8a8..513df2de9 100644 --- a/scrapy/core/downloader/handlers/http11.py +++ b/scrapy/core/downloader/handlers/http11.py @@ -303,11 +303,14 @@ class ScrapyAgent: 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 (formerly Crawlera), " + "it doesn't require this mode anymore, so you should " + "update scrapy-crawlera to 1.3.0+ 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) @@ -434,6 +437,11 @@ class ScrapyAgent: def _cb_bodydone(self, result, request, url): headers = Headers(result["txresponse"].headers.getAllRawHeaders()) 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), @@ -442,6 +450,7 @@ class ScrapyAgent: flags=result["flags"], certificate=result["certificate"], ip_address=result["ip_address"], + protocol=protocol, ) if result.get("failure"): result["failure"].value.response = response diff --git a/scrapy/core/downloader/webclient.py b/scrapy/core/downloader/webclient.py index c13683393..9524cce2b 100644 --- a/scrapy/core/downloader/webclient.py +++ b/scrapy/core/downloader/webclient.py @@ -7,7 +7,7 @@ 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 @@ -110,7 +110,7 @@ class ScrapyHTTPClientFactory(ClientFactory): 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) + 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) diff --git a/scrapy/core/scheduler.py b/scrapy/core/scheduler.py index a18c26b17..9ce823dbc 100644 --- a/scrapy/core/scheduler.py +++ b/scrapy/core/scheduler.py @@ -1,14 +1,10 @@ import os import json import logging -import warnings from os.path import join, exists -from queuelib import PriorityQueue - from scrapy.utils.misc import load_object, create_instance from scrapy.utils.job import job_dir -from scrapy.utils.deprecate import ScrapyDeprecationWarning logger = logging.getLogger(__name__) @@ -56,14 +52,6 @@ class Scheduler: 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 - dqclass = load_object(settings['SCHEDULER_DISK_QUEUE']) mqclass = load_object(settings['SCHEDULER_MEMORY_QUEUE']) logunser = settings.getbool('SCHEDULER_DEBUG') diff --git a/scrapy/core/spidermw.py b/scrapy/core/spidermw.py index 763e0cdf6..289292da7 100644 --- a/scrapy/core/spidermw.py +++ b/scrapy/core/spidermw.py @@ -41,86 +41,92 @@ 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 = (f"Middleware {_fname(method)} 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(iterable, exception_processor_index, recover_to): + def _process_spider_input(self, scrape_func, response, request, spider): + 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 {_fname(method)} 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, spider, iterable, exception_processor_index, recover_to): + 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, spider, _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 self._process_spider_output(response, spider, result, method_index + 1) + elif result is None: + continue + else: + msg = (f"Middleware {_fname(method)} must return None " + f"or an iterable, got {type(result)}") + raise _InvalidOutput(msg) + return _failure + + def _process_spider_output(self, response, spider, 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() + + 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 {_fname(method)} 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 = (f"Middleware {_fname(method)} must return None " - f"or an iterable, got {type(result)}") - raise _InvalidOutput(msg) - 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() - - 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 = (f"Middleware {_fname(method)} must return an " - f"iterable, got {type(result)}") - raise _InvalidOutput(msg) - - return MutableChain(result, recovered) + def _process_callback_output(self, response, spider, result): + recovered = MutableChain() + result = self._evaluate_iterable(response, spider, result, 0, recovered) + return MutableChain(self._process_spider_output(response, spider, result), recovered) + def scrape_response(self, scrape_func, response, request, spider): def process_callback_output(result): - recovered = MutableChain() - result = _evaluate_iterable(result, 0, recovered) - return MutableChain(process_spider_output(result), recovered) + return self._process_callback_output(response, spider, result) - dfd = mustbe_deferred(process_spider_input, response) + def process_spider_exception(_failure): + return self._process_spider_exception(response, spider, _failure) + + dfd = mustbe_deferred(self._process_spider_input, scrape_func, response, request, spider) dfd.addCallbacks(callback=process_callback_output, errback=process_spider_exception) return dfd diff --git a/scrapy/http/request/form.py b/scrapy/http/request/form.py index 2815303a2..7f267c800 100644 --- a/scrapy/http/request/form.py +++ b/scrapy/http/request/form.py @@ -160,7 +160,7 @@ def _select_value(ele, n, v): 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: diff --git a/scrapy/http/response/__init__.py b/scrapy/http/response/__init__.py index c635fde69..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): @@ -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/pipelines/media.py b/scrapy/pipelines/media.py index 0a12f3e2c..0c2ee6856 100644 --- a/scrapy/pipelines/media.py +++ b/scrapy/pipelines/media.py @@ -86,7 +86,7 @@ class MediaPipeline: info = self.spiderinfo requests = arg_to_iter(self.get_media_requests(item, info)) dlist = [self._process_request(r, info, item) for r in requests] - dfd = DeferredList(dlist, consumeErrors=1) + dfd = DeferredList(dlist, consumeErrors=True) return dfd.addCallback(self.item_completed, item, info) def _process_request(self, request, info, item): diff --git a/scrapy/utils/asyncgen.py b/scrapy/utils/asyncgen.py new file mode 100644 index 000000000..7f697af5f --- /dev/null +++ b/scrapy/utils/asyncgen.py @@ -0,0 +1,5 @@ +async def collect_asyncgen(result): + results = [] + async for x in result: + results.append(x) + return results diff --git a/scrapy/utils/defer.py b/scrapy/utils/defer.py index 21ba02a0b..6db9cc117 100644 --- a/scrapy/utils/defer.py +++ b/scrapy/utils/defer.py @@ -105,7 +105,7 @@ def process_parallel(callbacks, input, *a, **kw): callbacks """ dfds = [defer.succeed(input).addCallback(x, *a, **kw) for x in callbacks] - d = defer.DeferredList(dfds, fireOnOneErrback=1, consumeErrors=1) + d = defer.DeferredList(dfds, fireOnOneErrback=True, consumeErrors=True) d.addCallbacks(lambda r: [x[1] for x in r], lambda f: f.value.subFailure) return d diff --git a/scrapy/utils/gz.py b/scrapy/utils/gz.py index 11d433cf5..76156a4b8 100644 --- a/scrapy/utils/gz.py +++ b/scrapy/utils/gz.py @@ -1,7 +1,6 @@ +import struct from gzip import GzipFile from io import BytesIO -import re -import struct from scrapy.utils.decorators import deprecated @@ -42,17 +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/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/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/project.py b/scrapy/utils/project.py index fd13d85e3..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 @@ -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', 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/spider.py b/scrapy/utils/spider.py index f3a9a67a3..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 diff --git a/setup.cfg b/setup.cfg index 8101443e3..0c9f6b963 100644 --- a/setup.cfg +++ b/setup.cfg @@ -55,9 +55,6 @@ ignore_errors = True [mypy-scrapy.utils.response] ignore_errors = True -[mypy-scrapy.utils.spider] -ignore_errors = True - [mypy-scrapy.utils.trackref] ignore_errors = True diff --git a/setup.py b/setup.py index 0c2281400..b5c42a3c2 100644 --- a/setup.py +++ b/setup.py @@ -24,7 +24,6 @@ install_requires = [ 'cssselect>=0.9.1', 'itemloaders>=1.0.1', 'parsel>=1.5.0', - 'PyDispatcher>=2.0.5', 'pyOpenSSL>=16.2.0', 'queuelib>=1.4.2', 'service_identity>=16.0.0', @@ -34,11 +33,12 @@ install_requires = [ 'itemadapter>=0.1.0', ] 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"'] = [ - 'lxml>=3.5.0', - ] + 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, @@ -49,14 +49,14 @@ if has_environment_marker_platform_impl_support(): 'PyPyDispatcher>=2.1.0', ] else: - install_requires.append('lxml>=3.5.0') + 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', diff --git a/tests/requirements-py3.txt b/tests/requirements-py3.txt index 7f8a5c52e..bd72c8c46 100644 --- a/tests/requirements-py3.txt +++ b/tests/requirements-py3.txt @@ -1,21 +1,18 @@ # Tests requirements attrs dataclasses; python_version == '3.6' -mitmproxy; python_version >= '3.7' -mitmproxy >= 4.0.4, < 5; python_version >= '3.6' and python_version < '3.7' pyftpdlib -# https://github.com/pytest-dev/pytest-twisted/issues/93 -pytest != 5.4, != 5.4.1 +pytest pytest-cov -pytest-twisted >= 1.11 pytest-xdist sybil >= 1.3.0 # https://github.com/cjw296/sybil/issues/20#issuecomment-605433422 testfixtures -uvloop; platform_system != "Windows" +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 # optional for HTTP compress downloader middleware tests -zstandard # 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/test_dependencies.py b/tests/test_dependencies.py index 5d0a1d0c9..93e7311d2 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==([\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 3e8d7e6b9..f51a6cd3c 100644 --- a/tests/test_downloader_handlers.py +++ b/tests/test_downloader_handlers.py @@ -115,6 +115,7 @@ 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') @@ -360,6 +361,13 @@ class Http10TestCase(HttpTestCase): """HTTP 1.0 test case""" download_handler_cls = 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): scheme = 'https' @@ -489,6 +497,13 @@ 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' @@ -962,6 +977,7 @@ 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): @@ -1120,3 +1136,10 @@ 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_downloadermiddleware.py b/tests/test_downloadermiddleware.py index 79f24c8a1..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 @@ -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_proxy_connect.py b/tests/test_proxy_connect.py index 9eabe6b49..afdfb2578 100644 --- a/tests/test_proxy_connect.py +++ b/tests/test_proxy_connect.py @@ -1,12 +1,9 @@ import json import os -import platform import re import sys from subprocess import Popen, PIPE from urllib.parse import urlsplit, urlunsplit -from unittest import skipIf - from testfixtures import LogCapture from twisted.internet import defer from twisted.trial.unittest import TestCase @@ -57,13 +54,14 @@ def _wrong_credentials(proxy_url): return urlunsplit(bad_auth_proxy) -@skipIf("pypy" in sys.executable, - "mitmproxy does not support PyPy") -@skipIf(platform.system() == 'Windows' and sys.version_info < (3, 7), - "mitmproxy does not support Windows when running Python < 3.7") 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() diff --git a/tests/test_utils_defer.py b/tests/test_utils_defer.py index e60242a3b..7a5f458c7 100644 --- a/tests/test_utils_defer.py +++ b/tests/test_utils_defer.py @@ -1,8 +1,10 @@ +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 ( + deferred_f_from_coro_f, iter_errback, mustbe_deferred, process_chain, @@ -117,3 +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_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_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_webclient.py b/tests/test_webclient.py index a60181a3a..f935a8689 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 @@ -414,6 +417,8 @@ class WebClientCustomCiphersSSLTestCase(WebClientSSLTestCase): ).addCallback(self.assertEqual, to_bytes(s)) def testPayloadDisabledCipher(self): + if sys.implementation.name == "pypy" and parse_version(cryptography.__version__) <= parse_version("2.3.1"): + self.skipTest("This does work in PyPy with cryptography<=2.3.1") s = "0123456789" * 10 settings = Settings({'DOWNLOADER_CLIENT_TLS_CIPHERS': 'ECDHE-RSA-AES256-GCM-SHA384'}) client_context_factory = create_instance(ScrapyClientContextFactory, settings=settings, crawler=None) diff --git a/tox.ini b/tox.ini index ea356c56a..e70aef2d2 100644 --- a/tox.ini +++ b/tox.ini @@ -11,6 +11,10 @@ minversion = 1.7.0 deps = -ctests/constraints.txt -rtests/requirements-py3.txt + # mitmproxy does not support PyPy + # mitmproxy does not support Windows when running Python < 3.7 + mitmproxy >= 4.0.4; python_version >= '3.7' 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>=1.4.87 Pillow>=4.0.0 @@ -20,8 +24,10 @@ passenv = 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} [testenv:typing] basepython = python3 @@ -66,7 +72,6 @@ deps = itemadapter==0.1.0 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 @@ -74,15 +79,24 @@ deps = 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 [testenv:pinned] deps = {[pinned]deps} lxml==3.5.0 + PyDispatcher==2.0.5 +setenv = + {[pinned]setenv} [testenv:windows-pinned] basepython = python3 @@ -91,6 +105,9 @@ 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 +setenv = + {[pinned]setenv} [testenv:extra-deps] deps = @@ -103,8 +120,10 @@ commands = {[testenv]commands} --reactor=asyncio [testenv:asyncio-pinned] -commands = {[testenv:asyncio]commands} deps = {[testenv:pinned]deps} +commands = {[testenv:asyncio]commands} +setenv = + {[pinned]setenv} [testenv:pypy3] basepython = pypy3 @@ -113,11 +132,13 @@ commands = [testenv:pypy3-pinned] basepython = {[testenv:pypy3]basepython} -commands = {[testenv:pypy3]commands} deps = {[pinned]deps} lxml==4.0.0 PyPyDispatcher==2.1.0 +commands = {[testenv:pypy3]commands} +setenv = + {[pinned]setenv} [docs] changedir = docs