RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

merged master

This commit is contained in:
Georgiy Zatserklianyi 2024-10-17 22:14:54 +02:00
parent d8fb9d2e7e 6d65708cb7
commit 145a369198
287 changed files with 10336 additions and 4464 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
.bandit.yml
View File

@ -1,21 +1,7 @@
skips:
- B101
- B113 # https://github.com/PyCQA/bandit/issues/1010
- B105
- B301
- B303
- B306
- B307
- B311
- B320
- B321
- B324
- B402 # https://github.com/scrapy/scrapy/issues/4180
- B403
- B404
- B406
- B410
- B503
- B603
- B605
- B101 # assert_used, needed for mypy
- B321 # ftplib, https://github.com/scrapy/scrapy/issues/4180
- B402 # import_ftplib, https://github.com/scrapy/scrapy/issues/4180
- B411 # import_xmlrpclib, https://github.com/PyCQA/bandit/issues/1082
- B503 # ssl_with_bad_defaults
exclude_dirs: ['tests']

6
.bumpversion.cfg
View File

@ -1,7 +1,11 @@
[bumpversion]
current_version = 2.11.0
current_version = 2.11.2
commit = True
tag = True
tag_name = {new_version}
[bumpversion:file:scrapy/VERSION]
[bumpversion:file:SECURITY.md]
parse = (?P<major>\d+)\.(?P<minor>\d+)\.x
serialize = {major}.{minor}.x

6
.coveragerc
View File

@ -4,3 +4,9 @@ include = scrapy/*
omit =
tests/*
disable_warnings = include-ignored
[report]
# https://github.com/nedbat/coveragepy/issues/831#issuecomment-517778185
exclude_lines =
pragma: no cover
if TYPE_CHECKING:

62
.flake8
View File

@ -1,8 +1,67 @@
[flake8]
max-line-length = 119
ignore = W503, E203
extend-select = TC, TC1
ignore =
# black disagrees with flake8 about these
E203, E501, E701, E704, W503
# Assigning to `os.environ` doesn't clear the environment.
B003
# Do not use mutable data structures for argument defaults.
B006
# Loop control variable not used within the loop body.
B007
# Do not perform function calls in argument defaults.
B008
# return/continue/break inside finally blocks cause exceptions to be
# silenced.
B012
# Star-arg unpacking after a keyword argument is strongly discouraged
B026
# No explicit stacklevel argument found.
B028
# docstring does contain unindexed parameters
P102
# other string does contain unindexed parameters
P103
# Missing docstring in public module
D100
# Missing docstring in public class
D101
# Missing docstring in public method
D102
# Missing docstring in public function
D103
# Missing docstring in public package
D104
# Missing docstring in magic method
D105
# Missing docstring in public nested class
D106
# Missing docstring in __init__
D107
# One-line docstring should fit on one line with quotes
D200
# No blank lines allowed after function docstring
D202
# 1 blank line required between summary line and description
D205
# Multi-line docstring closing quotes should be on a separate line
D209
# First line should end with a period
D400
# First line should be in imperative mood; try rephrasing
D401
# First line should not be the function's "signature"
D402
# First word of the first line should be properly capitalized
D403
# Annotation in typing.cast() should be a string literal
TC006
exclude =
docs/conf.py
@ -16,6 +75,7 @@ per-file-ignores =
scrapy/linkextractors/__init__.py:E402,F401
scrapy/selector/__init__.py:F401
scrapy/spiders/__init__.py:E402,F401
tests/CrawlerRunner/change_reactor.py:E402
# Issues pending a review:
scrapy/utils/url.py:F403,F405

4
.git-blame-ignore-revs
View File

@ -1,7 +1,7 @@
# .git-blame-ignore-revs
# adding black formatter to all the code
e211ec0aa26ecae0da8ae55d064ea60e1efe4d0d
# re applying black to the code with default line length
# reapplying black to the code with default line length
303f0a70fcf8067adf0a909c2096a5009162383a
# reaplying black again and removing line length on pre-commit black config
# reapplying black again and removing line length on pre-commit black config
c5cdd0d30ceb68ccba04af0e71d1b8e6678e2962

11
.github/workflows/checks.yml vendored
View File

@ -15,10 +15,13 @@ jobs:
- python-version: "3.12"
env:
TOXENV: pylint
- python-version: 3.8
- python-version: "3.9"
env:
TOXENV: typing
- python-version: "3.11" # Keep in sync with .readthedocs.yml
- python-version: "3.9"
env:
TOXENV: typing-tests
- python-version: "3.12" # Keep in sync with .readthedocs.yml
env:
TOXENV: docs
- python-version: "3.12"
@ -29,7 +32,7 @@ jobs:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
@ -43,4 +46,4 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pre-commit/action@v3.0.0
- uses: pre-commit/action@v3.0.1

4
.github/workflows/publish.yml vendored
View File

@ -13,13 +13,13 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v4
- uses: actions/setup-python@v5
with:
python-version: 3.12
- run: |
pip install --upgrade build twine
python -m build
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@v1.6.4
uses: pypa/gh-action-pypi-publish@v1.10.3
with:
password: ${{ secrets.PYPI_TOKEN }}

6
.github/workflows/tests-macos.yml vendored
View File

@ -7,17 +7,17 @@ concurrency:
jobs:
tests:
runs-on: macos-11
runs-on: macos-latest
strategy:
fail-fast: false
matrix:
python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
python-version: ["3.9", "3.10", "3.11", "3.12"]
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}

14
.github/workflows/tests-ubuntu.yml vendored
View File

@ -12,7 +12,7 @@ jobs:
fail-fast: false
matrix:
include:
- python-version: 3.9
- python-version: "3.9"
env:
TOXENV: py
- python-version: "3.10"
@ -35,19 +35,19 @@ jobs:
TOXENV: pypy3
# pinned deps
- python-version: 3.8.17
- python-version: 3.9.19
env:
TOXENV: pinned
- python-version: 3.8.17
- python-version: 3.9.19
env:
TOXENV: asyncio-pinned
- python-version: pypy3.8
- python-version: pypy3.9
env:
TOXENV: pypy3-pinned
- python-version: 3.8.17
- python-version: 3.9.19
env:
TOXENV: extra-deps-pinned
- python-version: 3.8.17
- python-version: 3.9.19
env:
TOXENV: botocore-pinned
@ -62,7 +62,7 @@ jobs:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}

7
.github/workflows/tests-windows.yml vendored
View File

@ -12,12 +12,9 @@ jobs:
fail-fast: false
matrix:
include:
- python-version: 3.8
- python-version: "3.9"
env:
TOXENV: windows-pinned
- python-version: 3.9
env:
TOXENV: py
- python-version: "3.10"
env:
TOXENV: py
@ -35,7 +32,7 @@ jobs:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}

24
.pre-commit-config.yaml
View File

@ -1,24 +1,36 @@
repos:
- repo: https://github.com/PyCQA/bandit
rev: 1.7.5
rev: 1.7.9
hooks:
- id: bandit
args: [-r, -c, .bandit.yml]
- repo: https://github.com/PyCQA/flake8
rev: 6.1.0
rev: 7.1.0
hooks:
- id: flake8
additional_dependencies:
- flake8-bugbear
- flake8-comprehensions
- flake8-debugger
- flake8-docstrings
- flake8-string-format
- flake8-type-checking
- repo: https://github.com/psf/black.git
rev: 23.9.1
rev: 24.4.2
hooks:
- id: black
- repo: https://github.com/pycqa/isort
rev: 5.12.0
rev: 5.13.2
hooks:
- id: isort
- repo: https://github.com/adamchainz/blacken-docs
rev: 1.16.0
rev: 1.18.0
hooks:
- id: blacken-docs
additional_dependencies:
- black==23.9.1
- black==24.4.2
- repo: https://github.com/asottile/pyupgrade
rev: v3.18.0
hooks:
- id: pyupgrade
args: [--py39-plus]

2
.readthedocs.yml
View File

@ -9,7 +9,7 @@ build:
tools:
# For available versions, see:
# https://docs.readthedocs.io/en/stable/config-file/v2.html#build-tools-python
python: "3.11" # Keep in sync with .github/workflows/checks.yml
python: "3.12" # Keep in sync with .github/workflows/checks.yml
python:
install:

12
MANIFEST.in
View File

@ -1,9 +1,8 @@
include README.rst
include AUTHORS
include INSTALL
include LICENSE
include MANIFEST.in
include CODE_OF_CONDUCT.md
include CONTRIBUTING.md
include INSTALL.md
include NEWS
include SECURITY.md
include scrapy/VERSION
include scrapy/mime.types
@ -12,16 +11,13 @@ include scrapy/py.typed
include codecov.yml
include conftest.py
include pytest.ini
include requirements-*.txt
include tox.ini
recursive-include scrapy/templates *
recursive-include scrapy license.txt
recursive-include docs *
prune docs/build
recursive-include extras *
recursive-include bin *
recursive-include tests *
global-exclude __pycache__ *.py[cod]

2
README.rst
View File

@ -59,7 +59,7 @@ including a list of features.
Requirements
============
* Python 3.8+
* Python 3.9+
* Works on Linux, Windows, macOS, BSD
Install

12
SECURITY.md Normal file
View File

@ -0,0 +1,12 @@
# Security Policy
## Supported Versions
| Version | Supported |
| ------- | ------------------ |
| 2.11.x | :white_check_mark: |
| < 2.11.x | :x: |
## Reporting a Vulnerability
Please report the vulnerability using https://github.com/scrapy/scrapy/security/advisories/new.

18
conftest.py
View File

@ -1,10 +1,6 @@
import platform
import sys
from pathlib import Path
import pytest
from twisted import version as twisted_version
from twisted.python.versions import Version
from twisted.web.http import H2_ENABLED
from scrapy.utils.reactor import install_reactor
@ -85,14 +81,12 @@ def only_not_asyncio(request, reactor_pytest):
def requires_uvloop(request):
if not request.node.get_closest_marker("requires_uvloop"):
return
if sys.implementation.name == "pypy":
pytest.skip("uvloop does not support pypy properly")
if platform.system() == "Windows":
pytest.skip("uvloop does not support Windows")
if twisted_version == Version("twisted", 21, 2, 0):
pytest.skip("https://twistedmatrix.com/trac/ticket/10106")
if sys.version_info >= (3, 12):
pytest.skip("uvloop doesn't support Python 3.12 yet")
try:
import uvloop
del uvloop
except ImportError:
pytest.skip("uvloop is not installed")
def pytest_configure(config):

5
docs/conf.py
View File

@ -10,7 +10,6 @@
# serve to show the default.
import sys
from datetime import datetime
from pathlib import Path
# If your extensions are in another directory, add it here. If the directory
@ -48,7 +47,7 @@ master_doc = "index"
# General information about the project.
project = "Scrapy"
copyright = f"2008–{datetime.now().year}, Scrapy developers"
copyright = "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
@ -227,7 +226,7 @@ latex_documents = [
# A list of regular expressions that match URIs that should not be checked when
# doing a linkcheck build.
linkcheck_ignore = [
"http://localhost:\d+",
r"http://localhost:\d+",
"http://hg.scrapy.org",
"http://directory.google.com/",
]

56
docs/faq.rst
View File

@ -138,39 +138,37 @@ 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 <custom-spider-middleware>` that requires
less memory. For example:
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.downloadermiddlewares.offsite.OffsiteMiddleware` downloader
middleware with a :ref:`custom downloader middleware
<topics-downloader-middleware-custom>` 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.
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`_.
See also `other suggestions at StackOverflow
<https://stackoverflow.com/q/36440681>`__.
.. note:: Remember to disable
:class:`scrapy.spidermiddlewares.offsite.OffsiteMiddleware` when you enable
your custom implementation:
:class:`scrapy.downloadermiddlewares.offsite.OffsiteMiddleware` when you
enable your custom implementation:
.. code-block:: python
SPIDER_MIDDLEWARES = {
"scrapy.spidermiddlewares.offsite.OffsiteMiddleware": None,
"myproject.middlewares.CustomOffsiteMiddleware": 500,
DOWNLOADER_MIDDLEWARES = {
"scrapy.downloadermiddlewares.offsite.OffsiteMiddleware": None,
"myproject.middlewares.CustomOffsiteMiddleware": 50,
}
.. _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?
--------------------------------------------------
@ -206,12 +204,10 @@ I get "Filtered offsite request" messages. How can I fix them?
Those messages (logged with ``DEBUG`` level) don't necessarily mean there is a
problem, so you may not need to fix them.
Those messages are thrown by the Offsite Spider Middleware, which is a spider
middleware (enabled by default) whose purpose is to filter out requests to
domains outside the ones covered by the spider.
For more info see:
:class:`~scrapy.spidermiddlewares.offsite.OffsiteMiddleware`.
Those messages are thrown by
:class:`~scrapy.downloadermiddlewares.offsite.OffsiteMiddleware`, which is a
downloader middleware (enabled by default) whose purpose is to filter out
requests to domains outside the ones covered by the spider.
What is the recommended way to deploy a Scrapy crawler in production?
---------------------------------------------------------------------
@ -273,7 +269,7 @@ To dump into a CSV file::
scrapy crawl myspider -O items.csv
To dump into a XML file::
To dump into an XML file::
scrapy crawl myspider -O items.xml
@ -297,9 +293,13 @@ build the DOM of the entire feed in memory, and this can be quite slow and
consume a lot of memory.
In order to avoid parsing all the entire feed at once in memory, you can use
the functions ``xmliter`` and ``csviter`` from ``scrapy.utils.iterators``
module. In fact, this is what the feed spiders (see :ref:`topics-spiders`) use
under the cover.
the :func:`~scrapy.utils.iterators.xmliter_lxml` and
:func:`~scrapy.utils.iterators.csviter` functions. In fact, this is what
:class:`~scrapy.spiders.XMLFeedSpider` uses.
.. autofunction:: scrapy.utils.iterators.xmliter_lxml
.. autofunction:: scrapy.utils.iterators.csviter
Does Scrapy manage cookies automatically?
-----------------------------------------
@ -417,8 +417,8 @@ How can I make a blank request?
blank_request = Request("data:,")
In this case, the URL is set to a data URI scheme. Data URLs allow you to include data
in-line in web pages as if they were external resources. The "data:" scheme with an empty
In this case, the URL is set to a data URI scheme. Data URLs allow you to include data
inline within web pages, similar to external resources. The "data:" scheme with an empty
content (",") essentially creates a request to a data URL without any specific content.

15
docs/intro/install.rst
View File

@ -9,7 +9,7 @@ Installation guide
Supported Python versions
=========================
Scrapy requires Python 3.8+, either the CPython implementation (default) or
Scrapy requires Python 3.9+, either the CPython implementation (default) or
the PyPy implementation (see :ref:`python:implementations`).
.. _intro-install-scrapy:
@ -37,7 +37,7 @@ 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`.
For more detailed and platform specifics instructions, as well as
For more detailed and platform-specific instructions, as well as
troubleshooting information, read on.
@ -101,7 +101,7 @@ Windows
-------
Though it's possible to install Scrapy on Windows using pip, we recommend you
to install `Anaconda`_ or `Miniconda`_ and use the package from the
install `Anaconda`_ or `Miniconda`_ and use the package from the
`conda-forge`_ channel, which will avoid most installation issues.
Once you've installed `Anaconda`_ or `Miniconda`_, install Scrapy with::
@ -141,7 +141,7 @@ But it should support older versions of Ubuntu too, like Ubuntu 14.04,
albeit with potential issues with TLS connections.
**Don't** use the ``python-scrapy`` package provided by Ubuntu, they are
typically too old and slow to catch up with latest Scrapy.
typically too old and slow to catch up with the latest Scrapy release.
To install Scrapy on Ubuntu (or Ubuntu-based) systems, you need to install
@ -170,7 +170,7 @@ macOS
Building Scrapy's dependencies requires the presence of a C compiler and
development headers. On macOS this is typically provided by Apple’s Xcode
development tools. To install the Xcode command line tools open a terminal
development tools. To install the Xcode command-line tools, open a terminal
window and run::
xcode-select --install
@ -200,11 +200,6 @@ solutions:
brew install python
* Latest versions of python have ``pip`` bundled with them so you won't need
to install it separately. If this is not the case, upgrade python::
brew update; brew upgrade python
* *(Optional)* :ref:`Install Scrapy inside a Python virtual environment
<intro-using-virtualenv>`.

20
docs/intro/overview.rst
View File

@ -44,13 +44,13 @@ https://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``
Put this in a text file, name it something like ``quotes_spider.py``
and run the spider using the :command:`runspider` command::
scrapy runspider quotes_spider.py -o quotes.jsonl
When this finishes you will have in the ``quotes.jsonl`` file a list of the
quotes in JSON Lines format, containing text and author, looking like this::
quotes in JSON Lines format, containing the text and author, which will look like this::
{"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"}
@ -65,27 +65,27 @@ When you ran the command ``scrapy runspider quotes_spider.py``, Scrapy looked fo
Spider definition inside it and ran it through its crawler engine.
The crawl started by making requests to the URLs defined in the ``start_urls``
attribute (in this case, only the URL for quotes in *humor* category)
attribute (in this case, only the URL for quotes in the *humor* category)
and called the default callback method ``parse``, passing the response object as
an argument. In the ``parse`` callback, we loop through the quote elements
using a CSS Selector, yield a Python dict with the extracted quote text and author,
look for a link to the next page and schedule another request using the same
``parse`` method as callback.
Here you notice one of the main advantages about Scrapy: requests are
Here you will notice one of the main advantages of Scrapy: requests are
:ref:`scheduled and processed asynchronously <topics-architecture>`. This
means that Scrapy doesn't need to wait for a request to be finished and
processed, it can send another request or do other things in the meantime. This
also means that other requests can keep going even if some request fails or an
also means that other requests can keep going even if a request fails or an
error happens while handling it.
While this enables you to do very fast crawls (sending multiple concurrent
requests at the same time, in a fault-tolerant way) Scrapy also gives you
control over the politeness of the crawl through :ref:`a few settings
<topics-settings-ref>`. You can do things like setting a download delay between
each request, limiting amount of concurrent requests per domain or per IP, and
each request, limiting the amount of concurrent requests per domain or per IP, and
even :ref:`using an auto-throttling extension <topics-autothrottle>` that tries
to figure out these automatically.
to figure these settings out automatically.
.. note::
@ -106,10 +106,10 @@ scraping easy and efficient, such as:
* Built-in support for :ref:`selecting and extracting <topics-selectors>` data
from HTML/XML sources using extended CSS selectors and XPath expressions,
with helper methods to extract using regular expressions.
with helper methods for extraction using regular expressions.
* An :ref:`interactive shell console <topics-shell>` (IPython aware) for trying
out the CSS and XPath expressions to scrape data, very useful when writing or
out the CSS and XPath expressions to scrape data, which is very useful when writing or
debugging your spiders.
* Built-in support for :ref:`generating feed exports <topics-feed-exports>` in
@ -124,7 +124,7 @@ scraping easy and efficient, such as:
well-defined API (middlewares, :ref:`extensions <topics-extensions>`, and
:ref:`pipelines <topics-item-pipeline>`).
* Wide range of built-in extensions and middlewares for handling:
* A wide range of built-in extensions and middlewares for handling:
- cookies and session handling
- HTTP features like compression, authentication, caching

55
docs/intro/tutorial.rst
View File

@ -18,11 +18,11 @@ This tutorial will walk you through these tasks:
4. Changing spider to recursively follow links
5. Using spider arguments
Scrapy is written in Python_. If you're new to the language you might want to
start by getting an idea of what the language is like, to get the most out of
Scrapy.
Scrapy is written in Python_. The more you learn about Python, the more you
can get out of Scrapy.
If you're already familiar with other languages, and want to learn Python quickly, the `Python Tutorial`_ is a good resource.
If you're already familiar with other languages and want to learn Python quickly, the
`Python Tutorial`_ is a good resource.
If you're new to programming and want to start with Python, the following books
may be useful to you:
@ -76,10 +76,9 @@ This will create a ``tutorial`` directory with the following contents::
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.Spider` and define the initial requests to make,
optionally how to follow links in the pages, and how to parse the downloaded
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.Spider` and define the initial
requests to be made, and optionally, how to follow links in pages and parse the downloaded
page content to extract data.
This is the code for our first Spider. Save it in a file named
@ -138,7 +137,7 @@ To put our spider to work, go to the project's top level directory and run::
scrapy crawl quotes
This command runs the spider with name ``quotes`` that we've just added, that
This command runs the spider named ``quotes`` that we've just added, that
will send some requests for the ``quotes.toscrape.com`` domain. You will get an output
similar to this::
@ -169,7 +168,7 @@ Scrapy schedules the :class:`scrapy.Request <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
``parse`` method) passing the response as argument.
``parse`` method) passing the response as an argument.
A shortcut to the start_requests method
@ -217,8 +216,8 @@ using the :ref:`Scrapy shell <topics-shell>`. Run::
.. note::
Remember to always enclose urls in quotes when running Scrapy shell from
command-line, otherwise urls containing arguments (i.e. ``&`` character)
Remember to always enclose URLs in quotes when running Scrapy shell from the
command line, otherwise URLs containing arguments (i.e. ``&`` character)
will not work.
On Windows, use double quotes instead::
@ -257,7 +256,7 @@ 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` objects that wrap around XML/HTML elements
and allow you to run further queries to fine-grain the selection or extract the
and allow you to run further queries to refine the selection or extract the
data.
To extract the text from the title above, you can do:
@ -354,12 +353,12 @@ Besides `CSS`_, Scrapy selectors also support using `XPath`_ expressions:
XPath expressions are very powerful, and are the foundation of Scrapy
Selectors. In fact, CSS selectors are converted to XPath under-the-hood. You
can see that if you read closely the text representation of the selector
objects in the shell.
can see that if you read the text representation of the selector
objects in the shell closely.
While perhaps not as popular as CSS selectors, XPath expressions offer more
power because besides navigating the structure, it can also look at the
content. Using XPath, you're able to select things like: *select the link
content. Using XPath, you're able to select things like: *the link
that contains the text "Next Page"*. This makes XPath very fitting to the task
of scraping, and we encourage you to learn XPath even if you already know how to
construct CSS selectors, it will make scraping much easier.
@ -422,7 +421,7 @@ variable, so that we can run our CSS selectors directly on a particular quote:
>>> quote = response.css("div.quote")[0]
Now, let's extract ``text``, ``author`` and the ``tags`` from that quote
Now, let's extract the ``text``, ``author`` and ``tags`` from that quote
using the ``quote`` object we just created:
.. code-block:: pycon
@ -448,7 +447,7 @@ to get all of them:
from sys import version_info
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:
quote elements and put them together into a Python dictionary:
.. code-block:: pycon
@ -465,8 +464,8 @@ quotes elements and put them together into a Python dictionary:
Extracting data in our spider
-----------------------------
Let's get back to our spider. Until now, it doesn't extract any data in
particular, just saves the whole HTML page to a local file. Let's integrate the
Let's get back to our spider. Until now, it hasn't extracted any data in
particular, just saving the whole HTML page to a local file. Let's integrate the
extraction logic above into our spider.
A Scrapy spider typically generates many dictionaries containing the data
@ -529,8 +528,8 @@ using a different serialization format, such as `JSON Lines`_::
scrapy crawl quotes -o quotes.jsonl
The `JSON Lines`_ format is useful because it's stream-like, you can easily
append new records to it. It doesn't have the same problem of JSON when you run
The `JSON Lines`_ format is useful because it's stream-like, so you can easily
append new records to it. It doesn't have the same problem as JSON when you run
twice. Also, as each record is a separate line, you can process big files
without having to fit everything in memory, there are tools like `JQ`_ to help
do that at the command-line.
@ -555,7 +554,7 @@ from https://quotes.toscrape.com, you want quotes from all the pages in the webs
Now that you know how to extract data from pages, let's see how to follow links
from them.
First thing is to extract the link to the page we want to follow. Examining
The first thing to do is extract the link to the page we want to follow. Examining
our page, we can see there is a link to the next page with the following
markup:
@ -589,7 +588,7 @@ There is also an ``attrib`` property available
>>> response.css("li.next a").attrib["href"]
'/page/2/'
Let's see now our spider modified to recursively follow the link to the next
Now let's see our spider, modified to recursively follow the link to the next
page, extracting data from it:
.. code-block:: python
@ -756,8 +755,8 @@ Another interesting thing this spider demonstrates is that, even if there are
many quotes from the same author, we don't need to worry about visiting the
same author page multiple times. By default, Scrapy filters out duplicated
requests to URLs already visited, avoiding the problem of hitting servers too
much because of a programming mistake. This can be configured by the setting
:setting:`DUPEFILTER_CLASS`.
much because of a programming mistake. This can be configured in the
:setting:`DUPEFILTER_CLASS` setting.
Hopefully by now you have a good understanding of how to use the mechanism
of following links and callbacks with Scrapy.
@ -824,12 +823,12 @@ Next steps
==========
This tutorial covered only the basics of Scrapy, but there's a lot of other
features not mentioned here. Check the :ref:`topics-whatelse` section in
features not mentioned here. Check the :ref:`topics-whatelse` section in the
:ref:`intro-overview` chapter for a quick overview of the most important ones.
You can continue from the section :ref:`section-basics` to know more about the
command-line tool, spiders, selectors and other things the tutorial hasn't covered like
modeling the scraped data. If you prefer to play with an example project, check
modeling the scraped data. If you'd prefer to play with an example project, check
the :ref:`intro-examples` section.
.. _JSON: https://en.wikipedia.org/wiki/JSON

271
docs/news.rst
View File

@ -3,6 +3,235 @@
Release notes
=============
.. _release-VERSION:
Scrapy VERSION (YYYY-MM-DD)
---------------------------
New features
~~~~~~~~~~~~
- If :setting:`SPIDER_LOADER_WARN_ONLY` is set to ``True``,
``SpiderLoader`` does not raise :exc:`SyntaxError` but emits a warning instead.
Deprecations
~~~~~~~~~~~~
- :meth:`scrapy.core.downloader.Downloader._get_slot_key` is deprecated, use
:meth:`scrapy.core.downloader.Downloader.get_slot_key` instead.
(:issue:`6340`)
.. _release-2.11.2:
Scrapy 2.11.2 (2024-05-14)
--------------------------
Security bug fixes
~~~~~~~~~~~~~~~~~~
- Redirects to non-HTTP protocols are no longer followed. Please, see the
`23j4-mw76-5v7h security advisory`_ for more information. (:issue:`457`)
.. _23j4-mw76-5v7h security advisory: https://github.com/scrapy/scrapy/security/advisories/GHSA-23j4-mw76-5v7h
- The ``Authorization`` header is now dropped on redirects to a different
scheme (``http://`` or ``https://``) or port, even if the domain is the
same. Please, see the `4qqq-9vqf-3h3f security advisory`_ for more
information.
.. _4qqq-9vqf-3h3f security advisory: https://github.com/scrapy/scrapy/security/advisories/GHSA-4qqq-9vqf-3h3f
- When using system proxy settings that are different for ``http://`` and
``https://``, redirects to a different URL scheme will now also trigger the
corresponding change in proxy settings for the redirected request. Please,
see the `jm3v-qxmh-hxwv security advisory`_ for more information.
(:issue:`767`)
.. _jm3v-qxmh-hxwv security advisory: https://github.com/scrapy/scrapy/security/advisories/GHSA-jm3v-qxmh-hxwv
- :attr:`Spider.allowed_domains <scrapy.Spider.allowed_domains>` is now
enforced for all requests, and not only requests from spider callbacks.
(:issue:`1042`, :issue:`2241`, :issue:`6358`)
- :func:`~scrapy.utils.iterators.xmliter_lxml` no longer resolves XML
entities. (:issue:`6265`)
- defusedxml_ is now used to make
:class:`scrapy.http.request.rpc.XmlRpcRequest` more secure.
(:issue:`6250`, :issue:`6251`)
.. _defusedxml: https://github.com/tiran/defusedxml
Bug fixes
~~~~~~~~~
- Restored support for brotlipy_, which had been dropped in Scrapy 2.11.1 in
favor of brotli_. (:issue:`6261`)
.. _brotli: https://github.com/google/brotli
.. note:: brotlipy is deprecated, both in Scrapy and upstream. Use brotli
instead if you can.
- Make :setting:`METAREFRESH_IGNORE_TAGS` ``["noscript"]`` by default. This
prevents
:class:`~scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware` from
following redirects that would not be followed by web browsers with
JavaScript enabled. (:issue:`6342`, :issue:`6347`)
- During :ref:`feed export <topics-feed-exports>`, do not close the
underlying file from :ref:`built-in post-processing plugins
<builtin-plugins>`.
(:issue:`5932`, :issue:`6178`, :issue:`6239`)
- :class:`LinkExtractor <scrapy.linkextractors.lxmlhtml.LxmlLinkExtractor>`
now properly applies the ``unique`` and ``canonicalize`` parameters.
(:issue:`3273`, :issue:`6221`)
- Do not initialize the scheduler disk queue if :setting:`JOBDIR` is an empty
string. (:issue:`6121`, :issue:`6124`)
- Fix :attr:`Spider.logger <scrapy.Spider.logger>` not logging custom extra
information. (:issue:`6323`, :issue:`6324`)
- ``robots.txt`` files with a non-UTF-8 encoding no longer prevent parsing
the UTF-8-compatible (e.g. ASCII) parts of the document.
(:issue:`6292`, :issue:`6298`)
- :meth:`scrapy.http.cookies.WrappedRequest.get_header` no longer raises an
exception if ``default`` is ``None``.
(:issue:`6308`, :issue:`6310`)
- :class:`~scrapy.selector.Selector` now uses
:func:`scrapy.utils.response.get_base_url` to determine the base URL of a
given :class:`~scrapy.http.Response`. (:issue:`6265`)
- The :meth:`media_to_download` method of :ref:`media pipelines
<topics-media-pipeline>` now logs exceptions before stripping them.
(:issue:`5067`, :issue:`5068`)
- When passing a callback to the :command:`parse` command, build the callback
callable with the right signature.
(:issue:`6182`)
Documentation
~~~~~~~~~~~~~
- Add a FAQ entry about :ref:`creating blank requests <faq-blank-request>`.
(:issue:`6203`, :issue:`6208`)
- Document that :attr:`scrapy.selector.Selector.type` can be ``"json"``.
(:issue:`6328`, :issue:`6334`)
Quality assurance
~~~~~~~~~~~~~~~~~
- Make builds reproducible. (:issue:`5019`, :issue:`6322`)
- Packaging and test fixes.
(:issue:`6286`, :issue:`6290`, :issue:`6312`, :issue:`6316`, :issue:`6344`)
.. _release-2.11.1:
Scrapy 2.11.1 (2024-02-14)
--------------------------
Highlights:
- Security bug fixes.
- Support for Twisted >= 23.8.0.
- Documentation improvements.
Security bug fixes
~~~~~~~~~~~~~~~~~~
- Addressed `ReDoS vulnerabilities`_:
- ``scrapy.utils.iterators.xmliter`` is now deprecated in favor of
:func:`~scrapy.utils.iterators.xmliter_lxml`, which
:class:`~scrapy.spiders.XMLFeedSpider` now uses.
To minimize the impact of this change on existing code,
:func:`~scrapy.utils.iterators.xmliter_lxml` now supports indicating
the node namespace with a prefix in the node name, and big files with
highly nested trees when using libxml2 2.7+.
- Fixed regular expressions in the implementation of the
:func:`~scrapy.utils.response.open_in_browser` function.
Please, see the `cc65-xxvf-f7r9 security advisory`_ for more information.
.. _ReDoS vulnerabilities: https://owasp.org/www-community/attacks/Regular_expression_Denial_of_Service_-_ReDoS
.. _cc65-xxvf-f7r9 security advisory: https://github.com/scrapy/scrapy/security/advisories/GHSA-cc65-xxvf-f7r9
- :setting:`DOWNLOAD_MAXSIZE` and :setting:`DOWNLOAD_WARNSIZE` now also apply
to the decompressed response body. Please, see the `7j7m-v7m3-jqm7 security
advisory`_ for more information.
.. _7j7m-v7m3-jqm7 security advisory: https://github.com/scrapy/scrapy/security/advisories/GHSA-7j7m-v7m3-jqm7
- Also in relation with the `7j7m-v7m3-jqm7 security advisory`_, the
deprecated ``scrapy.downloadermiddlewares.decompression`` module has been
removed.
- The ``Authorization`` header is now dropped on redirects to a different
domain. Please, see the `cw9j-q3vf-hrrv security advisory`_ for more
information.
.. _cw9j-q3vf-hrrv security advisory: https://github.com/scrapy/scrapy/security/advisories/GHSA-cw9j-q3vf-hrrv
Modified requirements
~~~~~~~~~~~~~~~~~~~~~
- The Twisted dependency is no longer restricted to < 23.8.0. (:issue:`6024`,
:issue:`6064`, :issue:`6142`)
Bug fixes
~~~~~~~~~
- The OS signal handling code was refactored to no longer use private Twisted
functions. (:issue:`6024`, :issue:`6064`, :issue:`6112`)
Documentation
~~~~~~~~~~~~~
- Improved documentation for :class:`~scrapy.crawler.Crawler` initialization
changes made in the 2.11.0 release. (:issue:`6057`, :issue:`6147`)
- Extended documentation for :attr:`Request.meta <scrapy.http.Request.meta>`.
(:issue:`5565`)
- Fixed the :reqmeta:`dont_merge_cookies` documentation. (:issue:`5936`,
:issue:`6077`)
- Added a link to Zyte's export guides to the :ref:`feed exports
<topics-feed-exports>` documentation. (:issue:`6183`)
- Added a missing note about backward-incompatible changes in
:class:`~scrapy.exporters.PythonItemExporter` to the 2.11.0 release notes.
(:issue:`6060`, :issue:`6081`)
- Added a missing note about removing the deprecated
``scrapy.utils.boto.is_botocore()`` function to the 2.8.0 release notes.
(:issue:`6056`, :issue:`6061`)
- Other documentation improvements. (:issue:`6128`, :issue:`6144`,
:issue:`6163`, :issue:`6190`, :issue:`6192`)
Quality assurance
~~~~~~~~~~~~~~~~~
- Added Python 3.12 to the CI configuration, re-enabled tests that were
disabled when the pre-release support was added. (:issue:`5985`,
:issue:`6083`, :issue:`6098`)
- Fixed a test issue on PyPy 7.3.14. (:issue:`6204`, :issue:`6205`)
.. _release-2.11.0:
Scrapy 2.11.0 (2023-09-18)
@ -62,6 +291,9 @@ Deprecation removals
1.0.0, use :attr:`CrawlerRunner.spider_loader
<scrapy.crawler.CrawlerRunner.spider_loader>` instead. (:issue:`6010`)
- The :func:`scrapy.utils.response.response_httprepr` function, deprecated in
Scrapy 2.6.0, has now been removed. (:issue:`6111`)
Deprecations
~~~~~~~~~~~~
@ -1157,6 +1389,9 @@ Deprecations
Instead, call :meth:`~scrapy.core.engine.ExecutionEngine.open_spider`
first to set the :class:`~scrapy.Spider` object.
- :func:`scrapy.utils.response.response_httprepr` is now deprecated.
(:issue:`4972`)
New features
~~~~~~~~~~~~
@ -1295,7 +1530,7 @@ Documentation
- Provided better context and instructions to disable the
:setting:`URLLENGTH_LIMIT` setting. (:issue:`5135`, :issue:`5250`)
- Documented that :ref:`reppy-parser` does not support Python 3.9+.
- Documented that Reppy parser does not support Python 3.9+.
(:issue:`5226`, :issue:`5231`)
- Documented :ref:`the scheduler component <topics-scheduler>`.
@ -2871,6 +3106,38 @@ affect subclasses:
(:issue:`3884`)
.. _release-1.8.4:
Scrapy 1.8.4 (2024-02-14)
-------------------------
**Security bug fixes:**
- Due to its `ReDoS vulnerabilities`_, ``scrapy.utils.iterators.xmliter`` is
now deprecated in favor of :func:`~scrapy.utils.iterators.xmliter_lxml`,
which :class:`~scrapy.spiders.XMLFeedSpider` now uses.
To minimize the impact of this change on existing code,
:func:`~scrapy.utils.iterators.xmliter_lxml` now supports indicating
the node namespace as a prefix in the node name, and big files with highly
nested trees when using libxml2 2.7+.
Please, see the `cc65-xxvf-f7r9 security advisory`_ for more information.
- :setting:`DOWNLOAD_MAXSIZE` and :setting:`DOWNLOAD_WARNSIZE` now also apply
to the decompressed response body. Please, see the `7j7m-v7m3-jqm7 security
advisory`_ for more information.
- Also in relation with the `7j7m-v7m3-jqm7 security advisory`_, use of the
``scrapy.downloadermiddlewares.decompression`` module is discouraged and
will trigger a warning.
- The ``Authorization`` header is now dropped on redirects to a different
domain. Please, see the `cw9j-q3vf-hrrv security advisory`_ for more
information.
.. _cw9j-q3vf-hrrv security advisory: https://github.com/scrapy/scrapy/security/advisories/GHSA-cw9j-q3vf-hrrv
.. _release-1.8.3:
@ -3077,7 +3344,7 @@ New features
* A new :setting:`ROBOTSTXT_PARSER` setting allows choosing which robots.txt_
parser to use. It includes built-in support for
:ref:`RobotFileParser <python-robotfileparser>`,
:ref:`Protego <protego-parser>` (default), :ref:`Reppy <reppy-parser>`, and
:ref:`Protego <protego-parser>` (default), Reppy, and
:ref:`Robotexclusionrulesparser <rerp-parser>`, and allows you to
:ref:`implement support for additional parsers
<support-for-new-robots-parser>` (:issue:`754`, :issue:`2669`,

3
docs/topics/addons.rst
View File

@ -150,8 +150,7 @@ Access the crawler instance:
def from_crawler(cls, crawler):
return cls(crawler)
def update_settings(self, settings):
...
def update_settings(self, settings): ...
Use a fallback component:

14
docs/topics/autothrottle.rst
View File

@ -47,6 +47,18 @@ effect, but there are some important differences:
AutoThrottle doesn't have these issues.
Disabling throttling on a downloader slot
=========================================
It is possible to disable AutoThrottle for a specific download slot at run time
by setting its ``throttle`` attribute to ``False``, e.g. using
:setting:`DOWNLOAD_SLOTS`.
Note, however, that AutoThrottle still determines the starting delay of every
slot by setting the ``download_delay`` attribute on the running spider. You
might want to set a custom value for the ``delay`` attribute of the slot, e.g.
using :setting:`DOWNLOAD_SLOTS`.
Throttling algorithm
====================
@ -131,7 +143,7 @@ AUTOTHROTTLE_TARGET_CONCURRENCY
Default: ``1.0``
Average number of requests Scrapy should be sending in parallel to remote
websites.
websites. It must be higher than ``0.0``.
By default, AutoThrottle adjusts the delay to send a single
concurrent request to each of the remote websites. Set this option to

4
docs/topics/benchmarking.rst
View File

@ -24,7 +24,8 @@ You should see an output like this::
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.corestats.CoreStats']
2016-12-16 21:18:49 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
['scrapy.downloadermiddlewares.offsite.OffsiteMiddleware',
'scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
'scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
@ -37,7 +38,6 @@ You should see an output like this::
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2016-12-16 21:18:49 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']

2
docs/topics/broad-crawls.rst
View File

@ -116,7 +116,7 @@ Reduce log level
When doing broad crawls you are often only interested in the crawl rates you
get and any errors found. These stats are reported by Scrapy when using the
``INFO`` log level. In order to save CPU (and log storage requirements) you
should not use ``DEBUG`` log level when preforming large broad crawls in
should not use ``DEBUG`` log level when performing large broad crawls in
production. Using ``DEBUG`` level when developing your (broad) crawler may be
fine though.

18
docs/topics/commands.rst
View File

@ -6,7 +6,7 @@
Command line tool
=================
Scrapy is controlled through the ``scrapy`` command-line tool, to be referred
Scrapy is controlled through the ``scrapy`` command-line tool, to be referred to
here as the "Scrapy tool" to differentiate it from the sub-commands, which we
just call "commands" or "Scrapy commands".
@ -185,8 +185,8 @@ And you can see all available commands with::
There are two kinds of commands, those that only work from inside a Scrapy
project (Project-specific commands) and those that also work without an active
Scrapy project (Global commands), though they may behave slightly different
when running from inside a project (as they would use the project overridden
Scrapy project (Global commands), though they may behave slightly differently
when run from inside a project (as they would use the project overridden
settings).
Global commands:
@ -236,7 +236,7 @@ genspider
.. versionadded:: 2.6.0
The ability to pass a URL instead of a domain.
Create a new spider in the current folder or in the current project's ``spiders`` folder, if called from inside a project. The ``<name>`` parameter is set as the spider's ``name``, while ``<domain or URL>`` is used to generate the ``allowed_domains`` and ``start_urls`` spider's attributes.
Creates a new spider in the current folder or in the current project's ``spiders`` folder, if called from inside a project. The ``<name>`` parameter is set as the spider's ``name``, while ``<domain or URL>`` is used to generate the ``allowed_domains`` and ``start_urls`` spider's attributes.
Usage example::
@ -253,7 +253,7 @@ Usage example::
$ scrapy genspider -t crawl scrapyorg scrapy.org
Created spider 'scrapyorg' using template 'crawl'
This is just a convenience shortcut command for creating spiders based on
This is just a convenient shortcut command for creating spiders based on
pre-defined templates, but certainly not the only way to create spiders. You
can just create the spider source code files yourself, instead of using this
command.
@ -274,9 +274,9 @@ Supported options:
* ``-a NAME=VALUE``: set a spider argument (may be repeated)
* ``--output FILE`` or ``-o FILE``: append scraped items to the end of FILE (use - for stdout), to define format set a colon at the end of the output URI (i.e. ``-o FILE:FORMAT``)
* ``--output FILE`` or ``-o FILE``: append scraped items to the end of FILE (use - for stdout). To define the output format, set a colon at the end of the output URI (i.e. ``-o FILE:FORMAT``)
* ``--overwrite-output FILE`` or ``-O FILE``: dump scraped items into FILE, overwriting any existing file, to define format set a colon at the end of the output URI (i.e. ``-O FILE:FORMAT``)
* ``--overwrite-output FILE`` or ``-O FILE``: dump scraped items into FILE, overwriting any existing file. To define the output format, set a colon at the end of the output URI (i.e. ``-O FILE:FORMAT``)
* ``--output-format FORMAT`` or ``-t FORMAT``: deprecated way to define format to use for dumping items, does not work in combination with ``-O``
@ -353,7 +353,7 @@ edit
Edit the given spider using the editor defined in the ``EDITOR`` environment
variable or (if unset) the :setting:`EDITOR` setting.
This command is provided only as a convenience shortcut for the most common
This command is provided only as a convenient shortcut for the most common
case, the developer is of course free to choose any tool or IDE to write and
debug spiders.
@ -372,7 +372,7 @@ fetch
Downloads the given URL using the Scrapy downloader and writes the contents to
standard output.
The interesting thing about this command is that it fetches the page how the
The interesting thing about this command is that it fetches the page the way the
spider would download it. For example, if the spider has a ``USER_AGENT``
attribute which overrides the User Agent, it will use that one.

12
docs/topics/contracts.rst
View File

@ -20,13 +20,13 @@ following example:
This function parses a sample response. Some contracts are mingled
with this docstring.
@url http://www.amazon.com/s?field-keywords=selfish+gene
@url http://www.example.com/s?field-keywords=selfish+gene
@returns items 1 16
@returns requests 0 0
@scrapes Title Author Year Price
"""
This callback is tested using three built-in contracts:
You can use the following contracts:
.. module:: scrapy.contracts.default
@ -46,6 +46,14 @@ This callback is tested using three built-in contracts:
@cb_kwargs {"arg1": "value1", "arg2": "value2", ...}
.. class:: MetadataContract
This contract (``@meta``) sets the :attr:`meta <scrapy.Request.meta>`
attribute for the sample request. It must be a valid JSON dictionary.
::
@meta {"arg1": "value1", "arg2": "value2", ...}
.. class:: ReturnsContract
This contract (``@returns``) sets lower and upper bounds for the items and

18
docs/topics/debug.rst
View File

@ -125,25 +125,15 @@ Fortunately, the :command:`shell` is your bread and butter in this case (see
See also: :ref:`topics-shell-inspect-response`.
Open in browser
===============
Sometimes you just want to see how a certain response looks in a browser, you
can use the ``open_in_browser`` function for that. Here is an example of how
you would use it:
can use the :func:`~scrapy.utils.response.open_in_browser` function for that:
.. code-block:: python
.. autofunction:: scrapy.utils.response.open_in_browser
from scrapy.utils.response import open_in_browser
def parse_details(self, response):
if "item name" not in response.body:
open_in_browser(response)
``open_in_browser`` will open a browser with the response received by Scrapy at
that point, adjusting the `base tag`_ so that images and styles are displayed
properly.
Logging
=======
@ -163,8 +153,6 @@ available in all future runs should they be necessary again:
For more information, check the :ref:`topics-logging` section.
.. _base tag: https://www.w3schools.com/tags/tag_base.asp
.. _debug-vscode:
Visual Studio Code

80
docs/topics/downloader-middleware.rst
View File

@ -809,6 +809,44 @@ HttpProxyMiddleware
Keep in mind this value will take precedence over ``http_proxy``/``https_proxy``
environment variables, and it will also ignore ``no_proxy`` environment variable.
OffsiteMiddleware
-----------------
.. module:: scrapy.downloadermiddlewares.offsite
:synopsis: Offsite Middleware
.. class:: OffsiteMiddleware
.. versionadded:: 2.11.2
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.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``.
When your spider returns a request for a domain not belonging to those
covered by the spider, this middleware will log a debug message similar to
this one::
DEBUG: Filtered offsite request to 'offsite.example': <GET http://offsite.example/some/page.html>
To avoid filling the log with too much noise, it will only print one of
these messages for each new domain filtered. So, for example, if another
request for ``offsite.example`` is filtered, no log message will be
printed. But if a request for ``other.example`` is filtered, a message
will be printed (but only for the first request filtered).
If the spider doesn't define an
: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.Request.dont_filter` attribute
set, the offsite middleware will allow the request even if its domain is not
listed in allowed domains.
RedirectMiddleware
------------------
@ -928,7 +966,15 @@ Meta tags within these tags are ignored.
.. versionchanged:: 2.0
The default value of :setting:`METAREFRESH_IGNORE_TAGS` changed from
``['script', 'noscript']`` to ``[]``.
``["script", "noscript"]`` to ``[]``.
.. versionchanged:: 2.11.2
The default value of :setting:`METAREFRESH_IGNORE_TAGS` changed from
``[]`` to ``["noscript"]``.
.. versionchanged:: VERSION
The default value of :setting:`METAREFRESH_IGNORE_TAGS` changed from
``[]`` to ``['noscript']``.
.. setting:: METAREFRESH_MAXDELAY
@ -1086,7 +1132,6 @@ RobotsTxtMiddleware
* :ref:`Protego <protego-parser>` (default)
* :ref:`RobotFileParser <python-robotfileparser>`
* :ref:`Robotexclusionrulesparser <rerp-parser>`
* :ref:`Reppy <reppy-parser>` (deprecated)
You can change the robots.txt_ parser with the :setting:`ROBOTSTXT_PARSER`
setting. Or you can also :ref:`implement support for a new parser <support-for-new-robots-parser>`.
@ -1154,37 +1199,6 @@ In order to use this parser, set:
* :setting:`ROBOTSTXT_PARSER` to ``scrapy.robotstxt.PythonRobotParser``
.. _reppy-parser:
Reppy parser
~~~~~~~~~~~~
Based on `Reppy <https://github.com/seomoz/reppy/>`_:
* is a Python wrapper around `Robots Exclusion Protocol Parser for C++
<https://github.com/seomoz/rep-cpp>`_
* is compliant with `Martijn Koster's 1996 draft specification
<https://www.robotstxt.org/norobots-rfc.txt>`_
* supports wildcard matching
* uses the length based rule
Native implementation, provides better speed than Protego.
In order to use this parser:
* Install `Reppy <https://github.com/seomoz/reppy/>`_ by running ``pip install reppy``
.. warning:: `Upstream issue #122
<https://github.com/seomoz/reppy/issues/122>`_ prevents reppy usage in Python 3.9+.
Because of this the Reppy parser is deprecated.
* Set :setting:`ROBOTSTXT_PARSER` setting to
``scrapy.robotstxt.ReppyRobotParser``
.. _rerp-parser:
Robotexclusionrulesparser

7
docs/topics/dynamic-content.rst
View File

@ -115,15 +115,14 @@ Handling different response formats
Once you have a response with the desired data, how you extract the desired
data from it depends on the type of response:
- If the response is HTML or XML, use :ref:`selectors
- If the response is HTML, XML or JSON, use :ref:`selectors
<topics-selectors>` as usual.
- If the response is JSON, use :func:`json.loads` to load the desired data from
:attr:`response.text <scrapy.http.TextResponse.text>`:
- If the response is JSON, use :func:`response.json()` to load the desired data:
.. code-block:: python
data = json.loads(response.text)
data = response.json()
If the desired data is inside HTML or XML code embedded within JSON data,
you can load that HTML or XML code into a

13
docs/topics/extensions.rst
View File

@ -317,6 +317,19 @@ crawls more than that, the spider will be closed with the reason
``closespider_pagecount``. If zero (or non set), spiders won't be closed by
number of crawled responses.
.. setting:: CLOSESPIDER_PAGECOUNT_NO_ITEM
CLOSESPIDER_PAGECOUNT_NO_ITEM
"""""""""""""""""""""""""""""
Default: ``0``
An integer which specifies the maximum number of consecutive responses to crawl
without items scraped. If the spider crawls more consecutive responses than that
and no items are scraped in the meantime, the spider will be closed with the
reason ``closespider_pagecount_no_item``. If zero (or not set), spiders won't be
closed by number of crawled responses with no items.
.. setting:: CLOSESPIDER_ERRORCOUNT
CLOSESPIDER_ERRORCOUNT

8
docs/topics/feed-exports.rst
View File

@ -390,7 +390,13 @@ Each plugin is a class that must implement the following methods:
.. method:: close(self)
Close the target file object.
Clean up the plugin.
For example, you might want to close a file wrapper that you might have
used to compress data written into the file received in the ``__init__``
method.
.. warning:: Do not close the file from the ``__init__`` method.
To pass a parameter to your plugin, use :ref:`feed options <feed-options>`. You
can then access those parameters from the ``__init__`` method of your plugin.

4
docs/topics/item-pipeline.rst
View File

@ -99,7 +99,7 @@ contain a price:
adapter["price"] = adapter["price"] * self.vat_factor
return item
else:
raise DropItem(f"Missing price in {item}")
raise DropItem("Missing price")
Write items to a JSON lines file
@ -254,7 +254,7 @@ returns multiples items with the same id:
def process_item(self, item, spider):
adapter = ItemAdapter(item)
if adapter["id"] in self.ids_seen:
raise DropItem(f"Duplicate item found: {item!r}")
raise DropItem(f"Item ID already seen: {adapter['id']}")
else:
self.ids_seen.add(adapter["id"])
return item

17
docs/topics/items.rst
View File

@ -48,7 +48,7 @@ make it the most feature-complete item type:
:class:`Item` objects replicate the standard :class:`dict` API, including
its ``__init__`` method.
:class:`Item` allows defining field names, so that:
:class:`Item` allows the defining of field names, so that:
- :class:`KeyError` is raised when using undefined field names (i.e.
prevents typos going unnoticed)
@ -57,7 +57,7 @@ make it the most feature-complete item type:
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
:class:`Item` also allows the defining of field metadata, which can be used to
:ref:`customize serialization <topics-exporters-field-serialization>`.
:mod:`trackref` tracks :class:`Item` objects to help find memory leaks
@ -94,11 +94,11 @@ Dataclass objects
.. versionadded:: 2.2
:func:`~dataclasses.dataclass` allows defining item classes with field names,
:func:`~dataclasses.dataclass` allows the defining of item classes with field names,
so that :ref:`item exporters <topics-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:
Additionally, ``dataclass`` items also allow you to:
* define the type and default value of each defined field.
@ -126,7 +126,7 @@ attr.s objects
.. versionadded:: 2.2
:func:`attr.s` allows defining item classes with field names,
:func:`attr.s` allows the defining of item classes with field names,
so that :ref:`item exporters <topics-exporters>` can export all fields by
default even if the first scraped object does not have values for all of them.
@ -399,12 +399,7 @@ In code that receives an item, such as methods of :ref:`item pipelines
<topics-spider-middleware>`, 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 <item-types>`:
.. autoclass:: itemadapter.ItemAdapter
.. autofunction:: itemadapter.is_item
any supported item type.
Other classes related to items
==============================

2
docs/topics/link-extractors.rst
View File

@ -85,7 +85,7 @@ LxmlLinkExtractor
:param restrict_xpaths: is an XPath (or list of XPath's) which defines
regions inside the response where links should be extracted from.
If given, only the text selected by those XPath will be scanned for
links. See examples below.
links.
:type restrict_xpaths: str or list
:param restrict_css: a CSS selector (or list of selectors) which defines

8
docs/topics/media-pipeline.rst
View File

@ -532,14 +532,14 @@ See here the methods that you can override in your custom Files Pipeline:
.. code-block:: python
from pathlib import PurePosixPath
from urllib.parse import urlparse
from scrapy.utils.httpobj import urlparse_cached
from scrapy.pipelines.files import FilesPipeline
class MyFilesPipeline(FilesPipeline):
def file_path(self, request, response=None, info=None, *, item=None):
return "files/" + PurePosixPath(urlparse(request.url).path).name
return "files/" + PurePosixPath(urlparse_cached(request).path).name
Similarly, you can use the ``item`` to determine the file path based on some item
property.
@ -690,14 +690,14 @@ See here the methods that you can override in your custom Images Pipeline:
.. code-block:: python
from pathlib import PurePosixPath
from urllib.parse import urlparse
from scrapy.utils.httpobj import urlparse_cached
from scrapy.pipelines.images import ImagesPipeline
class MyImagesPipeline(ImagesPipeline):
def file_path(self, request, response=None, info=None, *, item=None):
return "files/" + PurePosixPath(urlparse(request.url).path).name
return "files/" + PurePosixPath(urlparse_cached(request).path).name
Similarly, you can use the ``item`` to determine the file path based on some item
property.

43
docs/topics/practices.rst
View File

@ -92,7 +92,6 @@ reactor after ``MySpider`` has finished running.
.. code-block:: python
from twisted.internet import reactor
import scrapy
from scrapy.crawler import CrawlerRunner
from scrapy.utils.log import configure_logging
@ -107,6 +106,37 @@ reactor after ``MySpider`` has finished running.
runner = CrawlerRunner()
d = runner.crawl(MySpider)
from twisted.internet import reactor
d.addBoth(lambda _: reactor.stop())
reactor.run() # the script will block here until the crawling is finished
Same example but using a non-default reactor, it's only necessary call
``install_reactor`` if you are using ``CrawlerRunner`` since ``CrawlerProcess`` already does this automatically.
.. code-block:: python
import scrapy
from scrapy.crawler import CrawlerRunner
from scrapy.utils.log import configure_logging
class MySpider(scrapy.Spider):
# Your spider definition
...
configure_logging({"LOG_FORMAT": "%(levelname)s: %(message)s"})
from scrapy.utils.reactor import install_reactor
install_reactor("twisted.internet.asyncioreactor.AsyncioSelectorReactor")
runner = CrawlerRunner()
d = runner.crawl(MySpider)
from twisted.internet import reactor
d.addBoth(lambda _: reactor.stop())
reactor.run() # the script will block here until the crawling is finished
@ -151,7 +181,6 @@ Same example using :class:`~scrapy.crawler.CrawlerRunner`:
.. code-block:: python
import scrapy
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
@ -173,6 +202,9 @@ Same example using :class:`~scrapy.crawler.CrawlerRunner`:
runner.crawl(MySpider1)
runner.crawl(MySpider2)
d = runner.join()
from twisted.internet import reactor
d.addBoth(lambda _: reactor.stop())
reactor.run() # the script will block here until all crawling jobs are finished
@ -181,7 +213,7 @@ Same example but running the spiders sequentially by chaining the deferreds:
.. code-block:: python
from twisted.internet import reactor, defer
from twisted.internet import defer
from scrapy.crawler import CrawlerRunner
from scrapy.utils.log import configure_logging
from scrapy.utils.project import get_project_settings
@ -209,6 +241,8 @@ Same example but running the spiders sequentially by chaining the deferreds:
reactor.stop()
from twisted.internet import reactor
crawl()
reactor.run() # the script will block here until the last crawl call is finished
@ -289,7 +323,8 @@ Here are some tips to keep in mind when dealing with these kinds of sites:
services like `ProxyMesh`_. An open source alternative is `scrapoxy`_, a
super proxy that you can attach your own proxies to.
* use a ban avoidance service, such as `Zyte API`_, which provides a `Scrapy
plugin <https://github.com/scrapy-plugins/scrapy-zyte-api>`__
plugin <https://github.com/scrapy-plugins/scrapy-zyte-api>`__ and additional
features, like `AI web scraping <https://www.zyte.com/ai-web-scraping/>`__
If you are still unable to prevent your bot getting banned, consider contacting
`commercial support`_.

4
docs/topics/request-response.rst
View File

@ -94,13 +94,14 @@ Request objects
.. code-block:: python
request_with_cookies = Request(
url="http://www.example.com",
url="https://www.example.com",
cookies=[
{
"name": "currency",
"value": "USD",
"domain": "example.com",
"path": "/currency",
"secure": True,
},
],
)
@ -677,6 +678,7 @@ Those are:
* :reqmeta:`download_fail_on_dataloss`
* :reqmeta:`download_latency`
* :reqmeta:`download_maxsize`
* :reqmeta:`download_warnsize`
* :reqmeta:`download_timeout`
* ``ftp_password`` (See :setting:`FTP_PASSWORD` for more info)
* ``ftp_user`` (See :setting:`FTP_USER` for more info)

14
docs/topics/selectors.rst
View File

@ -1032,10 +1032,8 @@ whereas the CSS lookup is translated into XPath and thus runs more efficiently,
so performance-wise its uses are limited to situations that are not easily
described with CSS selectors.
Parsel also simplifies adding your own XPath extensions.
.. autofunction:: parsel.xpathfuncs.set_xpathfunc
Parsel also simplifies adding your own XPath extensions with
:func:`~parsel.xpathfuncs.set_xpathfunc`.
.. _topics-selectors-ref:
@ -1062,6 +1060,12 @@ Selector objects
For convenience, this method can be called as ``response.css()``
.. automethod:: jmespath
.. note::
For convenience, this method can be called as ``response.jmespath()``
.. automethod:: get
See also: :ref:`old-extraction-api`
@ -1094,6 +1098,8 @@ SelectorList objects
.. automethod:: css
.. automethod:: jmespath
.. automethod:: getall
See also: :ref:`old-extraction-api`

52
docs/topics/settings.rst
View File

@ -674,6 +674,7 @@ Default:
.. code-block:: python
{
"scrapy.downloadermiddlewares.offsite.OffsiteMiddleware": 50,
"scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware": 100,
"scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware": 300,
"scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware": 350,
@ -835,7 +836,7 @@ The default HTTPS handler uses HTTP/1.1. To use HTTP/2:
.. setting:: DOWNLOAD_SLOTS
DOWNLOAD_SLOTS
----------------
--------------
Default: ``{}``
@ -844,7 +845,12 @@ Allows to define concurrency/delay parameters on per slot (domain) basis:
.. code-block:: python
DOWNLOAD_SLOTS = {
"quotes.toscrape.com": {"concurrency": 1, "delay": 2, "randomize_delay": False},
"quotes.toscrape.com": {
"concurrency": 1,
"delay": 2,
"randomize_delay": False,
"throttle": False,
},
"books.toscrape.com": {"delay": 3, "randomize_delay": False},
}
@ -856,6 +862,9 @@ Allows to define concurrency/delay parameters on per slot (domain) basis:
- :setting:`CONCURRENT_REQUESTS_PER_DOMAIN`: ``concurrency``
- :setting:`RANDOMIZE_DOWNLOAD_DELAY`: ``randomize_delay``
There is no global setting for ``throttle``, whose default value is
``None``.
.. setting:: DOWNLOAD_TIMEOUT
@ -873,40 +882,42 @@ The amount of time (in secs) that the downloader will wait before timing out.
Request.meta key.
.. setting:: DOWNLOAD_MAXSIZE
.. reqmeta:: download_maxsize
DOWNLOAD_MAXSIZE
----------------
Default: ``1073741824`` (1024MB)
Default: ``1073741824`` (1 GiB)
The maximum response size (in bytes) that downloader will download.
The maximum response body size (in bytes) allowed. Bigger responses are
aborted and ignored.
If you want to disable it set to 0.
This applies both before and after compression. If decompressing a response
body would exceed this limit, decompression is aborted and the response is
ignored.
.. reqmeta:: download_maxsize
Use ``0`` to disable this limit.
.. note::
This size can be set per spider using :attr:`download_maxsize`
spider attribute and per-request using :reqmeta:`download_maxsize`
Request.meta key.
This limit can be set per spider using the :attr:`download_maxsize` spider
attribute and per request using the :reqmeta:`download_maxsize` Request.meta
key.
.. setting:: DOWNLOAD_WARNSIZE
.. reqmeta:: download_warnsize
DOWNLOAD_WARNSIZE
-----------------
Default: ``33554432`` (32MB)
Default: ``33554432`` (32 MiB)
The response size (in bytes) that downloader will start to warn.
If the size of a response exceeds this value, before or after compression, a
warning will be logged about it.
If you want to disable it set to 0.
Use ``0`` to disable this limit.
.. note::
This size can be set per spider using :attr:`download_warnsize`
spider attribute and per-request using :reqmeta:`download_warnsize`
Request.meta key.
This limit can be set per spider using the :attr:`download_warnsize` spider
attribute and per request using the :reqmeta:`download_warnsize` Request.meta
key.
.. setting:: DOWNLOAD_FAIL_ON_DATALOSS
@ -1569,7 +1580,7 @@ SPIDER_LOADER_WARN_ONLY
Default: ``False``
By default, when Scrapy tries to import spider classes from :setting:`SPIDER_MODULES`,
it will fail loudly if there is any ``ImportError`` exception.
it will fail loudly if there is any ``ImportError`` or ``SyntaxError`` exception.
But you can choose to silence this exception and turn it into a simple
warning by setting ``SPIDER_LOADER_WARN_ONLY = True``.
@ -1603,7 +1614,6 @@ Default:
{
"scrapy.spidermiddlewares.httperror.HttpErrorMiddleware": 50,
"scrapy.spidermiddlewares.offsite.OffsiteMiddleware": 500,
"scrapy.spidermiddlewares.referer.RefererMiddleware": 700,
"scrapy.spidermiddlewares.urllength.UrlLengthMiddleware": 800,
"scrapy.spidermiddlewares.depth.DepthMiddleware": 900,

27
docs/topics/signals.rst
View File

@ -159,8 +159,9 @@ item_scraped
:param spider: the spider which scraped the item
:type spider: :class:`~scrapy.Spider` object
:param response: the response from where the item was scraped
:type response: :class:`~scrapy.http.Response` object
:param response: the response from where the item was scraped, or ``None``
if it was yielded from :meth:`~scrapy.Spider.start_requests`.
:type response: :class:`~scrapy.http.Response` | ``None``
item_dropped
~~~~~~~~~~~~
@ -179,8 +180,9 @@ item_dropped
:param spider: the spider which scraped the item
:type spider: :class:`~scrapy.Spider` object
:param response: the response from where the item was dropped
:type response: :class:`~scrapy.http.Response` object
:param response: the response from where the item was dropped, or ``None``
if it was yielded from :meth:`~scrapy.Spider.start_requests`.
:type response: :class:`~scrapy.http.Response` | ``None``
:param exception: the exception (which must be a
:exc:`~scrapy.exceptions.DropItem` subclass) which caused the item
@ -201,8 +203,10 @@ item_error
:param item: the item that caused the error in the :ref:`topics-item-pipeline`
:type item: :ref:`item object <item-types>`
:param response: the response being processed when the exception was raised
:type response: :class:`~scrapy.http.Response` object
:param response: the response being processed when the exception was
raised, or ``None`` if it was yielded from
:meth:`~scrapy.Spider.start_requests`.
:type response: :class:`~scrapy.http.Response` | ``None``
:param spider: the spider which raised the exception
:type spider: :class:`~scrapy.Spider` object
@ -343,11 +347,18 @@ request_scheduled
.. signal:: request_scheduled
.. function:: request_scheduled(request, spider)
Sent when the engine schedules a :class:`~scrapy.Request`, to be
downloaded later.
Sent when the engine is asked to schedule a :class:`~scrapy.Request`, to be
downloaded later, before the request reaches the :ref:`scheduler
<topics-scheduler>`.
Raise :exc:`~scrapy.exceptions.IgnoreRequest` to drop a request before it
reaches the scheduler.
This signal does not support returning deferreds from its handlers.
.. versionadded:: 2.11.2
Allow dropping requests with :exc:`~scrapy.exceptions.IgnoreRequest`.
:param request: the request that reached the scheduler
:type request: :class:`~scrapy.Request` object

42
docs/topics/spider-middleware.rst
View File

@ -51,8 +51,8 @@ value. For example, if you want to disable the off-site middleware:
.. code-block:: python
SPIDER_MIDDLEWARES = {
"myproject.middlewares.CustomSpiderMiddleware": 543,
"scrapy.spidermiddlewares.offsite.OffsiteMiddleware": None,
"scrapy.spidermiddlewares.referer.RefererMiddleware": None,
"myproject.middlewares.CustomRefererSpiderMiddleware": 700,
}
Finally, keep in mind that some middlewares may need to be enabled through a
@ -176,7 +176,7 @@ object gives you access, for example, to the :ref:`settings <topics-settings>`.
items).
It receives an iterable (in the ``start_requests`` parameter) and must
return another iterable of :class:`~scrapy.Request` objects.
return another iterable of :class:`~scrapy.Request` objects and/or :ref:`item objects <topics-items>`.
.. note:: When implementing this method in your spider middleware, you
should always return an iterable (that follows the input one) and
@ -313,42 +313,6 @@ Default: ``False``
Pass all responses, regardless of its status code.
OffsiteMiddleware
-----------------
.. module:: scrapy.spidermiddlewares.offsite
:synopsis: Offsite Spider Middleware
.. class:: 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.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``.
When your spider returns a request for a domain not belonging to those
covered by the spider, this middleware will log a debug message similar to
this one::
DEBUG: Filtered offsite request to 'www.othersite.com': <GET http://www.othersite.com/some/page.html>
To avoid filling the log with too much noise, it will only print one of
these messages for each new domain filtered. So, for example, if another
request for ``www.othersite.com`` is filtered, no log message will be
printed. But if a request for ``someothersite.com`` is filtered, a message
will be printed (but only for the first request filtered).
If the spider doesn't define an
: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.Request.dont_filter` attribute
set, the offsite middleware will allow the request even if its domain is not
listed in allowed domains.
RefererMiddleware
-----------------

6
docs/topics/spiders.rst
View File

@ -75,7 +75,8 @@ scrapy.Spider
An optional list of strings containing domains that this spider is
allowed to crawl. Requests for URLs not belonging to the domain names
specified in this list (or their subdomains) won't be followed if
:class:`~scrapy.spidermiddlewares.offsite.OffsiteMiddleware` is enabled.
:class:`~scrapy.downloadermiddlewares.offsite.OffsiteMiddleware` is
enabled.
Let's say your target url is ``https://www.example.com/1.html``,
then add ``'example.com'`` to the list.
@ -202,7 +203,8 @@ scrapy.Spider
.. method:: start_requests()
This method must return an iterable with the first Requests to crawl for
This method must return an iterable with the first Requests to crawl and/or with :ref:`item objects
<topics-items>` for
this spider. It is called by Scrapy when the spider is opened for
scraping. Scrapy calls it only once, so it is safe to implement
:meth:`start_requests` as a generator.

4
docs/topics/telnetconsole.rst
View File

@ -172,8 +172,8 @@ TELNETCONSOLE_PORT
Default: ``[6023, 6073]``
The port range to use for the telnet console. If set to ``None`` or ``0``, a
dynamically assigned port is used.
The port range to use for the telnet console. If set to ``None``, a dynamically
assigned port is used.
.. setting:: TELNETCONSOLE_HOST

19
pylintrc
View File

@ -4,21 +4,14 @@ jobs=1 # >1 hides results
[MESSAGES CONTROL]
disable=abstract-method,
anomalous-backslash-in-string,
arguments-differ,
arguments-renamed,
attribute-defined-outside-init,
bad-classmethod-argument,
bad-mcs-classmethod-argument,
bare-except,
broad-except,
broad-exception-raised,
c-extension-no-member,
catching-non-exception,
cell-var-from-loop,
comparison-with-callable,
consider-using-dict-items,
consider-using-in,
consider-using-with,
cyclic-import,
dangerous-default-value,
@ -32,7 +25,6 @@ disable=abstract-method,
implicit-str-concat,
import-error,
import-outside-toplevel,
import-self,
inconsistent-return-statements,
inherit-non-class,
invalid-name,
@ -44,7 +36,6 @@ disable=abstract-method,
logging-fstring-interpolation,
logging-not-lazy,
lost-exception,
method-hidden,
missing-docstring,
no-else-raise,
no-else-return,
@ -52,7 +43,7 @@ disable=abstract-method,
no-method-argument,
no-name-in-module,
no-self-argument,
no-value-for-parameter,
no-value-for-parameter, # https://github.com/pylint-dev/pylint/issues/3268
not-callable,
pointless-exception-statement,
pointless-statement,
@ -77,23 +68,15 @@ disable=abstract-method,
too-many-public-methods,
too-many-return-statements,
unbalanced-tuple-unpacking,
undefined-variable,
undefined-loop-variable,
unexpected-special-method-signature,
unnecessary-comprehension,
unnecessary-dunder-call,
unnecessary-pass,
unreachable,
unsubscriptable-object,
unused-argument,
unused-import,
unused-private-member,
unused-variable,
unused-wildcard-import,
use-dict-literal,
used-before-assignment,
useless-object-inheritance, # Required for Python 2 support
useless-return,
useless-super-delegation,
wildcard-import,
wrong-import-position

2
scrapy/VERSION
View File

@ -1 +1 @@
2.11.0
2.11.2

6
scrapy/__init__.py
View File

@ -33,12 +33,6 @@ 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, 8):
print(f"Scrapy {__version__} requires Python 3.8+")
sys.exit(1)
# Ignore noisy twisted deprecation warnings
warnings.filterwarnings("ignore", category=DeprecationWarning, module="twisted")

13
scrapy/addons.py
View File

@ -1,13 +1,16 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any, List
from typing import TYPE_CHECKING, Any
from scrapy.exceptions import NotConfigured
from scrapy.settings import Settings
from scrapy.utils.conf import build_component_list
from scrapy.utils.misc import build_from_crawler, load_object
if TYPE_CHECKING:
from scrapy.crawler import Crawler
from scrapy.settings import Settings
logger = logging.getLogger(__name__)
@ -15,9 +18,9 @@ logger = logging.getLogger(__name__)
class AddonManager:
"""This class facilitates loading and storing :ref:`topics-addons`."""
def __init__(self, crawler: "Crawler") -> None:
self.crawler: "Crawler" = crawler
self.addons: List[Any] = []
def __init__(self, crawler: Crawler) -> None:
self.crawler: Crawler = crawler
self.addons: list[Any] = []
def load_settings(self, settings: Settings) -> None:
"""Load add-ons and configurations from a settings object and apply them.

59
scrapy/cmdline.py
View File

@ -1,9 +1,12 @@
from __future__ import annotations
import argparse
import cProfile
import inspect
import os
import sys
from importlib.metadata import entry_points
from typing import TYPE_CHECKING
import scrapy
from scrapy.commands import BaseRunSpiderCommand, ScrapyCommand, ScrapyHelpFormatter
@ -13,9 +16,21 @@ from scrapy.utils.misc import walk_modules
from scrapy.utils.project import get_project_settings, inside_project
from scrapy.utils.python import garbage_collect
if TYPE_CHECKING:
from collections.abc import Callable, Iterable
# typing.ParamSpec requires Python 3.10
from typing_extensions import ParamSpec
from scrapy.settings import BaseSettings, Settings
_P = ParamSpec("_P")
class ScrapyArgumentParser(argparse.ArgumentParser):
def _parse_optional(self, arg_string):
def _parse_optional(
self, arg_string: str
) -> tuple[argparse.Action | None, str, str | None] | None:
# if starts with -: it means that is a parameter not a argument
if arg_string[:2] == "-:":
return None
@ -23,7 +38,7 @@ class ScrapyArgumentParser(argparse.ArgumentParser):
return super()._parse_optional(arg_string)
def _iter_command_classes(module_name):
def _iter_command_classes(module_name: str) -> Iterable[type[ScrapyCommand]]:
# TODO: add `name` attribute to commands and merge this function with
# scrapy.utils.spider.iter_spider_classes
for module in walk_modules(module_name):
@ -37,8 +52,8 @@ def _iter_command_classes(module_name):
yield obj
def _get_commands_from_module(module, inproject):
d = {}
def _get_commands_from_module(module: str, inproject: bool) -> dict[str, ScrapyCommand]:
d: dict[str, ScrapyCommand] = {}
for cmd in _iter_command_classes(module):
if inproject or not cmd.requires_project:
cmdname = cmd.__module__.split(".")[-1]
@ -46,8 +61,10 @@ def _get_commands_from_module(module, inproject):
return d
def _get_commands_from_entry_points(inproject, group="scrapy.commands"):
cmds = {}
def _get_commands_from_entry_points(
inproject: bool, group: str = "scrapy.commands"
) -> dict[str, ScrapyCommand]:
cmds: dict[str, ScrapyCommand] = {}
if sys.version_info >= (3, 10):
eps = entry_points(group=group)
else:
@ -61,7 +78,9 @@ def _get_commands_from_entry_points(inproject, group="scrapy.commands"):
return cmds
def _get_commands_dict(settings, inproject):
def _get_commands_dict(
settings: BaseSettings, inproject: bool
) -> dict[str, ScrapyCommand]:
cmds = _get_commands_from_module("scrapy.commands", inproject)
cmds.update(_get_commands_from_entry_points(inproject))
cmds_module = settings["COMMANDS_MODULE"]
@ -70,16 +89,17 @@ def _get_commands_dict(settings, inproject):
return cmds
def _pop_command_name(argv):
def _pop_command_name(argv: list[str]) -> str | None:
i = 0
for arg in argv[1:]:
if not arg.startswith("-"):
del argv[i]
return arg
i += 1
return None
def _print_header(settings, inproject):
def _print_header(settings: BaseSettings, inproject: bool) -> None:
version = scrapy.__version__
if inproject:
print(f"Scrapy {version} - active project: {settings['BOT_NAME']}\n")
@ -88,7 +108,7 @@ def _print_header(settings, inproject):
print(f"Scrapy {version} - no active project\n")
def _print_commands(settings, inproject):
def _print_commands(settings: BaseSettings, inproject: bool) -> None:
_print_header(settings, inproject)
print("Usage:")
print(" scrapy <command> [options] [args]\n")
@ -103,13 +123,20 @@ def _print_commands(settings, inproject):
print('Use "scrapy <command> -h" to see more info about a command')
def _print_unknown_command(settings, cmdname, inproject):
def _print_unknown_command(
settings: BaseSettings, cmdname: str, inproject: bool
) -> None:
_print_header(settings, inproject)
print(f"Unknown command: {cmdname}\n")
print('Use "scrapy" to see available commands')
def _run_print_help(parser, func, *a, **kw):
def _run_print_help(
parser: argparse.ArgumentParser,
func: Callable[_P, None],
*a: _P.args,
**kw: _P.kwargs,
) -> None:
try:
func(*a, **kw)
except UsageError as e:
@ -120,7 +147,7 @@ def _run_print_help(parser, func, *a, **kw):
sys.exit(2)
def execute(argv=None, settings=None):
def execute(argv: list[str] | None = None, settings: Settings | None = None) -> None:
if argv is None:
argv = sys.argv
@ -162,14 +189,16 @@ def execute(argv=None, settings=None):
sys.exit(cmd.exitcode)
def _run_command(cmd, args, opts):
def _run_command(cmd: ScrapyCommand, args: list[str], opts: argparse.Namespace) -> None:
if opts.profile:
_run_command_profiled(cmd, args, opts)
else:
cmd.run(args, opts)
def _run_command_profiled(cmd, args, opts):
def _run_command_profiled(
cmd: ScrapyCommand, args: list[str], opts: argparse.Namespace
) -> None:
if opts.profile:
sys.stderr.write(f"scrapy: writing cProfile stats to {opts.profile!r}\n")
loc = locals()

61
scrapy/commands/__init__.py
View File

@ -1,62 +1,70 @@
"""
Base class for Scrapy commands
"""
from __future__ import annotations
import argparse
import builtins
import os
from pathlib import Path
from typing import Any, Dict, List, Optional
from typing import TYPE_CHECKING, Any
from twisted.python import failure
from scrapy.crawler import CrawlerProcess
from scrapy.exceptions import UsageError
from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli
if TYPE_CHECKING:
from collections.abc import Iterable
from scrapy.crawler import Crawler, CrawlerProcess
class ScrapyCommand:
requires_project = False
crawler_process: Optional[CrawlerProcess] = None
requires_project: bool = False
crawler_process: CrawlerProcess | None = None
# default settings to be used for this command instead of global defaults
default_settings: Dict[str, Any] = {}
default_settings: dict[str, Any] = {}
exitcode = 0
exitcode: int = 0
def __init__(self) -> None:
self.settings: Any = None # set in scrapy.cmdline
def set_crawler(self, crawler):
def set_crawler(self, crawler: Crawler) -> None:
if hasattr(self, "_crawler"):
raise RuntimeError("crawler already set")
self._crawler = crawler
self._crawler: Crawler = crawler
def syntax(self):
def syntax(self) -> str:
"""
Command syntax (preferably one-line). Do not include command name.
"""
return ""
def short_desc(self):
def short_desc(self) -> str:
"""
A short description of the command
"""
return ""
def long_desc(self):
def long_desc(self) -> str:
"""A long description of the command. Return short description when not
available. It cannot contain newlines since contents will be formatted
by optparser which removes newlines and wraps text.
"""
return self.short_desc()
def help(self):
def help(self) -> str:
"""An extensive help for the command. It will be shown when using the
"help" command. It can contain newlines since no post-formatting will
be applied to its contents.
"""
return self.long_desc()
def add_options(self, parser):
def add_options(self, parser: argparse.ArgumentParser) -> None:
"""
Populate option parse with options available for this command
"""
@ -91,7 +99,7 @@ class ScrapyCommand:
)
group.add_argument("--pdb", action="store_true", help="enable pdb on failure")
def process_options(self, args, opts):
def process_options(self, args: list[str], opts: argparse.Namespace) -> None:
try:
self.settings.setdict(arglist_to_dict(opts.set), priority="cmdline")
except ValueError:
@ -116,7 +124,7 @@ class ScrapyCommand:
if opts.pdb:
failure.startDebugMode()
def run(self, args: List[str], opts: argparse.Namespace) -> None:
def run(self, args: list[str], opts: argparse.Namespace) -> None:
"""
Entry point for running commands
"""
@ -128,8 +136,8 @@ class BaseRunSpiderCommand(ScrapyCommand):
Common class used to share functionality between the crawl, parse and runspider commands
"""
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
def add_options(self, parser: argparse.ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument(
"-a",
dest="spargs",
@ -161,8 +169,8 @@ class BaseRunSpiderCommand(ScrapyCommand):
help="format to use for dumping items",
)
def process_options(self, args, opts):
ScrapyCommand.process_options(self, args, opts)
def process_options(self, args: list[str], opts: argparse.Namespace) -> None:
super().process_options(args, opts)
try:
opts.spargs = arglist_to_dict(opts.spargs)
except ValueError:
@ -182,7 +190,13 @@ class ScrapyHelpFormatter(argparse.HelpFormatter):
Help Formatter for scrapy command line help messages.
"""
def __init__(self, prog, indent_increment=2, max_help_position=24, width=None):
def __init__(
self,
prog: str,
indent_increment: int = 2,
max_help_position: int = 24,
width: int | None = None,
):
super().__init__(
prog,
indent_increment=indent_increment,
@ -190,11 +204,12 @@ class ScrapyHelpFormatter(argparse.HelpFormatter):
width=width,
)
def _join_parts(self, part_strings):
parts = self.format_part_strings(part_strings)
def _join_parts(self, part_strings: Iterable[str]) -> str:
# scrapy.commands.list shadows builtins.list
parts = self.format_part_strings(builtins.list(part_strings))
return super()._join_parts(parts)
def format_part_strings(self, part_strings):
def format_part_strings(self, part_strings: list[str]) -> list[str]:
"""
Underline and title case command line help message headers.
"""

31
scrapy/commands/bench.py
View File

@ -1,12 +1,22 @@
import subprocess
from __future__ import annotations
import argparse
import subprocess # nosec
import sys
import time
from typing import TYPE_CHECKING, Any
from urllib.parse import urlencode
import scrapy
from scrapy.commands import ScrapyCommand
from scrapy.http import Response, TextResponse
from scrapy.linkextractors import LinkExtractor
if TYPE_CHECKING:
from collections.abc import Iterable
from scrapy import Request
class Command(ScrapyCommand):
default_settings = {
@ -15,24 +25,28 @@ class Command(ScrapyCommand):
"CLOSESPIDER_TIMEOUT": 10,
}
def short_desc(self):
def short_desc(self) -> str:
return "Run quick benchmark test"
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
with _BenchServer():
assert self.crawler_process
self.crawler_process.crawl(_BenchSpider, total=100000)
self.crawler_process.start()
class _BenchServer:
def __enter__(self):
def __enter__(self) -> None:
from scrapy.utils.test import get_testenv
pargs = [sys.executable, "-u", "-m", "scrapy.utils.benchserver"]
self.proc = subprocess.Popen(pargs, stdout=subprocess.PIPE, env=get_testenv())
self.proc = subprocess.Popen(
pargs, stdout=subprocess.PIPE, env=get_testenv()
) # nosec
assert self.proc.stdout
self.proc.stdout.readline()
def __exit__(self, exc_type, exc_value, traceback):
def __exit__(self, exc_type, exc_value, traceback) -> None:
self.proc.kill()
self.proc.wait()
time.sleep(0.2)
@ -47,11 +61,12 @@ class _BenchSpider(scrapy.Spider):
baseurl = "http://localhost:8998"
link_extractor = LinkExtractor()
def start_requests(self):
def start_requests(self) -> Iterable[Request]:
qargs = {"total": self.total, "show": self.show}
url = f"{self.baseurl}?{urlencode(qargs, doseq=True)}"
return [scrapy.Request(url, dont_filter=True)]
def parse(self, response):
def parse(self, response: Response) -> Any:
assert isinstance(Response, TextResponse)
for link in self.link_extractor.extract_links(response):
yield scrapy.Request(link.url, callback=self.parse)

16
scrapy/commands/check.py
View File

@ -1,3 +1,4 @@
import argparse
import time
from collections import defaultdict
from unittest import TextTestResult as _TextTestResult
@ -10,7 +11,7 @@ from scrapy.utils.misc import load_object, set_environ
class TextTestResult(_TextTestResult):
def printSummary(self, start, stop):
def printSummary(self, start: float, stop: float) -> None:
write = self.stream.write
writeln = self.stream.writeln
@ -42,14 +43,14 @@ class Command(ScrapyCommand):
requires_project = True
default_settings = {"LOG_ENABLED": False}
def syntax(self):
def syntax(self) -> str:
return "[options] <spider>"
def short_desc(self):
def short_desc(self) -> str:
return "Check spider contracts"
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
def add_options(self, parser: argparse.ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument(
"-l",
"--list",
@ -66,7 +67,7 @@ class Command(ScrapyCommand):
help="print contract tests for all spiders",
)
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
# load contracts
contracts = build_component_list(self.settings.getwithbase("SPIDER_CONTRACTS"))
conman = ContractsManager(load_object(c) for c in contracts)
@ -76,12 +77,13 @@ class Command(ScrapyCommand):
# contract requests
contract_reqs = defaultdict(list)
assert self.crawler_process
spider_loader = self.crawler_process.spider_loader
with set_environ(SCRAPY_CHECK="true"):
for spidername in args or spider_loader.list():
spidercls = spider_loader.load(spidername)
spidercls.start_requests = lambda s: conman.from_spider(s, result)
spidercls.start_requests = lambda s: conman.from_spider(s, result) # type: ignore[assignment,method-assign,return-value]
tested_methods = conman.tested_methods_from_spidercls(spidercls)
if opts.list:

18
scrapy/commands/crawl.py
View File

@ -1,17 +1,26 @@
from __future__ import annotations
from typing import TYPE_CHECKING, cast
from twisted.python.failure import Failure
from scrapy.commands import BaseRunSpiderCommand
from scrapy.exceptions import UsageError
if TYPE_CHECKING:
import argparse
class Command(BaseRunSpiderCommand):
requires_project = True
def syntax(self):
def syntax(self) -> str:
return "[options] <spider>"
def short_desc(self):
def short_desc(self) -> str:
return "Run a spider"
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
if len(args) < 1:
raise UsageError()
elif len(args) > 1:
@ -20,10 +29,11 @@ class Command(BaseRunSpiderCommand):
)
spname = args[0]
assert self.crawler_process
crawl_defer = self.crawler_process.crawl(spname, **opts.spargs)
if getattr(crawl_defer, "result", None) is not None and issubclass(
crawl_defer.result.type, Exception
cast(Failure, crawl_defer.result).type, Exception
):
self.exitcode = 1
else:

15
scrapy/commands/edit.py
View File

@ -1,3 +1,4 @@
import argparse
import os
import sys
@ -9,32 +10,34 @@ class Command(ScrapyCommand):
requires_project = True
default_settings = {"LOG_ENABLED": False}
def syntax(self):
def syntax(self) -> str:
return "<spider>"
def short_desc(self):
def short_desc(self) -> str:
return "Edit spider"
def long_desc(self):
def long_desc(self) -> str:
return (
"Edit a spider using the editor defined in the EDITOR environment"
" variable or else the EDITOR setting"
)
def _err(self, msg):
def _err(self, msg: str) -> None:
sys.stderr.write(msg + os.linesep)
self.exitcode = 1
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
if len(args) != 1:
raise UsageError()
editor = self.settings["EDITOR"]
assert self.crawler_process
try:
spidercls = self.crawler_process.spider_loader.load(args[0])
except KeyError:
return self._err(f"Spider not found: {args[0]}")
sfile = sys.modules[spidercls.__module__].__file__
assert sfile
sfile = sfile.replace(".pyc", ".py")
self.exitcode = os.system(f'{editor} "{sfile}"')
self.exitcode = os.system(f'{editor} "{sfile}"') # nosec

31
scrapy/commands/fetch.py
View File

@ -1,34 +1,38 @@
from __future__ import annotations
import sys
from argparse import Namespace
from typing import List, Type
from typing import TYPE_CHECKING
from w3lib.url import is_url
from scrapy import Spider
from scrapy.commands import ScrapyCommand
from scrapy.exceptions import UsageError
from scrapy.http import Request
from scrapy.http import Request, Response
from scrapy.utils.datatypes import SequenceExclude
from scrapy.utils.spider import DefaultSpider, spidercls_for_request
if TYPE_CHECKING:
from argparse import ArgumentParser, Namespace
class Command(ScrapyCommand):
requires_project = False
def syntax(self):
def syntax(self) -> str:
return "[options] <url>"
def short_desc(self):
def short_desc(self) -> str:
return "Fetch a URL using the Scrapy downloader"
def long_desc(self):
def long_desc(self) -> str:
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)
def add_options(self, parser: ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument("--spider", dest="spider", help="use this spider")
parser.add_argument(
"--headers",
@ -44,23 +48,24 @@ class Command(ScrapyCommand):
help="do not handle HTTP 3xx status codes and print response as-is",
)
def _print_headers(self, headers, prefix):
def _print_headers(self, headers: dict[bytes, list[bytes]], prefix: bytes) -> None:
for key, values in headers.items():
for value in values:
self._print_bytes(prefix + b" " + key + b": " + value)
def _print_response(self, response, opts):
def _print_response(self, response: Response, opts: Namespace) -> None:
if opts.headers:
assert response.request
self._print_headers(response.request.headers, b">")
print(">")
self._print_headers(response.headers, b"<")
else:
self._print_bytes(response.body)
def _print_bytes(self, bytes_):
def _print_bytes(self, bytes_: bytes) -> None:
sys.stdout.buffer.write(bytes_ + b"\n")
def run(self, args: List[str], opts: Namespace) -> None:
def run(self, args: list[str], opts: Namespace) -> None:
if len(args) != 1 or not is_url(args[0]):
raise UsageError()
request = Request(
@ -76,7 +81,7 @@ class Command(ScrapyCommand):
else:
request.meta["handle_httpstatus_all"] = True
spidercls: Type[Spider] = DefaultSpider
spidercls: type[Spider] = DefaultSpider
assert self.crawler_process
spider_loader = self.crawler_process.spider_loader
if opts.spider:

53
scrapy/commands/genspider.py
View File

@ -1,9 +1,12 @@
from __future__ import annotations
import argparse
import os
import shutil
import string
from importlib import import_module
from pathlib import Path
from typing import Optional, cast
from typing import Any, cast
from urllib.parse import urlparse
import scrapy
@ -12,7 +15,7 @@ from scrapy.exceptions import UsageError
from scrapy.utils.template import render_templatefile, string_camelcase
def sanitize_module_name(module_name):
def sanitize_module_name(module_name: str) -> str:
"""Sanitize the given module name, by replacing dashes and points
with underscores and prefixing it with a letter if it doesn't start
with one
@ -23,7 +26,7 @@ def sanitize_module_name(module_name):
return module_name
def extract_domain(url):
def extract_domain(url: str) -> str:
"""Extract domain name from URL string"""
o = urlparse(url)
if o.scheme == "" and o.netloc == "":
@ -31,7 +34,7 @@ def extract_domain(url):
return o.netloc
def verify_url_scheme(url):
def verify_url_scheme(url: str) -> str:
"""Check url for scheme and insert https if none found."""
parsed = urlparse(url)
if parsed.scheme == "" and parsed.netloc == "":
@ -43,14 +46,14 @@ class Command(ScrapyCommand):
requires_project = False
default_settings = {"LOG_ENABLED": False}
def syntax(self):
def syntax(self) -> str:
return "[options] <name> <domain>"
def short_desc(self):
def short_desc(self) -> str:
return "Generate new spider using pre-defined templates"
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
def add_options(self, parser: argparse.ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument(
"-l",
"--list",
@ -86,7 +89,7 @@ class Command(ScrapyCommand):
help="If the spider already exists, overwrite it with the template",
)
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
if opts.list:
self._list_templates()
return
@ -113,23 +116,39 @@ class Command(ScrapyCommand):
if template_file:
self._genspider(module, name, url, opts.template, template_file)
if opts.edit:
self.exitcode = os.system(f'scrapy edit "{name}"')
self.exitcode = os.system(f'scrapy edit "{name}"') # nosec
def _genspider(self, module, name, url, template_name, template_file):
"""Generate the spider module, based on the given template"""
def _generate_template_variables(
self,
module: str,
name: str,
url: str,
template_name: str,
) -> dict[str, Any]:
capitalized_module = "".join(s.capitalize() for s in module.split("_"))
domain = extract_domain(url)
tvars = {
return {
"project_name": self.settings.get("BOT_NAME"),
"ProjectName": string_camelcase(self.settings.get("BOT_NAME")),
"module": module,
"name": name,
"url": url,
"domain": domain,
"domain": extract_domain(url),
"classname": f"{capitalized_module}Spider",
}
def _genspider(
self,
module: str,
name: str,
url: str,
template_name: str,
template_file: str | os.PathLike,
) -> None:
"""Generate the spider module, based on the given template"""
tvars = self._generate_template_variables(module, name, url, template_name)
if self.settings.get("NEWSPIDER_MODULE"):
spiders_module = import_module(self.settings["NEWSPIDER_MODULE"])
assert spiders_module.__file__
spiders_dir = Path(spiders_module.__file__).parent.resolve()
else:
spiders_module = None
@ -144,7 +163,7 @@ class Command(ScrapyCommand):
if spiders_module:
print(f"in module:\n {spiders_module.__name__}.{module}")
def _find_template(self, template: str) -> Optional[Path]:
def _find_template(self, template: str) -> Path | None:
template_file = Path(self.templates_dir, f"{template}.tmpl")
if template_file.exists():
return template_file
@ -152,7 +171,7 @@ class Command(ScrapyCommand):
print('Use "scrapy genspider --list" to see all available templates.')
return None
def _list_templates(self):
def _list_templates(self) -> None:
print("Available templates:")
for file in sorted(Path(self.templates_dir).iterdir()):
if file.suffix == ".tmpl":

12
scrapy/commands/list.py
View File

@ -1,13 +1,21 @@
from __future__ import annotations
from typing import TYPE_CHECKING
from scrapy.commands import ScrapyCommand
if TYPE_CHECKING:
import argparse
class Command(ScrapyCommand):
requires_project = True
default_settings = {"LOG_ENABLED": False}
def short_desc(self):
def short_desc(self) -> str:
return "List available spiders"
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
assert self.crawler_process
for s in sorted(self.crawler_process.spider_loader.list()):
print(s)

130
scrapy/commands/parse.py
View File

@ -1,16 +1,19 @@
from __future__ import annotations
import argparse
import functools
import inspect
import json
import logging
from typing import Dict
from typing import TYPE_CHECKING, Any, TypeVar, overload
from itemadapter import ItemAdapter, is_item
from twisted.internet.defer import maybeDeferred
from twisted.internet.defer import Deferred, maybeDeferred
from w3lib.url import is_url
from scrapy.commands import BaseRunSpiderCommand
from scrapy.exceptions import UsageError
from scrapy.http import Request
from scrapy.http import Request, Response
from scrapy.utils import display
from scrapy.utils.asyncgen import collect_asyncgen
from scrapy.utils.defer import aiter_errback, deferred_from_coro
@ -18,26 +21,38 @@ from scrapy.utils.log import failure_to_exc_info
from scrapy.utils.misc import arg_to_iter
from scrapy.utils.spider import spidercls_for_request
if TYPE_CHECKING:
from collections.abc import AsyncGenerator, Coroutine, Iterable
from twisted.python.failure import Failure
from scrapy.http.request import CallbackT
from scrapy.spiders import Spider
logger = logging.getLogger(__name__)
_T = TypeVar("_T")
class Command(BaseRunSpiderCommand):
requires_project = True
spider = None
items: Dict[int, list] = {}
requests: Dict[int, list] = {}
spider: Spider | None = None
items: dict[int, list[Any]] = {}
requests: dict[int, list[Request]] = {}
spidercls: type[Spider] | None
first_response = None
def syntax(self):
def syntax(self) -> str:
return "[options] <url>"
def short_desc(self):
def short_desc(self) -> str:
return "Parse URL (using its spider) and print the results"
def add_options(self, parser):
BaseRunSpiderCommand.add_options(self, parser)
def add_options(self, parser: argparse.ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument(
"--spider",
dest="spider",
@ -106,7 +121,7 @@ class Command(BaseRunSpiderCommand):
)
@property
def max_level(self):
def max_level(self) -> int:
max_items, max_requests = 0, 0
if self.items:
max_items = max(self.items)
@ -114,13 +129,21 @@ class Command(BaseRunSpiderCommand):
max_requests = max(self.requests)
return max(max_items, max_requests)
def handle_exception(self, _failure):
def handle_exception(self, _failure: Failure) -> None:
logger.error(
"An error is caught while iterating the async iterable",
exc_info=failure_to_exc_info(_failure),
)
def iterate_spider_output(self, result):
@overload
def iterate_spider_output(
self, result: AsyncGenerator[_T] | Coroutine[Any, Any, _T]
) -> Deferred[_T]: ...
@overload
def iterate_spider_output(self, result: _T) -> Iterable[Any]: ...
def iterate_spider_output(self, result: Any) -> Iterable[Any] | Deferred[Any]:
if inspect.isasyncgen(result):
d = deferred_from_coro(
collect_asyncgen(aiter_errback(result, self.handle_exception))
@ -133,15 +156,15 @@ class Command(BaseRunSpiderCommand):
return d
return arg_to_iter(deferred_from_coro(result))
def add_items(self, lvl, new_items):
def add_items(self, lvl: int, new_items: list[Any]) -> None:
old_items = self.items.get(lvl, [])
self.items[lvl] = old_items + new_items
def add_requests(self, lvl, new_reqs):
def add_requests(self, lvl: int, new_reqs: list[Request]) -> None:
old_reqs = self.requests.get(lvl, [])
self.requests[lvl] = old_reqs + new_reqs
def print_items(self, lvl=None, colour=True):
def print_items(self, lvl: int | None = None, colour: bool = True) -> None:
if lvl is None:
items = [item for lst in self.items.values() for item in lst]
else:
@ -150,7 +173,7 @@ class Command(BaseRunSpiderCommand):
print("# Scraped Items ", "-" * 60)
display.pprint([ItemAdapter(x).asdict() for x in items], colorize=colour)
def print_requests(self, lvl=None, colour=True):
def print_requests(self, lvl: int | None = None, colour: bool = True) -> None:
if lvl is None:
if self.requests:
requests = self.requests[max(self.requests)]
@ -162,7 +185,7 @@ class Command(BaseRunSpiderCommand):
print("# Requests ", "-" * 65)
display.pprint(requests, colorize=colour)
def print_results(self, opts):
def print_results(self, opts: argparse.Namespace) -> None:
colour = not opts.nocolour
if opts.verbose:
@ -179,7 +202,14 @@ class Command(BaseRunSpiderCommand):
if not opts.nolinks:
self.print_requests(colour=colour)
def _get_items_and_requests(self, spider_output, opts, depth, spider, callback):
def _get_items_and_requests(
self,
spider_output: Iterable[Any],
opts: argparse.Namespace,
depth: int,
spider: Spider,
callback: CallbackT,
) -> tuple[list[Any], list[Request], argparse.Namespace, int, Spider, CallbackT]:
items, requests = [], []
for x in spider_output:
if is_item(x):
@ -188,14 +218,21 @@ class Command(BaseRunSpiderCommand):
requests.append(x)
return items, requests, opts, depth, spider, callback
def run_callback(self, response, callback, cb_kwargs=None):
def run_callback(
self,
response: Response,
callback: CallbackT,
cb_kwargs: dict[str, Any] | None = None,
) -> Deferred[Any]:
cb_kwargs = cb_kwargs or {}
d = maybeDeferred(self.iterate_spider_output, callback(response, **cb_kwargs))
return d
def get_callback_from_rules(self, spider, response):
def get_callback_from_rules(
self, spider: Spider, response: Response
) -> CallbackT | str | None:
if getattr(spider, "rules", None):
for rule in spider.rules:
for rule in spider.rules: # type: ignore[attr-defined]
if rule.link_extractor.matches(response.url):
return rule.callback or "parse"
else:
@ -204,8 +241,10 @@ class Command(BaseRunSpiderCommand):
"please specify a callback to use for parsing",
{"spider": spider.name},
)
return None
def set_spidercls(self, url, opts):
def set_spidercls(self, url: str, opts: argparse.Namespace) -> None:
assert self.crawler_process
spider_loader = self.crawler_process.spider_loader
if opts.spider:
try:
@ -219,13 +258,15 @@ class Command(BaseRunSpiderCommand):
if not self.spidercls:
logger.error("Unable to find spider for: %(url)s", {"url": url})
def _start_requests(spider):
def _start_requests(spider: Spider) -> Iterable[Request]:
yield self.prepare_request(spider, Request(url), opts)
if self.spidercls:
self.spidercls.start_requests = _start_requests
self.spidercls.start_requests = _start_requests # type: ignore[assignment,method-assign]
def start_parsing(self, url, opts):
def start_parsing(self, url: str, opts: argparse.Namespace) -> None:
assert self.crawler_process
assert self.spidercls
self.crawler_process.crawl(self.spidercls, **opts.spargs)
self.pcrawler = list(self.crawler_process.crawlers)[0]
self.crawler_process.start()
@ -233,7 +274,12 @@ class Command(BaseRunSpiderCommand):
if not self.first_response:
logger.error("No response downloaded for: %(url)s", {"url": url})
def scraped_data(self, args):
def scraped_data(
self,
args: tuple[
list[Any], list[Request], argparse.Namespace, int, Spider, CallbackT
],
) -> list[Any]:
items, requests, opts, depth, spider, callback = args
if opts.pipelines:
itemproc = self.pcrawler.engine.scraper.itemproc
@ -252,8 +298,14 @@ class Command(BaseRunSpiderCommand):
return scraped_data
def _get_callback(self, *, spider, opts, response=None):
cb = None
def _get_callback(
self,
*,
spider: Spider,
opts: argparse.Namespace,
response: Response | None = None,
) -> CallbackT:
cb: str | CallbackT | None = None
if response:
cb = response.meta["_callback"]
if not cb:
@ -270,6 +322,7 @@ class Command(BaseRunSpiderCommand):
cb = "parse"
if not callable(cb):
assert cb is not None
cb_method = getattr(spider, cb, None)
if callable(cb_method):
cb = cb_method
@ -277,10 +330,13 @@ class Command(BaseRunSpiderCommand):
raise ValueError(
f"Cannot find callback {cb!r} in spider: {spider.name}"
)
assert callable(cb)
return cb
def prepare_request(self, spider, request, opts):
def callback(response, **cb_kwargs):
def prepare_request(
self, spider: Spider, request: Request, opts: argparse.Namespace
) -> Request:
def callback(response: Response, **cb_kwargs: Any) -> Deferred[list[Any]]:
# memorize first request
if not self.first_response:
self.first_response = response
@ -288,7 +344,7 @@ class Command(BaseRunSpiderCommand):
cb = self._get_callback(spider=spider, opts=opts, response=response)
# parse items and requests
depth = response.meta["_depth"]
depth: int = response.meta["_depth"]
d = self.run_callback(response, cb, cb_kwargs)
d.addCallback(self._get_items_and_requests, opts, depth, spider, callback)
@ -311,13 +367,13 @@ class Command(BaseRunSpiderCommand):
request.callback = callback
return request
def process_options(self, args, opts):
BaseRunSpiderCommand.process_options(self, args, opts)
def process_options(self, args: list[str], opts: argparse.Namespace) -> None:
super().process_options(args, opts)
self.process_request_meta(opts)
self.process_request_cb_kwargs(opts)
def process_request_meta(self, opts):
def process_request_meta(self, opts: argparse.Namespace) -> None:
if opts.meta:
try:
opts.meta = json.loads(opts.meta)
@ -328,7 +384,7 @@ class Command(BaseRunSpiderCommand):
print_help=False,
)
def process_request_cb_kwargs(self, opts):
def process_request_cb_kwargs(self, opts: argparse.Namespace) -> None:
if opts.cbkwargs:
try:
opts.cbkwargs = json.loads(opts.cbkwargs)
@ -339,7 +395,7 @@ class Command(BaseRunSpiderCommand):
print_help=False,
)
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
# parse arguments
if not len(args) == 1 or not is_url(args[0]):
raise UsageError()

22
scrapy/commands/runspider.py
View File

@ -1,16 +1,21 @@
from __future__ import annotations
import argparse
import sys
from importlib import import_module
from os import PathLike
from pathlib import Path
from types import ModuleType
from typing import Union
from typing import TYPE_CHECKING
from scrapy.commands import BaseRunSpiderCommand
from scrapy.exceptions import UsageError
from scrapy.utils.spider import iter_spider_classes
if TYPE_CHECKING:
from os import PathLike
from types import ModuleType
def _import_file(filepath: Union[str, PathLike]) -> ModuleType:
def _import_file(filepath: str | PathLike[str]) -> ModuleType:
abspath = Path(filepath).resolve()
if abspath.suffix not in (".py", ".pyw"):
raise ValueError(f"Not a Python source file: {abspath}")
@ -27,16 +32,16 @@ class Command(BaseRunSpiderCommand):
requires_project = False
default_settings = {"SPIDER_LOADER_WARN_ONLY": True}
def syntax(self):
def syntax(self) -> str:
return "[options] <spider_file>"
def short_desc(self):
def short_desc(self) -> str:
return "Run a self-contained spider (without creating a project)"
def long_desc(self):
def long_desc(self) -> str:
return "Run the spider defined in the given file"
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
if len(args) != 1:
raise UsageError()
filename = Path(args[0])
@ -51,6 +56,7 @@ class Command(BaseRunSpiderCommand):
raise UsageError(f"No spider found in file: {filename}\n")
spidercls = spclasses.pop()
assert self.crawler_process
self.crawler_process.crawl(spidercls, **opts.spargs)
self.crawler_process.start()

12
scrapy/commands/settings.py
View File

@ -1,3 +1,4 @@
import argparse
import json
from scrapy.commands import ScrapyCommand
@ -8,14 +9,14 @@ class Command(ScrapyCommand):
requires_project = False
default_settings = {"LOG_ENABLED": False, "SPIDER_LOADER_WARN_ONLY": True}
def syntax(self):
def syntax(self) -> str:
return "[options]"
def short_desc(self):
def short_desc(self) -> str:
return "Get settings values"
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
def add_options(self, parser: argparse.ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument(
"--get", dest="get", metavar="SETTING", help="print raw setting value"
)
@ -44,7 +45,8 @@ class Command(ScrapyCommand):
help="print setting value, interpreted as a list",
)
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
assert self.crawler_process
settings = self.crawler_process.settings
if opts.get:
s = settings.get(opts.get)

28
scrapy/commands/shell.py
View File

@ -3,9 +3,11 @@ Scrapy Shell
See documentation in docs/topics/shell.rst
"""
from argparse import Namespace
from __future__ import annotations
from threading import Thread
from typing import List, Type
from typing import TYPE_CHECKING, Any
from scrapy import Spider
from scrapy.commands import ScrapyCommand
@ -14,6 +16,9 @@ from scrapy.shell import Shell
from scrapy.utils.spider import DefaultSpider, spidercls_for_request
from scrapy.utils.url import guess_scheme
if TYPE_CHECKING:
from argparse import ArgumentParser, Namespace
class Command(ScrapyCommand):
requires_project = False
@ -23,20 +28,20 @@ class Command(ScrapyCommand):
"DUPEFILTER_CLASS": "scrapy.dupefilters.BaseDupeFilter",
}
def syntax(self):
def syntax(self) -> str:
return "[url|file]"
def short_desc(self):
def short_desc(self) -> str:
return "Interactive scraping console"
def long_desc(self):
def long_desc(self) -> str:
return (
"Interactive console for scraping the given url or file. "
"Use ./file.html syntax or full path for local file."
)
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
def add_options(self, parser: ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument(
"-c",
dest="code",
@ -51,13 +56,13 @@ class Command(ScrapyCommand):
help="do not handle HTTP 3xx status codes and print response as-is",
)
def update_vars(self, vars):
def update_vars(self, vars: dict[str, Any]) -> None:
"""You can use this function to update the Scrapy objects that will be
available in the shell
"""
pass
def run(self, args: List[str], opts: Namespace) -> None:
def run(self, args: list[str], opts: Namespace) -> None:
url = args[0] if args else None
if url:
# first argument may be a local file
@ -66,7 +71,7 @@ class Command(ScrapyCommand):
assert self.crawler_process
spider_loader = self.crawler_process.spider_loader
spidercls: Type[Spider] = DefaultSpider
spidercls: type[Spider] = DefaultSpider
if opts.spider:
spidercls = spider_loader.load(opts.spider)
elif url:
@ -87,7 +92,8 @@ class Command(ScrapyCommand):
shell = Shell(crawler, update_vars=self.update_vars, code=opts.code)
shell.start(url=url, redirect=not opts.no_redirect)
def _start_crawler_thread(self):
def _start_crawler_thread(self) -> None:
assert self.crawler_process
t = Thread(
target=self.crawler_process.start,
kwargs={"stop_after_crawl": False, "install_signal_handlers": False},

19
scrapy/commands/startproject.py
View File

@ -1,3 +1,6 @@
from __future__ import annotations
import argparse
import os
import re
import string
@ -11,7 +14,7 @@ from scrapy.commands import ScrapyCommand
from scrapy.exceptions import UsageError
from scrapy.utils.template import render_templatefile, string_camelcase
TEMPLATES_TO_RENDER = (
TEMPLATES_TO_RENDER: tuple[tuple[str, ...], ...] = (
("scrapy.cfg",),
("${project_name}", "settings.py.tmpl"),
("${project_name}", "items.py.tmpl"),
@ -22,7 +25,7 @@ TEMPLATES_TO_RENDER = (
IGNORE = ignore_patterns("*.pyc", "__pycache__", ".svn")
def _make_writable(path):
def _make_writable(path: str | os.PathLike) -> None:
current_permissions = os.stat(path).st_mode
os.chmod(path, current_permissions | OWNER_WRITE_PERMISSION)
@ -31,14 +34,14 @@ class Command(ScrapyCommand):
requires_project = False
default_settings = {"LOG_ENABLED": False, "SPIDER_LOADER_WARN_ONLY": True}
def syntax(self):
def syntax(self) -> str:
return "<project_name> [project_dir]"
def short_desc(self):
def short_desc(self) -> str:
return "Create new project"
def _is_valid_name(self, project_name):
def _module_exists(module_name):
def _is_valid_name(self, project_name: str) -> bool:
def _module_exists(module_name: str) -> bool:
spec = find_spec(module_name)
return spec is not None and spec.loader is not None
@ -53,7 +56,7 @@ class Command(ScrapyCommand):
return True
return False
def _copytree(self, src: Path, dst: Path):
def _copytree(self, src: Path, dst: Path) -> None:
"""
Since the original function always creates the directory, to resolve
the issue a new function had to be created. It's a simple copy and
@ -84,7 +87,7 @@ class Command(ScrapyCommand):
copystat(src, dst)
_make_writable(dst)
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
if len(args) not in (1, 2):
raise UsageError()

12
scrapy/commands/version.py
View File

@ -1,3 +1,5 @@
import argparse
import scrapy
from scrapy.commands import ScrapyCommand
from scrapy.utils.versions import scrapy_components_versions
@ -6,14 +8,14 @@ from scrapy.utils.versions import scrapy_components_versions
class Command(ScrapyCommand):
default_settings = {"LOG_ENABLED": False, "SPIDER_LOADER_WARN_ONLY": True}
def syntax(self):
def syntax(self) -> str:
return "[-v]"
def short_desc(self):
def short_desc(self) -> str:
return "Print Scrapy version"
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
def add_options(self, parser: argparse.ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument(
"--verbose",
"-v",
@ -22,7 +24,7 @@ class Command(ScrapyCommand):
help="also display twisted/python/platform info (useful for bug reports)",
)
def run(self, args, opts):
def run(self, args: list[str], opts: argparse.Namespace) -> None:
if opts.verbose:
versions = scrapy_components_versions()
width = max(len(n) for (n, _) in versions)

15
scrapy/commands/view.py
View File

@ -1,21 +1,28 @@
import argparse
import logging
from scrapy.commands import fetch
from scrapy.http import Response, TextResponse
from scrapy.utils.response import open_in_browser
logger = logging.getLogger(__name__)
class Command(fetch.Command):
def short_desc(self):
def short_desc(self) -> str:
return "Open URL in browser, as seen by Scrapy"
def long_desc(self):
def long_desc(self) -> str:
return (
"Fetch a URL using the Scrapy downloader and show its contents in a browser"
)
def add_options(self, parser):
def add_options(self, parser: argparse.ArgumentParser) -> None:
super().add_options(parser)
parser.add_argument("--headers", help=argparse.SUPPRESS)
def _print_response(self, response, opts):
def _print_response(self, response: Response, opts: argparse.Namespace) -> None:
if not isinstance(response, TextResponse):
logger.error("Cannot view a non-text response.")
return
open_in_browser(response)

79
scrapy/contracts/__init__.py
View File

@ -1,32 +1,44 @@
from __future__ import annotations
import re
import sys
from collections.abc import AsyncGenerator, Iterable
from functools import wraps
from inspect import getmembers
from types import CoroutineType
from typing import AsyncGenerator, Dict, Optional, Type
from unittest import TestCase
from typing import TYPE_CHECKING, Any, cast
from unittest import TestCase, TestResult
from scrapy.http import Request
from scrapy.http import Request, Response
from scrapy.utils.python import get_spec
from scrapy.utils.spider import iterate_spider_output
if TYPE_CHECKING:
from collections.abc import Callable
from twisted.python.failure import Failure
from scrapy import Spider
class Contract:
"""Abstract class for contracts"""
request_cls: Optional[Type[Request]] = None
request_cls: type[Request] | None = None
name: str
def __init__(self, method, *args):
def __init__(self, method: Callable, *args: Any):
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
self.args: tuple[Any, ...] = args
def add_pre_hook(self, request, results):
def add_pre_hook(self, request: Request, results: TestResult) -> Request:
if hasattr(self, "pre_process"):
cb = request.callback
assert cb is not None
@wraps(cb)
def wrapper(response, **cb_kwargs):
def wrapper(response: Response, **cb_kwargs: Any) -> list[Any]:
try:
results.startTest(self.testcase_pre)
self.pre_process(response)
@ -42,23 +54,24 @@ class Contract:
if isinstance(cb_result, (AsyncGenerator, CoroutineType)):
raise TypeError("Contracts don't support async callbacks")
return list( # pylint: disable=return-in-finally
iterate_spider_output(cb_result)
cast(Iterable[Any], iterate_spider_output(cb_result))
)
request.callback = wrapper
return request
def add_post_hook(self, request, results):
def add_post_hook(self, request: Request, results: TestResult) -> Request:
if hasattr(self, "post_process"):
cb = request.callback
assert cb is not None
@wraps(cb)
def wrapper(response, **cb_kwargs):
def wrapper(response: Response, **cb_kwargs: Any) -> list[Any]:
cb_result = cb(response, **cb_kwargs)
if isinstance(cb_result, (AsyncGenerator, CoroutineType)):
raise TypeError("Contracts don't support async callbacks")
output = list(iterate_spider_output(cb_result))
output = list(cast(Iterable[Any], iterate_spider_output(cb_result)))
try:
results.startTest(self.testcase_post)
self.post_process(output)
@ -76,18 +89,18 @@ class Contract:
return request
def adjust_request_args(self, args):
def adjust_request_args(self, args: dict[str, Any]) -> dict[str, Any]:
return args
class ContractsManager:
contracts: Dict[str, Contract] = {}
contracts: dict[str, type[Contract]] = {}
def __init__(self, contracts):
def __init__(self, contracts: Iterable[type[Contract]]):
for contract in contracts:
self.contracts[contract.name] = contract
def tested_methods_from_spidercls(self, spidercls):
def tested_methods_from_spidercls(self, spidercls: type[Spider]) -> list[str]:
is_method = re.compile(r"^\s*@", re.MULTILINE).search
methods = []
for key, value in getmembers(spidercls):
@ -96,21 +109,25 @@ class ContractsManager:
return methods
def extract_contracts(self, method):
contracts = []
def extract_contracts(self, method: Callable) -> list[Contract]:
contracts: list[Contract] = []
assert method.__doc__ is not None
for line in method.__doc__.split("\n"):
line = line.strip()
if line.startswith("@"):
name, args = re.match(r"@(\w+)\s*(.*)", line).groups()
m = re.match(r"@(\w+)\s*(.*)", line)
if m is None:
continue
name, args = m.groups()
args = re.split(r"\s+", args)
contracts.append(self.contracts[name](method, *args))
return contracts
def from_spider(self, spider, results):
requests = []
def from_spider(self, spider: Spider, results: TestResult) -> list[Request | None]:
requests: list[Request | None] = []
for method in self.tested_methods_from_spidercls(type(spider)):
bound_method = spider.__getattribute__(method)
try:
@ -121,7 +138,7 @@ class ContractsManager:
return requests
def from_method(self, method, results):
def from_method(self, method: Callable, results: TestResult) -> Request | None:
contracts = self.extract_contracts(method)
if contracts:
request_cls = Request
@ -154,22 +171,26 @@ class ContractsManager:
self._clean_req(request, method, results)
return request
return None
def _clean_req(self, request, method, results):
def _clean_req(
self, request: Request, method: Callable, results: TestResult
) -> None:
"""stop the request from returning objects and records any errors"""
cb = request.callback
assert cb is not None
@wraps(cb)
def cb_wrapper(response, **cb_kwargs):
def cb_wrapper(response: Response, **cb_kwargs: Any) -> None:
try:
output = cb(response, **cb_kwargs)
output = list(iterate_spider_output(output))
output = list(cast(Iterable[Any], iterate_spider_output(output)))
except Exception:
case = _create_testcase(method, "callback")
results.addError(case, sys.exc_info())
def eb_wrapper(failure):
def eb_wrapper(failure: Failure) -> None:
case = _create_testcase(method, "errback")
exc_info = failure.type, failure.value, failure.getTracebackObject()
results.addError(case, exc_info)
@ -178,11 +199,11 @@ class ContractsManager:
request.errback = eb_wrapper
def _create_testcase(method, desc):
spider = method.__self__.name
def _create_testcase(method: Callable, desc: str) -> TestCase:
spider = method.__self__.name # type: ignore[attr-defined]
class ContractTestCase(TestCase):
def __str__(_self):
def __str__(_self) -> str:
return f"[{spider}] {method.__name__} ({desc})"
name = f"{spider}_{method.__name__}"

35
scrapy/contracts/default.py
View File

@ -1,4 +1,7 @@
from __future__ import annotations
import json
from typing import Any, Callable
from itemadapter import ItemAdapter, is_item
@ -15,7 +18,7 @@ class UrlContract(Contract):
name = "url"
def adjust_request_args(self, args):
def adjust_request_args(self, args: dict[str, Any]) -> dict[str, Any]:
args["url"] = self.args[0]
return args
@ -29,11 +32,25 @@ class CallbackKeywordArgumentsContract(Contract):
name = "cb_kwargs"
def adjust_request_args(self, args):
def adjust_request_args(self, args: dict[str, Any]) -> dict[str, Any]:
args["cb_kwargs"] = json.loads(" ".join(self.args))
return args
class MetadataContract(Contract):
"""Contract to set metadata arguments for the request.
The value should be JSON-encoded dictionary, e.g.:
@meta {"arg1": "some value"}
"""
name = "meta"
def adjust_request_args(self, args: dict[str, Any]) -> dict[str, Any]:
args["meta"] = json.loads(" ".join(self.args))
return args
class ReturnsContract(Contract):
"""Contract to check the output of a callback
@ -48,14 +65,14 @@ class ReturnsContract(Contract):
"""
name = "returns"
object_type_verifiers = {
object_type_verifiers: dict[str | None, Callable[[Any], bool]] = {
"request": lambda x: isinstance(x, Request),
"requests": lambda x: isinstance(x, Request),
"item": is_item,
"items": is_item,
}
def __init__(self, *args, **kwargs):
def __init__(self, *args: Any, **kwargs: Any):
super().__init__(*args, **kwargs)
if len(self.args) not in [1, 2, 3]:
@ -66,16 +83,16 @@ class ReturnsContract(Contract):
self.obj_type_verifier = self.object_type_verifiers[self.obj_name]
try:
self.min_bound = int(self.args[1])
self.min_bound: float = int(self.args[1])
except IndexError:
self.min_bound = 1
try:
self.max_bound = int(self.args[2])
self.max_bound: float = int(self.args[2])
except IndexError:
self.max_bound = float("inf")
def post_process(self, output):
def post_process(self, output: list[Any]) -> None:
occurrences = 0
for x in output:
if self.obj_type_verifier(x):
@ -85,7 +102,7 @@ class ReturnsContract(Contract):
if not assertion:
if self.min_bound == self.max_bound:
expected = self.min_bound
expected = str(self.min_bound)
else:
expected = f"{self.min_bound}..{self.max_bound}"
@ -101,7 +118,7 @@ class ScrapesContract(Contract):
name = "scrapes"
def post_process(self, output):
def post_process(self, output: list[Any]) -> None:
for x in output:
if is_item(x):
missing = [arg for arg in self.args if arg not in ItemAdapter(x)]

84
scrapy/core/downloader/__init__.py
View File

@ -1,8 +1,11 @@
from __future__ import annotations
import random
import warnings
from collections import deque
from datetime import datetime
from time import time
from typing import TYPE_CHECKING, Any, Deque, Dict, Set, Tuple, cast
from typing import TYPE_CHECKING, Any, TypeVar, cast
from twisted.internet import task
from twisted.internet.defer import Deferred
@ -10,28 +13,40 @@ from twisted.internet.defer import Deferred
from scrapy import Request, Spider, signals
from scrapy.core.downloader.handlers import DownloadHandlers
from scrapy.core.downloader.middleware import DownloaderMiddlewareManager
from scrapy.http import Response
from scrapy.exceptions import ScrapyDeprecationWarning
from scrapy.resolver import dnscache
from scrapy.settings import BaseSettings
from scrapy.signalmanager import SignalManager
from scrapy.utils.defer import mustbe_deferred
from scrapy.utils.httpobj import urlparse_cached
if TYPE_CHECKING:
from scrapy.crawler import Crawler
from scrapy.http import Response
from scrapy.settings import BaseSettings
_T = TypeVar("_T")
class Slot:
"""Downloader slot"""
def __init__(self, concurrency: int, delay: float, randomize_delay: bool):
def __init__(
self,
concurrency: int,
delay: float,
randomize_delay: bool,
*,
throttle: bool | None = None,
):
self.concurrency: int = concurrency
self.delay: float = delay
self.randomize_delay: bool = randomize_delay
self.throttle = throttle
self.active: Set[Request] = set()
self.queue: Deque[Tuple[Request, Deferred]] = deque()
self.transferring: Set[Request] = set()
self.active: set[Request] = set()
self.queue: deque[tuple[Request, Deferred[Response]]] = deque()
self.transferring: set[Request] = set()
self.lastseen: float = 0
self.latercall = None
@ -40,7 +55,7 @@ class Slot:
def download_delay(self) -> float:
if self.randomize_delay:
return random.uniform(0.5 * self.delay, 1.5 * self.delay)
return random.uniform(0.5 * self.delay, 1.5 * self.delay) # nosec
return self.delay
def close(self) -> None:
@ -52,13 +67,15 @@ class Slot:
return (
f"{cls_name}(concurrency={self.concurrency!r}, "
f"delay={self.delay:.2f}, "
f"randomize_delay={self.randomize_delay!r})"
f"randomize_delay={self.randomize_delay!r}, "
f"throttle={self.throttle!r})"
)
def __str__(self) -> str:
return (
f"<downloader.Slot concurrency={self.concurrency!r} "
f"delay={self.delay:.2f} randomize_delay={self.randomize_delay!r} "
f"throttle={self.throttle!r} "
f"len(active)={len(self.active)} len(queue)={len(self.queue)} "
f"len(transferring)={len(self.transferring)} "
f"lastseen={datetime.fromtimestamp(self.lastseen).isoformat()}>"
@ -67,7 +84,7 @@ class Slot:
def _get_concurrency_delay(
concurrency: int, spider: Spider, settings: BaseSettings
) -> Tuple[int, float]:
) -> tuple[int, float]:
delay: float = settings.getfloat("DOWNLOAD_DELAY")
if hasattr(spider, "download_delay"):
delay = spider.download_delay
@ -81,11 +98,11 @@ def _get_concurrency_delay(
class Downloader:
DOWNLOAD_SLOT = "download_slot"
def __init__(self, crawler: "Crawler"):
def __init__(self, crawler: Crawler):
self.settings: BaseSettings = crawler.settings
self.signals: SignalManager = crawler.signals
self.slots: Dict[str, Slot] = {}
self.active: Set[Request] = set()
self.slots: dict[str, Slot] = {}
self.active: set[Request] = set()
self.handlers: DownloadHandlers = DownloadHandlers(crawler)
self.total_concurrency: int = self.settings.getint("CONCURRENT_REQUESTS")
self.domain_concurrency: int = self.settings.getint(
@ -98,24 +115,26 @@ class Downloader:
)
self._slot_gc_loop: task.LoopingCall = task.LoopingCall(self._slot_gc)
self._slot_gc_loop.start(60)
self.per_slot_settings: Dict[str, Dict[str, Any]] = self.settings.getdict(
self.per_slot_settings: dict[str, dict[str, Any]] = self.settings.getdict(
"DOWNLOAD_SLOTS", {}
)
def fetch(self, request: Request, spider: Spider) -> Deferred:
def _deactivate(response: Response) -> Response:
def fetch(self, request: Request, spider: Spider) -> Deferred[Response | Request]:
def _deactivate(response: _T) -> _T:
self.active.remove(request)
return response
self.active.add(request)
dfd = self.middleware.download(self._enqueue_request, request, spider)
dfd: Deferred[Response | Request] = self.middleware.download(
self._enqueue_request, request, spider
)
return dfd.addBoth(_deactivate)
def needs_backout(self) -> bool:
return len(self.active) >= self.total_concurrency
def _get_slot(self, request: Request, spider: Spider) -> Tuple[str, Slot]:
key = self._get_slot_key(request, spider)
def _get_slot(self, request: Request, spider: Spider) -> tuple[str, Slot]:
key = self.get_slot_key(request)
if key not in self.slots:
slot_settings = self.per_slot_settings.get(key, {})
conc = (
@ -127,12 +146,13 @@ class Downloader:
slot_settings.get("delay", delay),
)
randomize_delay = slot_settings.get("randomize_delay", self.randomize_delay)
new_slot = Slot(conc, delay, randomize_delay)
throttle = slot_settings.get("throttle", None)
new_slot = Slot(conc, delay, randomize_delay, throttle=throttle)
self.slots[key] = new_slot
return key, self.slots[key]
def _get_slot_key(self, request: Request, spider: Spider) -> str:
def get_slot_key(self, request: Request) -> str:
if self.DOWNLOAD_SLOT in request.meta:
return cast(str, request.meta[self.DOWNLOAD_SLOT])
@ -142,7 +162,15 @@ class Downloader:
return key
def _enqueue_request(self, request: Request, spider: Spider) -> Deferred:
def _get_slot_key(self, request: Request, spider: Spider | None) -> str:
warnings.warn(
"Use of this protected method is deprecated. Consider using its corresponding public method get_slot_key() instead.",
ScrapyDeprecationWarning,
stacklevel=2,
)
return self.get_slot_key(request)
def _enqueue_request(self, request: Request, spider: Spider) -> Deferred[Response]:
key, slot = self._get_slot(request, spider)
request.meta[self.DOWNLOAD_SLOT] = key
@ -154,7 +182,7 @@ class Downloader:
self.signals.send_catch_log(
signal=signals.request_reached_downloader, request=request, spider=spider
)
deferred: Deferred = Deferred().addBoth(_deactivate)
deferred: Deferred[Response] = Deferred().addBoth(_deactivate)
slot.queue.append((request, deferred))
self._process_queue(spider, slot)
return deferred
@ -187,11 +215,15 @@ class Downloader:
self._process_queue(spider, slot)
break
def _download(self, slot: Slot, request: Request, spider: Spider) -> Deferred:
def _download(
self, slot: Slot, request: Request, spider: Spider
) -> Deferred[Response]:
# The order is very important for the following deferreds. Do not change!
# 1. Create the download deferred
dfd = mustbe_deferred(self.handlers.download_request, request, spider)
dfd: Deferred[Response] = mustbe_deferred(
self.handlers.download_request, request, spider
)
# 2. Notify response_downloaded listeners about the recent download
# before querying queue for next request
@ -212,7 +244,7 @@ class Downloader:
# middleware itself)
slot.transferring.add(request)
def finish_transferring(_: Any) -> Any:
def finish_transferring(_: _T) -> _T:
slot.transferring.remove(request)
self._process_queue(spider, slot)
self.signals.send_catch_log(

35
scrapy/core/downloader/contextfactory.py
View File

@ -1,5 +1,7 @@
from __future__ import annotations
import warnings
from typing import TYPE_CHECKING, Any, List, Optional
from typing import TYPE_CHECKING, Any
from OpenSSL import SSL
from twisted.internet._sslverify import _setAcceptableProtocols
@ -19,12 +21,17 @@ from scrapy.core.downloader.tls import (
ScrapyClientTLSOptions,
openssl_methods,
)
from scrapy.settings import BaseSettings
from scrapy.utils.misc import build_from_crawler, load_object
if TYPE_CHECKING:
from twisted.internet._sslverify import ClientTLSOptions
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy.crawler import Crawler
from scrapy.settings import BaseSettings
@implementer(IPolicyForHTTPS)
class ScrapyClientContextFactory(BrowserLikePolicyForHTTPS):
@ -42,7 +49,7 @@ class ScrapyClientContextFactory(BrowserLikePolicyForHTTPS):
self,
method: int = SSL.SSLv23_METHOD,
tls_verbose_logging: bool = False,
tls_ciphers: Optional[str] = None,
tls_ciphers: str | None = None,
*args: Any,
**kwargs: Any,
):
@ -62,11 +69,11 @@ class ScrapyClientContextFactory(BrowserLikePolicyForHTTPS):
method: int = SSL.SSLv23_METHOD,
*args: Any,
**kwargs: Any,
):
) -> Self:
tls_verbose_logging: bool = settings.getbool(
"DOWNLOADER_CLIENT_TLS_VERBOSE_LOGGING"
)
tls_ciphers: Optional[str] = settings["DOWNLOADER_CLIENT_TLS_CIPHERS"]
tls_ciphers: str | None = settings["DOWNLOADER_CLIENT_TLS_CIPHERS"]
return cls( # type: ignore[misc]
method=method,
tls_verbose_logging=tls_verbose_logging,
@ -97,11 +104,11 @@ class ScrapyClientContextFactory(BrowserLikePolicyForHTTPS):
# kept for old-style HTTP/1.0 downloader context twisted calls,
# e.g. connectSSL()
def getContext(self, hostname: Any = None, port: Any = None) -> SSL.Context:
ctx = self.getCertificateOptions().getContext()
ctx: SSL.Context = self.getCertificateOptions().getContext()
ctx.set_options(0x4) # OP_LEGACY_SERVER_CONNECT
return ctx
def creatorForNetloc(self, hostname: bytes, port: int) -> "ClientTLSOptions":
def creatorForNetloc(self, hostname: bytes, port: int) -> ClientTLSOptions:
return ScrapyClientTLSOptions(
hostname.decode("ascii"),
self.getContext(),
@ -128,7 +135,7 @@ class BrowserLikeContextFactory(ScrapyClientContextFactory):
``SSLv23_METHOD``) which allows TLS protocol negotiation.
"""
def creatorForNetloc(self, hostname: bytes, port: int) -> "ClientTLSOptions":
def creatorForNetloc(self, hostname: bytes, port: int) -> ClientTLSOptions:
# trustRoot set to platformTrust() will use the platform's root CAs.
#
# This means that a website like https://www.cacert.org will be rejected
@ -147,20 +154,22 @@ class AcceptableProtocolsContextFactory:
negotiation.
"""
def __init__(self, context_factory: Any, acceptable_protocols: List[bytes]):
def __init__(self, context_factory: Any, acceptable_protocols: list[bytes]):
verifyObject(IPolicyForHTTPS, context_factory)
self._wrapped_context_factory: Any = context_factory
self._acceptable_protocols: List[bytes] = acceptable_protocols
self._acceptable_protocols: list[bytes] = acceptable_protocols
def creatorForNetloc(self, hostname: bytes, port: int) -> "ClientTLSOptions":
options: "ClientTLSOptions" = self._wrapped_context_factory.creatorForNetloc(
def creatorForNetloc(self, hostname: bytes, port: int) -> ClientTLSOptions:
options: ClientTLSOptions = self._wrapped_context_factory.creatorForNetloc(
hostname, port
)
_setAcceptableProtocols(options._ctx, self._acceptable_protocols)
return options
def load_context_factory_from_settings(settings, crawler):
def load_context_factory_from_settings(
settings: BaseSettings, crawler: Crawler
) -> IPolicyForHTTPS:
ssl_method = openssl_methods[settings.get("DOWNLOADER_CLIENT_TLS_METHOD")]
context_factory_cls = load_object(settings["DOWNLOADER_CLIENTCONTEXTFACTORY"])
# try method-aware context factory

55
scrapy/core/downloader/handlers/__init__.py
View File

@ -1,10 +1,12 @@
"""Download handlers for different schemes"""
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any, Callable, Dict, Generator, Union, cast
from collections.abc import Callable
from typing import TYPE_CHECKING, Any, Protocol, cast
from twisted.internet import defer
from twisted.internet.defer import Deferred
from scrapy import Request, Spider, signals
from scrapy.exceptions import NotConfigured, NotSupported
@ -13,21 +15,38 @@ from scrapy.utils.misc import build_from_crawler, load_object
from scrapy.utils.python import without_none_values
if TYPE_CHECKING:
from collections.abc import Generator
from twisted.internet.defer import Deferred
from scrapy.crawler import Crawler
from scrapy.http import Response
logger = logging.getLogger(__name__)
class DownloadHandlerProtocol(Protocol):
def download_request(
self, request: Request, spider: Spider
) -> Deferred[Response]: ...
class DownloadHandlers:
def __init__(self, crawler: "Crawler"):
self._crawler: "Crawler" = crawler
self._schemes: Dict[
str, Union[str, Callable]
] = {} # stores acceptable schemes on instancing
self._handlers: Dict[str, Any] = {} # stores instanced handlers for schemes
self._notconfigured: Dict[str, str] = {} # remembers failed handlers
handlers: Dict[str, Union[str, Callable]] = without_none_values(
crawler.settings.getwithbase("DOWNLOAD_HANDLERS")
def __init__(self, crawler: Crawler):
self._crawler: Crawler = crawler
self._schemes: dict[str, str | Callable[..., Any]] = (
{}
) # stores acceptable schemes on instancing
self._handlers: dict[str, DownloadHandlerProtocol] = (
{}
) # stores instanced handlers for schemes
self._notconfigured: dict[str, str] = {} # remembers failed handlers
handlers: dict[str, str | Callable[..., Any]] = without_none_values(
cast(
"dict[str, str | Callable[..., Any]]",
crawler.settings.getwithbase("DOWNLOAD_HANDLERS"),
)
)
for scheme, clspath in handlers.items():
self._schemes[scheme] = clspath
@ -35,7 +54,7 @@ class DownloadHandlers:
crawler.signals.connect(self._close, signals.engine_stopped)
def _get_handler(self, scheme: str) -> Any:
def _get_handler(self, scheme: str) -> DownloadHandlerProtocol | None:
"""Lazy-load the downloadhandler for a scheme
only on the first request for that scheme.
"""
@ -49,10 +68,12 @@ class DownloadHandlers:
return self._load_handler(scheme)
def _load_handler(self, scheme: str, skip_lazy: bool = False) -> Any:
def _load_handler(
self, scheme: str, skip_lazy: bool = False
) -> DownloadHandlerProtocol | None:
path = self._schemes[scheme]
try:
dhcls = load_object(path)
dhcls: type[DownloadHandlerProtocol] = load_object(path)
if skip_lazy and getattr(dhcls, "lazy", True):
return None
dh = build_from_crawler(
@ -75,17 +96,17 @@ class DownloadHandlers:
self._handlers[scheme] = dh
return dh
def download_request(self, request: Request, spider: Spider) -> Deferred:
def download_request(self, request: Request, spider: Spider) -> Deferred[Response]:
scheme = urlparse_cached(request).scheme
handler = self._get_handler(scheme)
if not handler:
raise NotSupported(
f"Unsupported URL scheme '{scheme}': {self._notconfigured[scheme]}"
)
return cast(Deferred, handler.download_request(request, spider))
return handler.download_request(request, spider)
@defer.inlineCallbacks
def _close(self, *_a: Any, **_kw: Any) -> Generator[Deferred, Any, None]:
def _close(self, *_a: Any, **_kw: Any) -> Generator[Deferred[Any], Any, None]:
for dh in self._handlers.values():
if hasattr(dh, "close"):
yield dh.close()

10
scrapy/core/downloader/handlers/datauri.py
View File

@ -1,12 +1,16 @@
from typing import Any, Dict
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from w3lib.url import parse_data_uri
from scrapy import Request, Spider
from scrapy.http import Response, TextResponse
from scrapy.responsetypes import responsetypes
from scrapy.utils.decorators import defers
if TYPE_CHECKING:
from scrapy import Request, Spider
class DataURIDownloadHandler:
lazy = False
@ -16,7 +20,7 @@ class DataURIDownloadHandler:
uri = parse_data_uri(request.url)
respcls = responsetypes.from_mimetype(uri.media_type)
resp_kwargs: Dict[str, Any] = {}
resp_kwargs: dict[str, Any] = {}
if issubclass(respcls, TextResponse) and uri.media_type.split("/")[0] == "text":
charset = uri.media_type_parameters.get("charset")
resp_kwargs["encoding"] = charset

9
scrapy/core/downloader/handlers/file.py
View File

@ -1,16 +1,23 @@
from __future__ import annotations
from pathlib import Path
from typing import TYPE_CHECKING
from w3lib.url import file_uri_to_path
from scrapy.responsetypes import responsetypes
from scrapy.utils.decorators import defers
if TYPE_CHECKING:
from scrapy import Request, Spider
from scrapy.http import Response
class FileDownloadHandler:
lazy = False
@defers
def download_request(self, request, spider):
def download_request(self, request: Request, spider: Spider) -> Response:
filepath = file_uri_to_path(request.url)
body = Path(filepath).read_bytes()
respcls = responsetypes.from_args(filename=filepath, body=body)

64
scrapy/core/downloader/handlers/ftp.py
View File

@ -28,8 +28,11 @@ In case of status 200 request, response.headers will come with two keys:
'Size' - with size of the downloaded data
"""
from __future__ import annotations
import re
from io import BytesIO
from typing import TYPE_CHECKING, Any, BinaryIO
from urllib.parse import unquote
from twisted.internet.protocol import ClientCreator, Protocol
@ -40,22 +43,33 @@ from scrapy.responsetypes import responsetypes
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.python import to_bytes
if TYPE_CHECKING:
from twisted.internet.defer import Deferred
from twisted.python.failure import Failure
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.settings import BaseSettings
class ReceivedDataProtocol(Protocol):
def __init__(self, filename=None):
self.__filename = filename
self.body = open(filename, "wb") if filename else BytesIO()
self.size = 0
def __init__(self, filename: str | None = None):
self.__filename: str | None = filename
self.body: BinaryIO = open(filename, "wb") if filename else BytesIO()
self.size: int = 0
def dataReceived(self, data):
def dataReceived(self, data: bytes) -> None:
self.body.write(data)
self.size += len(data)
@property
def filename(self):
def filename(self) -> str | None:
return self.__filename
def close(self):
def close(self) -> None:
self.body.close() if self.filename else self.body.seek(0)
@ -65,21 +79,21 @@ _CODE_RE = re.compile(r"\d+")
class FTPDownloadHandler:
lazy = False
CODE_MAPPING = {
CODE_MAPPING: dict[str, int] = {
"550": 404,
"default": 503,
}
def __init__(self, settings):
def __init__(self, settings: BaseSettings):
self.default_user = settings["FTP_USER"]
self.default_password = settings["FTP_PASSWORD"]
self.passive_mode = settings["FTP_PASSIVE_MODE"]
@classmethod
def from_crawler(cls, crawler):
def from_crawler(cls, crawler: Crawler) -> Self:
return cls(crawler.settings)
def download_request(self, request, spider):
def download_request(self, request: Request, spider: Spider) -> Deferred[Response]:
from twisted.internet import reactor
parsed_url = urlparse_cached(request)
@ -91,28 +105,33 @@ class FTPDownloadHandler:
creator = ClientCreator(
reactor, FTPClient, user, password, passive=passive_mode
)
dfd = creator.connectTCP(parsed_url.hostname, parsed_url.port or 21)
dfd: Deferred[FTPClient] = creator.connectTCP(
parsed_url.hostname, parsed_url.port or 21
)
return dfd.addCallback(self.gotClient, request, unquote(parsed_url.path))
def gotClient(self, client, request, filepath):
def gotClient(
self, client: FTPClient, request: Request, filepath: str
) -> Deferred[Response]:
self.client = client
protocol = ReceivedDataProtocol(request.meta.get("ftp_local_filename"))
return client.retrieveFile(filepath, protocol).addCallbacks(
callback=self._build_response,
callbackArgs=(request, protocol),
errback=self._failed,
errbackArgs=(request,),
)
d = client.retrieveFile(filepath, protocol)
d.addCallback(self._build_response, request, protocol)
d.addErrback(self._failed, request)
return d
def _build_response(self, result, request, protocol):
def _build_response(
self, result: Any, request: Request, protocol: ReceivedDataProtocol
) -> Response:
self.result = result
protocol.close()
headers = {"local filename": protocol.filename or "", "size": protocol.size}
body = to_bytes(protocol.filename or protocol.body.read())
respcls = responsetypes.from_args(url=request.url, body=body)
return respcls(url=request.url, status=200, body=body, headers=headers)
# hints for Headers-related types may need to be fixed to not use AnyStr
return respcls(url=request.url, status=200, body=body, headers=headers) # type: ignore[arg-type]
def _failed(self, result, request):
def _failed(self, result: Failure, request: Request) -> Response:
message = result.getErrorMessage()
if result.type == CommandFailed:
m = _CODE_RE.search(message)
@ -122,4 +141,5 @@ class FTPDownloadHandler:
return Response(
url=request.url, status=httpcode, body=to_bytes(message)
)
assert result.type
raise result.type(result.value)

40
scrapy/core/downloader/handlers/http10.py
View File

@ -1,31 +1,51 @@
"""Download handlers for http and https schemes
"""
"""Download handlers for http and https schemes"""
from __future__ import annotations
from typing import TYPE_CHECKING
from scrapy.utils.misc import build_from_crawler, load_object
from scrapy.utils.python import to_unicode
if TYPE_CHECKING:
from twisted.internet.defer import Deferred
from twisted.internet.interfaces import IConnector
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Request, Spider
from scrapy.core.downloader.contextfactory import ScrapyClientContextFactory
from scrapy.core.downloader.webclient import ScrapyHTTPClientFactory
from scrapy.crawler import Crawler
from scrapy.http import Response
from scrapy.settings import BaseSettings
class HTTP10DownloadHandler:
lazy = False
def __init__(self, settings, crawler=None):
self.HTTPClientFactory = load_object(settings["DOWNLOADER_HTTPCLIENTFACTORY"])
self.ClientContextFactory = load_object(
def __init__(self, settings: BaseSettings, crawler: Crawler):
self.HTTPClientFactory: type[ScrapyHTTPClientFactory] = load_object(
settings["DOWNLOADER_HTTPCLIENTFACTORY"]
)
self.ClientContextFactory: type[ScrapyClientContextFactory] = load_object(
settings["DOWNLOADER_CLIENTCONTEXTFACTORY"]
)
self._settings = settings
self._crawler = crawler
self._settings: BaseSettings = settings
self._crawler: Crawler = crawler
@classmethod
def from_crawler(cls, crawler):
def from_crawler(cls, crawler: Crawler) -> Self:
return cls(crawler.settings, crawler)
def download_request(self, request, spider):
def download_request(self, request: Request, spider: Spider) -> Deferred[Response]:
"""Return a deferred for the HTTP download"""
factory = self.HTTPClientFactory(request)
self._connect(factory)
return factory.deferred
def _connect(self, factory):
def _connect(self, factory: ScrapyHTTPClientFactory) -> IConnector:
from twisted.internet import reactor
host, port = to_unicode(factory.host), factory.port

311
scrapy/core/downloader/handlers/http11.py
View File

@ -1,65 +1,90 @@
"""Download handlers for http and https schemes"""
from __future__ import annotations
import ipaddress
import logging
import re
from contextlib import suppress
from io import BytesIO
from time import time
from typing import TYPE_CHECKING, Any, TypedDict, TypeVar
from urllib.parse import urldefrag, urlunparse
from twisted.internet import defer, protocol, ssl
from twisted.internet import ssl
from twisted.internet.defer import CancelledError, Deferred, succeed
from twisted.internet.endpoints import TCP4ClientEndpoint
from twisted.internet.error import TimeoutError
from twisted.internet.protocol import Factory, Protocol, connectionDone
from twisted.python.failure import Failure
from twisted.web.client import (
URI,
Agent,
HTTPConnectionPool,
ResponseDone,
ResponseFailed,
)
from twisted.web.client import URI, Agent, HTTPConnectionPool
from twisted.web.client import Response as TxResponse
from twisted.web.client import ResponseDone, ResponseFailed
from twisted.web.http import PotentialDataLoss, _DataLoss
from twisted.web.http_headers import Headers as TxHeaders
from twisted.web.iweb import UNKNOWN_LENGTH, IBodyProducer
from twisted.web.iweb import UNKNOWN_LENGTH, IBodyProducer, IPolicyForHTTPS
from zope.interface import implementer
from scrapy import signals
from scrapy import Request, Spider, signals
from scrapy.core.downloader.contextfactory import load_context_factory_from_settings
from scrapy.core.downloader.webclient import _parse
from scrapy.exceptions import StopDownload
from scrapy.http import Headers
from scrapy.http import Headers, Response
from scrapy.responsetypes import responsetypes
from scrapy.utils.python import to_bytes, to_unicode
if TYPE_CHECKING:
from twisted.internet.base import ReactorBase
from twisted.internet.interfaces import IConsumer
# typing.NotRequired and typing.Self require Python 3.11
from typing_extensions import NotRequired, Self
from scrapy.crawler import Crawler
from scrapy.settings import BaseSettings
logger = logging.getLogger(__name__)
_T = TypeVar("_T")
class _ResultT(TypedDict):
txresponse: TxResponse
body: bytes
flags: list[str] | None
certificate: ssl.Certificate | None
ip_address: ipaddress.IPv4Address | ipaddress.IPv6Address | None
failure: NotRequired[Failure | None]
class HTTP11DownloadHandler:
lazy = False
def __init__(self, settings, crawler=None):
def __init__(self, settings: BaseSettings, crawler: Crawler):
self._crawler = crawler
from twisted.internet import reactor
self._pool = HTTPConnectionPool(reactor, persistent=True)
self._pool: HTTPConnectionPool = HTTPConnectionPool(reactor, persistent=True)
self._pool.maxPersistentPerHost = settings.getint(
"CONCURRENT_REQUESTS_PER_DOMAIN"
)
self._pool._factory.noisy = False
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")
self._disconnect_timeout = 1
self._contextFactory: IPolicyForHTTPS = load_context_factory_from_settings(
settings, crawler
)
self._default_maxsize: int = settings.getint("DOWNLOAD_MAXSIZE")
self._default_warnsize: int = settings.getint("DOWNLOAD_WARNSIZE")
self._fail_on_dataloss: bool = settings.getbool("DOWNLOAD_FAIL_ON_DATALOSS")
self._disconnect_timeout: int = 1
@classmethod
def from_crawler(cls, crawler):
def from_crawler(cls, crawler: Crawler) -> Self:
return cls(crawler.settings, crawler)
def download_request(self, request, spider):
def download_request(self, request: Request, spider: Spider) -> Deferred[Response]:
"""Return a deferred for the HTTP download"""
agent = ScrapyAgent(
contextFactory=self._contextFactory,
@ -71,10 +96,10 @@ class HTTP11DownloadHandler:
)
return agent.download_request(request)
def close(self):
def close(self) -> Deferred[None]:
from twisted.internet import reactor
d = self._pool.closeCachedConnections()
d: Deferred[None] = self._pool.closeCachedConnections()
# closeCachedConnections will hang on network or server issues, so
# we'll manually timeout the deferred.
#
@ -85,7 +110,7 @@ class HTTP11DownloadHandler:
# issue a callback after `_disconnect_timeout` seconds.
delayed_call = reactor.callLater(self._disconnect_timeout, d.callback, [])
def cancel_delayed_call(result):
def cancel_delayed_call(result: _T) -> _T:
if delayed_call.active():
delayed_call.cancel()
return result
@ -115,39 +140,41 @@ class TunnelingTCP4ClientEndpoint(TCP4ClientEndpoint):
def __init__(
self,
reactor,
host,
port,
proxyConf,
contextFactory,
timeout=30,
bindAddress=None,
reactor: ReactorBase,
host: str,
port: int,
proxyConf: tuple[str, int, bytes | None],
contextFactory: IPolicyForHTTPS,
timeout: float = 30,
bindAddress: tuple[str, int] | None = None,
):
proxyHost, proxyPort, self._proxyAuthHeader = proxyConf
super().__init__(reactor, proxyHost, proxyPort, timeout, bindAddress)
self._tunnelReadyDeferred = defer.Deferred()
self._tunneledHost = host
self._tunneledPort = port
self._contextFactory = contextFactory
self._connectBuffer = bytearray()
self._tunnelReadyDeferred: Deferred[Protocol] = Deferred()
self._tunneledHost: str = host
self._tunneledPort: int = port
self._contextFactory: IPolicyForHTTPS = contextFactory
self._connectBuffer: bytearray = bytearray()
def requestTunnel(self, protocol):
def requestTunnel(self, protocol: Protocol) -> Protocol:
"""Asks the proxy to open a tunnel."""
assert protocol.transport
tunnelReq = tunnel_request_data(
self._tunneledHost, self._tunneledPort, self._proxyAuthHeader
)
protocol.transport.write(tunnelReq)
self._protocolDataReceived = protocol.dataReceived
protocol.dataReceived = self.processProxyResponse
protocol.dataReceived = self.processProxyResponse # type: ignore[method-assign]
self._protocol = protocol
return protocol
def processProxyResponse(self, rcvd_bytes):
def processProxyResponse(self, data: bytes) -> None:
"""Processes the response from the proxy. If the tunnel is successfully
created, notifies the client that we are ready to send requests. If not
raises a TunnelError.
"""
self._connectBuffer += rcvd_bytes
assert self._protocol.transport
self._connectBuffer += data
# make sure that enough (all) bytes are consumed
# and that we've got all HTTP headers (ending with a blank line)
# from the proxy so that we don't send those bytes to the TLS layer
@ -155,23 +182,24 @@ class TunnelingTCP4ClientEndpoint(TCP4ClientEndpoint):
# see https://github.com/scrapy/scrapy/issues/2491
if b"\r\n\r\n" not in self._connectBuffer:
return
self._protocol.dataReceived = self._protocolDataReceived
self._protocol.dataReceived = self._protocolDataReceived # type: ignore[method-assign]
respm = TunnelingTCP4ClientEndpoint._responseMatcher.match(self._connectBuffer)
if respm and int(respm.group("status")) == 200:
# set proper Server Name Indication extension
sslOptions = self._contextFactory.creatorForNetloc(
sslOptions = self._contextFactory.creatorForNetloc( # type: ignore[call-arg,misc]
self._tunneledHost, self._tunneledPort
)
self._protocol.transport.startTLS(sslOptions, self._protocolFactory)
self._tunnelReadyDeferred.callback(self._protocol)
else:
extra: Any
if respm:
extra = {
"status": int(respm.group("status")),
"reason": respm.group("reason").strip(),
}
else:
extra = rcvd_bytes[: self._truncatedLength]
extra = data[: self._truncatedLength]
self._tunnelReadyDeferred.errback(
TunnelError(
"Could not open CONNECT tunnel with proxy "
@ -179,11 +207,11 @@ class TunnelingTCP4ClientEndpoint(TCP4ClientEndpoint):
)
)
def connectFailed(self, reason):
def connectFailed(self, reason: Failure) -> None:
"""Propagates the errback to the appropriate deferred."""
self._tunnelReadyDeferred.errback(reason)
def connect(self, protocolFactory):
def connect(self, protocolFactory: Factory) -> Deferred[Protocol]:
self._protocolFactory = protocolFactory
connectDeferred = super().connect(protocolFactory)
connectDeferred.addCallback(self.requestTunnel)
@ -191,7 +219,9 @@ class TunnelingTCP4ClientEndpoint(TCP4ClientEndpoint):
return self._tunnelReadyDeferred
def tunnel_request_data(host, port, proxy_auth_header=None):
def tunnel_request_data(
host: str, port: int, proxy_auth_header: bytes | None = None
) -> bytes:
r"""
Return binary content of a CONNECT request.
@ -222,18 +252,19 @@ class TunnelingAgent(Agent):
def __init__(
self,
reactor,
proxyConf,
contextFactory=None,
connectTimeout=None,
bindAddress=None,
pool=None,
*,
reactor: ReactorBase,
proxyConf: tuple[str, int, bytes | None],
contextFactory: IPolicyForHTTPS,
connectTimeout: float | None = None,
bindAddress: bytes | None = None,
pool: HTTPConnectionPool | None = None,
):
super().__init__(reactor, contextFactory, connectTimeout, bindAddress, pool)
self._proxyConf = proxyConf
self._contextFactory = contextFactory
self._proxyConf: tuple[str, int, bytes | None] = proxyConf
self._contextFactory: IPolicyForHTTPS = contextFactory
def _getEndpoint(self, uri):
def _getEndpoint(self, uri: URI) -> TunnelingTCP4ClientEndpoint:
return TunnelingTCP4ClientEndpoint(
reactor=self._reactor,
host=uri.host,
@ -245,8 +276,15 @@ class TunnelingAgent(Agent):
)
def _requestWithEndpoint(
self, key, endpoint, method, parsedURI, headers, bodyProducer, requestPath
):
self,
key: Any,
endpoint: TCP4ClientEndpoint,
method: bytes,
parsedURI: bytes,
headers: TxHeaders | None,
bodyProducer: IBodyProducer | None,
requestPath: bytes,
) -> Deferred[TxResponse]:
# proxy host and port are required for HTTP pool `key`
# otherwise, same remote host connection request could reuse
# a cached tunneled connection to a different proxy
@ -264,7 +302,12 @@ class TunnelingAgent(Agent):
class ScrapyProxyAgent(Agent):
def __init__(
self, reactor, proxyURI, connectTimeout=None, bindAddress=None, pool=None
self,
reactor: ReactorBase,
proxyURI: bytes,
connectTimeout: float | None = None,
bindAddress: bytes | None = None,
pool: HTTPConnectionPool | None = None,
):
super().__init__(
reactor=reactor,
@ -272,9 +315,15 @@ class ScrapyProxyAgent(Agent):
bindAddress=bindAddress,
pool=pool,
)
self._proxyURI = URI.fromBytes(proxyURI)
self._proxyURI: URI = URI.fromBytes(proxyURI)
def request(self, method, uri, headers=None, bodyProducer=None):
def request(
self,
method: bytes,
uri: bytes,
headers: TxHeaders | None = None,
bodyProducer: IBodyProducer | None = None,
) -> Deferred[TxResponse]:
"""
Issue a new request via the configured proxy.
"""
@ -298,26 +347,27 @@ class ScrapyAgent:
def __init__(
self,
contextFactory=None,
connectTimeout=10,
bindAddress=None,
pool=None,
maxsize=0,
warnsize=0,
fail_on_dataloss=True,
crawler=None,
*,
contextFactory: IPolicyForHTTPS,
connectTimeout: float = 10,
bindAddress: bytes | None = None,
pool: HTTPConnectionPool | None = None,
maxsize: int = 0,
warnsize: int = 0,
fail_on_dataloss: bool = True,
crawler: Crawler,
):
self._contextFactory = contextFactory
self._connectTimeout = connectTimeout
self._bindAddress = bindAddress
self._pool = pool
self._maxsize = maxsize
self._warnsize = warnsize
self._fail_on_dataloss = fail_on_dataloss
self._txresponse = None
self._crawler = crawler
self._contextFactory: IPolicyForHTTPS = contextFactory
self._connectTimeout: float = connectTimeout
self._bindAddress: bytes | None = bindAddress
self._pool: HTTPConnectionPool | None = pool
self._maxsize: int = maxsize
self._warnsize: int = warnsize
self._fail_on_dataloss: bool = fail_on_dataloss
self._txresponse: TxResponse | None = None
self._crawler: Crawler = crawler
def _get_agent(self, request, timeout):
def _get_agent(self, request: Request, timeout: float) -> Agent:
from twisted.internet import reactor
bindaddress = request.meta.get("bindaddress") or self._bindAddress
@ -325,10 +375,10 @@ class ScrapyAgent:
if proxy:
proxyScheme, proxyNetloc, proxyHost, proxyPort, proxyParams = _parse(proxy)
scheme = _parse(request.url)[0]
proxyHost = to_unicode(proxyHost)
proxyHost_str = to_unicode(proxyHost)
if scheme == b"https":
proxyAuth = request.headers.get(b"Proxy-Authorization", None)
proxyConf = (proxyHost, proxyPort, proxyAuth)
proxyConf = (proxyHost_str, proxyPort, proxyAuth)
return self._TunnelingAgent(
reactor=reactor,
proxyConf=proxyConf,
@ -338,7 +388,9 @@ class ScrapyAgent:
pool=self._pool,
)
proxyScheme = proxyScheme or b"http"
proxyURI = urlunparse((proxyScheme, proxyNetloc, proxyParams, "", "", ""))
proxyURI = urlunparse(
(proxyScheme, proxyNetloc, proxyParams, b"", b"", b"")
)
return self._ProxyAgent(
reactor=reactor,
proxyURI=to_bytes(proxyURI, encoding="ascii"),
@ -355,7 +407,7 @@ class ScrapyAgent:
pool=self._pool,
)
def download_request(self, request):
def download_request(self, request: Request) -> Deferred[Response]:
from twisted.internet import reactor
timeout = request.meta.get("download_timeout") or self._connectTimeout
@ -372,20 +424,20 @@ class ScrapyAgent:
else:
bodyproducer = None
start_time = time()
d = agent.request(
d: Deferred[TxResponse] = agent.request(
method, to_bytes(url, encoding="ascii"), headers, bodyproducer
)
# set download latency
d.addCallback(self._cb_latency, request, start_time)
# response body is ready to be consumed
d.addCallback(self._cb_bodyready, request)
d.addCallback(self._cb_bodydone, request, url)
d2: Deferred[_ResultT] = d.addCallback(self._cb_bodyready, request)
d3: Deferred[Response] = d2.addCallback(self._cb_bodydone, request, url)
# check download timeout
self._timeout_cl = reactor.callLater(timeout, d.cancel)
d.addBoth(self._cb_timeout, request, url, timeout)
return d
self._timeout_cl = reactor.callLater(timeout, d3.cancel)
d3.addBoth(self._cb_timeout, request, url, timeout)
return d3
def _cb_timeout(self, result, request, url, timeout):
def _cb_timeout(self, result: _T, request: Request, url: str, timeout: float) -> _T:
if self._timeout_cl.active():
self._timeout_cl.cancel()
return result
@ -396,19 +448,21 @@ class ScrapyAgent:
raise TimeoutError(f"Getting {url} took longer than {timeout} seconds.")
def _cb_latency(self, result, request, start_time):
def _cb_latency(self, result: _T, request: Request, start_time: float) -> _T:
request.meta["download_latency"] = time() - start_time
return result
@staticmethod
def _headers_from_twisted_response(response):
def _headers_from_twisted_response(response: TxResponse) -> Headers:
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):
def _cb_bodyready(
self, txresponse: TxResponse, request: Request
) -> _ResultT | Deferred[_ResultT]:
headers_received_result = self._crawler.signals.send_catch_log(
signal=signals.headers_received,
headers=self._headers_from_twisted_response(txresponse),
@ -464,7 +518,7 @@ class ScrapyAgent:
logger.warning(warning_msg, warning_args)
txresponse._transport.loseConnection()
raise defer.CancelledError(warning_msg % warning_args)
raise CancelledError(warning_msg % warning_args)
if warnsize and expected_size > warnsize:
logger.warning(
@ -473,11 +527,11 @@ class ScrapyAgent:
{"size": expected_size, "warnsize": warnsize, "request": request},
)
def _cancel(_):
def _cancel(_: Any) -> None:
# Abort connection immediately.
txresponse._transport._producer.abortConnection()
d = defer.Deferred(_cancel)
d: Deferred[_ResultT] = Deferred(_cancel)
txresponse.deliverBody(
_ResponseReader(
finished=d,
@ -495,7 +549,9 @@ class ScrapyAgent:
return d
def _cb_bodydone(self, result, request, url):
def _cb_bodydone(
self, result: _ResultT, request: Request, url: str
) -> Response | Failure:
headers = self._headers_from_twisted_response(result["txresponse"])
respcls = responsetypes.from_args(headers=headers, url=url, body=result["body"])
try:
@ -514,6 +570,7 @@ class ScrapyAgent:
protocol=protocol,
)
if result.get("failure"):
assert result["failure"]
result["failure"].value.response = response
return result["failure"]
return response
@ -521,47 +578,49 @@ class ScrapyAgent:
@implementer(IBodyProducer)
class _RequestBodyProducer:
def __init__(self, body):
def __init__(self, body: bytes):
self.body = body
self.length = len(body)
def startProducing(self, consumer):
def startProducing(self, consumer: IConsumer) -> Deferred[None]:
consumer.write(self.body)
return defer.succeed(None)
return succeed(None)
def pauseProducing(self):
def pauseProducing(self) -> None:
pass
def stopProducing(self):
def stopProducing(self) -> None:
pass
class _ResponseReader(protocol.Protocol):
class _ResponseReader(Protocol):
def __init__(
self,
finished,
txresponse,
request,
maxsize,
warnsize,
fail_on_dataloss,
crawler,
finished: Deferred[_ResultT],
txresponse: TxResponse,
request: Request,
maxsize: int,
warnsize: int,
fail_on_dataloss: bool,
crawler: Crawler,
):
self._finished = finished
self._txresponse = txresponse
self._request = request
self._bodybuf = BytesIO()
self._maxsize = maxsize
self._warnsize = warnsize
self._fail_on_dataloss = fail_on_dataloss
self._fail_on_dataloss_warned = False
self._reached_warnsize = False
self._bytes_received = 0
self._certificate = None
self._ip_address = None
self._crawler = crawler
self._finished: Deferred[_ResultT] = finished
self._txresponse: TxResponse = txresponse
self._request: Request = request
self._bodybuf: BytesIO = BytesIO()
self._maxsize: int = maxsize
self._warnsize: int = warnsize
self._fail_on_dataloss: bool = fail_on_dataloss
self._fail_on_dataloss_warned: bool = False
self._reached_warnsize: bool = False
self._bytes_received: int = 0
self._certificate: ssl.Certificate | None = None
self._ip_address: ipaddress.IPv4Address | ipaddress.IPv6Address | None = None
self._crawler: Crawler = crawler
def _finish_response(self, flags=None, failure=None):
def _finish_response(
self, flags: list[str] | None = None, failure: Failure | None = None
) -> None:
self._finished.callback(
{
"txresponse": self._txresponse,
@ -573,7 +632,8 @@ class _ResponseReader(protocol.Protocol):
}
)
def connectionMade(self):
def connectionMade(self) -> None:
assert self.transport
if self._certificate is None:
with suppress(AttributeError):
self._certificate = ssl.Certificate(
@ -585,11 +645,12 @@ class _ResponseReader(protocol.Protocol):
self.transport._producer.getPeer().host
)
def dataReceived(self, bodyBytes):
def dataReceived(self, bodyBytes: bytes) -> None:
# This maybe called several times after cancel was called with buffered data.
if self._finished.called:
return
assert self.transport
self._bodybuf.write(bodyBytes)
self._bytes_received += len(bodyBytes)
@ -636,7 +697,7 @@ class _ResponseReader(protocol.Protocol):
{"warnsize": self._warnsize, "request": self._request},
)
def connectionLost(self, reason):
def connectionLost(self, reason: Failure = connectionDone) -> None:
if self._finished.called:
return

43
scrapy/core/downloader/handlers/http2.py
View File

@ -1,28 +1,33 @@
from __future__ import annotations
from time import time
from typing import Optional, Type, TypeVar
from typing import TYPE_CHECKING
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"
)
if TYPE_CHECKING:
from twisted.internet.base import DelayedCall
from twisted.internet.defer import Deferred
from twisted.web.iweb import IPolicyForHTTPS
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy.crawler import Crawler
from scrapy.http import Request, Response
from scrapy.settings import Settings
from scrapy.spiders import Spider
class H2DownloadHandler:
def __init__(self, settings: Settings, crawler: Optional[Crawler] = None):
def __init__(self, settings: Settings, crawler: Crawler):
self._crawler = crawler
from twisted.internet import reactor
@ -31,12 +36,10 @@ class H2DownloadHandler:
self._context_factory = load_context_factory_from_settings(settings, crawler)
@classmethod
def from_crawler(
cls: Type[H2DownloadHandlerOrSubclass], crawler: Crawler
) -> H2DownloadHandlerOrSubclass:
def from_crawler(cls, crawler: Crawler) -> Self:
return cls(crawler.settings, crawler)
def download_request(self, request: Request, spider: Spider) -> Deferred:
def download_request(self, request: Request, spider: Spider) -> Deferred[Response]:
agent = ScrapyH2Agent(
context_factory=self._context_factory,
pool=self._pool,
@ -54,11 +57,11 @@ class ScrapyH2Agent:
def __init__(
self,
context_factory,
context_factory: IPolicyForHTTPS,
pool: H2ConnectionPool,
connect_timeout: int = 10,
bind_address: Optional[bytes] = None,
crawler: Optional[Crawler] = None,
bind_address: bytes | None = None,
crawler: Crawler | None = None,
) -> None:
self._context_factory = context_factory
self._connect_timeout = connect_timeout
@ -66,7 +69,7 @@ class ScrapyH2Agent:
self._pool = pool
self._crawler = crawler
def _get_agent(self, request: Request, timeout: Optional[float]) -> H2Agent:
def _get_agent(self, request: Request, timeout: float | None) -> H2Agent:
from twisted.internet import reactor
bind_address = request.meta.get("bindaddress") or self._bind_address
@ -97,7 +100,7 @@ class ScrapyH2Agent:
pool=self._pool,
)
def download_request(self, request: Request, spider: Spider) -> Deferred:
def download_request(self, request: Request, spider: Spider) -> Deferred[Response]:
from twisted.internet import reactor
timeout = request.meta.get("download_timeout") or self._connect_timeout

39
scrapy/core/downloader/handlers/s3.py
View File

@ -1,21 +1,36 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from scrapy.core.downloader.handlers.http import HTTPDownloadHandler
from scrapy.exceptions import NotConfigured
from scrapy.utils.boto import is_botocore_available
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.misc import build_from_crawler
if TYPE_CHECKING:
from twisted.internet.defer import Deferred
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.http import Response
from scrapy.settings import BaseSettings
class S3DownloadHandler:
def __init__(
self,
settings,
settings: BaseSettings,
*,
crawler=None,
aws_access_key_id=None,
aws_secret_access_key=None,
aws_session_token=None,
httpdownloadhandler=HTTPDownloadHandler,
**kw,
crawler: Crawler,
aws_access_key_id: str | None = None,
aws_secret_access_key: str | None = None,
aws_session_token: str | None = None,
httpdownloadhandler: type[HTTPDownloadHandler] = HTTPDownloadHandler,
**kw: Any,
):
if not is_botocore_available():
raise NotConfigured("missing botocore library")
@ -43,8 +58,11 @@ class S3DownloadHandler:
if kw:
raise TypeError(f"Unexpected keyword arguments: {kw}")
if not self.anon:
assert aws_access_key_id is not None
assert aws_secret_access_key is not None
SignerCls = botocore.auth.AUTH_TYPE_MAPS["s3"]
self._signer = SignerCls(
# botocore.auth.BaseSigner doesn't have an __init__() with args, only subclasses do
self._signer = SignerCls( # type: ignore[call-arg]
botocore.credentials.Credentials(
aws_access_key_id, aws_secret_access_key, aws_session_token
)
@ -57,10 +75,10 @@ class S3DownloadHandler:
self._download_http = _http_handler.download_request
@classmethod
def from_crawler(cls, crawler, **kwargs):
def from_crawler(cls, crawler: Crawler, **kwargs: Any) -> Self:
return cls(crawler.settings, crawler=crawler, **kwargs)
def download_request(self, request, spider):
def download_request(self, request: Request, spider: Spider) -> Deferred[Response]:
p = urlparse_cached(request)
scheme = "https" if request.meta.get("is_secure") else "http"
bucket = p.hostname
@ -77,6 +95,7 @@ class S3DownloadHandler:
headers=request.headers.to_unicode_dict(),
data=request.body,
)
assert self._signer
self._signer.add_auth(awsrequest)
request = request.replace(url=url, headers=awsrequest.headers.items())
return self._download_http(request, spider)

42
scrapy/core/downloader/middleware.py
View File

@ -3,25 +3,34 @@ Downloader Middleware manager
See documentation in docs/topics/downloader-middleware.rst
"""
from typing import Any, Callable, Generator, List, Union, cast
from __future__ import annotations
from collections.abc import Callable
from typing import TYPE_CHECKING, Any, cast
from twisted.internet.defer import Deferred, inlineCallbacks
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
from scrapy.settings import BaseSettings
from scrapy.utils.conf import build_component_list
from scrapy.utils.defer import deferred_from_coro, mustbe_deferred
if TYPE_CHECKING:
from collections.abc import Generator
from twisted.python.failure import Failure
from scrapy import Spider
from scrapy.settings import BaseSettings
class DownloaderMiddlewareManager(MiddlewareManager):
component_name = "downloader middleware"
@classmethod
def _get_mwlist_from_settings(cls, settings: BaseSettings) -> List[Any]:
def _get_mwlist_from_settings(cls, settings: BaseSettings) -> list[Any]:
return build_component_list(settings.getwithbase("DOWNLOADER_MIDDLEWARES"))
def _add_middleware(self, mw: Any) -> None:
@ -33,10 +42,15 @@ class DownloaderMiddlewareManager(MiddlewareManager):
self.methods["process_exception"].appendleft(mw.process_exception)
def download(
self, download_func: Callable, request: Request, spider: Spider
) -> Deferred:
self,
download_func: Callable[[Request, Spider], Deferred[Response]],
request: Request,
spider: Spider,
) -> Deferred[Response | Request]:
@inlineCallbacks
def process_request(request: Request) -> Generator[Deferred, Any, Any]:
def process_request(
request: Request,
) -> Generator[Deferred[Any], Any, Response | Request]:
for method in self.methods["process_request"]:
method = cast(Callable, method)
response = yield deferred_from_coro(
@ -51,12 +65,12 @@ class DownloaderMiddlewareManager(MiddlewareManager):
)
if response:
return response
return (yield download_func(request=request, spider=spider))
return (yield download_func(request, spider))
@inlineCallbacks
def process_response(
response: Union[Response, Request]
) -> Generator[Deferred, Any, Union[Response, Request]]:
response: Response | Request,
) -> Generator[Deferred[Any], Any, Response | Request]:
if response is None:
raise TypeError("Received None in process_response")
elif isinstance(response, Request):
@ -79,7 +93,7 @@ class DownloaderMiddlewareManager(MiddlewareManager):
@inlineCallbacks
def process_exception(
failure: Failure,
) -> Generator[Deferred, Any, Union[Failure, Response, Request]]:
) -> Generator[Deferred[Any], Any, Failure | Response | Request]:
exception = failure.value
for method in self.methods["process_exception"]:
method = cast(Callable, method)
@ -97,7 +111,9 @@ class DownloaderMiddlewareManager(MiddlewareManager):
return response
return failure
deferred = mustbe_deferred(process_request, request)
deferred: Deferred[Response | Request] = mustbe_deferred(
process_request, request
)
deferred.addErrback(process_exception)
deferred.addCallback(process_response)
return deferred

4
scrapy/core/downloader/tls.py
View File

@ -1,5 +1,5 @@
import logging
from typing import Any, Dict
from typing import Any
from OpenSSL import SSL
from service_identity.exceptions import CertificateError
@ -21,7 +21,7 @@ METHOD_TLSv11 = "TLSv1.1"
METHOD_TLSv12 = "TLSv1.2"
openssl_methods: Dict[str, int] = {
openssl_methods: dict[str, int] = {
METHOD_TLS: SSL.SSLv23_METHOD, # protocol negotiation (recommended)
METHOD_TLSv10: SSL.TLSv1_METHOD, # TLS 1.0 only
METHOD_TLSv11: SSL.TLSv1_1_METHOD, # TLS 1.1 only

22
scrapy/core/downloader/webclient.py
View File

@ -1,20 +1,24 @@
from __future__ import annotations
import re
from time import time
from typing import Optional, Tuple
from typing import TYPE_CHECKING
from urllib.parse import ParseResult, urldefrag, urlparse, urlunparse
from twisted.internet import defer
from twisted.internet.protocol import ClientFactory
from twisted.web.http import HTTPClient
from scrapy import Request
from scrapy.http import Headers
from scrapy.http import Headers, Response
from scrapy.responsetypes import responsetypes
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.python import to_bytes, to_unicode
if TYPE_CHECKING:
from scrapy import Request
def _parsed_url_args(parsed: ParseResult) -> Tuple[bytes, bytes, bytes, int, bytes]:
def _parsed_url_args(parsed: ParseResult) -> tuple[bytes, bytes, bytes, int, bytes]:
# Assume parsed is urlparse-d from Request.url,
# which was passed via safe_url_string and is ascii-only.
path_str = urlunparse(("", "", parsed.path or "/", parsed.params, parsed.query, ""))
@ -29,7 +33,7 @@ def _parsed_url_args(parsed: ParseResult) -> Tuple[bytes, bytes, bytes, int, byt
return scheme, netloc, host, port, path
def _parse(url: str) -> Tuple[bytes, bytes, bytes, int, bytes]:
def _parse(url: str) -> tuple[bytes, bytes, bytes, int, bytes]:
"""Return tuple of (scheme, netloc, host, port, path),
all in bytes except for port which is int.
Assume url is from Request.url, which was passed via safe_url_string
@ -140,12 +144,12 @@ class ScrapyHTTPClientFactory(ClientFactory):
# converting to bytes to comply to Twisted interface
self.url: bytes = to_bytes(self._url, encoding="ascii")
self.method: bytes = to_bytes(request.method, encoding="ascii")
self.body: Optional[bytes] = request.body or None
self.body: bytes | None = request.body or None
self.headers: Headers = Headers(request.headers)
self.response_headers: Optional[Headers] = None
self.response_headers: Headers | None = None
self.timeout: float = request.meta.get("download_timeout") or timeout
self.start_time: float = time()
self.deferred: defer.Deferred = defer.Deferred().addCallback(
self.deferred: defer.Deferred[Response] = defer.Deferred().addCallback(
self._build_response, request
)
@ -155,7 +159,7 @@ class ScrapyHTTPClientFactory(ClientFactory):
# needed to add the callback _waitForDisconnect.
# Specifically this avoids the AttributeError exception when
# clientConnectionFailed method is called.
self._disconnectedDeferred: defer.Deferred = defer.Deferred()
self._disconnectedDeferred: defer.Deferred[None] = defer.Deferred()
self._set_connection_attributes(request)

162
scrapy/core/engine.py
View File

@ -4,60 +4,58 @@ This is the Scrapy engine which controls the Scheduler, Downloader and Spider.
For more information see docs/topics/architecture.rst
"""
from __future__ import annotations
import logging
from time import time
from typing import (
TYPE_CHECKING,
Any,
Callable,
Generator,
Iterable,
Iterator,
Optional,
Set,
Type,
Union,
cast,
)
from typing import TYPE_CHECKING, Any, TypeVar, cast
from itemadapter import is_item
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.downloader import Downloader
from scrapy.core.scraper import Scraper
from scrapy.exceptions import CloseSpider, DontCloseSpider
from scrapy.core.scraper import Scraper, _HandleOutputDeferred
from scrapy.exceptions import CloseSpider, DontCloseSpider, IgnoreRequest
from scrapy.http import Request, Response
from scrapy.logformatter import LogFormatter
from scrapy.settings import BaseSettings, Settings
from scrapy.settings import Settings
from scrapy.signalmanager import SignalManager
from scrapy.spiders import Spider
from scrapy.utils.log import failure_to_exc_info, logformatter_adapter
from scrapy.utils.misc import build_from_crawler, load_object
from scrapy.utils.reactor import CallLaterOnce
if TYPE_CHECKING:
from collections.abc import Callable, Generator, Iterable, Iterator
from scrapy.core.scheduler import BaseScheduler
from scrapy.crawler import Crawler
from scrapy.settings import BaseSettings
from scrapy.spiders import Spider
logger = logging.getLogger(__name__)
_T = TypeVar("_T")
class Slot:
def __init__(
self,
start_requests: Iterable[Request],
close_if_idle: bool,
nextcall: CallLaterOnce,
scheduler: "BaseScheduler",
nextcall: CallLaterOnce[None],
scheduler: BaseScheduler,
) -> None:
self.closing: Optional[Deferred] = None
self.inprogress: Set[Request] = set()
self.start_requests: Optional[Iterator[Request]] = iter(start_requests)
self.closing: Deferred[None] | None = None
self.inprogress: set[Request] = set()
self.start_requests: Iterator[Request] | None = iter(start_requests)
self.close_if_idle: bool = close_if_idle
self.nextcall: CallLaterOnce = nextcall
self.scheduler: "BaseScheduler" = scheduler
self.nextcall: CallLaterOnce[None] = nextcall
self.scheduler: BaseScheduler = scheduler
self.heartbeat: LoopingCall = LoopingCall(nextcall.schedule)
def add_request(self, request: Request) -> None:
@ -67,7 +65,7 @@ class Slot:
self.inprogress.remove(request)
self._maybe_fire_closing()
def close(self) -> Deferred:
def close(self) -> Deferred[None]:
self.closing = Deferred()
self._maybe_fire_closing()
return self.closing
@ -82,29 +80,35 @@ class Slot:
class ExecutionEngine:
def __init__(self, crawler: "Crawler", spider_closed_callback: Callable) -> None:
self.crawler: "Crawler" = crawler
def __init__(
self,
crawler: Crawler,
spider_closed_callback: Callable[[Spider], Deferred[None] | None],
) -> None:
self.crawler: Crawler = crawler
self.settings: Settings = crawler.settings
self.signals: SignalManager = crawler.signals
assert crawler.logformatter
self.logformatter: LogFormatter = crawler.logformatter
self.slot: Optional[Slot] = None
self.spider: Optional[Spider] = None
self.slot: Slot | None = None
self.spider: Spider | None = None
self.running: bool = False
self.paused: bool = False
self.scheduler_cls: Type["BaseScheduler"] = self._get_scheduler_class(
self.scheduler_cls: type[BaseScheduler] = self._get_scheduler_class(
crawler.settings
)
downloader_cls: Type[Downloader] = load_object(self.settings["DOWNLOADER"])
downloader_cls: type[Downloader] = load_object(self.settings["DOWNLOADER"])
self.downloader: Downloader = downloader_cls(crawler)
self.scraper = Scraper(crawler)
self._spider_closed_callback: Callable = spider_closed_callback
self.start_time: Optional[float] = None
self.scraper: Scraper = Scraper(crawler)
self._spider_closed_callback: Callable[[Spider], Deferred[None] | None] = (
spider_closed_callback
)
self.start_time: float | None = None
def _get_scheduler_class(self, settings: BaseSettings) -> Type["BaseScheduler"]:
def _get_scheduler_class(self, settings: BaseSettings) -> type[BaseScheduler]:
from scrapy.core.scheduler import BaseScheduler
scheduler_cls: Type = load_object(settings["SCHEDULER"])
scheduler_cls: type[BaseScheduler] = load_object(settings["SCHEDULER"])
if not issubclass(scheduler_cls, BaseScheduler):
raise TypeError(
f"The provided scheduler class ({settings['SCHEDULER']})"
@ -113,20 +117,20 @@ class ExecutionEngine:
return scheduler_cls
@inlineCallbacks
def start(self) -> Generator[Deferred, Any, None]:
def start(self) -> Generator[Deferred[Any], Any, None]:
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: Deferred = Deferred()
self._closewait: Deferred[None] = Deferred()
yield self._closewait
def stop(self) -> Deferred:
def stop(self) -> Deferred[None]:
"""Gracefully stop the execution engine"""
@inlineCallbacks
def _finish_stopping_engine(_: Any) -> Generator[Deferred, Any, None]:
def _finish_stopping_engine(_: Any) -> Generator[Deferred[Any], Any, None]:
yield self.signals.send_catch_log_deferred(signal=signals.engine_stopped)
self._closewait.callback(None)
@ -141,7 +145,7 @@ class ExecutionEngine:
)
return dfd.addBoth(_finish_stopping_engine)
def close(self) -> Deferred:
def close(self) -> Deferred[None]:
"""
Gracefully close the execution engine.
If it has already been started, stop it. In all cases, close the spider and the downloader.
@ -178,7 +182,7 @@ class ExecutionEngine:
if self.slot.start_requests is not None and not self._needs_backout():
try:
request = next(self.slot.start_requests)
request_or_item = next(self.slot.start_requests)
except StopIteration:
self.slot.start_requests = None
except Exception:
@ -189,7 +193,16 @@ class ExecutionEngine:
extra={"spider": self.spider},
)
else:
self.crawl(request)
if isinstance(request_or_item, Request):
self.crawl(request_or_item)
elif is_item(request_or_item):
self.scraper.start_itemproc(request_or_item, response=None)
else:
logger.error(
f"Got {request_or_item!r} among start requests. Only "
f"requests and items are supported. It will be "
f"ignored."
)
if self.spider_is_idle() and self.slot.close_if_idle:
self._spider_idle()
@ -204,7 +217,7 @@ class ExecutionEngine:
or self.scraper.slot.needs_backout()
)
def _next_request_from_scheduler(self) -> Optional[Deferred]:
def _next_request_from_scheduler(self) -> Deferred[None] | None:
assert self.slot is not None # typing
assert self.spider is not None # typing
@ -212,7 +225,7 @@ class ExecutionEngine:
if request is None:
return None
d = self._download(request)
d: Deferred[Response | Request] = self._download(request)
d.addBoth(self._handle_downloader_output, request)
d.addErrback(
lambda f: logger.info(
@ -226,8 +239,8 @@ class ExecutionEngine:
assert self.slot
self.slot.remove_request(request)
d.addBoth(_remove_request)
d.addErrback(
d2: Deferred[None] = d.addBoth(_remove_request)
d2.addErrback(
lambda f: logger.info(
"Error while removing request from slot",
exc_info=failure_to_exc_info(f),
@ -235,19 +248,19 @@ class ExecutionEngine:
)
)
slot = self.slot
d.addBoth(lambda _: slot.nextcall.schedule())
d.addErrback(
d2.addBoth(lambda _: slot.nextcall.schedule())
d2.addErrback(
lambda f: logger.info(
"Error while scheduling new request",
exc_info=failure_to_exc_info(f),
extra={"spider": self.spider},
)
)
return d
return d2
def _handle_downloader_output(
self, result: Union[Request, Response, Failure], request: Request
) -> Optional[Deferred]:
self, result: Request | Response | Failure, request: Request
) -> _HandleOutputDeferred | None:
assert self.spider is not None # typing
if not isinstance(result, (Request, Response, Failure)):
@ -291,33 +304,42 @@ class ExecutionEngine:
self.slot.nextcall.schedule() # type: ignore[union-attr]
def _schedule_request(self, request: Request, spider: Spider) -> None:
self.signals.send_catch_log(
signals.request_scheduled, request=request, spider=spider
request_scheduled_result = self.signals.send_catch_log(
signals.request_scheduled,
request=request,
spider=spider,
dont_log=IgnoreRequest,
)
for handler, result in request_scheduled_result:
if isinstance(result, Failure) and isinstance(result.value, IgnoreRequest):
return
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: Request) -> Deferred:
def download(self, request: Request) -> Deferred[Response]:
"""Return a Deferred which fires with a Response as result, only downloader middlewares are applied"""
if self.spider is None:
raise RuntimeError(f"No open spider to crawl: {request}")
return self._download(request).addBoth(self._downloaded, request)
d: Deferred[Response | Request] = self._download(request)
# Deferred.addBoth() overloads don't seem to support a Union[_T, Deferred[_T]] return type
d2: Deferred[Response] = d.addBoth(self._downloaded, request) # type: ignore[call-overload]
return d2
def _downloaded(
self, result: Union[Response, Request, Failure], request: Request
) -> Union[Deferred, Response, Failure]:
self, result: Response | Request | Failure, request: Request
) -> Deferred[Response] | Response | Failure:
assert self.slot is not None # typing
self.slot.remove_request(request)
return self.download(result) if isinstance(result, Request) else result
def _download(self, request: Request) -> Deferred:
def _download(self, request: Request) -> Deferred[Response | Request]:
assert self.slot is not None # typing
self.slot.add_request(request)
def _on_success(result: Union[Response, Request]) -> Union[Response, Request]:
def _on_success(result: Response | Request) -> Response | Request:
if not isinstance(result, (Response, Request)):
raise TypeError(
f"Incorrect type: expected Response or Request, got {type(result)}: {result!r}"
@ -339,21 +361,24 @@ class ExecutionEngine:
)
return result
def _on_complete(_: Any) -> Any:
def _on_complete(_: _T) -> _T:
assert self.slot is not None
self.slot.nextcall.schedule()
return _
assert self.spider is not None
dwld = self.downloader.fetch(request, self.spider)
dwld.addCallbacks(_on_success)
dwld: Deferred[Response | Request] = self.downloader.fetch(request, self.spider)
dwld.addCallback(_on_success)
dwld.addBoth(_on_complete)
return dwld
@inlineCallbacks
def open_spider(
self, spider: Spider, start_requests: Iterable = (), close_if_idle: bool = True
) -> Generator[Deferred, Any, None]:
self,
spider: Spider,
start_requests: Iterable[Request] = (),
close_if_idle: bool = True,
) -> Generator[Deferred[Any], Any, None]:
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})
@ -365,7 +390,8 @@ class ExecutionEngine:
self.slot = Slot(start_requests, close_if_idle, nextcall, scheduler)
self.spider = spider
if hasattr(scheduler, "open"):
yield scheduler.open(spider)
if d := scheduler.open(spider):
yield d
yield self.scraper.open_spider(spider)
assert self.crawler.stats
self.crawler.stats.open_spider(spider)
@ -398,7 +424,7 @@ class ExecutionEngine:
assert isinstance(ex, CloseSpider) # typing
self.close_spider(self.spider, reason=ex.reason)
def close_spider(self, spider: Spider, reason: str = "cancelled") -> Deferred:
def close_spider(self, spider: Spider, reason: str = "cancelled") -> Deferred[None]:
"""Close (cancel) spider and clear all its outstanding requests"""
if self.slot is None:
raise RuntimeError("Engine slot not assigned")
@ -412,7 +438,7 @@ class ExecutionEngine:
dfd = self.slot.close()
def log_failure(msg: str) -> Callable:
def log_failure(msg: str) -> Callable[[Failure], None]:
def errback(failure: Failure) -> None:
logger.error(
msg, exc_info=failure_to_exc_info(failure), extra={"spider": spider}

76
scrapy/core/http2/agent.py
View File

@ -1,10 +1,10 @@
from __future__ import annotations
from collections import deque
from typing import Deque, Dict, List, Optional, Tuple
from typing import TYPE_CHECKING
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,
@ -16,9 +16,17 @@ from twisted.web.error import SchemeNotSupported
from scrapy.core.downloader.contextfactory import AcceptableProtocolsContextFactory
from scrapy.core.http2.protocol import H2ClientFactory, H2ClientProtocol
from scrapy.http.request import Request
from scrapy.settings import Settings
from scrapy.spiders import Spider
if TYPE_CHECKING:
from twisted.internet.base import ReactorBase
from twisted.internet.endpoints import HostnameEndpoint
from scrapy.http import Request, Response
from scrapy.settings import Settings
from scrapy.spiders import Spider
ConnectionKeyT = tuple[bytes, bytes, int]
class H2ConnectionPool:
@ -28,19 +36,21 @@ class H2ConnectionPool:
# Store a dictionary which is used to get the respective
# H2ClientProtocolInstance using the key as Tuple(scheme, hostname, port)
self._connections: Dict[Tuple, H2ClientProtocol] = {}
self._connections: dict[ConnectionKeyT, H2ClientProtocol] = {}
# Save all requests that arrive before the connection is established
self._pending_requests: Dict[Tuple, Deque[Deferred]] = {}
self._pending_requests: dict[
ConnectionKeyT, deque[Deferred[H2ClientProtocol]]
] = {}
def get_connection(
self, key: Tuple, uri: URI, endpoint: HostnameEndpoint
) -> Deferred:
self, key: ConnectionKeyT, uri: URI, endpoint: HostnameEndpoint
) -> Deferred[H2ClientProtocol]:
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 = Deferred()
d: Deferred[H2ClientProtocol] = Deferred()
self._pending_requests[key].append(d)
return d
@ -54,22 +64,24 @@ class H2ConnectionPool:
return self._new_connection(key, uri, endpoint)
def _new_connection(
self, key: Tuple, uri: URI, endpoint: HostnameEndpoint
) -> Deferred:
self, key: ConnectionKeyT, uri: URI, endpoint: HostnameEndpoint
) -> Deferred[H2ClientProtocol]:
self._pending_requests[key] = deque()
conn_lost_deferred: Deferred = Deferred()
conn_lost_deferred: Deferred[list[BaseException]] = 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 = Deferred()
d: Deferred[H2ClientProtocol] = Deferred()
self._pending_requests[key].append(d)
return d
def put_connection(self, conn: H2ClientProtocol, key: Tuple) -> H2ClientProtocol:
def put_connection(
self, conn: H2ClientProtocol, key: ConnectionKeyT
) -> H2ClientProtocol:
self._connections[key] = conn
# Now as we have established a proper HTTP/2 connection
@ -81,7 +93,9 @@ class H2ConnectionPool:
return conn
def _remove_connection(self, errors: List[BaseException], key: Tuple) -> None:
def _remove_connection(
self, errors: list[BaseException], key: ConnectionKeyT
) -> None:
self._connections.pop(key)
# Call the errback of all the pending requests for this connection
@ -107,8 +121,8 @@ class H2Agent:
reactor: ReactorBase,
pool: H2ConnectionPool,
context_factory: BrowserLikePolicyForHTTPS = BrowserLikePolicyForHTTPS(),
connect_timeout: Optional[float] = None,
bind_address: Optional[bytes] = None,
connect_timeout: float | None = None,
bind_address: bytes | None = None,
) -> None:
self._reactor = reactor
self._pool = pool
@ -119,17 +133,17 @@ class H2Agent:
self._reactor, self._context_factory, connect_timeout, bind_address
)
def get_endpoint(self, uri: URI):
def get_endpoint(self, uri: URI) -> HostnameEndpoint:
return self.endpoint_factory.endpointForURI(uri)
def get_key(self, uri: URI) -> Tuple:
def get_key(self, uri: URI) -> ConnectionKeyT:
"""
Arguments:
uri - URI obtained directly from request URL
"""
return uri.scheme, uri.host, uri.port
def request(self, request: Request, spider: Spider) -> Deferred:
def request(self, request: Request, spider: Spider) -> Deferred[Response]:
uri = URI.fromBytes(bytes(request.url, encoding="utf-8"))
try:
endpoint = self.get_endpoint(uri)
@ -137,9 +151,11 @@ class H2Agent:
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
d: Deferred[H2ClientProtocol] = self._pool.get_connection(key, uri, endpoint)
d2: Deferred[Response] = d.addCallback(
lambda conn: conn.request(request, spider)
)
return d2
class ScrapyProxyH2Agent(H2Agent):
@ -149,8 +165,8 @@ class ScrapyProxyH2Agent(H2Agent):
proxy_uri: URI,
pool: H2ConnectionPool,
context_factory: BrowserLikePolicyForHTTPS = BrowserLikePolicyForHTTPS(),
connect_timeout: Optional[float] = None,
bind_address: Optional[bytes] = None,
connect_timeout: float | None = None,
bind_address: bytes | None = None,
) -> None:
super().__init__(
reactor=reactor,
@ -161,9 +177,9 @@ class ScrapyProxyH2Agent(H2Agent):
)
self._proxy_uri = proxy_uri
def get_endpoint(self, uri: URI):
def get_endpoint(self, uri: URI) -> HostnameEndpoint:
return self.endpoint_factory.endpointForURI(self._proxy_uri)
def get_key(self, uri: URI) -> Tuple:
def get_key(self, uri: URI) -> ConnectionKeyT:
"""We use the proxy uri instead of uri obtained from request url"""
return "http-proxy", self._proxy_uri.host, self._proxy_uri.port
return b"http-proxy", self._proxy_uri.host, self._proxy_uri.port

67
scrapy/core/http2/protocol.py
View File

@ -1,9 +1,10 @@
from __future__ import annotations
import ipaddress
import itertools
import logging
from collections import deque
from ipaddress import IPv4Address, IPv6Address
from typing import Dict, List, Optional, Union
from typing import TYPE_CHECKING, Any
from h2.config import H2Configuration
from h2.connection import H2Connection
@ -20,20 +21,30 @@ from h2.events import (
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.interfaces import (
IAddress,
IHandshakeListener,
IProtocolNegotiationFactory,
)
from twisted.internet.protocol import Factory, Protocol, connectionDone
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
from scrapy.http import Request, Response
if TYPE_CHECKING:
from ipaddress import IPv4Address, IPv6Address
from twisted.internet.defer import Deferred
from twisted.python.failure import Failure
from twisted.web.client import URI
from scrapy.settings import Settings
from scrapy.spiders import Spider
logger = logging.getLogger(__name__)
@ -52,7 +63,7 @@ class InvalidNegotiatedProtocol(H2Error):
class RemoteTerminatedConnection(H2Error):
def __init__(
self,
remote_ip_address: Optional[Union[IPv4Address, IPv6Address]],
remote_ip_address: IPv4Address | IPv6Address | None,
event: ConnectionTerminated,
) -> None:
self.remote_ip_address = remote_ip_address
@ -63,9 +74,7 @@ class RemoteTerminatedConnection(H2Error):
class MethodNotAllowed405(H2Error):
def __init__(
self, remote_ip_address: Optional[Union[IPv4Address, IPv6Address]]
) -> None:
def __init__(self, remote_ip_address: IPv4Address | IPv6Address | None) -> None:
self.remote_ip_address = remote_ip_address
def __str__(self) -> str:
@ -77,7 +86,10 @@ class H2ClientProtocol(Protocol, TimeoutMixin):
IDLE_TIMEOUT = 240
def __init__(
self, uri: URI, settings: Settings, conn_lost_deferred: Deferred
self,
uri: URI,
settings: Settings,
conn_lost_deferred: Deferred[list[BaseException]],
) -> None:
"""
Arguments:
@ -88,7 +100,7 @@ class H2ClientProtocol(Protocol, TimeoutMixin):
conn_lost_deferred -- Deferred fires with the reason: Failure to notify
that connection was lost
"""
self._conn_lost_deferred = conn_lost_deferred
self._conn_lost_deferred: Deferred[list[BaseException]] = conn_lost_deferred
config = H2Configuration(client_side=True, header_encoding="utf-8")
self.conn = H2Connection(config=config)
@ -99,19 +111,19 @@ class H2ClientProtocol(Protocol, TimeoutMixin):
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] = {}
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()
self._pending_request_stream_pool: deque[Stream] = 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] = []
self._conn_lost_errors: list[BaseException] = []
# Some meta data of this connection
# initialized when connection is successfully made
self.metadata: Dict = {
self.metadata: dict[str, Any] = {
# Peer certificate instance
"certificate": None,
# Address of the server we are connected to which
@ -204,14 +216,14 @@ class H2ClientProtocol(Protocol, TimeoutMixin):
data = self.conn.data_to_send()
self.transport.write(data)
def request(self, request: Request, spider: Spider) -> Deferred:
def request(self, request: Request, spider: Spider) -> Deferred[Response]:
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()
d: Deferred[Response] = stream.get_response()
# Add the stream to the request pool
self._pending_request_stream_pool.append(stream)
@ -236,7 +248,7 @@ class H2ClientProtocol(Protocol, TimeoutMixin):
self.conn.initiate_connection()
self._write_to_transport()
def _lose_connection_with_error(self, errors: List[BaseException]) -> None:
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
@ -339,7 +351,7 @@ class H2ClientProtocol(Protocol, TimeoutMixin):
self._pending_request_stream_pool.clear()
self.conn.close_connection()
def _handle_events(self, events: List[Event]) -> None:
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
@ -425,14 +437,17 @@ class H2ClientProtocol(Protocol, TimeoutMixin):
@implementer(IProtocolNegotiationFactory)
class H2ClientFactory(Factory):
def __init__(
self, uri: URI, settings: Settings, conn_lost_deferred: Deferred
self,
uri: URI,
settings: Settings,
conn_lost_deferred: Deferred[list[BaseException]],
) -> None:
self.uri = uri
self.settings = settings
self.conn_lost_deferred = conn_lost_deferred
def buildProtocol(self, addr) -> H2ClientProtocol:
def buildProtocol(self, addr: IAddress) -> H2ClientProtocol:
return H2ClientProtocol(self.uri, self.settings, self.conn_lost_deferred)
def acceptableProtocols(self) -> List[bytes]:
def acceptableProtocols(self) -> list[bytes]:
return [PROTOCOL_NAME]

47
scrapy/core/http2/stream.py
View File

@ -1,23 +1,26 @@
from __future__ import annotations
import logging
from enum import Enum
from io import BytesIO
from typing import TYPE_CHECKING, Dict, List, Optional, Tuple
from urllib.parse import urlparse
from typing import TYPE_CHECKING, Any
from h2.errors import ErrorCodes
from h2.exceptions import H2Error, ProtocolError, StreamClosedError
from hpack import HeaderTuple
from twisted.internet.defer import CancelledError, Deferred
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
from scrapy.utils.httpobj import urlparse_cached
if TYPE_CHECKING:
from hpack import HeaderTuple
from scrapy.core.http2.protocol import H2ClientProtocol
from scrapy.http import Request, Response
logger = logging.getLogger(__name__)
@ -87,7 +90,7 @@ class Stream:
self,
stream_id: int,
request: Request,
protocol: "H2ClientProtocol",
protocol: H2ClientProtocol,
download_maxsize: int = 0,
download_warnsize: int = 0,
) -> None:
@ -99,7 +102,7 @@ class Stream:
"""
self.stream_id: int = stream_id
self._request: Request = request
self._protocol: "H2ClientProtocol" = protocol
self._protocol: H2ClientProtocol = protocol
self._download_maxsize = self._request.meta.get(
"download_maxsize", download_maxsize
@ -110,18 +113,18 @@ class Stream:
# 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),
self.metadata: dict[str, Any] = {
"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),
"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
@ -131,7 +134,7 @@ class Stream:
# 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 = {
self._response: dict[str, Any] = {
# Data received frame by frame from the server is appended
# and passed to the response Deferred when completely received.
"body": BytesIO(),
@ -142,7 +145,7 @@ class Stream:
"headers": Headers({}),
}
def _cancel(_) -> None:
def _cancel(_: Any) -> None:
# Close this stream as gracefully as possible
# If the associated request is initiated we reset this stream
# else we directly call close() method
@ -151,7 +154,7 @@ class Stream:
else:
self.close(StreamCloseReason.CANCELLED)
self._deferred_response: Deferred = Deferred(_cancel)
self._deferred_response: Deferred[Response] = Deferred(_cancel)
def __repr__(self) -> str:
return f"Stream(id={self.stream_id!r})"
@ -177,7 +180,7 @@ class Stream:
and not self.metadata["reached_warnsize"]
)
def get_response(self) -> Deferred:
def get_response(self) -> Deferred[Response]:
"""Simply return a Deferred which fires when response
from the asynchronous request is available
"""
@ -185,7 +188,7 @@ class Stream:
def check_request_url(self) -> bool:
# Make sure that we are sending the request to the correct URL
url = urlparse(self._request.url)
url = urlparse_cached(self._request)
return (
url.netloc == str(self._protocol.metadata["uri"].host, "utf-8")
or url.netloc == str(self._protocol.metadata["uri"].netloc, "utf-8")
@ -193,8 +196,8 @@ class Stream:
== 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)
def _get_request_headers(self) -> list[tuple[str, str]]:
url = urlparse_cached(self._request)
path = url.path
if url.query:
@ -346,7 +349,7 @@ class Stream:
self._response["flow_controlled_size"], self.stream_id
)
def receive_headers(self, headers: List[HeaderTuple]) -> None:
def receive_headers(self, headers: list[HeaderTuple]) -> None:
for name, value in headers:
self._response["headers"].appendlist(name, value)
@ -379,7 +382,7 @@ class Stream:
def close(
self,
reason: StreamCloseReason,
errors: Optional[List[BaseException]] = None,
errors: list[BaseException] | None = None,
from_protocol: bool = False,
) -> None:
"""Based on the reason sent we will handle each case."""

87
scrapy/core/scheduler.py
View File

@ -4,22 +4,28 @@ import json
import logging
from abc import abstractmethod
from pathlib import Path
from typing import TYPE_CHECKING, Any, Optional, Type, TypeVar, cast
from typing import TYPE_CHECKING, Any, cast
from twisted.internet.defer import Deferred
# working around https://github.com/sphinx-doc/sphinx/issues/10400
from twisted.internet.defer import Deferred # noqa: TC002
from scrapy.crawler import Crawler
from scrapy.dupefilters import BaseDupeFilter
from scrapy.http.request import Request
from scrapy.spiders import Spider
from scrapy.statscollectors import StatsCollector
from scrapy.spiders import Spider # noqa: TC001
from scrapy.utils.job import job_dir
from scrapy.utils.misc import build_from_crawler, load_object
if TYPE_CHECKING:
# requires queuelib >= 1.6.2
from queuelib.queue import BaseQueue
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy.crawler import Crawler
from scrapy.dupefilters import BaseDupeFilter
from scrapy.http.request import Request
from scrapy.pqueues import ScrapyPriorityQueue
from scrapy.statscollectors import StatsCollector
logger = logging.getLogger(__name__)
@ -67,7 +73,7 @@ class BaseScheduler(metaclass=BaseSchedulerMeta):
"""
return cls()
def open(self, spider: Spider) -> Optional[Deferred]:
def open(self, spider: Spider) -> Deferred[None] | None:
"""
Called when the spider is opened by the engine. It receives the spider
instance as argument and it's useful to execute initialization code.
@ -77,7 +83,7 @@ class BaseScheduler(metaclass=BaseSchedulerMeta):
"""
pass
def close(self, reason: str) -> Optional[Deferred]:
def close(self, reason: str) -> Deferred[None] | None:
"""
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.
@ -109,7 +115,7 @@ class BaseScheduler(metaclass=BaseSchedulerMeta):
raise NotImplementedError()
@abstractmethod
def next_request(self) -> Optional[Request]:
def next_request(self) -> Request | None:
"""
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.
@ -121,9 +127,6 @@ class BaseScheduler(metaclass=BaseSchedulerMeta):
raise NotImplementedError()
SchedulerTV = TypeVar("SchedulerTV", bound="Scheduler")
class Scheduler(BaseScheduler):
"""
Default Scrapy scheduler. This implementation also handles duplication
@ -178,25 +181,25 @@ class Scheduler(BaseScheduler):
def __init__(
self,
dupefilter: BaseDupeFilter,
jobdir: Optional[str] = None,
dqclass=None,
mqclass=None,
jobdir: str | None = None,
dqclass: type[BaseQueue] | None = None,
mqclass: type[BaseQueue] | None = None,
logunser: bool = False,
stats: Optional[StatsCollector] = None,
pqclass=None,
crawler: Optional[Crawler] = None,
stats: StatsCollector | None = None,
pqclass: type[ScrapyPriorityQueue] | None = None,
crawler: Crawler | None = None,
):
self.df: BaseDupeFilter = dupefilter
self.dqdir: Optional[str] = self._dqdir(jobdir)
self.pqclass = pqclass
self.dqclass = dqclass
self.mqclass = mqclass
self.dqdir: str | None = self._dqdir(jobdir)
self.pqclass: type[ScrapyPriorityQueue] | None = pqclass
self.dqclass: type[BaseQueue] | None = dqclass
self.mqclass: type[BaseQueue] | None = mqclass
self.logunser: bool = logunser
self.stats: Optional[StatsCollector] = stats
self.crawler: Optional[Crawler] = crawler
self.stats: StatsCollector | None = stats
self.crawler: Crawler | None = crawler
@classmethod
def from_crawler(cls: Type[SchedulerTV], crawler: Crawler) -> SchedulerTV:
def from_crawler(cls, crawler: Crawler) -> Self:
"""
Factory method, initializes the scheduler with arguments taken from the crawl settings
"""
@ -215,18 +218,18 @@ class Scheduler(BaseScheduler):
def has_pending_requests(self) -> bool:
return len(self) > 0
def open(self, spider: Spider) -> Optional[Deferred]:
def open(self, spider: Spider) -> Deferred[None] | None:
"""
(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
self.spider: Spider = spider
self.mqs: ScrapyPriorityQueue = self._mq()
self.dqs: ScrapyPriorityQueue | None = self._dq() if self.dqdir else None
return self.df.open()
def close(self, reason: str) -> Optional[Deferred]:
def close(self, reason: str) -> Deferred[None] | None:
"""
(1) dump pending requests to disk if there is a disk queue
(2) return the result of the dupefilter's ``close`` method
@ -260,7 +263,7 @@ class Scheduler(BaseScheduler):
self.stats.inc_value("scheduler/enqueued", spider=self.spider)
return True
def next_request(self) -> Optional[Request]:
def next_request(self) -> Request | None:
"""
Return a :class:`~scrapy.http.Request` object from the memory queue,
falling back to the disk queue if the memory queue is empty.
@ -269,7 +272,7 @@ class Scheduler(BaseScheduler):
Increment the appropriate stats, such as: ``scheduler/dequeued``,
``scheduler/dequeued/disk``, ``scheduler/dequeued/memory``.
"""
request: Optional[Request] = self.mqs.pop()
request: Request | None = self.mqs.pop()
assert self.stats is not None
if request is not None:
self.stats.inc_value("scheduler/dequeued/memory", spider=self.spider)
@ -315,13 +318,15 @@ class Scheduler(BaseScheduler):
def _mqpush(self, request: Request) -> None:
self.mqs.push(request)
def _dqpop(self) -> Optional[Request]:
def _dqpop(self) -> Request | None:
if self.dqs is not None:
return self.dqs.pop()
return None
def _mq(self):
def _mq(self) -> ScrapyPriorityQueue:
"""Create a new priority queue instance, with in-memory storage"""
assert self.crawler
assert self.pqclass
return build_from_crawler(
self.pqclass,
self.crawler,
@ -329,9 +334,11 @@ class Scheduler(BaseScheduler):
key="",
)
def _dq(self):
def _dq(self) -> ScrapyPriorityQueue:
"""Create a new priority queue instance, with disk storage"""
assert self.crawler
assert self.dqdir
assert self.pqclass
state = self._read_dqs_state(self.dqdir)
q = build_from_crawler(
self.pqclass,
@ -348,7 +355,7 @@ class Scheduler(BaseScheduler):
)
return q
def _dqdir(self, jobdir: Optional[str]) -> Optional[str]:
def _dqdir(self, jobdir: str | None) -> str | None:
"""Return a folder name to keep disk queue state at"""
if jobdir:
dqdir = Path(jobdir, "requests.queue")
@ -357,13 +364,13 @@ class Scheduler(BaseScheduler):
return str(dqdir)
return None
def _read_dqs_state(self, dqdir: str) -> list:
def _read_dqs_state(self, dqdir: str) -> list[int]:
path = Path(dqdir, "active.json")
if not path.exists():
return []
with path.open(encoding="utf-8") as f:
return cast(list, json.load(f))
return cast(list[int], json.load(f))
def _write_dqs_state(self, dqdir: str, state: list) -> None:
def _write_dqs_state(self, dqdir: str, state: list[int]) -> None:
with Path(dqdir, "active.json").open("w", encoding="utf-8") as f:
json.dump(state, f)

133
scrapy/core/scraper.py
View File

@ -1,23 +1,12 @@
"""This module implements the Scraper component which parses responses and
extracts information from them"""
from __future__ import annotations
import logging
from collections import deque
from typing import (
TYPE_CHECKING,
Any,
AsyncGenerator,
AsyncIterable,
Deque,
Generator,
Iterable,
Optional,
Set,
Tuple,
Type,
Union,
)
from collections.abc import AsyncIterable, Iterator
from typing import TYPE_CHECKING, Any, TypeVar, Union, cast
from itemadapter import is_item
from twisted.internet.defer import Deferred, inlineCallbacks
@ -43,32 +32,37 @@ from scrapy.utils.misc import load_object, warn_on_generator_with_return_value
from scrapy.utils.spider import iterate_spider_output
if TYPE_CHECKING:
from collections.abc import Generator, Iterable
from scrapy.crawler import Crawler
QueueTuple = Tuple[Union[Response, Failure], Request, Deferred]
logger = logging.getLogger(__name__)
_T = TypeVar("_T")
_ParallelResult = list[tuple[bool, Iterator[Any]]]
_HandleOutputDeferred = Deferred[Union[_ParallelResult, None]]
QueueTuple = tuple[Union[Response, Failure], Request, _HandleOutputDeferred]
class Slot:
"""Scraper slot (one per running spider)"""
MIN_RESPONSE_SIZE = 1024
def __init__(self, max_active_size: int = 5000000):
self.max_active_size = max_active_size
self.queue: Deque[QueueTuple] = deque()
self.active: Set[Request] = set()
self.max_active_size: int = max_active_size
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
self.closing: Deferred[Spider] | None = None
def add_response_request(
self, result: Union[Response, Failure], request: Request
) -> Deferred:
deferred: Deferred = Deferred()
self, result: Response | Failure, request: Request
) -> _HandleOutputDeferred:
deferred: _HandleOutputDeferred = Deferred()
self.queue.append((result, request, deferred))
if isinstance(result, Response):
self.active_size += max(len(result.body), self.MIN_RESPONSE_SIZE)
@ -81,9 +75,7 @@ class Slot:
self.active.add(request)
return response, request, deferred
def finish_response(
self, result: Union[Response, Failure], request: Request
) -> None:
def finish_response(self, result: Response | Failure, request: Request) -> None:
self.active.remove(request)
if isinstance(result, Response):
self.active_size -= max(len(result.body), self.MIN_RESPONSE_SIZE)
@ -99,11 +91,11 @@ class Slot:
class Scraper:
def __init__(self, crawler: Crawler) -> None:
self.slot: Optional[Slot] = None
self.slot: Slot | None = None
self.spidermw: SpiderMiddlewareManager = SpiderMiddlewareManager.from_crawler(
crawler
)
itemproc_cls: Type[ItemPipelineManager] = load_object(
itemproc_cls: type[ItemPipelineManager] = load_object(
crawler.settings["ITEM_PROCESSOR"]
)
self.itemproc: ItemPipelineManager = itemproc_cls.from_crawler(crawler)
@ -114,12 +106,12 @@ class Scraper:
self.logformatter: LogFormatter = crawler.logformatter
@inlineCallbacks
def open_spider(self, spider: Spider) -> Generator[Deferred, Any, None]:
def open_spider(self, spider: Spider) -> Generator[Deferred[Any], Any, None]:
"""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: Spider) -> Deferred:
def close_spider(self, spider: Spider) -> Deferred[Spider]:
"""Close a spider being scraped and release its resources"""
if self.slot is None:
raise RuntimeError("Scraper slot not assigned")
@ -138,13 +130,13 @@ class Scraper:
self.slot.closing.callback(spider)
def enqueue_scrape(
self, result: Union[Response, Failure], request: Request, spider: Spider
) -> Deferred:
self, result: Response | Failure, request: Request, spider: Spider
) -> _HandleOutputDeferred:
if self.slot is None:
raise RuntimeError("Scraper slot not assigned")
dfd = self.slot.add_response_request(result, request)
def finish_scraping(_: Any) -> Any:
def finish_scraping(_: _T) -> _T:
assert self.slot is not None
self.slot.finish_response(result, request)
self._check_if_closing(spider)
@ -170,8 +162,8 @@ class Scraper:
self._scrape(response, request, spider).chainDeferred(deferred)
def _scrape(
self, result: Union[Response, Failure], request: Request, spider: Spider
) -> Deferred:
self, result: Response | Failure, request: Request, spider: Spider
) -> _HandleOutputDeferred:
"""
Handle the downloaded response or failure through the spider callback/errback
"""
@ -179,30 +171,35 @@ class Scraper:
raise TypeError(
f"Incorrect type: expected Response or Failure, got {type(result)}: {result!r}"
)
dfd = self._scrape2(
dfd: Deferred[Iterable[Any] | AsyncIterable[Any]] = 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
dfd2: _HandleOutputDeferred = dfd.addCallback(
self.handle_spider_output, request, cast(Response, result), spider
)
return dfd2
def _scrape2(
self, result: Union[Response, Failure], request: Request, spider: Spider
) -> Deferred:
self, result: Response | Failure, request: Request, spider: Spider
) -> Deferred[Iterable[Any] | AsyncIterable[Any]]:
"""
Handle the different cases of request's result been a Response or a Failure
"""
if isinstance(result, Response):
return self.spidermw.scrape_response(
# Deferreds are invariant so Mutable*Chain isn't matched to *Iterable
return self.spidermw.scrape_response( # type: ignore[return-value]
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)
dfd.addErrback(self._log_download_errors, result, request, spider)
return dfd
def call_spider(
self, result: Union[Response, Failure], request: Request, spider: Spider
) -> Deferred:
self, result: Response | Failure, request: Request, spider: Spider
) -> Deferred[Iterable[Any] | AsyncIterable[Any]]:
dfd: Deferred[Any]
if isinstance(result, Response):
if getattr(result, "request", None) is None:
result.request = request
@ -220,13 +217,16 @@ class Scraper:
if request.errback:
warn_on_generator_with_return_value(spider, request.errback)
dfd.addErrback(request.errback)
return dfd.addCallback(iterate_spider_output)
dfd2: Deferred[Iterable[Any] | AsyncIterable[Any]] = dfd.addCallback(
iterate_spider_output
)
return dfd2
def handle_spider_error(
self,
_failure: Failure,
request: Request,
response: Union[Response, Failure],
response: Response | Failure,
spider: Spider,
) -> None:
exc = _failure.value
@ -253,14 +253,15 @@ class Scraper:
def handle_spider_output(
self,
result: Union[Iterable, AsyncIterable],
result: Iterable[_T] | AsyncIterable[_T],
request: Request,
response: Union[Response, Failure],
response: Response,
spider: Spider,
) -> Deferred:
) -> _HandleOutputDeferred:
if not result:
return defer_succeed(None)
it: Union[Generator, AsyncGenerator]
it: Iterable[_T] | AsyncIterable[_T]
dfd: Deferred[_ParallelResult]
if isinstance(result, AsyncIterable):
it = aiter_errback(
result, self.handle_spider_error, request, response, spider
@ -285,23 +286,20 @@ class Scraper:
response,
spider,
)
return dfd
# returning Deferred[_ParallelResult] instead of Deferred[Union[_ParallelResult, None]]
return dfd # type: ignore[return-value]
def _process_spidermw_output(
self, output: Any, request: Request, response: Response, spider: Spider
) -> Optional[Deferred]:
) -> Deferred[Any] | None:
"""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):
assert self.crawler.engine is not None # typing
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)
return dfd
return self.start_itemproc(output, response=response)
elif output is None:
pass
else:
@ -313,13 +311,26 @@ class Scraper:
)
return None
def start_itemproc(self, item: Any, *, response: Response | None) -> Deferred[Any]:
"""Send *item* to the item pipelines for processing.
*response* is the source of the item data. If the item does not come
from response data, e.g. it was hard-coded, set it to ``None``.
"""
assert self.slot is not None # typing
assert self.crawler.spider is not None # typing
self.slot.itemproc_size += 1
dfd = self.itemproc.process_item(item, self.crawler.spider)
dfd.addBoth(self._itemproc_finished, item, response, self.crawler.spider)
return dfd
def _log_download_errors(
self,
spider_failure: Failure,
download_failure: Failure,
request: Request,
spider: Spider,
) -> Union[Failure, None]:
) -> Failure | None:
"""Log and silence errors that come from the engine (typically download
errors that got propagated thru here).
@ -353,8 +364,8 @@ class Scraper:
return None
def _itemproc_finished(
self, output: Any, item: Any, response: Response, spider: Spider
) -> Deferred:
self, output: Any, item: Any, response: Response | None, spider: Spider
) -> Deferred[Any]:
"""ItemProcessor finished for the given ``item`` and returned ``output``"""
assert self.slot is not None # typing
self.slot.itemproc_size -= 1

130
scrapy/core/spidermw.py
View File

@ -3,22 +3,14 @@ Spider Middleware manager
See documentation in docs/topics/spider-middleware.rst
"""
from __future__ import annotations
import logging
from collections.abc import AsyncIterable, Callable, Iterable
from inspect import isasyncgenfunction, iscoroutine
from itertools import islice
from typing import (
Any,
AsyncGenerator,
AsyncIterable,
Callable,
Generator,
Iterable,
List,
Optional,
Tuple,
Union,
cast,
)
from typing import TYPE_CHECKING, Any, TypeVar, Union, cast
from twisted.internet.defer import Deferred, inlineCallbacks
from twisted.python.failure import Failure
@ -27,7 +19,6 @@ from scrapy import Request, Spider
from scrapy.exceptions import _InvalidOutput
from scrapy.http import Response
from scrapy.middleware import MiddlewareManager
from scrapy.settings import BaseSettings
from scrapy.utils.asyncgen import as_async_generator, collect_asyncgen
from scrapy.utils.conf import build_component_list
from scrapy.utils.defer import (
@ -38,10 +29,19 @@ from scrapy.utils.defer import (
)
from scrapy.utils.python import MutableAsyncChain, MutableChain
if TYPE_CHECKING:
from collections.abc import Generator
from scrapy.settings import BaseSettings
logger = logging.getLogger(__name__)
ScrapeFunc = Callable[[Union[Response, Failure], Request, Spider], Any]
_T = TypeVar("_T")
ScrapeFunc = Callable[
[Union[Response, Failure], Request, Spider], Union[Iterable[_T], AsyncIterable[_T]]
]
def _isiterable(o: Any) -> bool:
@ -56,7 +56,7 @@ class SpiderMiddlewareManager(MiddlewareManager):
self.downgrade_warning_done = False
@classmethod
def _get_mwlist_from_settings(cls, settings: BaseSettings) -> List[Any]:
def _get_mwlist_from_settings(cls, settings: BaseSettings) -> list[Any]:
return build_component_list(settings.getwithbase("SPIDER_MIDDLEWARES"))
def _add_middleware(self, mw: Any) -> None:
@ -72,11 +72,11 @@ class SpiderMiddlewareManager(MiddlewareManager):
def _process_spider_input(
self,
scrape_func: ScrapeFunc,
scrape_func: ScrapeFunc[_T],
response: Response,
request: Request,
spider: Spider,
) -> Any:
) -> Iterable[_T] | AsyncIterable[_T]:
for method in self.methods["process_spider_input"]:
method = cast(Callable, method)
try:
@ -97,31 +97,39 @@ class SpiderMiddlewareManager(MiddlewareManager):
self,
response: Response,
spider: Spider,
iterable: Union[Iterable, AsyncIterable],
iterable: Iterable[_T] | AsyncIterable[_T],
exception_processor_index: int,
recover_to: Union[MutableChain, MutableAsyncChain],
) -> Union[Generator, AsyncGenerator]:
def process_sync(iterable: Iterable) -> Generator:
recover_to: MutableChain[_T] | MutableAsyncChain[_T],
) -> Iterable[_T] | AsyncIterable[_T]:
def process_sync(iterable: Iterable[_T]) -> Iterable[_T]:
try:
yield from iterable
except Exception as ex:
exception_result = self._process_spider_exception(
response, spider, Failure(ex), exception_processor_index
exception_result = cast(
Union[Failure, MutableChain[_T]],
self._process_spider_exception(
response, spider, Failure(ex), exception_processor_index
),
)
if isinstance(exception_result, Failure):
raise
assert isinstance(recover_to, MutableChain)
recover_to.extend(exception_result)
async def process_async(iterable: AsyncIterable) -> AsyncGenerator:
async def process_async(iterable: AsyncIterable[_T]) -> AsyncIterable[_T]:
try:
async for r in iterable:
yield r
except Exception as ex:
exception_result = self._process_spider_exception(
response, spider, Failure(ex), exception_processor_index
exception_result = cast(
Union[Failure, MutableAsyncChain[_T]],
self._process_spider_exception(
response, spider, Failure(ex), exception_processor_index
),
)
if isinstance(exception_result, Failure):
raise
assert isinstance(recover_to, MutableAsyncChain)
recover_to.extend(exception_result)
if isinstance(iterable, AsyncIterable):
@ -134,7 +142,7 @@ class SpiderMiddlewareManager(MiddlewareManager):
spider: Spider,
_failure: Failure,
start_index: int = 0,
) -> Union[Failure, MutableChain]:
) -> Failure | MutableChain[_T] | MutableAsyncChain[_T]:
exception = _failure.value
# don't handle _InvalidOutput exception
if isinstance(exception, _InvalidOutput):
@ -150,14 +158,18 @@ class SpiderMiddlewareManager(MiddlewareManager):
if _isiterable(result):
# stop exception handling by handing control over to the
# process_spider_output chain if an iterable has been returned
dfd: Deferred = self._process_spider_output(
response, spider, result, method_index + 1
dfd: Deferred[MutableChain[_T] | MutableAsyncChain[_T]] = (
self._process_spider_output(
response, spider, result, method_index + 1
)
)
# _process_spider_output() returns a Deferred only because of downgrading so this can be
# simplified when downgrading is removed.
if dfd.called:
# the result is available immediately if _process_spider_output didn't do downgrading
return cast(MutableChain, dfd.result)
return cast(
Union[MutableChain[_T], MutableAsyncChain[_T]], dfd.result
)
# we forbid waiting here because otherwise we would need to return a deferred from
# _process_spider_exception too, which complicates the architecture
msg = f"Async iterable returned from {method.__qualname__} cannot be downgraded"
@ -180,12 +192,12 @@ class SpiderMiddlewareManager(MiddlewareManager):
self,
response: Response,
spider: Spider,
result: Union[Iterable, AsyncIterable],
result: Iterable[_T] | AsyncIterable[_T],
start_index: int = 0,
) -> Generator[Deferred, Any, Union[MutableChain, MutableAsyncChain]]:
) -> Generator[Deferred[Any], Any, MutableChain[_T] | MutableAsyncChain[_T]]:
# 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: Union[MutableChain, MutableAsyncChain]
recovered: MutableChain[_T] | MutableAsyncChain[_T]
last_result_is_async = isinstance(result, AsyncIterable)
if last_result_is_async:
recovered = MutableAsyncChain()
@ -236,8 +248,10 @@ class SpiderMiddlewareManager(MiddlewareManager):
# 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 = self._process_spider_exception(
response, spider, Failure(ex), method_index + 1
exception_result: Failure | MutableChain[_T] | MutableAsyncChain[_T] = (
self._process_spider_exception(
response, spider, Failure(ex), method_index + 1
)
)
if isinstance(exception_result, Failure):
raise
@ -266,16 +280,22 @@ class SpiderMiddlewareManager(MiddlewareManager):
return MutableChain(result, recovered) # type: ignore[arg-type]
async def _process_callback_output(
self, response: Response, spider: Spider, result: Union[Iterable, AsyncIterable]
) -> Union[MutableChain, MutableAsyncChain]:
recovered: Union[MutableChain, MutableAsyncChain]
self,
response: Response,
spider: Spider,
result: Iterable[_T] | AsyncIterable[_T],
) -> MutableChain[_T] | MutableAsyncChain[_T]:
recovered: MutableChain[_T] | MutableAsyncChain[_T]
if isinstance(result, AsyncIterable):
recovered = MutableAsyncChain()
else:
recovered = MutableChain()
result = self._evaluate_iterable(response, spider, result, 0, recovered)
result = await maybe_deferred_to_future(
self._process_spider_output(response, spider, result)
cast(
"Deferred[Iterable[_T] | AsyncIterable[_T]]",
self._process_spider_output(response, spider, result),
)
)
if isinstance(result, AsyncIterable):
return MutableAsyncChain(result, recovered)
@ -286,41 +306,43 @@ class SpiderMiddlewareManager(MiddlewareManager):
def scrape_response(
self,
scrape_func: ScrapeFunc,
scrape_func: ScrapeFunc[_T],
response: Response,
request: Request,
spider: Spider,
) -> Deferred:
) -> Deferred[MutableChain[_T] | MutableAsyncChain[_T]]:
async def process_callback_output(
result: Union[Iterable, AsyncIterable]
) -> Union[MutableChain, MutableAsyncChain]:
result: Iterable[_T] | AsyncIterable[_T],
) -> MutableChain[_T] | MutableAsyncChain[_T]:
return await self._process_callback_output(response, spider, result)
def process_spider_exception(_failure: Failure) -> Union[Failure, MutableChain]:
def process_spider_exception(
_failure: Failure,
) -> Failure | MutableChain[_T] | MutableAsyncChain[_T]:
return self._process_spider_exception(response, spider, _failure)
dfd = mustbe_deferred(
dfd: Deferred[Iterable[_T] | AsyncIterable[_T]] = mustbe_deferred(
self._process_spider_input, scrape_func, response, request, spider
)
dfd.addCallbacks(
callback=deferred_f_from_coro_f(process_callback_output),
errback=process_spider_exception,
dfd2: Deferred[MutableChain[_T] | MutableAsyncChain[_T]] = dfd.addCallback(
deferred_f_from_coro_f(process_callback_output)
)
return dfd
dfd2.addErrback(process_spider_exception)
return dfd2
def process_start_requests(
self, start_requests: Iterable[Request], spider: Spider
) -> Deferred:
) -> Deferred[Iterable[Request]]:
return self._process_chain("process_start_requests", start_requests, spider)
# This method is only needed until _async compatibility methods are removed.
@staticmethod
def _get_async_method_pair(
mw: Any, methodname: str
) -> Union[None, Callable, Tuple[Callable, Callable]]:
normal_method: Optional[Callable] = getattr(mw, methodname, None)
) -> Callable | tuple[Callable, Callable] | None:
normal_method: Callable | None = getattr(mw, methodname, None)
methodname_async = methodname + "_async"
async_method: Optional[Callable] = getattr(mw, methodname_async, None)
async_method: Callable | None = getattr(mw, methodname_async, None)
if not async_method:
return normal_method
if not normal_method:

103
scrapy/crawler.py
View File

@ -4,7 +4,7 @@ import logging
import pprint
import signal
import warnings
from typing import TYPE_CHECKING, Any, Dict, Generator, Optional, Set, Type, Union, cast
from typing import TYPE_CHECKING, Any, TypeVar, cast
from twisted.internet.defer import (
Deferred,
@ -12,13 +12,6 @@ from twisted.internet.defer import (
inlineCallbacks,
maybeDeferred,
)
try:
# zope >= 5.0 only supports MultipleInvalid
from zope.interface.exceptions import MultipleInvalid
except ImportError:
MultipleInvalid = None
from zope.interface.verify import verifyClass
from scrapy import Spider, signals
@ -49,17 +42,22 @@ from scrapy.utils.reactor import (
)
if TYPE_CHECKING:
from collections.abc import Generator, Iterable
from scrapy.spiderloader import SpiderLoader
from scrapy.utils.request import RequestFingerprinter
logger = logging.getLogger(__name__)
_T = TypeVar("_T")
class Crawler:
def __init__(
self,
spidercls: Type[Spider],
settings: Union[None, Dict[str, Any], Settings] = None,
spidercls: type[Spider],
settings: dict[str, Any] | Settings | None = None,
init_reactor: bool = False,
):
if isinstance(spidercls, Spider):
@ -68,7 +66,7 @@ class Crawler:
if isinstance(settings, dict) or settings is None:
settings = Settings(settings)
self.spidercls: Type[Spider] = spidercls
self.spidercls: type[Spider] = spidercls
self.settings: Settings = settings.copy()
self.spidercls.update_settings(self.settings)
self._update_root_log_handler()
@ -80,12 +78,12 @@ class Crawler:
self.crawling: bool = False
self._started: bool = False
self.extensions: Optional[ExtensionManager] = None
self.stats: Optional[StatsCollector] = None
self.logformatter: Optional[LogFormatter] = None
self.request_fingerprinter: Optional[RequestFingerprinter] = None
self.spider: Optional[Spider] = None
self.engine: Optional[ExecutionEngine] = None
self.extensions: ExtensionManager | None = None
self.stats: StatsCollector | None = None
self.logformatter: LogFormatter | None = None
self.request_fingerprinter: RequestFingerprinter | None = None
self.spider: Spider | None = None
self.engine: ExecutionEngine | None = None
def _update_root_log_handler(self) -> None:
if get_scrapy_root_handler() is not None:
@ -106,7 +104,7 @@ class Crawler:
self.__remove_handler = lambda: logging.root.removeHandler(handler)
self.signals.connect(self.__remove_handler, signals.engine_stopped)
lf_cls: Type[LogFormatter] = load_object(self.settings["LOG_FORMATTER"])
lf_cls: type[LogFormatter] = load_object(self.settings["LOG_FORMATTER"])
self.logformatter = lf_cls.from_crawler(self)
self.request_fingerprinter = build_from_crawler(
@ -129,6 +127,8 @@ class Crawler:
if is_asyncio_reactor_installed() and event_loop:
verify_installed_asyncio_event_loop(event_loop)
log_reactor_info()
self.extensions = ExtensionManager.from_crawler(self)
self.settings.freeze()
@ -138,7 +138,7 @@ class Crawler:
)
@inlineCallbacks
def crawl(self, *args: Any, **kwargs: Any) -> Generator[Deferred, Any, None]:
def crawl(self, *args: Any, **kwargs: Any) -> Generator[Deferred[Any], Any, None]:
if self.crawling:
raise RuntimeError("Crawling already taking place")
if self._started:
@ -170,7 +170,7 @@ class Crawler:
return ExecutionEngine(self, lambda _: self.stop())
@inlineCallbacks
def stop(self) -> Generator[Deferred, Any, None]:
def stop(self) -> Generator[Deferred[Any], Any, None]:
"""Starts a graceful stop of the crawler and returns a deferred that is
fired when the crawler is stopped."""
if self.crawling:
@ -179,16 +179,18 @@ class Crawler:
yield maybeDeferred(self.engine.stop)
@staticmethod
def _get_component(component_class, components):
def _get_component(
component_class: type[_T], components: Iterable[Any]
) -> _T | None:
for component in components:
if isinstance(component, component_class):
return component
return None
def get_addon(self, cls):
def get_addon(self, cls: type[_T]) -> _T | None:
return self._get_component(cls, self.addons.addons)
def get_downloader_middleware(self, cls):
def get_downloader_middleware(self, cls: type[_T]) -> _T | None:
if not self.engine:
raise RuntimeError(
"Crawler.get_downloader_middleware() can only be called after "
@ -196,7 +198,7 @@ class Crawler:
)
return self._get_component(cls, self.engine.downloader.middleware.middlewares)
def get_extension(self, cls):
def get_extension(self, cls: type[_T]) -> _T | None:
if not self.extensions:
raise RuntimeError(
"Crawler.get_extension() can only be called after the "
@ -204,7 +206,7 @@ class Crawler:
)
return self._get_component(cls, self.extensions.middlewares)
def get_item_pipeline(self, cls):
def get_item_pipeline(self, cls: type[_T]) -> _T | None:
if not self.engine:
raise RuntimeError(
"Crawler.get_item_pipeline() can only be called after the "
@ -212,7 +214,7 @@ class Crawler:
)
return self._get_component(cls, self.engine.scraper.itemproc.middlewares)
def get_spider_middleware(self, cls):
def get_spider_middleware(self, cls: type[_T]) -> _T | None:
if not self.engine:
raise RuntimeError(
"Crawler.get_spider_middleware() can only be called after the "
@ -241,28 +243,28 @@ class CrawlerRunner:
)
@staticmethod
def _get_spider_loader(settings: BaseSettings):
def _get_spider_loader(settings: BaseSettings) -> SpiderLoader:
"""Get SpiderLoader instance from settings"""
cls_path = settings.get("SPIDER_LOADER_CLASS")
loader_cls = load_object(cls_path)
verifyClass(ISpiderLoader, loader_cls)
return loader_cls.from_settings(settings.frozencopy())
return cast("SpiderLoader", loader_cls.from_settings(settings.frozencopy()))
def __init__(self, settings: Union[Dict[str, Any], Settings, None] = None):
def __init__(self, settings: dict[str, Any] | Settings | None = None):
if isinstance(settings, dict) or settings is None:
settings = Settings(settings)
self.settings = settings
self.spider_loader = self._get_spider_loader(settings)
self._crawlers: Set[Crawler] = set()
self._active: Set[Deferred] = set()
self.settings: Settings = settings
self.spider_loader: SpiderLoader = self._get_spider_loader(settings)
self._crawlers: set[Crawler] = set()
self._active: set[Deferred[None]] = set()
self.bootstrap_failed = False
def crawl(
self,
crawler_or_spidercls: Union[Type[Spider], str, Crawler],
crawler_or_spidercls: type[Spider] | str | Crawler,
*args: Any,
**kwargs: Any,
) -> Deferred:
) -> Deferred[None]:
"""
Run a crawler with the provided arguments.
@ -292,12 +294,12 @@ class CrawlerRunner:
crawler = self.create_crawler(crawler_or_spidercls)
return self._crawl(crawler, *args, **kwargs)
def _crawl(self, crawler: Crawler, *args: Any, **kwargs: Any) -> Deferred:
def _crawl(self, crawler: Crawler, *args: Any, **kwargs: Any) -> Deferred[None]:
self.crawlers.add(crawler)
d = crawler.crawl(*args, **kwargs)
self._active.add(d)
def _done(result: Any) -> Any:
def _done(result: _T) -> _T:
self.crawlers.discard(crawler)
self._active.discard(d)
self.bootstrap_failed |= not getattr(crawler, "spider", None)
@ -306,7 +308,7 @@ class CrawlerRunner:
return d.addBoth(_done)
def create_crawler(
self, crawler_or_spidercls: Union[Type[Spider], str, Crawler]
self, crawler_or_spidercls: type[Spider] | str | Crawler
) -> Crawler:
"""
Return a :class:`~scrapy.crawler.Crawler` object.
@ -327,13 +329,12 @@ class CrawlerRunner:
return crawler_or_spidercls
return self._create_crawler(crawler_or_spidercls)
def _create_crawler(self, spidercls: Union[str, Type[Spider]]) -> Crawler:
def _create_crawler(self, spidercls: str | type[Spider]) -> Crawler:
if isinstance(spidercls, str):
spidercls = self.spider_loader.load(spidercls)
# temporary cast until self.spider_loader is typed
return Crawler(cast(Type[Spider], spidercls), self.settings)
return Crawler(spidercls, self.settings)
def stop(self) -> Deferred:
def stop(self) -> Deferred[Any]:
"""
Stops simultaneously all the crawling jobs taking place.
@ -342,7 +343,7 @@ class CrawlerRunner:
return DeferredList([c.stop() for c in list(self.crawlers)])
@inlineCallbacks
def join(self) -> Generator[Deferred, Any, None]:
def join(self) -> Generator[Deferred[Any], Any, None]:
"""
join()
@ -379,13 +380,13 @@ class CrawlerProcess(CrawlerRunner):
def __init__(
self,
settings: Union[Dict[str, Any], Settings, None] = None,
settings: dict[str, Any] | Settings | None = None,
install_root_handler: bool = True,
):
super().__init__(settings)
configure_logging(self.settings, install_root_handler)
log_scrapy_info(self.settings)
self._initialized_reactor = False
self._initialized_reactor: bool = False
def _signal_shutdown(self, signum: int, _: Any) -> None:
from twisted.internet import reactor
@ -408,15 +409,13 @@ class CrawlerProcess(CrawlerRunner):
)
reactor.callFromThread(self._stop_reactor)
def _create_crawler(self, spidercls: Union[Type[Spider], str]) -> Crawler:
def _create_crawler(self, spidercls: type[Spider] | str) -> Crawler:
if isinstance(spidercls, str):
spidercls = self.spider_loader.load(spidercls)
init_reactor = not self._initialized_reactor
self._initialized_reactor = True
# temporary cast until self.spider_loader is typed
return Crawler(
cast(Type[Spider], spidercls), self.settings, init_reactor=init_reactor
)
return Crawler(spidercls, self.settings, init_reactor=init_reactor)
def start(
self, stop_after_crawl: bool = True, install_signal_handlers: bool = True
@ -445,7 +444,9 @@ class CrawlerProcess(CrawlerRunner):
d.addBoth(self._stop_reactor)
resolver_class = load_object(self.settings["DNS_RESOLVER"])
resolver = build_from_crawler(resolver_class, self, reactor=reactor)
# We pass self, which is CrawlerProcess, instead of Crawler here,
# which works because the default resolvers only use crawler.settings.
resolver = build_from_crawler(resolver_class, self, reactor=reactor) # type: ignore[arg-type]
resolver.install_on_reactor()
tp = reactor.getThreadPool()
tp.adjustPoolsize(maxthreads=self.settings.getint("REACTOR_THREADPOOL_MAXSIZE"))
@ -456,7 +457,7 @@ class CrawlerProcess(CrawlerRunner):
)
reactor.run(installSignalHandlers=install_signal_handlers) # blocking call
def _graceful_stop_reactor(self) -> Deferred:
def _graceful_stop_reactor(self) -> Deferred[Any]:
d = self.stop()
d.addBoth(self._stop_reactor)
return d

12
scrapy/downloadermiddlewares/ajaxcrawl.py
View File

@ -2,20 +2,22 @@ from __future__ import annotations
import logging
import re
from typing import TYPE_CHECKING, Union
from typing import TYPE_CHECKING
from w3lib import html
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.exceptions import NotConfigured
from scrapy.http import HtmlResponse, Response
from scrapy.settings import BaseSettings
if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.settings import BaseSettings
logger = logging.getLogger(__name__)
@ -41,7 +43,7 @@ class AjaxCrawlMiddleware:
def process_response(
self, request: Request, response: Response, spider: Spider
) -> Union[Request, Response]:
) -> Request | Response:
if not isinstance(response, HtmlResponse) or response.status != 200:
return response

55
scrapy/downloadermiddlewares/cookies.py
View File

@ -2,22 +2,11 @@ from __future__ import annotations
import logging
from collections import defaultdict
from http.cookiejar import Cookie
from typing import (
TYPE_CHECKING,
Any,
DefaultDict,
Dict,
Iterable,
Optional,
Sequence,
Union,
)
from typing import TYPE_CHECKING, Any
from tldextract import TLDExtract
from scrapy import Request, Spider, signals
from scrapy.crawler import Crawler
from scrapy import signals
from scrapy.exceptions import NotConfigured
from scrapy.http import Response
from scrapy.http.cookies import CookieJar
@ -25,14 +14,22 @@ from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.python import to_unicode
if TYPE_CHECKING:
from collections.abc import Iterable, Sequence
from http.cookiejar import Cookie
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.http.request import VerboseCookie
logger = logging.getLogger(__name__)
_split_domain = TLDExtract(include_psl_private_domains=True)
_UNSET = object()
def _is_public_domain(domain: str) -> bool:
@ -44,7 +41,7 @@ class CookiesMiddleware:
"""This middleware enables working with sites that need cookies"""
def __init__(self, debug: bool = False):
self.jars: DefaultDict[Any, CookieJar] = defaultdict(CookieJar)
self.jars: defaultdict[Any, CookieJar] = defaultdict(CookieJar)
self.debug: bool = debug
@classmethod
@ -79,7 +76,7 @@ class CookiesMiddleware:
def process_request(
self, request: Request, spider: Spider
) -> Union[Request, Response, None]:
) -> Request | Response | None:
if request.meta.get("dont_merge_cookies", False):
return None
@ -96,7 +93,7 @@ class CookiesMiddleware:
def process_response(
self, request: Request, response: Response, spider: Spider
) -> Union[Request, Response]:
) -> Request | Response:
if request.meta.get("dont_merge_cookies", False):
return response
@ -132,12 +129,13 @@ class CookiesMiddleware:
msg = f"Received cookies from: {response}\n{cookies}"
logger.debug(msg, extra={"spider": spider})
def _format_cookie(self, cookie: Dict[str, Any], request: Request) -> Optional[str]:
def _format_cookie(self, cookie: VerboseCookie, request: Request) -> str | None:
"""
Given a dict consisting of cookie components, return its string representation.
Decode from bytes if necessary.
"""
decoded = {}
flags = set()
for key in ("name", "value", "path", "domain"):
if cookie.get(key) is None:
if key in ("name", "value"):
@ -145,22 +143,29 @@ class CookiesMiddleware:
logger.warning(msg)
return None
continue
if isinstance(cookie[key], (bool, float, int, str)):
decoded[key] = str(cookie[key])
# https://github.com/python/mypy/issues/7178, https://github.com/python/mypy/issues/9168
if isinstance(cookie[key], (bool, float, int, str)): # type: ignore[literal-required]
decoded[key] = str(cookie[key]) # type: ignore[literal-required]
else:
try:
decoded[key] = cookie[key].decode("utf8")
decoded[key] = cookie[key].decode("utf8") # type: ignore[literal-required]
except UnicodeDecodeError:
logger.warning(
"Non UTF-8 encoded cookie found in request %s: %s",
request,
cookie,
)
decoded[key] = cookie[key].decode("latin1", errors="replace")
decoded[key] = cookie[key].decode("latin1", errors="replace") # type: ignore[literal-required]
for flag in ("secure",):
value = cookie.get(flag, _UNSET)
if value is _UNSET or not value:
continue
flags.add(flag)
cookie_str = f"{decoded.pop('name')}={decoded.pop('value')}"
for key, value in decoded.items(): # path, domain
cookie_str += f"; {key.capitalize()}={value}"
for flag in flags: # secure
cookie_str += f"; {flag.capitalize()}"
return cookie_str
def _get_request_cookies(
@ -171,11 +176,13 @@ class CookiesMiddleware:
"""
if not request.cookies:
return []
cookies: Iterable[Dict[str, Any]]
cookies: Iterable[VerboseCookie]
if isinstance(request.cookies, dict):
cookies = ({"name": k, "value": v} for k, v in request.cookies.items())
cookies = tuple({"name": k, "value": v} for k, v in request.cookies.items())
else:
cookies = request.cookies
for cookie in cookies:
cookie.setdefault("secure", urlparse_cached(request).scheme == "https")
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)

18
scrapy/downloadermiddlewares/defaultheaders.py
View File

@ -3,23 +3,27 @@ DefaultHeaders downloader middleware
See documentation in docs/topics/downloader-middleware.rst
"""
from __future__ import annotations
from typing import TYPE_CHECKING, Iterable, Tuple, Union
from typing import TYPE_CHECKING
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.http import Response
from scrapy.utils.python import without_none_values
if TYPE_CHECKING:
from collections.abc import Iterable
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.http import Response
class DefaultHeadersMiddleware:
def __init__(self, headers: Iterable[Tuple[str, str]]):
self._headers: Iterable[Tuple[str, str]] = headers
def __init__(self, headers: Iterable[tuple[str, str]]):
self._headers: Iterable[tuple[str, str]] = headers
@classmethod
def from_crawler(cls, crawler: Crawler) -> Self:
@ -28,7 +32,7 @@ class DefaultHeadersMiddleware:
def process_request(
self, request: Request, spider: Spider
) -> Union[Request, Response, None]:
) -> Request | Response | None:
for k, v in self._headers:
request.headers.setdefault(k, v)
return None

10
scrapy/downloadermiddlewares/downloadtimeout.py
View File

@ -3,18 +3,20 @@ Download timeout middleware
See documentation in docs/topics/downloader-middleware.rst
"""
from __future__ import annotations
from typing import TYPE_CHECKING, Union
from typing import TYPE_CHECKING
from scrapy import Request, Spider, signals
from scrapy.crawler import Crawler
from scrapy.http import Response
if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy.crawler import Crawler
from scrapy.http import Response
class DownloadTimeoutMiddleware:
def __init__(self, timeout: float = 180):
@ -31,7 +33,7 @@ class DownloadTimeoutMiddleware:
def process_request(
self, request: Request, spider: Spider
) -> Union[Request, Response, None]:
) -> Request | Response | None:
if self._timeout:
request.meta.setdefault("download_timeout", self._timeout)
return None

9
scrapy/downloadermiddlewares/httpauth.py
View File

@ -6,19 +6,20 @@ See documentation in docs/topics/downloader-middleware.rst
from __future__ import annotations
from typing import TYPE_CHECKING, Union
from typing import TYPE_CHECKING
from w3lib.http import basic_auth_header
from scrapy import Request, Spider, signals
from scrapy.crawler import Crawler
from scrapy.http import Response
from scrapy.utils.url import url_is_from_any_domain
if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy.crawler import Crawler
from scrapy.http import Response
class HttpAuthMiddleware:
"""Set Basic HTTP Authorization header
@ -39,7 +40,7 @@ class HttpAuthMiddleware:
def process_request(
self, request: Request, spider: Spider
) -> Union[Request, Response, None]:
) -> Request | Response | None:
auth = getattr(self, "auth", None)
if auth and b"Authorization" not in request.headers:
if not self.domain or url_is_from_any_domain(request.url, [self.domain]):

29
scrapy/downloadermiddlewares/httpcache.py
View File

@ -1,7 +1,7 @@
from __future__ import annotations
from email.utils import formatdate
from typing import TYPE_CHECKING, Optional, Union
from typing import TYPE_CHECKING
from twisted.internet import defer
from twisted.internet.error import (
@ -16,19 +16,20 @@ 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
if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy.crawler import Crawler
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
class HttpCacheMiddleware:
DOWNLOAD_EXCEPTIONS = (
@ -68,7 +69,7 @@ class HttpCacheMiddleware:
def process_request(
self, request: Request, spider: Spider
) -> Union[Request, Response, None]:
) -> Request | Response | None:
if request.meta.get("dont_cache", False):
return None
@ -78,7 +79,7 @@ class HttpCacheMiddleware:
return None
# Look for cached response and check if expired
cachedresponse: Optional[Response] = self.storage.retrieve_response(
cachedresponse: Response | None = self.storage.retrieve_response(
spider, request
)
if cachedresponse is None:
@ -102,7 +103,7 @@ class HttpCacheMiddleware:
def process_response(
self, request: Request, response: Response, spider: Spider
) -> Union[Request, Response]:
) -> Request | Response:
if request.meta.get("dont_cache", False):
return response
@ -117,7 +118,7 @@ class HttpCacheMiddleware:
response.headers["Date"] = formatdate(usegmt=True)
# Do not validate first-hand responses
cachedresponse: Optional[Response] = request.meta.pop("cached_response", None)
cachedresponse: Response | None = request.meta.pop("cached_response", None)
if cachedresponse is None:
self.stats.inc_value("httpcache/firsthand", spider=spider)
self._cache_response(spider, response, request, cachedresponse)
@ -133,8 +134,8 @@ class HttpCacheMiddleware:
def process_exception(
self, request: Request, exception: Exception, spider: Spider
) -> Union[Request, Response, None]:
cachedresponse: Optional[Response] = request.meta.pop("cached_response", None)
) -> Request | Response | None:
cachedresponse: Response | None = request.meta.pop("cached_response", None)
if cachedresponse is not None and isinstance(
exception, self.DOWNLOAD_EXCEPTIONS
):
@ -147,7 +148,7 @@ class HttpCacheMiddleware:
spider: Spider,
response: Response,
request: Request,
cachedresponse: Optional[Response],
cachedresponse: Response | None,
) -> None:
if self.policy.should_cache_response(response, request):
self.stats.inc_value("httpcache/store", spider=spider)

164
scrapy/downloadermiddlewares/httpcompression.py
View File

@ -1,67 +1,133 @@
from __future__ import annotations
import io
import zlib
from typing import TYPE_CHECKING, List, Optional, Union
import warnings
from itertools import chain
from logging import getLogger
from typing import TYPE_CHECKING, Any
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.exceptions import NotConfigured
from scrapy import Request, Spider, signals
from scrapy.exceptions import IgnoreRequest, NotConfigured
from scrapy.http import Response, TextResponse
from scrapy.responsetypes import responsetypes
from scrapy.statscollectors import StatsCollector
from scrapy.utils._compression import (
_DecompressionMaxSizeExceeded,
_inflate,
_unbrotli,
_unzstd,
)
from scrapy.utils.deprecate import ScrapyDeprecationWarning
from scrapy.utils.gz import gunzip
if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
ACCEPTED_ENCODINGS: List[bytes] = [b"gzip", b"deflate"]
from scrapy.crawler import Crawler
from scrapy.statscollectors import StatsCollector
logger = getLogger(__name__)
ACCEPTED_ENCODINGS: list[bytes] = [b"gzip", b"deflate"]
try:
import brotli
try:
import brotli # noqa: F401
except ImportError:
import brotlicffi # noqa: F401
except ImportError:
pass
else:
ACCEPTED_ENCODINGS.append(b"br")
except ImportError:
pass
try:
import zstandard
ACCEPTED_ENCODINGS.append(b"zstd")
import zstandard # noqa: F401
except ImportError:
pass
else:
ACCEPTED_ENCODINGS.append(b"zstd")
class HttpCompressionMiddleware:
"""This middleware allows compressed (gzip, deflate) traffic to be
sent/received from web sites"""
sent/received from websites"""
def __init__(self, stats: Optional[StatsCollector] = None):
self.stats = stats
def __init__(
self,
stats: StatsCollector | None = None,
*,
crawler: Crawler | None = None,
):
if not crawler:
self.stats = stats
self._max_size = 1073741824
self._warn_size = 33554432
return
self.stats = crawler.stats
self._max_size = crawler.settings.getint("DOWNLOAD_MAXSIZE")
self._warn_size = crawler.settings.getint("DOWNLOAD_WARNSIZE")
crawler.signals.connect(self.open_spider, signals.spider_opened)
@classmethod
def from_crawler(cls, crawler: Crawler) -> Self:
if not crawler.settings.getbool("COMPRESSION_ENABLED"):
raise NotConfigured
return cls(stats=crawler.stats)
try:
return cls(crawler=crawler)
except TypeError:
warnings.warn(
"HttpCompressionMiddleware subclasses must either modify "
"their '__init__' method to support a 'crawler' parameter or "
"reimplement their 'from_crawler' method.",
ScrapyDeprecationWarning,
)
mw = cls()
mw.stats = crawler.stats
mw._max_size = crawler.settings.getint("DOWNLOAD_MAXSIZE")
mw._warn_size = crawler.settings.getint("DOWNLOAD_WARNSIZE")
crawler.signals.connect(mw.open_spider, signals.spider_opened)
return mw
def open_spider(self, spider: Spider) -> None:
if hasattr(spider, "download_maxsize"):
self._max_size = spider.download_maxsize
if hasattr(spider, "download_warnsize"):
self._warn_size = spider.download_warnsize
def process_request(
self, request: Request, spider: Spider
) -> Union[Request, Response, None]:
) -> Request | Response | None:
request.headers.setdefault("Accept-Encoding", b", ".join(ACCEPTED_ENCODINGS))
return None
def process_response(
self, request: Request, response: Response, spider: Spider
) -> Union[Request, Response]:
) -> Request | Response:
if request.method == "HEAD":
return response
if isinstance(response, Response):
content_encoding = response.headers.getlist("Content-Encoding")
if content_encoding:
encoding = content_encoding.pop()
decoded_body = self._decode(response.body, encoding.lower())
max_size = request.meta.get("download_maxsize", self._max_size)
warn_size = request.meta.get("download_warnsize", self._warn_size)
try:
decoded_body, content_encoding = self._handle_encoding(
response.body, content_encoding, max_size
)
except _DecompressionMaxSizeExceeded:
raise IgnoreRequest(
f"Ignored response {response} because its body "
f"({len(response.body)} B compressed) exceeded "
f"DOWNLOAD_MAXSIZE ({max_size} B) during "
f"decompression."
)
if len(response.body) < warn_size <= len(decoded_body):
logger.warning(
f"{response} body size after decompression "
f"({len(decoded_body)} B) is larger than the "
f"download warning size ({warn_size} B)."
)
response.headers["Content-Encoding"] = content_encoding
if self.stats:
self.stats.inc_value(
"httpcompression/response_bytes",
@ -74,36 +140,50 @@ class HttpCompressionMiddleware:
respcls = responsetypes.from_args(
headers=response.headers, url=response.url, body=decoded_body
)
kwargs = dict(cls=respcls, body=decoded_body)
kwargs: dict[str, Any] = {"body": decoded_body}
if issubclass(respcls, TextResponse):
# force recalculating the encoding until we make sure the
# responsetypes guessing is reliable
kwargs["encoding"] = None
response = response.replace(**kwargs)
response = response.replace(cls=respcls, **kwargs)
if not content_encoding:
del response.headers["Content-Encoding"]
return response
def _decode(self, body: bytes, encoding: bytes) -> bytes:
if encoding == b"gzip" or encoding == b"x-gzip":
body = gunzip(body)
def _handle_encoding(
self, body: bytes, content_encoding: list[bytes], max_size: int
) -> tuple[bytes, list[bytes]]:
to_decode, to_keep = self._split_encodings(content_encoding)
for encoding in to_decode:
body = self._decode(body, encoding, max_size)
return body, to_keep
def _split_encodings(
self, content_encoding: list[bytes]
) -> tuple[list[bytes], list[bytes]]:
to_keep: list[bytes] = [
encoding.strip().lower()
for encoding in chain.from_iterable(
encodings.split(b",") for encodings in content_encoding
)
]
to_decode: list[bytes] = []
while to_keep:
encoding = to_keep.pop()
if encoding not in ACCEPTED_ENCODINGS:
to_keep.append(encoding)
return to_decode, to_keep
to_decode.append(encoding)
return to_decode, to_keep
def _decode(self, body: bytes, encoding: bytes, max_size: int) -> bytes:
if encoding in {b"gzip", b"x-gzip"}:
return gunzip(body, max_size=max_size)
if encoding == b"deflate":
try:
body = zlib.decompress(body)
except zlib.error:
# ugly hack to work with raw deflate content that may
# be sent by microsoft servers. For more information, see:
# http://carsten.codimi.de/gzip.yaws/
# http://www.port80software.com/200ok/archive/2005/10/31/868.aspx
# http://www.gzip.org/zlib/zlib_faq.html#faq38
body = zlib.decompress(body, -15)
return _inflate(body, max_size=max_size)
if encoding == b"br" and b"br" in ACCEPTED_ENCODINGS:
body = brotli.decompress(body)
return _unbrotli(body, max_size=max_size)
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 _unzstd(body, max_size=max_size)
return body

40
scrapy/downloadermiddlewares/httpproxy.py
View File

@ -1,7 +1,7 @@
from __future__ import annotations
import base64
from typing import TYPE_CHECKING, Dict, Optional, Tuple, Union
from typing import TYPE_CHECKING
from urllib.parse import unquote, urlunparse
from urllib.request import ( # type: ignore[attr-defined]
_parse_proxy,
@ -9,10 +9,7 @@ from urllib.request import ( # type: ignore[attr-defined]
proxy_bypass,
)
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.exceptions import NotConfigured
from scrapy.http import Response
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.python import to_bytes
@ -20,11 +17,15 @@ if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.http import Response
class HttpProxyMiddleware:
def __init__(self, auth_encoding: Optional[str] = "latin-1"):
self.auth_encoding: Optional[str] = auth_encoding
self.proxies: Dict[str, Tuple[Optional[bytes], str]] = {}
def __init__(self, auth_encoding: str | None = "latin-1"):
self.auth_encoding: str | None = auth_encoding
self.proxies: dict[str, tuple[bytes | None, str]] = {}
for type_, url in getproxies().items():
try:
self.proxies[type_] = self._get_proxy(url, type_)
@ -37,7 +38,7 @@ class HttpProxyMiddleware:
def from_crawler(cls, crawler: Crawler) -> Self:
if not crawler.settings.getbool("HTTPPROXY_ENABLED"):
raise NotConfigured
auth_encoding: Optional[str] = crawler.settings.get("HTTPPROXY_AUTH_ENCODING")
auth_encoding: str | None = crawler.settings.get("HTTPPROXY_AUTH_ENCODING")
return cls(auth_encoding)
def _basic_auth_header(self, username: str, password: str) -> bytes:
@ -46,7 +47,7 @@ class HttpProxyMiddleware:
)
return base64.b64encode(user_pass)
def _get_proxy(self, url: str, orig_type: str) -> Tuple[Optional[bytes], str]:
def _get_proxy(self, url: str, orig_type: str) -> tuple[bytes | None, str]:
proxy_type, user, password, hostport = _parse_proxy(url)
proxy_url = urlunparse((proxy_type or orig_type, hostport, "", "", "", ""))
@ -59,27 +60,34 @@ class HttpProxyMiddleware:
def process_request(
self, request: Request, spider: Spider
) -> Union[Request, Response, None]:
creds, proxy_url = None, None
) -> Request | Response | None:
creds, proxy_url, scheme = None, None, None
if "proxy" in request.meta:
if request.meta["proxy"] is not None:
creds, proxy_url = self._get_proxy(request.meta["proxy"], "")
elif self.proxies:
parsed = urlparse_cached(request)
scheme = parsed.scheme
_scheme = parsed.scheme
if (
# 'no_proxy' is only supported by http schemes
scheme not in ("http", "https")
_scheme not in ("http", "https")
or (parsed.hostname and not proxy_bypass(parsed.hostname))
) and scheme in self.proxies:
) and _scheme in self.proxies:
scheme = _scheme
creds, proxy_url = self.proxies[scheme]
self._set_proxy_and_creds(request, proxy_url, creds)
self._set_proxy_and_creds(request, proxy_url, creds, scheme)
return None
def _set_proxy_and_creds(
self, request: Request, proxy_url: Optional[str], creds: Optional[bytes]
self,
request: Request,
proxy_url: str | None,
creds: bytes | None,
scheme: str | None,
) -> None:
if scheme:
request.meta["_scheme_proxy"] = True
if proxy_url:
request.meta["proxy"] = proxy_url
elif request.meta.get("proxy") is not None:

89
scrapy/downloadermiddlewares/offsite.py Normal file
View File

@ -0,0 +1,89 @@
from __future__ import annotations
import logging
import re
import warnings
from typing import TYPE_CHECKING
from scrapy import Request, Spider, signals
from scrapy.exceptions import IgnoreRequest
from scrapy.utils.httpobj import urlparse_cached
if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy.crawler import Crawler
from scrapy.statscollectors import StatsCollector
logger = logging.getLogger(__name__)
class OffsiteMiddleware:
@classmethod
def from_crawler(cls, crawler: Crawler) -> Self:
assert crawler.stats
o = cls(crawler.stats)
crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
crawler.signals.connect(o.request_scheduled, signal=signals.request_scheduled)
return o
def __init__(self, stats: StatsCollector):
self.stats = stats
self.domains_seen: set[str] = set()
def spider_opened(self, spider: Spider) -> None:
self.host_regex: re.Pattern[str] = self.get_host_regex(spider)
def request_scheduled(self, request: Request, spider: Spider) -> None:
self.process_request(request, spider)
def process_request(self, request: Request, spider: Spider) -> None:
if request.dont_filter or self.should_follow(request, spider):
return None
domain = urlparse_cached(request).hostname
if domain and domain not in self.domains_seen:
self.domains_seen.add(domain)
logger.debug(
"Filtered offsite request to %(domain)r: %(request)s",
{"domain": domain, "request": request},
extra={"spider": spider},
)
self.stats.inc_value("offsite/domains", spider=spider)
self.stats.inc_value("offsite/filtered", spider=spider)
raise IgnoreRequest
def should_follow(self, request: Request, spider: Spider) -> bool:
regex = self.host_regex
# hostname can be None for wrong urls (like javascript links)
host = urlparse_cached(request).hostname or ""
return bool(regex.search(host))
def get_host_regex(self, spider: Spider) -> re.Pattern[str]:
"""Override this method to implement a different offsite policy"""
allowed_domains = getattr(spider, "allowed_domains", None)
if not allowed_domains:
return re.compile("") # allow all by default
url_pattern = re.compile(r"^https?://.*$")
port_pattern = re.compile(r":\d+$")
domains = []
for domain in allowed_domains:
if domain is None:
continue
if url_pattern.match(domain):
message = (
"allowed_domains accepts only domains, not URLs. "
f"Ignoring URL entry {domain} in allowed_domains."
)
warnings.warn(message)
elif port_pattern.search(domain):
message = (
"allowed_domains accepts only domains without ports. "
f"Ignoring entry {domain} in allowed_domains."
)
warnings.warn(message)
else:
domains.append(re.escape(domain))
regex = rf'^(.*\.)?({"|".join(domains)})$'
return re.compile(regex)

81
scrapy/downloadermiddlewares/redirect.py
View File

@ -1,16 +1,13 @@
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any, List, Union, cast
from urllib.parse import urljoin, urlparse
from typing import TYPE_CHECKING, Any, cast
from urllib.parse import urljoin
from w3lib.url import safe_url_string
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.exceptions import IgnoreRequest, NotConfigured
from scrapy.http import HtmlResponse, Response
from scrapy.settings import BaseSettings
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.response import get_meta_refresh
@ -18,6 +15,11 @@ if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Request, Spider
from scrapy.crawler import Crawler
from scrapy.settings import BaseSettings
logger = logging.getLogger(__name__)
@ -27,13 +29,52 @@ def _build_redirect_request(
redirect_request = source_request.replace(
url=url,
**kwargs,
cls=None,
cookies=None,
)
if "Cookie" in redirect_request.headers:
source_request_netloc = urlparse_cached(source_request).netloc
redirect_request_netloc = urlparse_cached(redirect_request).netloc
if source_request_netloc != redirect_request_netloc:
if "_scheme_proxy" in redirect_request.meta:
source_request_scheme = urlparse_cached(source_request).scheme
redirect_request_scheme = urlparse_cached(redirect_request).scheme
if source_request_scheme != redirect_request_scheme:
redirect_request.meta.pop("_scheme_proxy")
redirect_request.meta.pop("proxy", None)
redirect_request.meta.pop("_auth_proxy", None)
redirect_request.headers.pop(b"Proxy-Authorization", None)
has_cookie_header = "Cookie" in redirect_request.headers
has_authorization_header = "Authorization" in redirect_request.headers
if has_cookie_header or has_authorization_header:
default_ports = {"http": 80, "https": 443}
parsed_source_request = urlparse_cached(source_request)
source_scheme, source_host, source_port = (
parsed_source_request.scheme,
parsed_source_request.hostname,
parsed_source_request.port
or default_ports.get(parsed_source_request.scheme),
)
parsed_redirect_request = urlparse_cached(redirect_request)
redirect_scheme, redirect_host, redirect_port = (
parsed_redirect_request.scheme,
parsed_redirect_request.hostname,
parsed_redirect_request.port
or default_ports.get(parsed_redirect_request.scheme),
)
if has_cookie_header and (
redirect_scheme not in {source_scheme, "https"}
or source_host != redirect_host
):
del redirect_request.headers["Cookie"]
# https://fetch.spec.whatwg.org/#ref-for-cors-non-wildcard-request-header-name
if has_authorization_header and (
source_scheme != redirect_scheme
or source_host != redirect_host
or source_port != redirect_port
):
del redirect_request.headers["Authorization"]
return redirect_request
@ -103,7 +144,7 @@ class RedirectMiddleware(BaseRedirectMiddleware):
def process_response(
self, request: Request, response: Response, spider: Spider
) -> Union[Request, Response]:
) -> Request | Response:
if (
request.meta.get("dont_redirect", False)
or response.status in getattr(spider, "handle_httpstatus_list", [])
@ -119,13 +160,15 @@ class RedirectMiddleware(BaseRedirectMiddleware):
assert response.headers["Location"] is not None
location = safe_url_string(response.headers["Location"])
if response.headers["Location"].startswith(b"//"):
request_scheme = urlparse(request.url).scheme
request_scheme = urlparse_cached(request).scheme
location = request_scheme + "://" + location.lstrip("/")
redirected_url = urljoin(request.url, location)
redirected = _build_redirect_request(request, url=redirected_url)
if urlparse_cached(redirected).scheme not in {"http", "https"}:
return response
if response.status in (301, 307, 308) or request.method == "HEAD":
redirected = _build_redirect_request(request, url=redirected_url)
return self._redirect(redirected, request, spider, response.status)
redirected = self._redirect_request_using_get(request, redirected_url)
@ -137,22 +180,26 @@ class MetaRefreshMiddleware(BaseRedirectMiddleware):
def __init__(self, settings: BaseSettings):
super().__init__(settings)
self._ignore_tags: List[str] = settings.getlist("METAREFRESH_IGNORE_TAGS")
self._ignore_tags: list[str] = settings.getlist("METAREFRESH_IGNORE_TAGS")
self._maxdelay: int = settings.getint("METAREFRESH_MAXDELAY")
def process_response(
self, request: Request, response: Response, spider: Spider
) -> Union[Request, Response]:
) -> Request | Response:
if (
request.meta.get("dont_redirect", False)
or request.method == "HEAD"
or not isinstance(response, HtmlResponse)
or urlparse_cached(request).scheme not in {"http", "https"}
):
return response
interval, url = get_meta_refresh(response, ignore_tags=self._ignore_tags)
if url and cast(float, interval) < self._maxdelay:
redirected = self._redirect_request_using_get(request, url)
if not url:
return response
redirected = self._redirect_request_using_get(request, url)
if urlparse_cached(redirected).scheme not in {"http", "https"}:
return response
if cast(float, interval) < self._maxdelay:
return self._redirect(redirected, request, spider, "meta refresh")
return response

37
scrapy/downloadermiddlewares/retry.py
View File

@ -7,20 +7,17 @@ RETRY_TIMES - how many times to retry a failed page
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.
once the spider has finished crawling all regular (non-failed) pages.
"""
from __future__ import annotations
import warnings
from logging import Logger, getLogger
from typing import TYPE_CHECKING, Any, Optional, Tuple, Type, Union
from typing import TYPE_CHECKING, Any
from scrapy.crawler import Crawler
from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning
from scrapy.http import Response
from scrapy.http.request import Request
from scrapy.settings import BaseSettings, Settings
from scrapy.spiders import Spider
from scrapy.utils.misc import load_object
from scrapy.utils.python import global_object_name
from scrapy.utils.response import response_status_message
@ -29,10 +26,16 @@ if TYPE_CHECKING:
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy.crawler import Crawler
from scrapy.http import Response
from scrapy.http.request import Request
from scrapy.spiders import Spider
retry_logger = getLogger(__name__)
def backwards_compatibility_getattr(self: Any, name: str) -> Tuple[Any, ...]:
def backwards_compatibility_getattr(self: Any, name: str) -> tuple[Any, ...]:
if name == "EXCEPTIONS_TO_RETRY":
warnings.warn(
"Attribute RetryMiddleware.EXCEPTIONS_TO_RETRY is deprecated. "
@ -57,12 +60,12 @@ def get_retry_request(
request: Request,
*,
spider: Spider,
reason: Union[str, Exception, Type[Exception]] = "unspecified",
max_retry_times: Optional[int] = None,
priority_adjust: Optional[int] = None,
reason: str | Exception | type[Exception] = "unspecified",
max_retry_times: int | None = None,
priority_adjust: int | None = None,
logger: Logger = retry_logger,
stats_base_key: str = "retry",
) -> Optional[Request]:
) -> Request | None:
"""
Returns a new :class:`~scrapy.Request` object to retry the specified
request, or ``None`` if retries of the specified request have been
@ -146,9 +149,7 @@ class RetryMiddleware(metaclass=BackwardsCompatibilityMetaclass):
if not settings.getbool("RETRY_ENABLED"):
raise NotConfigured
self.max_retry_times = settings.getint("RETRY_TIMES")
self.retry_http_codes = set(
int(x) for x in settings.getlist("RETRY_HTTP_CODES")
)
self.retry_http_codes = {int(x) for x in settings.getlist("RETRY_HTTP_CODES")}
self.priority_adjust = settings.getint("RETRY_PRIORITY_ADJUST")
try:
@ -166,7 +167,7 @@ class RetryMiddleware(metaclass=BackwardsCompatibilityMetaclass):
def process_response(
self, request: Request, response: Response, spider: Spider
) -> Union[Request, Response]:
) -> Request | Response:
if request.meta.get("dont_retry", False):
return response
if response.status in self.retry_http_codes:
@ -176,7 +177,7 @@ class RetryMiddleware(metaclass=BackwardsCompatibilityMetaclass):
def process_exception(
self, request: Request, exception: Exception, spider: Spider
) -> Union[Request, Response, None]:
) -> Request | Response | None:
if isinstance(exception, self.exceptions_to_retry) and not request.meta.get(
"dont_retry", False
):
@ -186,9 +187,9 @@ class RetryMiddleware(metaclass=BackwardsCompatibilityMetaclass):
def _retry(
self,
request: Request,
reason: Union[str, Exception, Type[Exception]],
reason: str | Exception | type[Exception],
spider: Spider,
) -> Optional[Request]:
) -> Request | None:
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(

40
scrapy/downloadermiddlewares/robotstxt.py
View File

@ -7,28 +7,32 @@ enable this middleware and enable the ROBOTSTXT_OBEY setting.
from __future__ import annotations
import logging
from typing import TYPE_CHECKING, Any, Dict, Optional, Union
from typing import TYPE_CHECKING, TypeVar
from twisted.internet.defer import Deferred, maybeDeferred
from twisted.python.failure import Failure
from scrapy import Spider
from scrapy.crawler import Crawler
from scrapy.exceptions import IgnoreRequest, NotConfigured
from scrapy.http import Request, Response
from scrapy.http.request import NO_CALLBACK
from scrapy.robotstxt import RobotParser
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.log import failure_to_exc_info
from scrapy.utils.misc import load_object
if TYPE_CHECKING:
from twisted.python.failure import Failure
# typing.Self requires Python 3.11
from typing_extensions import Self
from scrapy import Spider
from scrapy.crawler import Crawler
from scrapy.robotstxt import RobotParser
logger = logging.getLogger(__name__)
_T = TypeVar("_T")
class RobotsTxtMiddleware:
DOWNLOAD_PRIORITY: int = 1000
@ -37,11 +41,11 @@ class RobotsTxtMiddleware:
if not crawler.settings.getbool("ROBOTSTXT_OBEY"):
raise NotConfigured
self._default_useragent: str = crawler.settings.get("USER_AGENT", "Scrapy")
self._robotstxt_useragent: Optional[str] = crawler.settings.get(
self._robotstxt_useragent: str | None = crawler.settings.get(
"ROBOTSTXT_USER_AGENT", None
)
self.crawler: Crawler = crawler
self._parsers: Dict[str, Union[RobotParser, Deferred, None]] = {}
self._parsers: dict[str, RobotParser | Deferred[RobotParser | None] | None] = {}
self._parserimpl: RobotParser = load_object(
crawler.settings.get("ROBOTSTXT_PARSER")
)
@ -53,22 +57,26 @@ class RobotsTxtMiddleware:
def from_crawler(cls, crawler: Crawler) -> Self:
return cls(crawler)
def process_request(self, request: Request, spider: Spider) -> Optional[Deferred]:
def process_request(
self, request: Request, spider: Spider
) -> Deferred[None] | None:
if request.meta.get("dont_obey_robotstxt"):
return None
if request.url.startswith("data:") or request.url.startswith("file:"):
return None
d: Deferred = maybeDeferred(self.robot_parser, request, spider)
d.addCallback(self.process_request_2, request, spider)
return d
d: Deferred[RobotParser | None] = maybeDeferred(
self.robot_parser, request, spider # type: ignore[call-overload]
)
d2: Deferred[None] = d.addCallback(self.process_request_2, request, spider)
return d2
def process_request_2(
self, rp: Optional[RobotParser], request: Request, spider: Spider
self, rp: RobotParser | None, request: Request, spider: Spider
) -> None:
if rp is None:
return
useragent: Union[str, bytes, None] = self._robotstxt_useragent
useragent: str | bytes | None = self._robotstxt_useragent
if not useragent:
useragent = request.headers.get(b"User-Agent", self._default_useragent)
assert useragent is not None
@ -84,7 +92,7 @@ class RobotsTxtMiddleware:
def robot_parser(
self, request: Request, spider: Spider
) -> Union[RobotParser, Deferred, None]:
) -> RobotParser | Deferred[RobotParser | None] | None:
url = urlparse_cached(request)
netloc = url.netloc
@ -107,9 +115,9 @@ class RobotsTxtMiddleware:
parser = self._parsers[netloc]
if isinstance(parser, Deferred):
d: Deferred = Deferred()
d: Deferred[RobotParser | None] = Deferred()
def cb(result: Any) -> Any:
def cb(result: RobotParser | None) -> RobotParser | None:
d.callback(result)
return result

Some files were not shown because too many files have changed in this diff Show More