diff --git a/.bandit.yml b/.bandit.yml index 2aae8a0aa..6e8331c0f 100644 --- a/.bandit.yml +++ b/.bandit.yml @@ -1,21 +1,19 @@ 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 +- B105 # hardcoded_password_string +- B301 # pickle +- B307 # eval +- B311 # random +- B320 # xml_bad_etree +- B321 # ftplib, https://github.com/scrapy/scrapy/issues/4180 +- B324 # hashlib "Use of weak SHA1 hash for security" +- B402 # import_ftplib, https://github.com/scrapy/scrapy/issues/4180 +- B403 # import_pickle +- B404 # import_subprocess +- B406 # import_xml_sax +- B410 # import_lxml +- B411 # import_xmlrpclib, https://github.com/PyCQA/bandit/issues/1082 +- B503 # ssl_with_bad_defaults +- B603 # subprocess_without_shell_equals_true +- B605 # start_process_with_a_shell exclude_dirs: ['tests'] diff --git a/.bumpversion.cfg b/.bumpversion.cfg index f76bf783d..968a34d96 100644 --- a/.bumpversion.cfg +++ b/.bumpversion.cfg @@ -1,7 +1,11 @@ [bumpversion] -current_version = 2.11.0 +current_version = 2.11.1 commit = True tag = True tag_name = {new_version} [bumpversion:file:scrapy/VERSION] + +[bumpversion:file:SECURITY.md] +parse = (?P\d+)\.(?P\d+)\.x +serialize = {major}.{minor}.x diff --git a/.flake8 b/.flake8 index 544d72956..62ccad9cf 100644 --- a/.flake8 +++ b/.flake8 @@ -1,7 +1,7 @@ [flake8] max-line-length = 119 -ignore = W503, E203 +ignore = E203, E501, E701, E704, W503 exclude = docs/conf.py diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 0cff5cc73..a911d4cfe 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,19 +1,19 @@ repos: - repo: https://github.com/PyCQA/bandit - rev: 1.7.5 + rev: 1.7.7 hooks: - id: bandit args: [-r, -c, .bandit.yml] - repo: https://github.com/PyCQA/flake8 - rev: 6.1.0 + rev: 7.0.0 hooks: - id: flake8 - repo: https://github.com/psf/black.git - rev: 23.9.1 + rev: 24.2.0 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 @@ -21,4 +21,4 @@ repos: hooks: - id: blacken-docs additional_dependencies: - - black==23.9.1 + - black==24.2.0 diff --git a/README.rst b/README.rst index 1918850d6..14adff648 100644 --- a/README.rst +++ b/README.rst @@ -17,9 +17,10 @@ Scrapy :target: https://github.com/scrapy/scrapy/actions?query=workflow%3AUbuntu :alt: Ubuntu -.. image:: https://github.com/scrapy/scrapy/workflows/macOS/badge.svg - :target: https://github.com/scrapy/scrapy/actions?query=workflow%3AmacOS - :alt: macOS +.. .. image:: https://github.com/scrapy/scrapy/workflows/macOS/badge.svg + .. :target: https://github.com/scrapy/scrapy/actions?query=workflow%3AmacOS + .. :alt: macOS + .. image:: https://github.com/scrapy/scrapy/workflows/Windows/badge.svg :target: https://github.com/scrapy/scrapy/actions?query=workflow%3AWindows @@ -41,7 +42,7 @@ Scrapy Overview ======== -Scrapy is a fast high-level web crawling and web scraping framework, used to +Scrapy is a BSD-licensed fast high-level web crawling and web scraping framework, used to crawl websites and extract structured data from their pages. It can be used for a wide range of purposes, from data mining to monitoring and automated testing. @@ -110,4 +111,4 @@ See https://scrapy.org/companies/ for a list. Commercial Support ================== -See https://scrapy.org/support/ for details. +See https://scrapy.org/support/ for details. \ No newline at end of file diff --git a/SECURITY.md b/SECURITY.md new file mode 100644 index 000000000..51305d95e --- /dev/null +++ b/SECURITY.md @@ -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. diff --git a/docs/_tests/quotes.html b/docs/_tests/quotes.html index 71aff8847..f4002ecd1 100644 --- a/docs/_tests/quotes.html +++ b/docs/_tests/quotes.html @@ -273,7 +273,7 @@ Quotes by: GoodReads.com

- Made with ❤ by Scrapinghub + Made with ❤ by Zyte

diff --git a/docs/_tests/quotes1.html b/docs/_tests/quotes1.html index 71aff8847..f4002ecd1 100644 --- a/docs/_tests/quotes1.html +++ b/docs/_tests/quotes1.html @@ -273,7 +273,7 @@ Quotes by: GoodReads.com

- Made with ❤ by Scrapinghub + Made with ❤ by Zyte

diff --git a/docs/conf.py b/docs/conf.py index 9ca0f817a..399078010 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -227,7 +227,7 @@ 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/", ] diff --git a/docs/contributing.rst b/docs/contributing.rst index 2b3249601..d728338da 100644 --- a/docs/contributing.rst +++ b/docs/contributing.rst @@ -178,7 +178,7 @@ Scrapy: * We use `black `_ for code formatting. There is a hook in the pre-commit config that will automatically format your code before every commit. You can also - run black manually with ``tox -e black``. + run black manually with ``tox -e pre-commit``. * Don't put your name in the code you contribute; git provides enough metadata to identify author of the code. diff --git a/docs/faq.rst b/docs/faq.rst index 20dd814df..7090f0bcd 100644 --- a/docs/faq.rst +++ b/docs/faq.rst @@ -297,9 +297,13 @@ 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? ----------------------------------------- @@ -405,6 +409,23 @@ or :class:`~scrapy.signals.headers_received` signals and raising a :ref:`topics-stop-response-download` topic for additional information and examples. +.. _faq-blank-request: + +How can I make a blank request? +------------------------------- + +.. code-block:: python + + from scrapy import 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 +content (",") essentially creates a request to a data URL without any specific content. + + Running ``runspider`` I get ``error: No spider found in file: `` -------------------------------------------------------------------------- diff --git a/docs/news.rst b/docs/news.rst index 5db37969c..fafea0bf8 100644 --- a/docs/news.rst +++ b/docs/news.rst @@ -3,6 +3,105 @@ Release notes ============= +.. _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 `. + (: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 + ` 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) @@ -32,8 +131,10 @@ Backward-incompatible changes :meth:`scrapy.crawler.Crawler.__init__` and before the settings are finalized and frozen. This change was needed to allow changing the settings in :meth:`scrapy.Spider.from_crawler`. If you want to access the final - setting values in the spider code as early as possible you can do this in - :meth:`~scrapy.Spider.start_requests`. (:issue:`6038`) + setting values and the initialized :class:`~scrapy.crawler.Crawler` + attributes in the spider code as early as possible you can do this in + :meth:`~scrapy.Spider.start_requests` or in a handler of the + :signal:`engine_started` signal. (:issue:`6038`) - The :meth:`TextResponse.json ` method now requires the response to be in a valid JSON encoding (UTF-8, UTF-16, or @@ -60,6 +161,9 @@ Deprecation removals 1.0.0, use :attr:`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 ~~~~~~~~~~~~ @@ -1155,6 +1259,9 @@ 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 ~~~~~~~~~~~~ @@ -2869,6 +2976,38 @@ 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: diff --git a/docs/requirements.txt b/docs/requirements.txt index 9f9aef711..5f683d34c 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1,4 +1,4 @@ -sphinx==5.0.2 -sphinx-hoverxref==1.1.1 -sphinx-notfound-page==0.8 -sphinx-rtd-theme==1.0.0 +sphinx==6.2.1 +sphinx-hoverxref==1.3.0 +sphinx-notfound-page==1.0.0 +sphinx-rtd-theme==2.0.0 diff --git a/docs/topics/addons.rst b/docs/topics/addons.rst index 1bf2172bd..d2fc41003 100644 --- a/docs/topics/addons.rst +++ b/docs/topics/addons.rst @@ -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: diff --git a/docs/topics/autothrottle.rst b/docs/topics/autothrottle.rst index 8e6aae65c..5370d77b3 100644 --- a/docs/topics/autothrottle.rst +++ b/docs/topics/autothrottle.rst @@ -131,7 +131,7 @@ 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 diff --git a/docs/topics/debug.rst b/docs/topics/debug.rst index 49c5b0410..988e37bbd 100644 --- a/docs/topics/debug.rst +++ b/docs/topics/debug.rst @@ -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 diff --git a/docs/topics/feed-exports.rst b/docs/topics/feed-exports.rst index 700775e4b..922b765db 100644 --- a/docs/topics/feed-exports.rst +++ b/docs/topics/feed-exports.rst @@ -13,6 +13,11 @@ Scrapy provides this functionality out of the box with the Feed Exports, which allows you to generate feeds with the scraped items, using multiple serialization formats and storage backends. +This page provides detailed documentation for all feed export features. If you +are looking for a step-by-step guide, check out `Zyte’s export guides`_. + +.. _Zyte’s export guides: https://docs.zyte.com/web-scraping/guides/export/index.html#exporting-scraped-data + .. _topics-feed-format: Serialization formats @@ -385,7 +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 `. You can then access those parameters from the ``__init__`` method of your plugin. diff --git a/docs/topics/items.rst b/docs/topics/items.rst index 3c38ac2dc..97ed7a900 100644 --- a/docs/topics/items.rst +++ b/docs/topics/items.rst @@ -399,12 +399,7 @@ In code that receives an item, such as methods of :ref:`item pipelines `, 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 `: - -.. autoclass:: itemadapter.ItemAdapter - -.. autofunction:: itemadapter.is_item - +any supported item type. Other classes related to items ============================== diff --git a/docs/topics/media-pipeline.rst b/docs/topics/media-pipeline.rst index da0587aa4..c96dd0f99 100644 --- a/docs/topics/media-pipeline.rst +++ b/docs/topics/media-pipeline.rst @@ -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. diff --git a/docs/topics/practices.rst b/docs/topics/practices.rst index f64da22d8..b1b8c9e9c 100644 --- a/docs/topics/practices.rst +++ b/docs/topics/practices.rst @@ -288,9 +288,8 @@ Here are some tips to keep in mind when dealing with these kinds of sites: * use a pool of rotating IPs. For example, the free `Tor project`_ or paid services like `ProxyMesh`_. An open source alternative is `scrapoxy`_, a super proxy that you can attach your own proxies to. -* use a highly distributed downloader that circumvents bans internally, so you - can just focus on parsing clean pages. One example of such downloaders is - `Zyte Smart Proxy Manager`_ +* use a ban avoidance service, such as `Zyte API`_, which provides a `Scrapy + plugin `__ If you are still unable to prevent your bot getting banned, consider contacting `commercial support`_. @@ -301,4 +300,4 @@ If you are still unable to prevent your bot getting banned, consider contacting .. _Common Crawl: https://commoncrawl.org/ .. _testspiders: https://github.com/scrapinghub/testspiders .. _scrapoxy: https://scrapoxy.io/ -.. _Zyte Smart Proxy Manager: https://www.zyte.com/smart-proxy-manager/ +.. _Zyte API: https://docs.zyte.com/zyte-api/get-started.html diff --git a/docs/topics/request-response.rst b/docs/topics/request-response.rst index adf3d0f4a..eb70ebce8 100644 --- a/docs/topics/request-response.rst +++ b/docs/topics/request-response.rst @@ -193,18 +193,47 @@ Request objects :meth:`replace`. .. attribute:: Request.meta + :value: {} - A dict that contains arbitrary metadata for this request. This dict is - empty for new Requests, and is usually populated by different Scrapy - components (extensions, middlewares, etc). So the data contained in this - dict depends on the extensions you have enabled. + A dictionary of arbitrary metadata for the request. - See :ref:`topics-request-meta` for a list of special meta keys - recognized by Scrapy. + You may extend request metadata as you see fit. - This dict is :doc:`shallow copied ` when the request is - cloned using the ``copy()`` or ``replace()`` methods, and can also be - accessed, in your spider, from the ``response.meta`` attribute. + Request metadata can also be accessed through the + :attr:`~scrapy.http.Response.meta` attribute of a response. + + To pass data from one spider callback to another, consider using + :attr:`cb_kwargs` instead. However, request metadata may be the right + choice in certain scenarios, such as to maintain some debugging data + across all follow-up requests (e.g. the source URL). + + A common use of request metadata is to define request-specific + parameters for Scrapy components (extensions, middlewares, etc.). For + example, if you set ``dont_retry`` to ``True``, + :class:`~scrapy.downloadermiddlewares.retry.RetryMiddleware` will never + retry that request, even if it fails. See :ref:`topics-request-meta`. + + You may also use request metadata in your custom Scrapy components, for + example, to keep request state information relevant to your component. + For example, + :class:`~scrapy.downloadermiddlewares.retry.RetryMiddleware` uses the + ``retry_times`` metadata key to keep track of how many times a request + has been retried so far. + + Copying all the metadata of a previous request into a new, follow-up + request in a spider callback is a bad practice, because request + metadata may include metadata set by Scrapy components that is not + meant to be copied into other requests. For example, copying the + ``retry_times`` metadata key into follow-up requests can lower the + amount of retries allowed for those follow-up requests. + + You should only copy all request metadata from one request to another + if the new request is meant to replace the old request, as is often the + case when returning a request from a :ref:`downloader middleware + ` method. + + Also mind that the :meth:`copy` and :meth:`replace` request methods + :doc:`shallow-copy ` request metadata. .. attribute:: Request.cb_kwargs @@ -440,60 +469,6 @@ import path. .. autoclass:: scrapy.utils.request.RequestFingerprinter - -.. setting:: REQUEST_FINGERPRINTER_IMPLEMENTATION - -REQUEST_FINGERPRINTER_IMPLEMENTATION -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -.. versionadded:: 2.7 - -Default: ``'2.6'`` - -Determines which request fingerprinting algorithm is used by the default -request fingerprinter class (see :setting:`REQUEST_FINGERPRINTER_CLASS`). - -Possible values are: - -- ``'2.6'`` (default) - - This implementation uses the same request fingerprinting algorithm as - Scrapy 2.6 and earlier versions. - - Even though this is the default value for backward compatibility reasons, - it is a deprecated value. - -- ``'2.7'`` - - This implementation was introduced in Scrapy 2.7 to fix an issue of the - previous implementation. - - New projects should use this value. The :command:`startproject` command - sets this value in the generated ``settings.py`` file. - -If you are using the default value (``'2.6'``) for this setting, and you are -using Scrapy components where changing the request fingerprinting algorithm -would cause undesired results, you need to carefully decide when to change the -value of this setting, or switch the :setting:`REQUEST_FINGERPRINTER_CLASS` -setting to a custom request fingerprinter class that implements the 2.6 request -fingerprinting algorithm and does not log this warning ( -:ref:`2.6-request-fingerprinter` includes an example implementation of such a -class). - -Scenarios where changing the request fingerprinting algorithm may cause -undesired results include, for example, using the HTTP cache middleware (see -:class:`~scrapy.downloadermiddlewares.httpcache.HttpCacheMiddleware`). -Changing the request fingerprinting algorithm would invalidate the current -cache, requiring you to redownload all requests again. - -Otherwise, set :setting:`REQUEST_FINGERPRINTER_IMPLEMENTATION` to ``'2.7'`` in -your settings to switch already to the request fingerprinting implementation -that will be the only request fingerprinting implementation available in a -future version of Scrapy, and remove the deprecation warning triggered by using -the default value (``'2.6'``). - - -.. _2.6-request-fingerprinter: .. _custom-request-fingerprinter: Writing your own request fingerprinter @@ -702,6 +677,7 @@ 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) @@ -1328,3 +1304,13 @@ XmlResponse objects line. See :attr:`TextResponse.encoding`. .. _bug in lxml: https://bugs.launchpad.net/lxml/+bug/1665241 + +JsonResponse objects +-------------------- + +.. class:: JsonResponse(url[, ...]) + + The :class:`JsonResponse` class is a subclass of :class:`TextResponse` + that is used when the response has a `JSON MIME type + `_ in its `Content-Type` + header. diff --git a/docs/topics/selectors.rst b/docs/topics/selectors.rst index 4a64d530b..e32fc2b70 100644 --- a/docs/topics/selectors.rst +++ b/docs/topics/selectors.rst @@ -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: diff --git a/docs/topics/settings.rst b/docs/topics/settings.rst index 06f8481ba..439aedc18 100644 --- a/docs/topics/settings.rst +++ b/docs/topics/settings.rst @@ -873,40 +873,42 @@ 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 diff --git a/docs/topics/spiders.rst b/docs/topics/spiders.rst index 20452d558..30677fe74 100644 --- a/docs/topics/spiders.rst +++ b/docs/topics/spiders.rst @@ -142,8 +142,14 @@ scrapy.Spider method, which is handy if you want to modify them based on arguments. As a consequence, these settings aren't the final values as they can be modified later by e.g. :ref:`add-ons - `. The final settings are available in the - :meth:`start_requests` method and later. + `. For the same reason, most of the + :class:`~scrapy.crawler.Crawler` attributes aren't initialized at + this point. + + The final settings and the initialized + :class:`~scrapy.crawler.Crawler` attributes are available in the + :meth:`start_requests` method, handlers of the + :signal:`engine_started` signal and later. :param crawler: crawler to which the spider will be bound :type crawler: :class:`~scrapy.crawler.Crawler` instance diff --git a/pylintrc b/pylintrc index c8654b8d3..c60e4e16a 100644 --- a/pylintrc +++ b/pylintrc @@ -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 diff --git a/scrapy/VERSION b/scrapy/VERSION index 46b81d815..6ceb272ee 100644 --- a/scrapy/VERSION +++ b/scrapy/VERSION @@ -1 +1 @@ -2.11.0 +2.11.1 diff --git a/scrapy/addons.py b/scrapy/addons.py index 9060d4f3f..65d7a0310 100644 --- a/scrapy/addons.py +++ b/scrapy/addons.py @@ -4,7 +4,7 @@ from typing import TYPE_CHECKING, Any, List from scrapy.exceptions import NotConfigured from scrapy.settings import Settings from scrapy.utils.conf import build_component_list -from scrapy.utils.misc import create_instance, load_object +from scrapy.utils.misc import build_from_crawler, load_object if TYPE_CHECKING: from scrapy.crawler import Crawler @@ -32,9 +32,7 @@ class AddonManager: for clspath in build_component_list(settings["ADDONS"]): try: addoncls = load_object(clspath) - addon = create_instance( - addoncls, settings=settings, crawler=self.crawler - ) + addon = build_from_crawler(addoncls, self.crawler) addon.update_settings(settings) self.addons.append(addon) except NotConfigured as e: diff --git a/scrapy/commands/__init__.py b/scrapy/commands/__init__.py index 2aa569cdd..27993710e 100644 --- a/scrapy/commands/__init__.py +++ b/scrapy/commands/__init__.py @@ -1,6 +1,7 @@ """ Base class for Scrapy commands """ + import argparse import os from pathlib import Path diff --git a/scrapy/commands/parse.py b/scrapy/commands/parse.py index ac937e464..c9f8586d3 100644 --- a/scrapy/commands/parse.py +++ b/scrapy/commands/parse.py @@ -1,3 +1,4 @@ +import functools import inspect import json import logging @@ -251,39 +252,40 @@ class Command(BaseRunSpiderCommand): return scraped_data + def _get_callback(self, *, spider, opts, response=None): + cb = None + if response: + cb = response.meta["_callback"] + if not cb: + if opts.callback: + cb = opts.callback + elif response and opts.rules and self.first_response == response: + cb = self.get_callback_from_rules(spider, response) + if not cb: + raise ValueError( + f"Cannot find a rule that matches {response.url!r} in spider: " + f"{spider.name}" + ) + else: + cb = "parse" + + if not callable(cb): + cb_method = getattr(spider, cb, None) + if callable(cb_method): + cb = cb_method + else: + raise ValueError( + f"Cannot find callback {cb!r} in spider: {spider.name}" + ) + return cb + def prepare_request(self, spider, request, opts): def callback(response, **cb_kwargs): # memorize first request if not self.first_response: self.first_response = response - # determine real callback - cb = response.meta["_callback"] - if not cb: - if opts.callback: - cb = opts.callback - elif opts.rules and self.first_response == response: - cb = self.get_callback_from_rules(spider, response) - - if not cb: - logger.error( - "Cannot find a rule that matches %(url)r in spider: %(spider)s", - {"url": response.url, "spider": spider.name}, - ) - return - else: - cb = "parse" - - if not callable(cb): - cb_method = getattr(spider, cb, None) - if callable(cb_method): - cb = cb_method - else: - logger.error( - "Cannot find callback %(callback)r in spider: %(spider)s", - {"callback": cb, "spider": spider.name}, - ) - return + cb = self._get_callback(spider=spider, opts=opts, response=response) # parse items and requests depth = response.meta["_depth"] @@ -303,6 +305,9 @@ class Command(BaseRunSpiderCommand): request.meta["_depth"] = 1 request.meta["_callback"] = request.callback + if not request.callback and not opts.rules: + cb = self._get_callback(spider=spider, opts=opts) + functools.update_wrapper(callback, cb) request.callback = callback return request diff --git a/scrapy/commands/shell.py b/scrapy/commands/shell.py index 12e37babc..f72a23c6a 100644 --- a/scrapy/commands/shell.py +++ b/scrapy/commands/shell.py @@ -3,6 +3,7 @@ Scrapy Shell See documentation in docs/topics/shell.rst """ + from argparse import Namespace from threading import Thread from typing import List, Type diff --git a/scrapy/core/downloader/contextfactory.py b/scrapy/core/downloader/contextfactory.py index 909cc273f..dba4d8cdc 100644 --- a/scrapy/core/downloader/contextfactory.py +++ b/scrapy/core/downloader/contextfactory.py @@ -20,7 +20,7 @@ from scrapy.core.downloader.tls import ( openssl_methods, ) from scrapy.settings import BaseSettings -from scrapy.utils.misc import create_instance, load_object +from scrapy.utils.misc import build_from_crawler, load_object if TYPE_CHECKING: from twisted.internet._sslverify import ClientTLSOptions @@ -165,18 +165,16 @@ def load_context_factory_from_settings(settings, crawler): context_factory_cls = load_object(settings["DOWNLOADER_CLIENTCONTEXTFACTORY"]) # try method-aware context factory try: - context_factory = create_instance( - objcls=context_factory_cls, - settings=settings, - crawler=crawler, + context_factory = build_from_crawler( + context_factory_cls, + crawler, method=ssl_method, ) except TypeError: # use context factory defaults - context_factory = create_instance( - objcls=context_factory_cls, - settings=settings, - crawler=crawler, + context_factory = build_from_crawler( + context_factory_cls, + crawler, ) msg = ( f"{settings['DOWNLOADER_CLIENTCONTEXTFACTORY']} does not accept " diff --git a/scrapy/core/downloader/handlers/__init__.py b/scrapy/core/downloader/handlers/__init__.py index 6a211aafa..ade51ca63 100644 --- a/scrapy/core/downloader/handlers/__init__.py +++ b/scrapy/core/downloader/handlers/__init__.py @@ -9,7 +9,7 @@ from twisted.internet.defer import Deferred from scrapy import Request, Spider, signals from scrapy.exceptions import NotConfigured, NotSupported from scrapy.utils.httpobj import urlparse_cached -from scrapy.utils.misc import create_instance, load_object +from scrapy.utils.misc import build_from_crawler, load_object from scrapy.utils.python import without_none_values if TYPE_CHECKING: @@ -21,9 +21,9 @@ logger = logging.getLogger(__name__) class DownloadHandlers: def __init__(self, crawler: "Crawler"): self._crawler: "Crawler" = crawler - self._schemes: Dict[ - str, Union[str, Callable] - ] = {} # stores acceptable schemes on instancing + 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( @@ -55,10 +55,9 @@ class DownloadHandlers: dhcls = load_object(path) if skip_lazy and getattr(dhcls, "lazy", True): return None - dh = create_instance( - objcls=dhcls, - settings=self._crawler.settings, - crawler=self._crawler, + dh = build_from_crawler( + dhcls, + self._crawler, ) except NotConfigured as ex: self._notconfigured[scheme] = str(ex) diff --git a/scrapy/core/downloader/handlers/http10.py b/scrapy/core/downloader/handlers/http10.py index 6c1dac4a5..d168c2b2e 100644 --- a/scrapy/core/downloader/handlers/http10.py +++ b/scrapy/core/downloader/handlers/http10.py @@ -1,6 +1,7 @@ """Download handlers for http and https schemes """ -from scrapy.utils.misc import create_instance, load_object + +from scrapy.utils.misc import build_from_crawler, load_object from scrapy.utils.python import to_unicode @@ -30,10 +31,9 @@ class HTTP10DownloadHandler: host, port = to_unicode(factory.host), factory.port if factory.scheme == b"https": - client_context_factory = create_instance( - objcls=self.ClientContextFactory, - settings=self._settings, - crawler=self._crawler, + client_context_factory = build_from_crawler( + self.ClientContextFactory, + self._crawler, ) return reactor.connectSSL(host, port, factory, client_context_factory) return reactor.connectTCP(host, port, factory) diff --git a/scrapy/core/downloader/handlers/s3.py b/scrapy/core/downloader/handlers/s3.py index 81d8e8115..1f7533759 100644 --- a/scrapy/core/downloader/handlers/s3.py +++ b/scrapy/core/downloader/handlers/s3.py @@ -2,7 +2,7 @@ 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 create_instance +from scrapy.utils.misc import build_from_crawler class S3DownloadHandler: @@ -50,10 +50,9 @@ class S3DownloadHandler: ) ) - _http_handler = create_instance( - objcls=httpdownloadhandler, - settings=settings, - crawler=crawler, + _http_handler = build_from_crawler( + httpdownloadhandler, + crawler, ) self._download_http = _http_handler.download_request diff --git a/scrapy/core/downloader/middleware.py b/scrapy/core/downloader/middleware.py index dca13c01e..52ebe4e22 100644 --- a/scrapy/core/downloader/middleware.py +++ b/scrapy/core/downloader/middleware.py @@ -3,6 +3,7 @@ Downloader Middleware manager See documentation in docs/topics/downloader-middleware.rst """ + from typing import Any, Callable, Generator, List, Union, cast from twisted.internet.defer import Deferred, inlineCallbacks diff --git a/scrapy/core/engine.py b/scrapy/core/engine.py index dd1f56f8c..2db085081 100644 --- a/scrapy/core/engine.py +++ b/scrapy/core/engine.py @@ -4,6 +4,7 @@ This is the Scrapy engine which controls the Scheduler, Downloader and Spider. For more information see docs/topics/architecture.rst """ + import logging from time import time from typing import ( @@ -34,7 +35,7 @@ from scrapy.settings import BaseSettings, 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 create_instance, load_object +from scrapy.utils.misc import build_from_crawler, load_object from scrapy.utils.reactor import CallLaterOnce if TYPE_CHECKING: @@ -358,9 +359,7 @@ class ExecutionEngine: raise RuntimeError(f"No free spider slot when opening {spider.name!r}") logger.info("Spider opened", extra={"spider": spider}) nextcall = CallLaterOnce(self._next_request) - scheduler = create_instance( - self.scheduler_cls, settings=None, crawler=self.crawler - ) + scheduler = build_from_crawler(self.scheduler_cls, self.crawler) start_requests = yield self.scraper.spidermw.process_start_requests( start_requests, spider ) diff --git a/scrapy/core/http2/stream.py b/scrapy/core/http2/stream.py index 39d5921f4..4132fc385 100644 --- a/scrapy/core/http2/stream.py +++ b/scrapy/core/http2/stream.py @@ -2,7 +2,6 @@ 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 h2.errors import ErrorCodes from h2.exceptions import H2Error, ProtocolError, StreamClosedError @@ -15,6 +14,7 @@ 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 scrapy.core.http2.protocol import H2ClientProtocol @@ -111,17 +111,17 @@ 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), + "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 @@ -185,7 +185,7 @@ 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") @@ -194,7 +194,7 @@ class Stream: ) def _get_request_headers(self) -> List[Tuple[str, str]]: - url = urlparse(self._request.url) + url = urlparse_cached(self._request) path = url.path if url.query: diff --git a/scrapy/core/scheduler.py b/scrapy/core/scheduler.py index 17c95f1ea..f41b83a67 100644 --- a/scrapy/core/scheduler.py +++ b/scrapy/core/scheduler.py @@ -14,7 +14,7 @@ from scrapy.http.request import Request from scrapy.spiders import Spider from scrapy.statscollectors import StatsCollector from scrapy.utils.job import job_dir -from scrapy.utils.misc import create_instance, load_object +from scrapy.utils.misc import build_from_crawler, load_object if TYPE_CHECKING: # typing.Self requires Python 3.11 @@ -202,7 +202,7 @@ class Scheduler(BaseScheduler): """ dupefilter_cls = load_object(crawler.settings["DUPEFILTER_CLASS"]) return cls( - dupefilter=create_instance(dupefilter_cls, crawler.settings, crawler), + dupefilter=build_from_crawler(dupefilter_cls, crawler), jobdir=job_dir(crawler.settings), dqclass=load_object(crawler.settings["SCHEDULER_DISK_QUEUE"]), mqclass=load_object(crawler.settings["SCHEDULER_MEMORY_QUEUE"]), @@ -322,10 +322,9 @@ class Scheduler(BaseScheduler): def _mq(self): """Create a new priority queue instance, with in-memory storage""" - return create_instance( + return build_from_crawler( self.pqclass, - settings=None, - crawler=self.crawler, + self.crawler, downstream_queue_cls=self.mqclass, key="", ) @@ -334,10 +333,9 @@ class Scheduler(BaseScheduler): """Create a new priority queue instance, with disk storage""" assert self.dqdir state = self._read_dqs_state(self.dqdir) - q = create_instance( + q = build_from_crawler( self.pqclass, - settings=None, - crawler=self.crawler, + self.crawler, downstream_queue_cls=self.dqclass, key=self.dqdir, startprios=state, diff --git a/scrapy/core/scraper.py b/scrapy/core/scraper.py index 8fb16b8a9..272841e01 100644 --- a/scrapy/core/scraper.py +++ b/scrapy/core/scraper.py @@ -1,5 +1,6 @@ """This module implements the Scraper component which parses responses and extracts information from them""" + from __future__ import annotations import logging diff --git a/scrapy/core/spidermw.py b/scrapy/core/spidermw.py index dcf1a6dbc..1ccfd08a2 100644 --- a/scrapy/core/spidermw.py +++ b/scrapy/core/spidermw.py @@ -3,6 +3,7 @@ Spider Middleware manager See documentation in docs/topics/spider-middleware.rst """ + import logging from inspect import isasyncgenfunction, iscoroutine from itertools import islice @@ -103,8 +104,7 @@ class SpiderMiddlewareManager(MiddlewareManager): ) -> Union[Generator, AsyncGenerator]: def process_sync(iterable: Iterable) -> Generator: try: - for r in iterable: - yield r + yield from iterable except Exception as ex: exception_result = self._process_spider_exception( response, spider, Failure(ex), exception_processor_index diff --git a/scrapy/crawler.py b/scrapy/crawler.py index 1d3a11208..1db9ace28 100644 --- a/scrapy/crawler.py +++ b/scrapy/crawler.py @@ -39,7 +39,7 @@ from scrapy.utils.log import ( log_reactor_info, log_scrapy_info, ) -from scrapy.utils.misc import create_instance, load_object +from scrapy.utils.misc import build_from_crawler, load_object from scrapy.utils.ossignal import install_shutdown_handlers, signal_names from scrapy.utils.reactor import ( install_reactor, @@ -109,10 +109,9 @@ class Crawler: lf_cls: Type[LogFormatter] = load_object(self.settings["LOG_FORMATTER"]) self.logformatter = lf_cls.from_crawler(self) - self.request_fingerprinter = create_instance( + self.request_fingerprinter = build_from_crawler( load_object(self.settings["REQUEST_FINGERPRINTER_CLASS"]), - settings=self.settings, - crawler=self, + self, ) reactor_class: str = self.settings["TWISTED_REACTOR"] @@ -179,6 +178,48 @@ class Crawler: assert self.engine yield maybeDeferred(self.engine.stop) + @staticmethod + def _get_component(component_class, components): + for component in components: + if isinstance(component, component_class): + return component + return None + + def get_addon(self, cls): + return self._get_component(cls, self.addons.addons) + + def get_downloader_middleware(self, cls): + if not self.engine: + raise RuntimeError( + "Crawler.get_downloader_middleware() can only be called after " + "the crawl engine has been created." + ) + return self._get_component(cls, self.engine.downloader.middleware.middlewares) + + def get_extension(self, cls): + if not self.extensions: + raise RuntimeError( + "Crawler.get_extension() can only be called after the " + "extension manager has been created." + ) + return self._get_component(cls, self.extensions.middlewares) + + def get_item_pipeline(self, cls): + if not self.engine: + raise RuntimeError( + "Crawler.get_item_pipeline() can only be called after the " + "crawl engine has been created." + ) + return self._get_component(cls, self.engine.scraper.itemproc.middlewares) + + def get_spider_middleware(self, cls): + if not self.engine: + raise RuntimeError( + "Crawler.get_spider_middleware() can only be called after the " + "crawl engine has been created." + ) + return self._get_component(cls, self.engine.scraper.spidermw.middlewares) + class CrawlerRunner: """ @@ -404,7 +445,7 @@ class CrawlerProcess(CrawlerRunner): d.addBoth(self._stop_reactor) resolver_class = load_object(self.settings["DNS_RESOLVER"]) - resolver = create_instance(resolver_class, self.settings, self, reactor=reactor) + resolver = build_from_crawler(resolver_class, self, reactor=reactor) resolver.install_on_reactor() tp = reactor.getThreadPool() tp.adjustPoolsize(maxthreads=self.settings.getint("REACTOR_THREADPOOL_MAXSIZE")) diff --git a/scrapy/downloadermiddlewares/defaultheaders.py b/scrapy/downloadermiddlewares/defaultheaders.py index 8aec37cf1..58fd415b9 100644 --- a/scrapy/downloadermiddlewares/defaultheaders.py +++ b/scrapy/downloadermiddlewares/defaultheaders.py @@ -3,6 +3,7 @@ DefaultHeaders downloader middleware See documentation in docs/topics/downloader-middleware.rst """ + from __future__ import annotations from typing import TYPE_CHECKING, Iterable, Tuple, Union diff --git a/scrapy/downloadermiddlewares/downloadtimeout.py b/scrapy/downloadermiddlewares/downloadtimeout.py index 1c904c05b..fd7c03a38 100644 --- a/scrapy/downloadermiddlewares/downloadtimeout.py +++ b/scrapy/downloadermiddlewares/downloadtimeout.py @@ -3,6 +3,7 @@ Download timeout middleware See documentation in docs/topics/downloader-middleware.rst """ + from __future__ import annotations from typing import TYPE_CHECKING, Union diff --git a/scrapy/downloadermiddlewares/httpcompression.py b/scrapy/downloadermiddlewares/httpcompression.py index d44eb933a..aebdfb3e4 100644 --- a/scrapy/downloadermiddlewares/httpcompression.py +++ b/scrapy/downloadermiddlewares/httpcompression.py @@ -1,50 +1,93 @@ from __future__ import annotations -import io -import zlib +import warnings +from itertools import chain +from logging import getLogger from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union -from scrapy import Request, Spider +from scrapy import Request, Spider, signals from scrapy.crawler import Crawler -from scrapy.exceptions import NotConfigured +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 +logger = getLogger(__name__) + ACCEPTED_ENCODINGS: List[bytes] = [b"gzip", b"deflate"] try: - import brotli - - ACCEPTED_ENCODINGS.append(b"br") + import brotli # noqa: F401 except ImportError: pass +else: + ACCEPTED_ENCODINGS.append(b"br") 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""" - def __init__(self, stats: Optional[StatsCollector] = None): - self.stats = stats + def __init__( + self, + stats: Optional[StatsCollector] = None, + *, + crawler: Optional[Crawler] = 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): + 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 @@ -60,8 +103,26 @@ class HttpCompressionMiddleware: 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", @@ -74,7 +135,7 @@ class HttpCompressionMiddleware: respcls = responsetypes.from_args( headers=response.headers, url=response.url, body=decoded_body ) - kwargs: Dict[str, Any] = dict(body=decoded_body) + kwargs: Dict[str, Any] = {"cls": respcls, "body": decoded_body} if issubclass(respcls, TextResponse): # force recalculating the encoding until we make sure the # responsetypes guessing is reliable @@ -85,25 +146,35 @@ class HttpCompressionMiddleware: 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, content_encoding, max_size): + 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): + to_keep = [ + encoding.strip().lower() + for encoding in chain.from_iterable( + encodings.split(b",") for encodings in content_encoding + ) + ] + to_decode = [] + 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 diff --git a/scrapy/downloadermiddlewares/redirect.py b/scrapy/downloadermiddlewares/redirect.py index 7b1401ac8..e5ebf2273 100644 --- a/scrapy/downloadermiddlewares/redirect.py +++ b/scrapy/downloadermiddlewares/redirect.py @@ -2,7 +2,7 @@ from __future__ import annotations import logging from typing import TYPE_CHECKING, Any, List, Union, cast -from urllib.parse import urljoin, urlparse +from urllib.parse import urljoin from w3lib.url import safe_url_string @@ -30,11 +30,17 @@ def _build_redirect_request( cls=None, cookies=None, ) - if "Cookie" in redirect_request.headers: + has_cookie_header = "Cookie" in redirect_request.headers + has_authorization_header = "Authorization" in redirect_request.headers + if has_cookie_header or has_authorization_header: source_request_netloc = urlparse_cached(source_request).netloc redirect_request_netloc = urlparse_cached(redirect_request).netloc if source_request_netloc != redirect_request_netloc: - del redirect_request.headers["Cookie"] + if has_cookie_header: + del redirect_request.headers["Cookie"] + # https://fetch.spec.whatwg.org/#ref-for-cors-non-wildcard-request-header-name + if has_authorization_header: + del redirect_request.headers["Authorization"] return redirect_request @@ -120,7 +126,7 @@ 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) diff --git a/scrapy/downloadermiddlewares/retry.py b/scrapy/downloadermiddlewares/retry.py index 3c494de78..46587a898 100644 --- a/scrapy/downloadermiddlewares/retry.py +++ b/scrapy/downloadermiddlewares/retry.py @@ -9,6 +9,7 @@ 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. """ + from __future__ import annotations import warnings diff --git a/scrapy/exceptions.py b/scrapy/exceptions.py index 6d188c489..e7ecdbe0c 100644 --- a/scrapy/exceptions.py +++ b/scrapy/exceptions.py @@ -4,6 +4,7 @@ Scrapy core exceptions These exceptions are documented in docs/topics/exceptions.rst. Please don't add new exceptions here without documenting them there. """ + from typing import Any # Internal diff --git a/scrapy/extension.py b/scrapy/extension.py index 4e365cfa1..6be14450c 100644 --- a/scrapy/extension.py +++ b/scrapy/extension.py @@ -3,6 +3,7 @@ The Extension Manager See documentation in docs/topics/extensions.rst """ + from scrapy.middleware import MiddlewareManager from scrapy.utils.conf import build_component_list diff --git a/scrapy/extensions/corestats.py b/scrapy/extensions/corestats.py index 302a615f2..717c249d9 100644 --- a/scrapy/extensions/corestats.py +++ b/scrapy/extensions/corestats.py @@ -1,6 +1,7 @@ """ Extension for collecting core stats like items scraped and start/finish times """ + from datetime import datetime, timezone from scrapy import signals diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index fadbbb582..e5e363b52 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -28,7 +28,7 @@ from scrapy.utils.defer import maybe_deferred_to_future from scrapy.utils.deprecate import create_deprecated_class from scrapy.utils.ftp import ftp_store_file from scrapy.utils.log import failure_to_exc_info -from scrapy.utils.misc import create_instance, load_object +from scrapy.utils.misc import build_from_crawler, load_object from scrapy.utils.python import without_none_values logger = logging.getLogger(__name__) @@ -371,7 +371,7 @@ class FeedSlot: self._exporting = True def _get_instance(self, objcls, *args, **kwargs): - return create_instance(objcls, self.settings, self.crawler, *args, **kwargs) + return build_from_crawler(objcls, self.crawler, *args, **kwargs) def _get_exporter(self, file, format, *args, **kwargs): return self._get_instance(self.exporters[format], file, *args, **kwargs) diff --git a/scrapy/extensions/logstats.py b/scrapy/extensions/logstats.py index 78874a6db..9f63e9c4b 100644 --- a/scrapy/extensions/logstats.py +++ b/scrapy/extensions/logstats.py @@ -9,7 +9,10 @@ logger = logging.getLogger(__name__) class LogStats: - """Log basic scraping stats periodically""" + """Log basic scraping stats periodically like: + * RPM - Requests per Minute + * IPM - Items per Minute + """ def __init__(self, stats, interval=60.0): self.stats = stats @@ -35,24 +38,45 @@ class LogStats: self.task.start(self.interval) def log(self, spider): - items = self.stats.get_value("item_scraped_count", 0) - pages = self.stats.get_value("response_received_count", 0) - irate = (items - self.itemsprev) * self.multiplier - prate = (pages - self.pagesprev) * self.multiplier - self.pagesprev, self.itemsprev = pages, items + self.calculate_stats() msg = ( "Crawled %(pages)d pages (at %(pagerate)d pages/min), " "scraped %(items)d items (at %(itemrate)d items/min)" ) log_args = { - "pages": pages, - "pagerate": prate, - "items": items, - "itemrate": irate, + "pages": self.pages, + "pagerate": self.prate, + "items": self.items, + "itemrate": self.irate, } logger.info(msg, log_args, extra={"spider": spider}) + def calculate_stats(self): + self.items = self.stats.get_value("item_scraped_count", 0) + self.pages = self.stats.get_value("response_received_count", 0) + self.irate = (self.items - self.itemsprev) * self.multiplier + self.prate = (self.pages - self.pagesprev) * self.multiplier + self.pagesprev, self.itemsprev = self.pages, self.items + def spider_closed(self, spider, reason): if self.task and self.task.running: self.task.stop() + + rpm_final, ipm_final = self.calculate_final_stats(spider) + self.stats.set_value("responses_per_minute", rpm_final) + self.stats.set_value("items_per_minute", ipm_final) + + def calculate_final_stats(self, spider): + start_time = self.stats.get_value("start_time") + finished_time = self.stats.get_value("finished_time") + + if not start_time or not finished_time: + return None, None + + mins_elapsed = (finished_time - start_time).seconds / 60 + + items = self.stats.get_value("item_scraped_count", 0) + pages = self.stats.get_value("response_received_count", 0) + + return (pages / mins_elapsed), (items / mins_elapsed) diff --git a/scrapy/extensions/memusage.py b/scrapy/extensions/memusage.py index 221967bda..4d4501c44 100644 --- a/scrapy/extensions/memusage.py +++ b/scrapy/extensions/memusage.py @@ -3,6 +3,7 @@ MemoryUsage extension See documentation in docs/topics/extensions.rst """ + import logging import socket import sys @@ -128,9 +129,9 @@ class MemoryUsage: def _send_report(self, rcpts, subject): """send notification mail with some additional useful info""" stats = self.crawler.stats - s = f"Memory usage at engine startup : {stats.get_value('memusage/startup')/1024/1024}M\r\n" - s += f"Maximum memory usage : {stats.get_value('memusage/max')/1024/1024}M\r\n" - s += f"Current memory usage : {self.get_virtual_size()/1024/1024}M\r\n" + s = f"Memory usage at engine startup : {stats.get_value('memusage/startup') / 1024 / 1024}M\r\n" + s += f"Maximum memory usage : {stats.get_value('memusage/max') / 1024 / 1024}M\r\n" + s += f"Current memory usage : {self.get_virtual_size() / 1024 / 1024}M\r\n" s += ( "ENGINE STATUS ------------------------------------------------------- \r\n" diff --git a/scrapy/extensions/postprocessing.py b/scrapy/extensions/postprocessing.py index 79e3b1656..f8b59827b 100644 --- a/scrapy/extensions/postprocessing.py +++ b/scrapy/extensions/postprocessing.py @@ -1,6 +1,7 @@ """ Extension for processing data before they are exported to feeds. """ + from bz2 import BZ2File from gzip import GzipFile from io import IOBase @@ -42,7 +43,6 @@ class GzipPlugin: def close(self) -> None: self.gzipfile.close() - self.file.close() class Bz2Plugin: @@ -69,7 +69,6 @@ class Bz2Plugin: def close(self) -> None: self.bz2file.close() - self.file.close() class LZMAPlugin: @@ -111,7 +110,6 @@ class LZMAPlugin: def close(self) -> None: self.lzmafile.close() - self.file.close() # io.IOBase is subclassed here, so that exporters can use the PostProcessingManager diff --git a/scrapy/extensions/throttle.py b/scrapy/extensions/throttle.py index 396800775..d217c7a69 100644 --- a/scrapy/extensions/throttle.py +++ b/scrapy/extensions/throttle.py @@ -16,6 +16,11 @@ class AutoThrottle: self.target_concurrency = crawler.settings.getfloat( "AUTOTHROTTLE_TARGET_CONCURRENCY" ) + if self.target_concurrency <= 0.0: + raise NotConfigured( + f"AUTOTHROTTLE_TARGET_CONCURRENCY " + f"({self.target_concurrency!r}) must be higher than 0." + ) crawler.signals.connect(self._spider_opened, signal=signals.spider_opened) crawler.signals.connect( self._response_downloaded, signal=signals.response_downloaded diff --git a/scrapy/http/__init__.py b/scrapy/http/__init__.py index ac3946302..d0b726bad 100644 --- a/scrapy/http/__init__.py +++ b/scrapy/http/__init__.py @@ -12,5 +12,6 @@ from scrapy.http.request.json_request import JsonRequest from scrapy.http.request.rpc import XmlRpcRequest from scrapy.http.response import Response from scrapy.http.response.html import HtmlResponse +from scrapy.http.response.json import JsonResponse from scrapy.http.response.text import TextResponse from scrapy.http.response.xml import XmlResponse diff --git a/scrapy/http/headers.py b/scrapy/http/headers.py index 21eb9fb73..73aee7178 100644 --- a/scrapy/http/headers.py +++ b/scrapy/http/headers.py @@ -113,7 +113,9 @@ class Headers(CaselessDict): return ((k, self.getlist(k)) for k in self.keys()) def values(self) -> List[Optional[bytes]]: # type: ignore[override] - return [self[k] for k in self.keys()] + return [ + self[k] for k in self.keys() # pylint: disable=consider-using-dict-items + ] def to_string(self) -> bytes: # cast() can be removed if the headers_dict_to_raw() hint is improved diff --git a/scrapy/http/request/__init__.py b/scrapy/http/request/__init__.py index 4effc2178..e7fdd5d54 100644 --- a/scrapy/http/request/__init__.py +++ b/scrapy/http/request/__init__.py @@ -4,6 +4,7 @@ requests in Scrapy. See documentation in docs/topics/request-response.rst """ + from __future__ import annotations import inspect @@ -187,12 +188,10 @@ class Request(object_ref): @overload def replace( self, *args: Any, cls: Type[RequestTypeVar], **kwargs: Any - ) -> RequestTypeVar: - ... + ) -> RequestTypeVar: ... @overload - def replace(self, *args: Any, cls: None = None, **kwargs: Any) -> Self: - ... + def replace(self, *args: Any, cls: None = None, **kwargs: Any) -> Self: ... def replace( self, *args: Any, cls: Optional[Type[Request]] = None, **kwargs: Any @@ -252,12 +251,16 @@ class Request(object_ref): """ d = { "url": self.url, # urls are safe (safe_string_url) - "callback": _find_method(spider, self.callback) - if callable(self.callback) - else self.callback, - "errback": _find_method(spider, self.errback) - if callable(self.errback) - else self.errback, + "callback": ( + _find_method(spider, self.callback) + if callable(self.callback) + else self.callback + ), + "errback": ( + _find_method(spider, self.errback) + if callable(self.errback) + else self.errback + ), "headers": dict(self.headers), } for attr in self.attributes: diff --git a/scrapy/http/request/rpc.py b/scrapy/http/request/rpc.py index bde860a66..e20e7c438 100644 --- a/scrapy/http/request/rpc.py +++ b/scrapy/http/request/rpc.py @@ -4,12 +4,17 @@ This module implements the XmlRpcRequest class which is a more convenient class See documentation in docs/topics/request-response.rst """ + import xmlrpc.client as xmlrpclib from typing import Any, Optional +import defusedxml.xmlrpc + from scrapy.http.request import Request from scrapy.utils.python import get_func_args +defusedxml.xmlrpc.monkey_patch() + DUMPS_ARGS = get_func_args(xmlrpclib.dumps) diff --git a/scrapy/http/response/__init__.py b/scrapy/http/response/__init__.py index e889a6460..166b19b0b 100644 --- a/scrapy/http/response/__init__.py +++ b/scrapy/http/response/__init__.py @@ -4,6 +4,7 @@ responses in Scrapy. See documentation in docs/topics/request-response.rst """ + from __future__ import annotations from ipaddress import IPv4Address, IPv6Address @@ -147,12 +148,10 @@ class Response(object_ref): @overload def replace( self, *args: Any, cls: Type[ResponseTypeVar], **kwargs: Any - ) -> ResponseTypeVar: - ... + ) -> ResponseTypeVar: ... @overload - def replace(self, *args: Any, cls: None = None, **kwargs: Any) -> Self: - ... + def replace(self, *args: Any, cls: None = None, **kwargs: Any) -> Self: ... def replace( self, *args: Any, cls: Optional[Type[Response]] = None, **kwargs: Any diff --git a/scrapy/http/response/json.py b/scrapy/http/response/json.py new file mode 100644 index 000000000..219691094 --- /dev/null +++ b/scrapy/http/response/json.py @@ -0,0 +1,12 @@ +""" +This module implements the JsonResponse class that is used when the response +has a JSON MIME type in its Content-Type header. + +See documentation in docs/topics/request-response.rst +""" + +from scrapy.http.response.text import TextResponse + + +class JsonResponse(TextResponse): + pass diff --git a/scrapy/http/response/text.py b/scrapy/http/response/text.py index 6596d8a5c..2816610fb 100644 --- a/scrapy/http/response/text.py +++ b/scrapy/http/response/text.py @@ -4,6 +4,7 @@ discovering (through HTTP headers) to base Response class. See documentation in docs/topics/request-response.rst """ + from __future__ import annotations import json diff --git a/scrapy/link.py b/scrapy/link.py index 0868ae5ef..4bdbc1823 100644 --- a/scrapy/link.py +++ b/scrapy/link.py @@ -4,6 +4,7 @@ This module defines the Link object used in Link extractors. For actual link extractors implementation see scrapy.linkextractors, or its documentation in: docs/topics/link-extractors.rst """ + from typing import Any diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.py index 3774430a7..73a63651c 100644 --- a/scrapy/linkextractors/__init__.py +++ b/scrapy/linkextractors/__init__.py @@ -5,6 +5,7 @@ This package contains a collection of Link Extractors. For more info see docs/topics/link-extractors.rst """ + import re # common file extensions that are not followed if they occur in links diff --git a/scrapy/linkextractors/lxmlhtml.py b/scrapy/linkextractors/lxmlhtml.py index 23cbd0116..d76db20ba 100644 --- a/scrapy/linkextractors/lxmlhtml.py +++ b/scrapy/linkextractors/lxmlhtml.py @@ -1,6 +1,7 @@ """ Link extractor based on lxml.html """ + import logging import operator from functools import partial diff --git a/scrapy/loader/__init__.py b/scrapy/loader/__init__.py index 1042a3d48..529fa279e 100644 --- a/scrapy/loader/__init__.py +++ b/scrapy/loader/__init__.py @@ -3,6 +3,7 @@ Item Loader See documentation in docs/topics/loaders.rst """ + import itemloaders from scrapy.item import Item diff --git a/scrapy/mail.py b/scrapy/mail.py index 237327451..4b18b6003 100644 --- a/scrapy/mail.py +++ b/scrapy/mail.py @@ -3,6 +3,7 @@ Mail sending helpers See documentation in docs/topics/email.rst """ + import logging from email import encoders as Encoders from email.mime.base import MIMEBase diff --git a/scrapy/middleware.py b/scrapy/middleware.py index 090588130..f60c726f9 100644 --- a/scrapy/middleware.py +++ b/scrapy/middleware.py @@ -23,7 +23,7 @@ from scrapy import Spider from scrapy.exceptions import NotConfigured from scrapy.settings import Settings from scrapy.utils.defer import process_chain, process_parallel -from scrapy.utils.misc import create_instance, load_object +from scrapy.utils.misc import build_from_crawler, build_from_settings, load_object if TYPE_CHECKING: # typing.Self requires Python 3.11 @@ -64,7 +64,10 @@ class MiddlewareManager: for clspath in mwlist: try: mwcls = load_object(clspath) - mw = create_instance(mwcls, settings, crawler) + if crawler is not None: + mw = build_from_crawler(mwcls, crawler) + else: + mw = build_from_settings(mwcls, settings) middlewares.append(mw) enabled.append(clspath) except NotConfigured as e: diff --git a/scrapy/pipelines/__init__.py b/scrapy/pipelines/__init__.py index c97d71fb6..f9544d329 100644 --- a/scrapy/pipelines/__init__.py +++ b/scrapy/pipelines/__init__.py @@ -3,6 +3,7 @@ Item pipeline See documentation in docs/item-pipeline.rst """ + from typing import Any, List from twisted.internet.defer import Deferred diff --git a/scrapy/pipelines/files.py b/scrapy/pipelines/files.py index 5c09ab37e..1d7625299 100644 --- a/scrapy/pipelines/files.py +++ b/scrapy/pipelines/files.py @@ -3,12 +3,12 @@ Files Pipeline See documentation in topics/media-pipeline.rst """ + import base64 import functools import hashlib import logging import mimetypes -import os import time from collections import defaultdict from contextlib import suppress @@ -66,7 +66,7 @@ class FSFilesStore: absolute_path = self._get_filesystem_path(path) try: last_modified = absolute_path.stat().st_mtime - except os.error: + except OSError: return {} with absolute_path.open("rb") as f: @@ -340,7 +340,9 @@ class FilesPipeline(MediaPipeline): DEFAULT_FILES_URLS_FIELD = "file_urls" DEFAULT_FILES_RESULT_FIELD = "files" - def __init__(self, store_uri, download_func=None, settings=None): + def __init__( + self, store_uri: Union[str, PathLike], download_func=None, settings=None + ): store_uri = _to_string(store_uri) if not store_uri: raise NotConfigured diff --git a/scrapy/pipelines/images.py b/scrapy/pipelines/images.py index 1bd9832a8..8169583f8 100644 --- a/scrapy/pipelines/images.py +++ b/scrapy/pipelines/images.py @@ -3,12 +3,14 @@ Images Pipeline See documentation in topics/media-pipeline.rst """ + import functools import hashlib import warnings from contextlib import suppress from io import BytesIO -from typing import Dict, Tuple +from os import PathLike +from typing import Dict, Tuple, Union from itemadapter import ItemAdapter @@ -53,7 +55,9 @@ class ImagesPipeline(FilesPipeline): DEFAULT_IMAGES_URLS_FIELD = "image_urls" DEFAULT_IMAGES_RESULT_FIELD = "images" - def __init__(self, store_uri, download_func=None, settings=None): + def __init__( + self, store_uri: Union[str, PathLike], download_func=None, settings=None + ): try: from PIL import Image diff --git a/scrapy/pipelines/media.py b/scrapy/pipelines/media.py index 75532034a..fc156ab41 100644 --- a/scrapy/pipelines/media.py +++ b/scrapy/pipelines/media.py @@ -112,14 +112,14 @@ class MediaPipeline: info.downloading.add(fp) dfd = mustbe_deferred(self.media_to_download, request, info, item=item) dfd.addCallback(self._check_media_to_download, request, info, item=item) + dfd.addErrback(self._log_exception) dfd.addBoth(self._cache_result_and_execute_waiters, fp, info) - dfd.addErrback( - lambda f: logger.error( - f.value, exc_info=failure_to_exc_info(f), extra={"spider": info.spider} - ) - ) return dfd.addBoth(lambda _: wad) # it must return wad at last + def _log_exception(self, result): + logger.exception(result) + return result + def _modify_media_request(self, request): if self.handle_httpstatus_list: request.meta["handle_httpstatus_list"] = self.handle_httpstatus_list diff --git a/scrapy/pqueues.py b/scrapy/pqueues.py index 62a9af477..b62d2fe58 100644 --- a/scrapy/pqueues.py +++ b/scrapy/pqueues.py @@ -1,7 +1,7 @@ import hashlib import logging -from scrapy.utils.misc import create_instance +from scrapy.utils.misc import build_from_crawler logger = logging.getLogger(__name__) @@ -72,9 +72,8 @@ class ScrapyPriorityQueue: self.curprio = min(startprios) def qfactory(self, key): - return create_instance( + return build_from_crawler( self.downstream_queue_cls, - None, self.crawler, self.key + "/" + str(key), ) diff --git a/scrapy/responsetypes.py b/scrapy/responsetypes.py index 9e411d4aa..702e50536 100644 --- a/scrapy/responsetypes.py +++ b/scrapy/responsetypes.py @@ -2,6 +2,7 @@ This module implements a class which returns the appropriate Response class based on different criteria. """ + from io import StringIO from mimetypes import MimeTypes from pkgutil import get_data @@ -21,9 +22,9 @@ class ResponseTypes: "application/xhtml+xml": "scrapy.http.HtmlResponse", "application/vnd.wap.xhtml+xml": "scrapy.http.HtmlResponse", "application/xml": "scrapy.http.XmlResponse", - "application/json": "scrapy.http.TextResponse", - "application/x-json": "scrapy.http.TextResponse", - "application/json-amazonui-streaming": "scrapy.http.TextResponse", + "application/json": "scrapy.http.JsonResponse", + "application/x-json": "scrapy.http.JsonResponse", + "application/json-amazonui-streaming": "scrapy.http.JsonResponse", "application/javascript": "scrapy.http.TextResponse", "application/x-javascript": "scrapy.http.TextResponse", "text/xml": "scrapy.http.XmlResponse", diff --git a/scrapy/selector/unified.py b/scrapy/selector/unified.py index 863fb6032..75d5e9fbd 100644 --- a/scrapy/selector/unified.py +++ b/scrapy/selector/unified.py @@ -1,6 +1,7 @@ """ XPath selectors based on lxml """ + from typing import Any, Optional, Type, Union from parsel import Selector as _ParselSelector diff --git a/scrapy/settings/__init__.py b/scrapy/settings/__init__.py index b5d8fdb12..d270a72f4 100644 --- a/scrapy/settings/__init__.py +++ b/scrapy/settings/__init__.py @@ -58,7 +58,6 @@ def get_settings_priority(priority: Union[int, str]) -> int: class SettingsAttribute: - """Class for storing data related to settings attributes. This class is intended for internal usage, you should try Settings class diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index d6b3585e2..49ab1b5ef 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -260,7 +260,7 @@ REFERER_ENABLED = True REFERRER_POLICY = "scrapy.spidermiddlewares.referer.DefaultReferrerPolicy" REQUEST_FINGERPRINTER_CLASS = "scrapy.utils.request.RequestFingerprinter" -REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.6" +REQUEST_FINGERPRINTER_IMPLEMENTATION = "SENTINEL" RETRY_ENABLED = True RETRY_TIMES = 2 # initial response + 2 retries = 3 requests diff --git a/scrapy/shell.py b/scrapy/shell.py index bb3b1461c..05909977a 100644 --- a/scrapy/shell.py +++ b/scrapy/shell.py @@ -3,6 +3,7 @@ See documentation in docs/topics/shell.rst """ + import os import signal diff --git a/scrapy/spidermiddlewares/httperror.py b/scrapy/spidermiddlewares/httperror.py index 94450b35b..35c869a75 100644 --- a/scrapy/spidermiddlewares/httperror.py +++ b/scrapy/spidermiddlewares/httperror.py @@ -3,6 +3,7 @@ HttpError Spider Middleware See documentation in docs/topics/spider-middleware.rst """ + from __future__ import annotations import logging diff --git a/scrapy/spidermiddlewares/offsite.py b/scrapy/spidermiddlewares/offsite.py index a5214702d..dd2fccfcb 100644 --- a/scrapy/spidermiddlewares/offsite.py +++ b/scrapy/spidermiddlewares/offsite.py @@ -3,6 +3,7 @@ Offsite Spider Middleware See documentation in docs/topics/spider-middleware.rst """ + from __future__ import annotations import logging diff --git a/scrapy/spidermiddlewares/referer.py b/scrapy/spidermiddlewares/referer.py index a29e0ebb5..a0b6851e5 100644 --- a/scrapy/spidermiddlewares/referer.py +++ b/scrapy/spidermiddlewares/referer.py @@ -2,6 +2,7 @@ RefererMiddleware: populates Request referer field, based on the Response which originated it. """ + from __future__ import annotations import warnings diff --git a/scrapy/spiders/__init__.py b/scrapy/spiders/__init__.py index e16d71727..72c2aaba7 100644 --- a/scrapy/spiders/__init__.py +++ b/scrapy/spiders/__init__.py @@ -3,6 +3,7 @@ Base class for Scrapy spiders See documentation in docs/topics/spiders.rst """ + from __future__ import annotations import logging diff --git a/scrapy/spiders/crawl.py b/scrapy/spiders/crawl.py index 31e845716..2a3913da5 100644 --- a/scrapy/spiders/crawl.py +++ b/scrapy/spiders/crawl.py @@ -85,7 +85,7 @@ class CrawlSpider(Spider): url=link.url, callback=self._callback, errback=self._errback, - meta=dict(rule=rule_index, link_text=link.text), + meta={"rule": rule_index, "link_text": link.text}, ) def _requests_to_follow(self, response): @@ -131,8 +131,7 @@ class CrawlSpider(Spider): def _handle_failure(self, failure, errback): if errback: results = errback(failure) or () - for request_or_item in iterate_spider_output(results): - yield request_or_item + yield from iterate_spider_output(results) def _compile_rules(self): self._rules = [] diff --git a/scrapy/spiders/feed.py b/scrapy/spiders/feed.py index 6afadc577..5caf8c79e 100644 --- a/scrapy/spiders/feed.py +++ b/scrapy/spiders/feed.py @@ -4,10 +4,11 @@ for scraping from an XML feed. See documentation in docs/topics/spiders.rst """ + from scrapy.exceptions import NotConfigured, NotSupported from scrapy.selector import Selector from scrapy.spiders import Spider -from scrapy.utils.iterators import csviter, xmliter +from scrapy.utils.iterators import csviter, xmliter_lxml from scrapy.utils.spider import iterate_spider_output @@ -58,8 +59,7 @@ class XMLFeedSpider(Spider): for selector in nodes: ret = iterate_spider_output(self.parse_node(response, selector)) - for result_item in self.process_results(response, ret): - yield result_item + yield from self.process_results(response, ret) def _parse(self, response, **kwargs): if not hasattr(self, "parse_node"): @@ -84,7 +84,7 @@ class XMLFeedSpider(Spider): return self.parse_nodes(response, nodes) def _iternodes(self, response): - for node in xmliter(response, self.itertag): + for node in xmliter_lxml(response, self.itertag): self._register_namespaces(node) yield node @@ -133,8 +133,7 @@ class CSVFeedSpider(Spider): response, self.delimiter, self.headers, quotechar=self.quotechar ): ret = iterate_spider_output(self.parse_row(response, row)) - for result_item in self.process_results(response, ret): - yield result_item + yield from self.process_results(response, ret) def _parse(self, response, **kwargs): if not hasattr(self, "parse_row"): diff --git a/scrapy/spiders/sitemap.py b/scrapy/spiders/sitemap.py index aaf75a519..cd83a1464 100644 --- a/scrapy/spiders/sitemap.py +++ b/scrapy/spiders/sitemap.py @@ -1,11 +1,19 @@ import logging import re +from typing import TYPE_CHECKING, Any from scrapy.http import Request, XmlResponse from scrapy.spiders import Spider +from scrapy.utils._compression import _DecompressionMaxSizeExceeded from scrapy.utils.gz import gunzip, gzip_magic_number from scrapy.utils.sitemap import Sitemap, sitemap_urls_from_robots +if TYPE_CHECKING: + # typing.Self requires Python 3.11 + from typing_extensions import Self + + from scrapy.crawler import Crawler + logger = logging.getLogger(__name__) @@ -14,6 +22,19 @@ class SitemapSpider(Spider): sitemap_rules = [("", "parse")] sitemap_follow = [""] sitemap_alternate_links = False + _max_size: int + _warn_size: int + + @classmethod + def from_crawler(cls, crawler: "Crawler", *args: Any, **kwargs: Any) -> "Self": + spider = super().from_crawler(crawler, *args, **kwargs) + spider._max_size = getattr( + spider, "download_maxsize", spider.settings.getint("DOWNLOAD_MAXSIZE") + ) + spider._warn_size = getattr( + spider, "download_warnsize", spider.settings.getint("DOWNLOAD_WARNSIZE") + ) + return spider def __init__(self, *a, **kw): super().__init__(*a, **kw) @@ -33,8 +54,7 @@ class SitemapSpider(Spider): attributes, for example, you can filter locs with lastmod greater than a given date (see docs). """ - for entry in entries: - yield entry + yield from entries def _parse_sitemap(self, response): if response.url.endswith("/robots.txt"): @@ -71,7 +91,19 @@ class SitemapSpider(Spider): if isinstance(response, XmlResponse): return response.body if gzip_magic_number(response): - return gunzip(response.body) + uncompressed_size = len(response.body) + max_size = response.meta.get("download_maxsize", self._max_size) + warn_size = response.meta.get("download_warnsize", self._warn_size) + try: + body = gunzip(response.body, max_size=max_size) + except _DecompressionMaxSizeExceeded: + return None + if uncompressed_size < warn_size <= len(body): + logger.warning( + f"{response} body size after decompression ({len(body)} B) " + f"is larger than the download warning size ({warn_size} B)." + ) + return body # actual gzipped sitemap files are decompressed above ; # if we are here (response body is not gzipped) # and have a response for .xml.gz, diff --git a/scrapy/statscollectors.py b/scrapy/statscollectors.py index 15193aac5..ab571a3ab 100644 --- a/scrapy/statscollectors.py +++ b/scrapy/statscollectors.py @@ -1,6 +1,7 @@ """ Scrapy extension for collecting scraping stats """ + import logging import pprint from typing import TYPE_CHECKING, Any, Dict, Optional diff --git a/scrapy/templates/project/module/settings.py.tmpl b/scrapy/templates/project/module/settings.py.tmpl index ecb1e5e5c..b4779e555 100644 --- a/scrapy/templates/project/module/settings.py.tmpl +++ b/scrapy/templates/project/module/settings.py.tmpl @@ -88,6 +88,5 @@ ROBOTSTXT_OBEY = True #HTTPCACHE_STORAGE = "scrapy.extensions.httpcache.FilesystemCacheStorage" # Set settings whose default value is deprecated to a future-proof value -REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7" TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor" FEED_EXPORT_ENCODING = "utf-8" diff --git a/scrapy/utils/_compression.py b/scrapy/utils/_compression.py new file mode 100644 index 000000000..5610595d3 --- /dev/null +++ b/scrapy/utils/_compression.py @@ -0,0 +1,94 @@ +import zlib +from io import BytesIO + +try: + import brotli +except ImportError: + pass + +try: + import zstandard +except ImportError: + pass + + +_CHUNK_SIZE = 65536 # 64 KiB + + +class _DecompressionMaxSizeExceeded(ValueError): + pass + + +def _inflate(data: bytes, *, max_size: int = 0) -> bytes: + decompressor = zlib.decompressobj() + raw_decompressor = zlib.decompressobj(wbits=-15) + input_stream = BytesIO(data) + output_stream = BytesIO() + output_chunk = b"." + decompressed_size = 0 + while output_chunk: + input_chunk = input_stream.read(_CHUNK_SIZE) + try: + output_chunk = decompressor.decompress(input_chunk) + except zlib.error: + if decompressor != raw_decompressor: + # 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 + decompressor = raw_decompressor + output_chunk = decompressor.decompress(input_chunk) + else: + raise + decompressed_size += len(output_chunk) + if max_size and decompressed_size > max_size: + raise _DecompressionMaxSizeExceeded( + f"The number of bytes decompressed so far " + f"({decompressed_size} B) exceed the specified maximum " + f"({max_size} B)." + ) + output_stream.write(output_chunk) + output_stream.seek(0) + return output_stream.read() + + +def _unbrotli(data: bytes, *, max_size: int = 0) -> bytes: + decompressor = brotli.Decompressor() + input_stream = BytesIO(data) + output_stream = BytesIO() + output_chunk = b"." + decompressed_size = 0 + while output_chunk: + input_chunk = input_stream.read(_CHUNK_SIZE) + output_chunk = decompressor.process(input_chunk) + decompressed_size += len(output_chunk) + if max_size and decompressed_size > max_size: + raise _DecompressionMaxSizeExceeded( + f"The number of bytes decompressed so far " + f"({decompressed_size} B) exceed the specified maximum " + f"({max_size} B)." + ) + output_stream.write(output_chunk) + output_stream.seek(0) + return output_stream.read() + + +def _unzstd(data: bytes, *, max_size: int = 0) -> bytes: + decompressor = zstandard.ZstdDecompressor() + stream_reader = decompressor.stream_reader(BytesIO(data)) + output_stream = BytesIO() + output_chunk = b"." + decompressed_size = 0 + while output_chunk: + output_chunk = stream_reader.read(_CHUNK_SIZE) + decompressed_size += len(output_chunk) + if max_size and decompressed_size > max_size: + raise _DecompressionMaxSizeExceeded( + f"The number of bytes decompressed so far " + f"({decompressed_size} B) exceed the specified maximum " + f"({max_size} B)." + ) + output_stream.write(output_chunk) + output_stream.seek(0) + return output_stream.read() diff --git a/scrapy/utils/defer.py b/scrapy/utils/defer.py index bf3c5ef5b..c391db9fd 100644 --- a/scrapy/utils/defer.py +++ b/scrapy/utils/defer.py @@ -1,6 +1,7 @@ """ Helper functions for dealing with Twisted deferreds """ + import asyncio import inspect from asyncio import Future @@ -304,13 +305,11 @@ _T = TypeVar("_T") @overload -def deferred_from_coro(o: _CT) -> Deferred: - ... +def deferred_from_coro(o: _CT) -> Deferred: ... @overload -def deferred_from_coro(o: _T) -> _T: - ... +def deferred_from_coro(o: _T) -> _T: ... def deferred_from_coro(o: _T) -> Union[Deferred, _T]: diff --git a/scrapy/utils/deprecate.py b/scrapy/utils/deprecate.py index ea577c44a..e0f2ac763 100644 --- a/scrapy/utils/deprecate.py +++ b/scrapy/utils/deprecate.py @@ -138,13 +138,11 @@ DEPRECATION_RULES: List[Tuple[str, str]] = [] @overload -def update_classpath(path: str) -> str: - ... +def update_classpath(path: str) -> str: ... @overload -def update_classpath(path: Any) -> Any: - ... +def update_classpath(path: Any) -> Any: ... def update_classpath(path: Any) -> Any: diff --git a/scrapy/utils/gz.py b/scrapy/utils/gz.py index c7f74030e..2e487d88b 100644 --- a/scrapy/utils/gz.py +++ b/scrapy/utils/gz.py @@ -1,31 +1,41 @@ import struct from gzip import GzipFile from io import BytesIO -from typing import List from scrapy.http import Response +from ._compression import _CHUNK_SIZE, _DecompressionMaxSizeExceeded -def gunzip(data: bytes) -> bytes: + +def gunzip(data: bytes, *, max_size: int = 0) -> bytes: """Gunzip the given data and return as much data as possible. This is resilient to CRC checksum errors. """ f = GzipFile(fileobj=BytesIO(data)) - output_list: List[bytes] = [] + output_stream = BytesIO() chunk = b"." + decompressed_size = 0 while chunk: try: - chunk = f.read1(8196) - output_list.append(chunk) + chunk = f.read1(_CHUNK_SIZE) except (OSError, EOFError, struct.error): # complete only if there is some data, otherwise re-raise # see issue 87 about catching struct.error - # some pages are quite small so output_list is empty - if output_list: + # some pages are quite small so output_stream is empty + if output_stream.getbuffer().nbytes > 0: break raise - return b"".join(output_list) + decompressed_size += len(chunk) + if max_size and decompressed_size > max_size: + raise _DecompressionMaxSizeExceeded( + f"The number of bytes decompressed so far " + f"({decompressed_size} B) exceed the specified maximum " + f"({max_size} B)." + ) + output_stream.write(chunk) + output_stream.seek(0) + return output_stream.read() def gzip_magic_number(response: Response) -> bool: diff --git a/scrapy/utils/iterators.py b/scrapy/utils/iterators.py index 55362efdf..93a2ba7a1 100644 --- a/scrapy/utils/iterators.py +++ b/scrapy/utils/iterators.py @@ -16,7 +16,11 @@ from typing import ( cast, overload, ) +from warnings import warn +from lxml import etree + +from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.http import Response, TextResponse from scrapy.selector import Selector from scrapy.utils.python import re_rsearch, to_unicode @@ -38,6 +42,16 @@ def xmliter( - a unicode string - a string encoded as utf-8 """ + warn( + ( + "xmliter is deprecated and its use strongly discouraged because " + "it is vulnerable to ReDoS attacks. Use xmliter_lxml instead. See " + "https://github.com/scrapy/scrapy/security/advisories/GHSA-cc65-xxvf-f7r9" + ), + ScrapyDeprecationWarning, + stacklevel=2, + ) + nodename_patt = re.escape(nodename) DOCUMENT_HEADER_RE = re.compile(r"<\?xml[^>]+>\s*", re.S) @@ -81,15 +95,34 @@ def xmliter_lxml( namespace: Optional[str] = None, prefix: str = "x", ) -> Generator[Selector, Any, None]: - from lxml import etree - reader = _StreamReader(obj) tag = f"{{{namespace}}}{nodename}" if namespace else nodename iterable = etree.iterparse( - cast("SupportsReadClose[bytes]", reader), tag=tag, encoding=reader.encoding + cast("SupportsReadClose[bytes]", reader), + encoding=reader.encoding, + events=("end", "start-ns"), + huge_tree=True, ) selxpath = "//" + (f"{prefix}:{nodename}" if namespace else nodename) - for _, node in iterable: + needs_namespace_resolution = not namespace and ":" in nodename + if needs_namespace_resolution: + prefix, nodename = nodename.split(":", maxsplit=1) + for event, data in iterable: + if event == "start-ns": + assert isinstance(data, tuple) + if needs_namespace_resolution: + _prefix, _namespace = data + if _prefix != prefix: + continue + namespace = _namespace + needs_namespace_resolution = False + selxpath = f"//{prefix}:{nodename}" + tag = f"{{{namespace}}}{nodename}" + continue + assert isinstance(data, etree._Element) + node = data + if node.tag != tag: + continue nodetext = etree.tostring(node, encoding="unicode") node.clear() xs = Selector(text=nodetext, type="xml") @@ -192,18 +225,17 @@ def csviter( @overload -def _body_or_str(obj: Union[Response, str, bytes]) -> str: - ... +def _body_or_str(obj: Union[Response, str, bytes]) -> str: ... @overload -def _body_or_str(obj: Union[Response, str, bytes], unicode: Literal[True]) -> str: - ... +def _body_or_str(obj: Union[Response, str, bytes], unicode: Literal[True]) -> str: ... @overload -def _body_or_str(obj: Union[Response, str, bytes], unicode: Literal[False]) -> bytes: - ... +def _body_or_str( + obj: Union[Response, str, bytes], unicode: Literal[False] +) -> bytes: ... def _body_or_str( diff --git a/scrapy/utils/misc.py b/scrapy/utils/misc.py index a9364bea2..7b43760a8 100644 --- a/scrapy/utils/misc.py +++ b/scrapy/utils/misc.py @@ -1,4 +1,5 @@ """Helper functions which don't fit anywhere else""" + import ast import hashlib import inspect @@ -25,6 +26,7 @@ from typing import ( cast, ) +from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.item import Item from scrapy.utils.datatypes import LocalWeakReferencedCache @@ -142,6 +144,13 @@ def create_instance(objcls, settings, crawler, *args, **kwargs): Raises ``TypeError`` if the resulting instance is ``None`` (e.g. if an extension has not been implemented correctly). """ + warnings.warn( + "The create_instance() function is deprecated. " + "Please use build_from_crawler() or build_from_settings() instead.", + category=ScrapyDeprecationWarning, + stacklevel=2, + ) + if settings is None: if crawler is None: raise ValueError("Specify at least one of settings and crawler.") @@ -160,6 +169,45 @@ def create_instance(objcls, settings, crawler, *args, **kwargs): return instance +def build_from_crawler(objcls, crawler, /, *args, **kwargs): + """Construct a class instance using its ``from_crawler`` constructor. + + ``*args`` and ``**kwargs`` are forwarded to the constructor. + + Raises ``TypeError`` if the resulting instance is ``None``. + """ + if hasattr(objcls, "from_crawler"): + instance = objcls.from_crawler(crawler, *args, **kwargs) + method_name = "from_crawler" + elif hasattr(objcls, "from_settings"): + instance = objcls.from_settings(crawler.settings, *args, **kwargs) + method_name = "from_settings" + else: + instance = objcls(*args, **kwargs) + method_name = "__new__" + if instance is None: + raise TypeError(f"{objcls.__qualname__}.{method_name} returned None") + return instance + + +def build_from_settings(objcls, settings, /, *args, **kwargs): + """Construct a class instance using its ``from_settings`` constructor. + + ``*args`` and ``**kwargs`` are forwarded to the constructor. + + Raises ``TypeError`` if the resulting instance is ``None``. + """ + if hasattr(objcls, "from_settings"): + instance = objcls.from_settings(settings, *args, **kwargs) + method_name = "from_settings" + else: + instance = objcls(*args, **kwargs) + method_name = "__new__" + if instance is None: + raise TypeError(f"{objcls.__qualname__}.{method_name} returned None") + return instance + + @contextmanager def set_environ(**kwargs: str) -> Generator[None, Any, None]: """Temporarily set environment variables inside the context manager and diff --git a/scrapy/utils/ossignal.py b/scrapy/utils/ossignal.py index db9a71273..5985a847e 100644 --- a/scrapy/utils/ossignal.py +++ b/scrapy/utils/ossignal.py @@ -24,7 +24,11 @@ def install_shutdown_handlers( (e.g. Pdb) """ signal.signal(signal.SIGTERM, function) - if signal.getsignal(signal.SIGINT) == signal.default_int_handler or override_sigint: + if ( + signal.getsignal(signal.SIGINT) # pylint: disable=comparison-with-callable + == signal.default_int_handler + or override_sigint + ): signal.signal(signal.SIGINT, function) # Catch Ctrl-Break in windows if hasattr(signal, "SIGBREAK"): diff --git a/scrapy/utils/python.py b/scrapy/utils/python.py index 0b5dc324f..1e7364e49 100644 --- a/scrapy/utils/python.py +++ b/scrapy/utils/python.py @@ -1,6 +1,7 @@ """ This module contains essential stuff that should've come with Python itself ;) """ + import collections.abc import gc import inspect @@ -57,8 +58,7 @@ def iflatten(x: Iterable) -> Iterable: Similar to ``.flatten()``, but returns iterator instead""" for el in x: if is_listlike(el): - for el_ in iflatten(el): - yield el_ + yield from iflatten(el) else: yield el @@ -162,7 +162,7 @@ def re_rsearch( pattern = re.compile(pattern) for chunk, offset in _chunk_iter(): - matches = [match for match in pattern.finditer(chunk)] + matches = list(pattern.finditer(chunk)) if matches: start, end = matches[-1].span() return offset + start, offset + end @@ -286,13 +286,11 @@ def equal_attributes( @overload -def without_none_values(iterable: Mapping) -> dict: - ... +def without_none_values(iterable: Mapping) -> dict: ... @overload -def without_none_values(iterable: Iterable) -> Iterable: - ... +def without_none_values(iterable: Iterable) -> Iterable: ... def without_none_values(iterable: Union[Mapping, Iterable]) -> Union[dict, Iterable]: diff --git a/scrapy/utils/request.py b/scrapy/utils/request.py index 24fcbd85e..e99d1eeb5 100644 --- a/scrapy/utils/request.py +++ b/scrapy/utils/request.py @@ -34,9 +34,6 @@ from scrapy.utils.python import to_bytes, to_unicode if TYPE_CHECKING: from scrapy.crawler import Crawler -_deprecated_fingerprint_cache: "WeakKeyDictionary[Request, Dict[Tuple[Optional[Tuple[bytes, ...]], bool], str]]" -_deprecated_fingerprint_cache = WeakKeyDictionary() - def _serialize_headers( headers: Iterable[bytes], request: Request @@ -44,125 +41,12 @@ def _serialize_headers( for header in headers: if header in request.headers: yield header - for value in request.headers.getlist(header): - yield value + yield from request.headers.getlist(header) -def request_fingerprint( - request: Request, - include_headers: Optional[Iterable[Union[bytes, str]]] = None, - keep_fragments: bool = False, -) -> str: - """ - Return the request fingerprint as an hexadecimal string. - - The request fingerprint is a hash that uniquely identifies the resource the - request points to. For example, take the following two urls: - - http://www.example.com/query?id=111&cat=222 - http://www.example.com/query?cat=222&id=111 - - Even though those are two different URLs both point to the same resource - and are equivalent (i.e. they should return the same response). - - Another example are cookies used to store session ids. Suppose the - following page is only accessible to authenticated users: - - http://www.example.com/members/offers.html - - Lots of sites use a cookie to store the session id, which adds a random - component to the HTTP Request and thus should be ignored when calculating - the fingerprint. - - For this reason, request headers are ignored by default when calculating - the fingerprint. If you want to include specific headers use the - include_headers argument, which is a list of Request headers to include. - - Also, servers usually ignore fragments in urls when handling requests, - so they are also ignored by default when calculating the fingerprint. - If you want to include them, set the keep_fragments argument to True - (for instance when handling requests with a headless browser). - """ - if include_headers or keep_fragments: - message = ( - "Call to deprecated function " - "scrapy.utils.request.request_fingerprint().\n" - "\n" - "If you are using this function in a Scrapy component because you " - "need a non-default fingerprinting algorithm, and you are OK " - "with that non-default fingerprinting algorithm being used by " - "all Scrapy components and not just the one calling this " - "function, use crawler.request_fingerprinter.fingerprint() " - "instead in your Scrapy component (you can get the crawler " - "object from the 'from_crawler' class method), and use the " - "'REQUEST_FINGERPRINTER_CLASS' setting to configure your " - "non-default fingerprinting algorithm.\n" - "\n" - "Otherwise, consider using the " - "scrapy.utils.request.fingerprint() function instead.\n" - "\n" - "If you switch to 'fingerprint()', or assign the " - "'REQUEST_FINGERPRINTER_CLASS' setting a class that uses " - "'fingerprint()', the generated fingerprints will not only be " - "bytes instead of a string, but they will also be different from " - "those generated by 'request_fingerprint()'. Before you switch, " - "make sure that you understand the consequences of this (e.g. " - "cache invalidation) and are OK with them; otherwise, consider " - "implementing your own function which returns the same " - "fingerprints as the deprecated 'request_fingerprint()' function." - ) - else: - message = ( - "Call to deprecated function " - "scrapy.utils.request.request_fingerprint().\n" - "\n" - "If you are using this function in a Scrapy component, and you " - "are OK with users of your component changing the fingerprinting " - "algorithm through settings, use " - "crawler.request_fingerprinter.fingerprint() instead in your " - "Scrapy component (you can get the crawler object from the " - "'from_crawler' class method).\n" - "\n" - "Otherwise, consider using the " - "scrapy.utils.request.fingerprint() function instead.\n" - "\n" - "Either way, the resulting fingerprints will be returned as " - "bytes, not as a string, and they will also be different from " - "those generated by 'request_fingerprint()'. Before you switch, " - "make sure that you understand the consequences of this (e.g. " - "cache invalidation) and are OK with them; otherwise, consider " - "implementing your own function which returns the same " - "fingerprints as the deprecated 'request_fingerprint()' function." - ) - warnings.warn(message, category=ScrapyDeprecationWarning, stacklevel=2) - processed_include_headers: Optional[Tuple[bytes, ...]] = None - if include_headers: - processed_include_headers = tuple( - to_bytes(h.lower()) for h in sorted(include_headers) - ) - cache = _deprecated_fingerprint_cache.setdefault(request, {}) - cache_key = (processed_include_headers, keep_fragments) - if cache_key not in cache: - fp = hashlib.sha1() - fp.update(to_bytes(request.method)) - fp.update( - to_bytes(canonicalize_url(request.url, keep_fragments=keep_fragments)) - ) - fp.update(request.body or b"") - if processed_include_headers: - for part in _serialize_headers(processed_include_headers, request): - fp.update(part) - cache[cache_key] = fp.hexdigest() - return cache[cache_key] - - -def _request_fingerprint_as_bytes(*args: Any, **kwargs: Any) -> bytes: - with warnings.catch_warnings(): - warnings.simplefilter("ignore") - return bytes.fromhex(request_fingerprint(*args, **kwargs)) - - -_fingerprint_cache: "WeakKeyDictionary[Request, Dict[Tuple[Optional[Tuple[bytes, ...]], bool], bytes]]" +_fingerprint_cache: ( + "WeakKeyDictionary[Request, Dict[Tuple[Optional[Tuple[bytes, ...]], bool], bytes]]" +) _fingerprint_cache = WeakKeyDictionary() @@ -232,8 +116,7 @@ def fingerprint( class RequestFingerprinterProtocol(Protocol): - def fingerprint(self, request: Request) -> bytes: - ... + def fingerprint(self, request: Request) -> bytes: ... class RequestFingerprinter: @@ -259,33 +142,15 @@ class RequestFingerprinter: "REQUEST_FINGERPRINTER_IMPLEMENTATION" ) else: - implementation = "2.6" - if implementation == "2.6": + implementation = "SENTINEL" + + if implementation != "SENTINEL": message = ( - "'2.6' is a deprecated value for the " - "'REQUEST_FINGERPRINTER_IMPLEMENTATION' setting.\n" - "\n" - "It is also the default value. In other words, it is normal " - "to get this warning if you have not defined a value for the " - "'REQUEST_FINGERPRINTER_IMPLEMENTATION' setting. This is so " - "for backward compatibility reasons, but it will change in a " - "future version of Scrapy.\n" - "\n" - "See the documentation of the " - "'REQUEST_FINGERPRINTER_IMPLEMENTATION' setting for " - "information on how to handle this deprecation." + "'REQUEST_FINGERPRINTER_IMPLEMENTATION' is a deprecated setting.\n" + "And it will be removed in future version of Scrapy." ) warnings.warn(message, category=ScrapyDeprecationWarning, stacklevel=2) - self._fingerprint = _request_fingerprint_as_bytes - elif implementation == "2.7": - self._fingerprint = fingerprint - else: - raise ValueError( - f"Got an invalid value on setting " - f"'REQUEST_FINGERPRINTER_IMPLEMENTATION': " - f"{implementation!r}. Valid values are '2.6' (deprecated) " - f"and '2.7'." - ) + self._fingerprint = fingerprint def fingerprint(self, request: Request) -> bytes: return self._fingerprint(request) diff --git a/scrapy/utils/response.py b/scrapy/utils/response.py index 77d54aff9..63a484b42 100644 --- a/scrapy/utils/response.py +++ b/scrapy/utils/response.py @@ -2,6 +2,7 @@ This module provides some useful functions for working with scrapy.http.Response objects """ + import os import re import tempfile @@ -29,9 +30,9 @@ def get_base_url(response: "scrapy.http.response.text.TextResponse") -> str: return _baseurl_cache[response] -_metaref_cache: "WeakKeyDictionary[Response, Union[Tuple[None, None], Tuple[float, str]]]" = ( - WeakKeyDictionary() -) +_metaref_cache: ( + "WeakKeyDictionary[Response, Union[Tuple[None, None], Tuple[float, str]]]" +) = WeakKeyDictionary() def get_meta_refresh( @@ -54,6 +55,18 @@ def response_status_message(status: Union[bytes, float, int, str]) -> str: return f"{status_int} {to_unicode(message)}" +def _remove_html_comments(body): + start = body.find(b"", start + 1) + if end == -1: + return body[:start] + else: + body = body[:start] + body[end + 3 :] + start = body.find(b"", b"", body, flags=re.DOTALL) - body = re.sub(rb"(|\s.*?>))", to_bytes(repl), body) + _remove_html_comments(body) + repl = rf'\0' + body = re.sub(rb"]*?>)", to_bytes(repl), body, count=1) ext = ".html" elif isinstance(response, TextResponse): ext = ".txt" diff --git a/scrapy/utils/signal.py b/scrapy/utils/signal.py index 21a12a19e..89cfbd2ec 100644 --- a/scrapy/utils/signal.py +++ b/scrapy/utils/signal.py @@ -1,4 +1,5 @@ """Helper functions for working with signals""" + import collections.abc import logging from typing import Any as TypingAny @@ -97,7 +98,10 @@ def send_catch_log_deferred( robustApply, receiver, signal=signal, sender=sender, *arguments, **named ) d.addErrback(logerror, receiver) - d.addBoth(lambda result: (receiver, result)) + # TODO https://pylint.readthedocs.io/en/latest/user_guide/messages/warning/cell-var-from-loop.html + d.addBoth( + lambda result: (receiver, result) # pylint: disable=cell-var-from-loop + ) dfds.append(d) d = DeferredList(dfds) d.addCallback(lambda out: [x[1] for x in out]) diff --git a/scrapy/utils/sitemap.py b/scrapy/utils/sitemap.py index 3d2ecc9a7..8bf941eb2 100644 --- a/scrapy/utils/sitemap.py +++ b/scrapy/utils/sitemap.py @@ -4,6 +4,7 @@ Module for processing Sitemaps. Note: The main purpose of this module is to provide support for the SitemapSpider, its API is subject to change without notice. """ + from typing import Any, Dict, Generator, Iterator, Optional from urllib.parse import urljoin diff --git a/scrapy/utils/spider.py b/scrapy/utils/spider.py index 704df8657..cbbb01d85 100644 --- a/scrapy/utils/spider.py +++ b/scrapy/utils/spider.py @@ -34,18 +34,15 @@ _T = TypeVar("_T") # https://stackoverflow.com/questions/60222982 @overload -def iterate_spider_output(result: AsyncGenerator) -> AsyncGenerator: # type: ignore[misc] - ... +def iterate_spider_output(result: AsyncGenerator) -> AsyncGenerator: ... # type: ignore[overload-overlap] @overload -def iterate_spider_output(result: CoroutineType) -> Deferred: - ... +def iterate_spider_output(result: CoroutineType) -> Deferred: ... @overload -def iterate_spider_output(result: _T) -> Iterable: - ... +def iterate_spider_output(result: _T) -> Iterable: ... def iterate_spider_output(result: Any) -> Union[Iterable, AsyncGenerator, Deferred]: @@ -83,8 +80,7 @@ def spidercls_for_request( default_spidercls: Type[Spider], log_none: bool = ..., log_multiple: bool = ..., -) -> Type[Spider]: - ... +) -> Type[Spider]: ... @overload @@ -94,8 +90,7 @@ def spidercls_for_request( default_spidercls: Literal[None], log_none: bool = ..., log_multiple: bool = ..., -) -> Optional[Type[Spider]]: - ... +) -> Optional[Type[Spider]]: ... @overload @@ -105,8 +100,7 @@ def spidercls_for_request( *, log_none: bool = ..., log_multiple: bool = ..., -) -> Optional[Type[Spider]]: - ... +) -> Optional[Type[Spider]]: ... def spidercls_for_request( diff --git a/scrapy/utils/ssl.py b/scrapy/utils/ssl.py index e74769c65..d520ef809 100644 --- a/scrapy/utils/ssl.py +++ b/scrapy/utils/ssl.py @@ -1,6 +1,6 @@ from typing import Any, Optional -import OpenSSL._util as pyOpenSSLutil # type: ignore[import-untyped] +import OpenSSL._util as pyOpenSSLutil import OpenSSL.SSL import OpenSSL.version from OpenSSL.crypto import X509Name diff --git a/scrapy/utils/test.py b/scrapy/utils/test.py index 709e0b00d..7a8c5c859 100644 --- a/scrapy/utils/test.py +++ b/scrapy/utils/test.py @@ -86,8 +86,6 @@ def get_crawler( # Set by default settings that prevent deprecation warnings. settings: Dict[str, Any] = {} - if prevent_warnings: - settings["REQUEST_FINGERPRINTER_IMPLEMENTATION"] = "2.7" settings.update(settings_dict or {}) runner = CrawlerRunner(settings) crawler = runner.create_crawler(spidercls or TestSpider) diff --git a/scrapy/utils/url.py b/scrapy/utils/url.py index 22b4197f9..9d97cb12f 100644 --- a/scrapy/utils/url.py +++ b/scrapy/utils/url.py @@ -5,6 +5,7 @@ library. Some of the functions that used to be imported from this module have been moved to the w3lib.url module. Always import those from there instead. """ + import re from typing import TYPE_CHECKING, Iterable, Optional, Type, Union, cast from urllib.parse import ParseResult, urldefrag, urlparse, urlunparse diff --git a/setup.py b/setup.py index 405633f55..2d6d26b0c 100644 --- a/setup.py +++ b/setup.py @@ -22,6 +22,7 @@ install_requires = [ "packaging", "tldextract", "lxml>=4.4.1", + "defusedxml>=0.7.1", ] extras_require = { ':platform_python_implementation == "CPython"': ["PyDispatcher>=2.0.5"], diff --git a/tests/CrawlerRunner/ip_address.py b/tests/CrawlerRunner/ip_address.py index 23260ab0d..5bf7512bc 100644 --- a/tests/CrawlerRunner/ip_address.py +++ b/tests/CrawlerRunner/ip_address.py @@ -9,6 +9,7 @@ from twisted.python.runtime import platform from scrapy import Request, Spider from scrapy.crawler import CrawlerRunner +from scrapy.utils.httpobj import urlparse_cached from scrapy.utils.log import configure_logging from tests.mockserver import MockDNSServer, MockServer @@ -30,7 +31,7 @@ class LocalhostSpider(Spider): yield Request(self.url) def parse(self, response): - netloc = urlparse(response.url).netloc + netloc = urlparse_cached(response).netloc host = netloc.split(":")[0] self.logger.info(f"Host: {host}") self.logger.info(f"Type: {type(response.ip_address)}") diff --git a/tests/mocks/dummydbm.py b/tests/mocks/dummydbm.py index 2869ff8f7..bde3de228 100644 --- a/tests/mocks/dummydbm.py +++ b/tests/mocks/dummydbm.py @@ -1,4 +1,5 @@ """DBM-like dummy module""" + import collections from typing import Any, DefaultDict diff --git a/tests/sample_data/compressed/bomb-br.bin b/tests/sample_data/compressed/bomb-br.bin new file mode 100644 index 000000000..50059866f --- /dev/null +++ b/tests/sample_data/compressed/bomb-br.bin @@ -0,0 +1,2 @@ +;nުVp SmoY2 +()-д=_o \ No newline at end of file diff --git a/tests/sample_data/compressed/bomb-deflate.bin b/tests/sample_data/compressed/bomb-deflate.bin new file mode 100644 index 000000000..3598aca07 Binary files /dev/null and b/tests/sample_data/compressed/bomb-deflate.bin differ diff --git a/tests/sample_data/compressed/bomb-gzip.bin b/tests/sample_data/compressed/bomb-gzip.bin new file mode 100644 index 000000000..64aa0c369 Binary files /dev/null and b/tests/sample_data/compressed/bomb-gzip.bin differ diff --git a/tests/sample_data/compressed/bomb-zstd.bin b/tests/sample_data/compressed/bomb-zstd.bin new file mode 100644 index 000000000..4b0efa8a4 Binary files /dev/null and b/tests/sample_data/compressed/bomb-zstd.bin differ diff --git a/tests/sample_data/compressed/html-gzip-deflate-gzip.bin b/tests/sample_data/compressed/html-gzip-deflate-gzip.bin new file mode 100644 index 000000000..d66f4c5a0 Binary files /dev/null and b/tests/sample_data/compressed/html-gzip-deflate-gzip.bin differ diff --git a/tests/sample_data/compressed/html-gzip-deflate.bin b/tests/sample_data/compressed/html-gzip-deflate.bin new file mode 100644 index 000000000..5066842ef Binary files /dev/null and b/tests/sample_data/compressed/html-gzip-deflate.bin differ diff --git a/tests/spiders.py b/tests/spiders.py index f29dea2a1..94969db99 100644 --- a/tests/spiders.py +++ b/tests/spiders.py @@ -1,6 +1,7 @@ """ Some spiders used for testing and benchmarking """ + import asyncio import time from urllib.parse import urlencode @@ -301,8 +302,7 @@ class BrokenStartRequestsSpider(FollowAllSpider): def parse(self, response): self.seedsseen.append(response.meta.get("seed")) - for req in super().parse(response): - yield req + yield from super().parse(response) class SingleRequestSpider(MetaSpider): diff --git a/tests/test_addons.py b/tests/test_addons.py index 0f4f2e5b8..f1b01bc5c 100644 --- a/tests/test_addons.py +++ b/tests/test_addons.py @@ -89,7 +89,7 @@ class AddonManagerTest(unittest.TestCase): self.assertEqual([a.number for a in manager.addons], expected_order) self.assertEqual(crawler.settings.getint("KEY1"), expected_order[-1]) - def test_create_instance(self): + def test_build_from_crawler(self): settings_dict = { "ADDONS": {"tests.test_addons.CreateInstanceAddon": 0}, "MYADDON": {"MYADDON_KEY": "val"}, @@ -167,12 +167,12 @@ class AddonManagerTest(unittest.TestCase): pass with patch("scrapy.addons.logger") as logger_mock: - with patch("scrapy.addons.create_instance") as create_instance_mock: + with patch("scrapy.addons.build_from_crawler") as build_from_crawler_mock: settings_dict = { "ADDONS": {LoggedAddon: 1}, } addon = LoggedAddon() - create_instance_mock.return_value = addon + build_from_crawler_mock.return_value = addon crawler = get_crawler(settings_dict=settings_dict) logger_mock.info.assert_called_once_with( "Enabled addons:\n%(addons)s", diff --git a/tests/test_command_check.py b/tests/test_command_check.py index 129ef0121..592494aba 100644 --- a/tests/test_command_check.py +++ b/tests/test_command_check.py @@ -16,11 +16,11 @@ import scrapy class CheckSpider(scrapy.Spider): name = '{self.spider_name}' - start_urls = ['http://toscrape.com'] + start_urls = ['data:,'] def parse(self, response, **cb_kwargs): \"\"\" - @url http://toscrape.com + @url data:, {contracts} \"\"\" {parse_def} diff --git a/tests/test_command_parse.py b/tests/test_command_parse.py index 037333c03..9356d6b79 100644 --- a/tests/test_command_parse.py +++ b/tests/test_command_parse.py @@ -78,9 +78,21 @@ class AsyncDefAsyncioGenExcSpider(scrapy.Spider): if i > 5: raise ValueError("Stopping the processing") +class CallbackSignatureDownloaderMiddleware: + def process_request(self, request, spider): + from inspect import signature + spider.logger.debug(f"request.callback signature: {{signature(request.callback)}}") + + class MySpider(scrapy.Spider): name = '{self.spider_name}' + custom_settings = {{ + "DOWNLOADER_MIDDLEWARES": {{ + CallbackSignatureDownloaderMiddleware: 0, + }} + }} + def parse(self, response): if getattr(self, 'test_arg', None): self.logger.debug('It Works!') @@ -220,7 +232,11 @@ ITEM_PIPELINES = {{'{self.project_name}.pipelines.MyPipeline': 1}} self.url("/html"), ] ) - self.assertIn("DEBUG: It Works!", _textmode(stderr)) + log = _textmode(stderr) + self.assertIn("DEBUG: It Works!", log) + self.assertIn( + "DEBUG: request.callback signature: (response, foo=None, key=None)", log + ) @defer.inlineCallbacks def test_request_without_meta(self): diff --git a/tests/test_commands.py b/tests/test_commands.py index 36f800850..febad21da 100644 --- a/tests/test_commands.py +++ b/tests/test_commands.py @@ -6,13 +6,12 @@ import platform import re import subprocess import sys -import tempfile from contextlib import contextmanager from itertools import chain from pathlib import Path from shutil import copytree, rmtree from stat import S_IWRITE as ANYONE_WRITE_PERMISSION -from tempfile import mkdtemp +from tempfile import TemporaryFile, mkdtemp from threading import Timer from typing import Dict, Generator, Optional, Union from unittest import skipIf @@ -82,7 +81,7 @@ class ProjectTest(unittest.TestCase): rmtree(self.temp_path) def call(self, *new_args, **kwargs): - with tempfile.TemporaryFile() as out: + with TemporaryFile() as out: args = (sys.executable, "-m", "scrapy.cmdline") + new_args return subprocess.call( args, stdout=out, stderr=out, cwd=self.cwd, env=self.env, **kwargs @@ -992,38 +991,11 @@ class MySpider(scrapy.Spider): class WindowsRunSpiderCommandTest(RunSpiderCommandTest): spider_filename = "myspider.pyw" - def setUp(self): - super().setUp() - def test_start_requests_errors(self): log = self.get_log(self.badspider, name="badspider.pyw") self.assertIn("start_requests", log) self.assertIn("badspider.pyw", log) - def test_run_good_spider(self): - super().test_run_good_spider() - - def test_runspider(self): - super().test_runspider() - - def test_runspider_dnscache_disabled(self): - super().test_runspider_dnscache_disabled() - - def test_runspider_log_level(self): - super().test_runspider_log_level() - - def test_runspider_log_short_names(self): - super().test_runspider_log_short_names() - - def test_runspider_no_spider_found(self): - super().test_runspider_no_spider_found() - - def test_output(self): - super().test_output() - - def test_overwrite_output(self): - super().test_overwrite_output() - def test_runspider_unable_to_load(self): raise unittest.SkipTest("Already Tested in 'RunSpiderCommandTest' ") diff --git a/tests/test_crawl.py b/tests/test_crawl.py index 96d43b2b9..6cde4ed8c 100644 --- a/tests/test_crawl.py +++ b/tests/test_crawl.py @@ -76,11 +76,11 @@ class CrawlTestCase(TestCase): @defer.inlineCallbacks def _test_delay(self, total, delay, randomize=False): - crawl_kwargs = dict( - maxlatency=delay * 2, - mockserver=self.mockserver, - total=total, - ) + crawl_kwargs = { + "maxlatency": delay * 2, + "mockserver": self.mockserver, + "total": total, + } tolerance = 1 - (0.6 if randomize else 0.2) settings = {"DOWNLOAD_DELAY": delay, "RANDOMIZE_DOWNLOAD_DELAY": randomize} diff --git a/tests/test_crawler.py b/tests/test_crawler.py index 92bd5f38f..989208694 100644 --- a/tests/test_crawler.py +++ b/tests/test_crawler.py @@ -12,12 +12,13 @@ import pytest from packaging.version import parse as parse_version from pexpect.popen_spawn import PopenSpawn from pytest import mark, raises -from twisted.internet import defer +from twisted.internet.defer import Deferred, inlineCallbacks from twisted.trial import unittest from w3lib import __version__ as w3lib_version from zope.interface.exceptions import MultipleInvalid import scrapy +from scrapy import Spider from scrapy.crawler import Crawler, CrawlerProcess, CrawlerRunner from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.extensions import telnet @@ -29,6 +30,19 @@ from scrapy.utils.spider import DefaultSpider from scrapy.utils.test import get_crawler from tests.mockserver import MockServer, get_mockserver_env +# To prevent warnings. +BASE_SETTINGS = { + "REQUEST_FINGERPRINTER_IMPLEMENTATION": "2.7", +} + + +def get_raw_crawler(spidercls=None, settings_dict=None): + """get_crawler alternative that only calls the __init__ method of the + crawler.""" + settings = Settings() + settings.setdict(settings_dict or {}) + return Crawler(spidercls or DefaultSpider, settings) + class BaseCrawlerTest(unittest.TestCase): def assertOptionIsDefault(self, settings, key): @@ -39,7 +53,7 @@ class BaseCrawlerTest(unittest.TestCase): class CrawlerTestCase(BaseCrawlerTest): def test_populate_spidercls_settings(self): spider_settings = {"TEST1": "spider", "TEST2": "spider"} - project_settings = {"TEST1": "project", "TEST3": "project"} + project_settings = {**BASE_SETTINGS, "TEST1": "project", "TEST3": "project"} class CustomSettingsSpider(DefaultSpider): custom_settings = spider_settings @@ -71,9 +85,9 @@ class CrawlerTestCase(BaseCrawlerTest): with raises(ValueError): Crawler(DefaultSpider()) - @defer.inlineCallbacks + @inlineCallbacks def test_crawler_crawl_twice_deprecated(self): - crawler = Crawler(NoRequestsSpider) + crawler = get_raw_crawler(NoRequestsSpider, BASE_SETTINGS) yield crawler.crawl() with pytest.warns( ScrapyDeprecationWarning, @@ -81,6 +95,358 @@ class CrawlerTestCase(BaseCrawlerTest): ): yield crawler.crawl() + def test_get_addon(self): + class ParentAddon: + pass + + class TrackingAddon(ParentAddon): + instances = [] + + def __init__(self): + TrackingAddon.instances.append(self) + + def update_settings(self, settings): + pass + + settings = { + **BASE_SETTINGS, + "ADDONS": { + TrackingAddon: 0, + }, + } + crawler = get_crawler(settings_dict=settings) + self.assertEqual(len(TrackingAddon.instances), 1) + expected = TrackingAddon.instances[-1] + + addon = crawler.get_addon(TrackingAddon) + self.assertEqual(addon, expected) + + addon = crawler.get_addon(DefaultSpider) + self.assertIsNone(addon) + + addon = crawler.get_addon(ParentAddon) + self.assertEqual(addon, expected) + + class ChildAddon(TrackingAddon): + pass + + addon = crawler.get_addon(ChildAddon) + self.assertIsNone(addon) + + @inlineCallbacks + def test_get_downloader_middleware(self): + class ParentDownloaderMiddleware: + pass + + class TrackingDownloaderMiddleware(ParentDownloaderMiddleware): + instances = [] + + def __init__(self): + TrackingDownloaderMiddleware.instances.append(self) + + class MySpider(Spider): + name = "myspider" + + @classmethod + def from_crawler(cls, crawler): + return cls(crawler=crawler) + + def __init__(self, crawler): + self.crawler = crawler + + def start_requests(self): + MySpider.result = crawler.get_downloader_middleware(MySpider.cls) + return + yield + + settings = { + **BASE_SETTINGS, + "DOWNLOADER_MIDDLEWARES": { + TrackingDownloaderMiddleware: 0, + }, + } + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = TrackingDownloaderMiddleware + yield crawler.crawl() + self.assertEqual(len(TrackingDownloaderMiddleware.instances), 1) + self.assertEqual(MySpider.result, TrackingDownloaderMiddleware.instances[-1]) + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = DefaultSpider + yield crawler.crawl() + self.assertIsNone(MySpider.result) + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = ParentDownloaderMiddleware + yield crawler.crawl() + self.assertEqual(MySpider.result, TrackingDownloaderMiddleware.instances[-1]) + + class ChildDownloaderMiddleware(TrackingDownloaderMiddleware): + pass + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = ChildDownloaderMiddleware + yield crawler.crawl() + self.assertIsNone(MySpider.result) + + def test_get_downloader_middleware_not_crawling(self): + crawler = get_raw_crawler(settings_dict=BASE_SETTINGS) + self.assertRaises( + RuntimeError, crawler.get_downloader_middleware, DefaultSpider + ) + + @inlineCallbacks + def test_get_downloader_middleware_no_engine(self): + class MySpider(Spider): + name = "myspider" + + @classmethod + def from_crawler(cls, crawler): + try: + crawler.get_downloader_middleware(DefaultSpider) + except Exception as e: + MySpider.result = e + raise + + crawler = get_raw_crawler(MySpider, BASE_SETTINGS) + with raises(RuntimeError): + yield crawler.crawl() + + @inlineCallbacks + def test_get_extension(self): + class ParentExtension: + pass + + class TrackingExtension(ParentExtension): + instances = [] + + def __init__(self): + TrackingExtension.instances.append(self) + + class MySpider(Spider): + name = "myspider" + + @classmethod + def from_crawler(cls, crawler): + return cls(crawler=crawler) + + def __init__(self, crawler): + self.crawler = crawler + + def start_requests(self): + MySpider.result = crawler.get_extension(MySpider.cls) + return + yield + + settings = { + **BASE_SETTINGS, + "EXTENSIONS": { + TrackingExtension: 0, + }, + } + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = TrackingExtension + yield crawler.crawl() + self.assertEqual(len(TrackingExtension.instances), 1) + self.assertEqual(MySpider.result, TrackingExtension.instances[-1]) + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = DefaultSpider + yield crawler.crawl() + self.assertIsNone(MySpider.result) + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = ParentExtension + yield crawler.crawl() + self.assertEqual(MySpider.result, TrackingExtension.instances[-1]) + + class ChildExtension(TrackingExtension): + pass + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = ChildExtension + yield crawler.crawl() + self.assertIsNone(MySpider.result) + + def test_get_extension_not_crawling(self): + crawler = get_raw_crawler(settings_dict=BASE_SETTINGS) + self.assertRaises(RuntimeError, crawler.get_extension, DefaultSpider) + + @inlineCallbacks + def test_get_extension_no_engine(self): + class MySpider(Spider): + name = "myspider" + + @classmethod + def from_crawler(cls, crawler): + try: + crawler.get_extension(DefaultSpider) + except Exception as e: + MySpider.result = e + raise + + crawler = get_raw_crawler(MySpider, BASE_SETTINGS) + with raises(RuntimeError): + yield crawler.crawl() + + @inlineCallbacks + def test_get_item_pipeline(self): + class ParentItemPipeline: + pass + + class TrackingItemPipeline(ParentItemPipeline): + instances = [] + + def __init__(self): + TrackingItemPipeline.instances.append(self) + + class MySpider(Spider): + name = "myspider" + + @classmethod + def from_crawler(cls, crawler): + return cls(crawler=crawler) + + def __init__(self, crawler): + self.crawler = crawler + + def start_requests(self): + MySpider.result = crawler.get_item_pipeline(MySpider.cls) + return + yield + + settings = { + **BASE_SETTINGS, + "ITEM_PIPELINES": { + TrackingItemPipeline: 0, + }, + } + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = TrackingItemPipeline + yield crawler.crawl() + self.assertEqual(len(TrackingItemPipeline.instances), 1) + self.assertEqual(MySpider.result, TrackingItemPipeline.instances[-1]) + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = DefaultSpider + yield crawler.crawl() + self.assertIsNone(MySpider.result) + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = ParentItemPipeline + yield crawler.crawl() + self.assertEqual(MySpider.result, TrackingItemPipeline.instances[-1]) + + class ChildItemPipeline(TrackingItemPipeline): + pass + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = ChildItemPipeline + yield crawler.crawl() + self.assertIsNone(MySpider.result) + + def test_get_item_pipeline_not_crawling(self): + crawler = get_raw_crawler(settings_dict=BASE_SETTINGS) + self.assertRaises(RuntimeError, crawler.get_item_pipeline, DefaultSpider) + + @inlineCallbacks + def test_get_item_pipeline_no_engine(self): + class MySpider(Spider): + name = "myspider" + + @classmethod + def from_crawler(cls, crawler): + try: + crawler.get_item_pipeline(DefaultSpider) + except Exception as e: + MySpider.result = e + raise + + crawler = get_raw_crawler(MySpider, BASE_SETTINGS) + with raises(RuntimeError): + yield crawler.crawl() + + @inlineCallbacks + def test_get_spider_middleware(self): + class ParentSpiderMiddleware: + pass + + class TrackingSpiderMiddleware(ParentSpiderMiddleware): + instances = [] + + def __init__(self): + TrackingSpiderMiddleware.instances.append(self) + + class MySpider(Spider): + name = "myspider" + + @classmethod + def from_crawler(cls, crawler): + return cls(crawler=crawler) + + def __init__(self, crawler): + self.crawler = crawler + + def start_requests(self): + MySpider.result = crawler.get_spider_middleware(MySpider.cls) + return + yield + + settings = { + **BASE_SETTINGS, + "SPIDER_MIDDLEWARES": { + TrackingSpiderMiddleware: 0, + }, + } + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = TrackingSpiderMiddleware + yield crawler.crawl() + self.assertEqual(len(TrackingSpiderMiddleware.instances), 1) + self.assertEqual(MySpider.result, TrackingSpiderMiddleware.instances[-1]) + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = DefaultSpider + yield crawler.crawl() + self.assertIsNone(MySpider.result) + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = ParentSpiderMiddleware + yield crawler.crawl() + self.assertEqual(MySpider.result, TrackingSpiderMiddleware.instances[-1]) + + class ChildSpiderMiddleware(TrackingSpiderMiddleware): + pass + + crawler = get_raw_crawler(MySpider, settings) + MySpider.cls = ChildSpiderMiddleware + yield crawler.crawl() + self.assertIsNone(MySpider.result) + + def test_get_spider_middleware_not_crawling(self): + crawler = get_raw_crawler(settings_dict=BASE_SETTINGS) + self.assertRaises(RuntimeError, crawler.get_spider_middleware, DefaultSpider) + + @inlineCallbacks + def test_get_spider_middleware_no_engine(self): + class MySpider(Spider): + name = "myspider" + + @classmethod + def from_crawler(cls, crawler): + try: + crawler.get_spider_middleware(DefaultSpider) + except Exception as e: + MySpider.result = e + raise + + crawler = get_raw_crawler(MySpider, BASE_SETTINGS) + with raises(RuntimeError): + yield crawler.crawl() + class SpiderSettingsTestCase(unittest.TestCase): def test_spider_custom_settings(self): @@ -223,20 +589,20 @@ class CrawlerRunnerHasSpider(unittest.TestCase): def _runner(self): return CrawlerRunner({"REQUEST_FINGERPRINTER_IMPLEMENTATION": "2.7"}) - @defer.inlineCallbacks + @inlineCallbacks def test_crawler_runner_bootstrap_successful(self): runner = self._runner() yield runner.crawl(NoRequestsSpider) self.assertFalse(runner.bootstrap_failed) - @defer.inlineCallbacks + @inlineCallbacks def test_crawler_runner_bootstrap_successful_for_several(self): runner = self._runner() yield runner.crawl(NoRequestsSpider) yield runner.crawl(NoRequestsSpider) self.assertFalse(runner.bootstrap_failed) - @defer.inlineCallbacks + @inlineCallbacks def test_crawler_runner_bootstrap_failed(self): runner = self._runner() @@ -249,7 +615,7 @@ class CrawlerRunnerHasSpider(unittest.TestCase): self.assertTrue(runner.bootstrap_failed) - @defer.inlineCallbacks + @inlineCallbacks def test_crawler_runner_bootstrap_failed_for_several(self): runner = self._runner() @@ -264,7 +630,7 @@ class CrawlerRunnerHasSpider(unittest.TestCase): self.assertTrue(runner.bootstrap_failed) - @defer.inlineCallbacks + @inlineCallbacks def test_crawler_runner_asyncio_enabled_true(self): if self.reactor_pytest == "asyncio": CrawlerRunner( @@ -531,7 +897,7 @@ class CrawlerProcessSubprocess(ScriptRunnerMixin, unittest.TestCase): p.expect_exact("Spider closed (shutdown)") p.wait() - @defer.inlineCallbacks + @inlineCallbacks def test_shutdown_forced(self): from twisted.internet import reactor @@ -543,7 +909,7 @@ class CrawlerProcessSubprocess(ScriptRunnerMixin, unittest.TestCase): p.kill(sig) p.expect_exact("shutting down gracefully") # sending the second signal too fast often causes problems - d = defer.Deferred() + d = Deferred() reactor.callLater(0.1, d.callback, None) yield d p.kill(sig) diff --git a/tests/test_downloader_handlers.py b/tests/test_downloader_handlers.py index f12243e1d..d3fd63847 100644 --- a/tests/test_downloader_handlers.py +++ b/tests/test_downloader_handlers.py @@ -2,8 +2,8 @@ import contextlib import os import shutil import sys -import tempfile from pathlib import Path +from tempfile import mkdtemp, mkstemp from typing import Optional, Type from unittest import SkipTest, mock @@ -29,7 +29,7 @@ from scrapy.http import Headers, HtmlResponse, Request from scrapy.http.response.text import TextResponse from scrapy.responsetypes import responsetypes from scrapy.spiders import Spider -from scrapy.utils.misc import create_instance +from scrapy.utils.misc import build_from_crawler from scrapy.utils.python import to_bytes from scrapy.utils.test import get_crawler, skip_if_no_boto from tests import NON_EXISTING_RESOLVABLE @@ -107,13 +107,14 @@ class LoadTestCase(unittest.TestCase): class FileTestCase(unittest.TestCase): def setUp(self): # add a special char to check that they are handled correctly - self.tmpname = Path(self.mktemp() + "^") + self.fd, self.tmpname = mkstemp(suffix="^") Path(self.tmpname).write_text("0123456789", encoding="utf-8") - handler = create_instance(FileDownloadHandler, None, get_crawler()) + handler = build_from_crawler(FileDownloadHandler, get_crawler()) self.download_request = handler.download_request def tearDown(self): - self.tmpname.unlink() + os.close(self.fd) + os.remove(self.tmpname) def test_download(self): def _test(response): @@ -122,12 +123,12 @@ class FileTestCase(unittest.TestCase): self.assertEqual(response.body, b"0123456789") self.assertEqual(response.protocol, None) - request = Request(path_to_file_uri(str(self.tmpname))) + request = Request(path_to_file_uri(self.tmpname)) assert request.url.upper().endswith("%5E") return self.download_request(request, Spider("foo")).addCallback(_test) def test_non_existent(self): - request = Request(path_to_file_uri(self.mktemp())) + request = Request(path_to_file_uri(mkdtemp())) d = self.download_request(request, Spider("foo")) return self.assertFailure(d, OSError) @@ -224,8 +225,7 @@ class HttpTestCase(unittest.TestCase): certfile = "keys/localhost.crt" def setUp(self): - self.tmpname = Path(self.mktemp()) - self.tmpname.mkdir() + self.tmpname = Path(mkdtemp()) (self.tmpname / "file").write_bytes(b"0123456789") r = static.File(str(self.tmpname)) r.putChild(b"redirect", util.Redirect(b"/file")) @@ -257,8 +257,8 @@ class HttpTestCase(unittest.TestCase): else: self.port = reactor.listenTCP(0, self.wrapper, interface=self.host) self.portno = self.port.getHost().port - self.download_handler = create_instance( - self.download_handler_cls, None, get_crawler() + self.download_handler = build_from_crawler( + self.download_handler_cls, get_crawler() ) self.download_request = self.download_handler.download_request @@ -557,7 +557,7 @@ class Http11TestCase(HttpTestCase): def test_download_broken_content_allow_data_loss_via_setting(self, url="broken"): crawler = get_crawler(settings_dict={"DOWNLOAD_FAIL_ON_DATALOSS": False}) - download_handler = create_instance(self.download_handler_cls, None, crawler) + download_handler = build_from_crawler(self.download_handler_cls, crawler) request = Request(self.getURL(url)) d = download_handler.download_request(request, Spider("foo")) d.addCallback(lambda r: r.flags) @@ -590,7 +590,7 @@ class Https11TestCase(Http11TestCase): crawler = get_crawler( settings_dict={"DOWNLOADER_CLIENT_TLS_VERBOSE_LOGGING": True} ) - download_handler = create_instance(self.download_handler_cls, None, crawler) + download_handler = build_from_crawler(self.download_handler_cls, crawler) try: with LogCapture() as log_capture: request = Request(self.getURL("file")) @@ -651,8 +651,7 @@ class Https11CustomCiphers(unittest.TestCase): certfile = "keys/localhost.crt" def setUp(self): - self.tmpname = Path(self.mktemp()) - self.tmpname.mkdir() + self.tmpname = Path(mkdtemp()) (self.tmpname / "file").write_bytes(b"0123456789") r = static.File(str(self.tmpname)) self.site = server.Site(r, timeout=None) @@ -669,9 +668,7 @@ class Https11CustomCiphers(unittest.TestCase): crawler = get_crawler( settings_dict={"DOWNLOADER_CLIENT_TLS_CIPHERS": "CAMELLIA256-SHA"} ) - self.download_handler = create_instance( - self.download_handler_cls, None, crawler - ) + self.download_handler = build_from_crawler(self.download_handler_cls, crawler) self.download_request = self.download_handler.download_request @defer.inlineCallbacks @@ -726,33 +723,6 @@ class Http11MockServerTestCase(unittest.TestCase): reason = crawler.spider.meta["close_reason"] self.assertTrue(reason, "finished") - @defer.inlineCallbacks - def test_download_gzip_response(self): - crawler = get_crawler(SingleRequestSpider, self.settings_dict) - body = b"1" * 100 # PayloadResource requires body length to be 100 - request = Request( - self.mockserver.url("/payload"), - method="POST", - body=body, - meta={"download_maxsize": 50}, - ) - yield crawler.crawl(seed=request) - failure = crawler.spider.meta["failure"] - # download_maxsize < 100, hence the CancelledError - self.assertIsInstance(failure.value, defer.CancelledError) - - # See issue https://twistedmatrix.com/trac/ticket/8175 - raise unittest.SkipTest("xpayload fails on PY3") - crawler = get_crawler(SingleRequestSpider, self.settings_dict) - request.headers.setdefault(b"Accept-Encoding", b"gzip,deflate") - request = request.replace(url=self.mockserver.url("/xpayload")) - yield crawler.crawl(seed=request) - # download_maxsize = 50 is enough for the gzipped response - failure = crawler.spider.meta.get("failure") - self.assertIsNone(failure) - reason = crawler.spider.meta["close_reason"] - self.assertTrue(reason, "finished") - class UriResource(resource.Resource): """Return the full uri that was requested""" @@ -778,8 +748,8 @@ class HttpProxyTestCase(unittest.TestCase): wrapper = WrappingFactory(site) self.port = reactor.listenTCP(0, wrapper, interface="127.0.0.1") self.portno = self.port.getHost().port - self.download_handler = create_instance( - self.download_handler_cls, None, get_crawler() + self.download_handler = build_from_crawler( + self.download_handler_cls, get_crawler() ) self.download_request = self.download_handler.download_request @@ -857,10 +827,9 @@ class S3AnonTestCase(unittest.TestCase): def setUp(self): skip_if_no_boto() crawler = get_crawler() - self.s3reqh = create_instance( - objcls=S3DownloadHandler, - settings=None, - crawler=crawler, + self.s3reqh = build_from_crawler( + S3DownloadHandler, + crawler, httpdownloadhandler=HttpDownloadHandlerMock, # anon=True, # implicit ) @@ -888,10 +857,9 @@ class S3TestCase(unittest.TestCase): def setUp(self): skip_if_no_boto() crawler = get_crawler() - s3reqh = create_instance( - objcls=S3DownloadHandler, - settings=None, - crawler=crawler, + s3reqh = build_from_crawler( + S3DownloadHandler, + crawler, aws_access_key_id=self.AWS_ACCESS_KEY_ID, aws_secret_access_key=self.AWS_SECRET_ACCESS_KEY, httpdownloadhandler=HttpDownloadHandlerMock, @@ -916,10 +884,9 @@ class S3TestCase(unittest.TestCase): def test_extra_kw(self): try: crawler = get_crawler() - create_instance( - objcls=S3DownloadHandler, - settings=None, - crawler=crawler, + build_from_crawler( + S3DownloadHandler, + crawler, extra_kw=True, ) except Exception as e: @@ -1047,8 +1014,7 @@ class BaseFTPTestCase(unittest.TestCase): from scrapy.core.downloader.handlers.ftp import FTPDownloadHandler # setup dirs and test file - self.directory = Path(self.mktemp()) - self.directory.mkdir() + self.directory = Path(mkdtemp()) userdir = self.directory / self.username userdir.mkdir() for filename, content in self.test_files: @@ -1066,9 +1032,7 @@ class BaseFTPTestCase(unittest.TestCase): self.port = reactor.listenTCP(0, self.factory, interface="127.0.0.1") self.portNum = self.port.getHost().port crawler = get_crawler() - self.download_handler = create_instance( - FTPDownloadHandler, crawler.settings, crawler - ) + self.download_handler = build_from_crawler(FTPDownloadHandler, crawler) self.addCleanup(self.port.stopListening) def tearDown(self): @@ -1126,7 +1090,7 @@ class BaseFTPTestCase(unittest.TestCase): return self._add_test_callbacks(d, _test) def test_ftp_local_filename(self): - f, local_fname = tempfile.mkstemp() + f, local_fname = mkstemp() fname_bytes = to_bytes(local_fname) local_fname = Path(local_fname) os.close(f) @@ -1147,7 +1111,7 @@ class BaseFTPTestCase(unittest.TestCase): return self._add_test_callbacks(d, _test) def _test_response_class(self, filename, response_class): - f, local_fname = tempfile.mkstemp() + f, local_fname = mkstemp() local_fname = Path(local_fname) os.close(f) meta = {} @@ -1197,9 +1161,7 @@ class AnonymousFTPTestCase(BaseFTPTestCase): from scrapy.core.downloader.handlers.ftp import FTPDownloadHandler # setup dir and test file - self.directory = Path(self.mktemp()) - self.directory.mkdir() - + self.directory = Path(mkdtemp()) for filename, content in self.test_files: (self.directory / filename).write_bytes(content) @@ -1212,9 +1174,7 @@ class AnonymousFTPTestCase(BaseFTPTestCase): self.port = reactor.listenTCP(0, self.factory, interface="127.0.0.1") self.portNum = self.port.getHost().port crawler = get_crawler() - self.download_handler = create_instance( - FTPDownloadHandler, crawler.settings, crawler - ) + self.download_handler = build_from_crawler(FTPDownloadHandler, crawler) self.addCleanup(self.port.stopListening) def tearDown(self): @@ -1224,9 +1184,7 @@ class AnonymousFTPTestCase(BaseFTPTestCase): class DataURITestCase(unittest.TestCase): def setUp(self): crawler = get_crawler() - self.download_handler = create_instance( - DataURIDownloadHandler, crawler.settings, crawler - ) + self.download_handler = build_from_crawler(DataURIDownloadHandler, crawler) self.download_request = self.download_handler.download_request self.spider = Spider("foo") diff --git a/tests/test_downloader_handlers_http2.py b/tests/test_downloader_handlers_http2.py index 31fa1430d..322075043 100644 --- a/tests/test_downloader_handlers_http2.py +++ b/tests/test_downloader_handlers_http2.py @@ -11,7 +11,7 @@ from twisted.web.http import H2_ENABLED from scrapy.http import Request from scrapy.spiders import Spider -from scrapy.utils.misc import create_instance +from scrapy.utils.misc import build_from_crawler from scrapy.utils.test import get_crawler from tests.mockserver import ssl_context_factory from tests.test_downloader_handlers import ( @@ -240,8 +240,8 @@ class Https2ProxyTestCase(Http11ProxyTestCase): interface=self.host, ) self.portno = self.port.getHost().port - self.download_handler = create_instance( - self.download_handler_cls, None, get_crawler() + self.download_handler = build_from_crawler( + self.download_handler_cls, get_crawler() ) self.download_request = self.download_handler.download_request diff --git a/tests/test_downloadermiddleware_cookies.py b/tests/test_downloadermiddleware_cookies.py index 4a81a638e..425fabcc7 100644 --- a/tests/test_downloadermiddleware_cookies.py +++ b/tests/test_downloadermiddleware_cookies.py @@ -320,7 +320,7 @@ class CookiesMiddlewareTest(TestCase): @pytest.mark.xfail(reason="Cookie header is not currently being processed") def test_keep_cookie_from_default_request_headers_middleware(self): - DEFAULT_REQUEST_HEADERS = dict(Cookie="default=value; asdf=qwerty") + DEFAULT_REQUEST_HEADERS = {"Cookie": "default=value; asdf=qwerty"} mw_default_headers = DefaultHeadersMiddleware(DEFAULT_REQUEST_HEADERS.items()) # overwrite with values from 'cookies' request argument req1 = Request("http://example.org", cookies={"default": "something"}) diff --git a/tests/test_downloadermiddleware_httpauth.py b/tests/test_downloadermiddleware_httpauth.py index fc110e6cc..500af6536 100644 --- a/tests/test_downloadermiddleware_httpauth.py +++ b/tests/test_downloadermiddleware_httpauth.py @@ -59,7 +59,7 @@ class HttpAuthMiddlewareTest(unittest.TestCase): self.assertEqual(req.headers["Authorization"], basic_auth_header("foo", "bar")) def test_auth_already_set(self): - req = Request("http://example.com/", headers=dict(Authorization="Digest 123")) + req = Request("http://example.com/", headers={"Authorization": "Digest 123"}) assert self.mw.process_request(req, self.spider) is None self.assertEqual(req.headers["Authorization"], b"Digest 123") @@ -79,6 +79,6 @@ class HttpAuthAnyMiddlewareTest(unittest.TestCase): self.assertEqual(req.headers["Authorization"], basic_auth_header("foo", "bar")) def test_auth_already_set(self): - req = Request("http://example.com/", headers=dict(Authorization="Digest 123")) + req = Request("http://example.com/", headers={"Authorization": "Digest 123"}) assert self.mw.process_request(req, self.spider) is None self.assertEqual(req.headers["Authorization"], b"Digest 123") diff --git a/tests/test_downloadermiddleware_httpcompression.py b/tests/test_downloadermiddleware_httpcompression.py index a96b710f3..ae5569d0a 100644 --- a/tests/test_downloadermiddleware_httpcompression.py +++ b/tests/test_downloadermiddleware_httpcompression.py @@ -1,15 +1,18 @@ from gzip import GzipFile from io import BytesIO +from logging import WARNING from pathlib import Path from unittest import SkipTest, TestCase +from warnings import catch_warnings +from testfixtures import LogCapture from w3lib.encoding import resolve_encoding from scrapy.downloadermiddlewares.httpcompression import ( ACCEPTED_ENCODINGS, HttpCompressionMiddleware, ) -from scrapy.exceptions import NotConfigured +from scrapy.exceptions import IgnoreRequest, NotConfigured, ScrapyDeprecationWarning from scrapy.http import HtmlResponse, Request, Response from scrapy.responsetypes import responsetypes from scrapy.spiders import Spider @@ -24,6 +27,8 @@ FORMAT = { "x-gzip": ("html-gzip.bin", "gzip"), "rawdeflate": ("html-rawdeflate.bin", "deflate"), "zlibdeflate": ("html-zlibdeflate.bin", "deflate"), + "gzip-deflate": ("html-gzip-deflate.bin", "gzip, deflate"), + "gzip-deflate-gzip": ("html-gzip-deflate-gzip.bin", "gzip, deflate, gzip"), "br": ("html-br.bin", "br"), # $ zstd raw.html --content-size -o html-zstd-static-content-size.bin "zstd-static-content-size": ("html-zstd-static-content-size.bin", "zstd"), @@ -34,6 +39,15 @@ FORMAT = { "html-zstd-streaming-no-content-size.bin", "zstd", ), + **{ + f"bomb-{format_id}": (f"bomb-{format_id}.bin", format_id) + for format_id in ( + "br", # 34 → 11 511 612 + "deflate", # 27 968 → 11 511 612 + "gzip", # 27 988 → 11 511 612 + "zstd", # 1 096 → 11 511 612 + ) + }, } @@ -114,18 +128,6 @@ class HttpCompressionTest(TestCase): self.assertStatsEqual("httpcompression/response_count", 1) self.assertStatsEqual("httpcompression/response_bytes", 74837) - def test_process_response_gzip_no_stats(self): - mw = HttpCompressionMiddleware() - response = self._getresponse("gzip") - request = response.request - - self.assertEqual(response.headers["Content-Encoding"], b"gzip") - newresponse = mw.process_response(request, response, self.spider) - self.assertEqual(mw.stats, None) - assert newresponse is not response - assert newresponse.body.startswith(b" body size after " + "decompression (11511612 B) is larger than the download " + "warning size (10000000 B)." + ), + ), + ) + + def test_download_warnsize_setting_br(self): + try: + import brotli # noqa: F401 + except ImportError: + raise SkipTest("no brotli") + self._test_download_warnsize_setting("br") + + def test_download_warnsize_setting_deflate(self): + self._test_download_warnsize_setting("deflate") + + def test_download_warnsize_setting_gzip(self): + self._test_download_warnsize_setting("gzip") + + def test_download_warnsize_setting_zstd(self): + try: + import zstandard # noqa: F401 + except ImportError: + raise SkipTest("no zstd support (zstandard)") + self._test_download_warnsize_setting("zstd") + + def _test_download_warnsize_spider_attr(self, compression_id): + class DownloadWarnSizeSpider(Spider): + download_warnsize = 10_000_000 + + crawler = get_crawler(DownloadWarnSizeSpider) + spider = crawler._create_spider("scrapytest.org") + mw = HttpCompressionMiddleware.from_crawler(crawler) + mw.open_spider(spider) + response = self._getresponse(f"bomb-{compression_id}") + + with LogCapture( + "scrapy.downloadermiddlewares.httpcompression", + propagate=False, + level=WARNING, + ) as log: + mw.process_response(response.request, response, spider) + log.check( + ( + "scrapy.downloadermiddlewares.httpcompression", + "WARNING", + ( + "<200 http://scrapytest.org/> body size after " + "decompression (11511612 B) is larger than the download " + "warning size (10000000 B)." + ), + ), + ) + + def test_download_warnsize_spider_attr_br(self): + try: + import brotli # noqa: F401 + except ImportError: + raise SkipTest("no brotli") + self._test_download_warnsize_spider_attr("br") + + def test_download_warnsize_spider_attr_deflate(self): + self._test_download_warnsize_spider_attr("deflate") + + def test_download_warnsize_spider_attr_gzip(self): + self._test_download_warnsize_spider_attr("gzip") + + def test_download_warnsize_spider_attr_zstd(self): + try: + import zstandard # noqa: F401 + except ImportError: + raise SkipTest("no zstd support (zstandard)") + self._test_download_warnsize_spider_attr("zstd") + + def _test_download_warnsize_request_meta(self, compression_id): + crawler = get_crawler(Spider) + spider = crawler._create_spider("scrapytest.org") + mw = HttpCompressionMiddleware.from_crawler(crawler) + mw.open_spider(spider) + response = self._getresponse(f"bomb-{compression_id}") + response.meta["download_warnsize"] = 10_000_000 + + with LogCapture( + "scrapy.downloadermiddlewares.httpcompression", + propagate=False, + level=WARNING, + ) as log: + mw.process_response(response.request, response, spider) + log.check( + ( + "scrapy.downloadermiddlewares.httpcompression", + "WARNING", + ( + "<200 http://scrapytest.org/> body size after " + "decompression (11511612 B) is larger than the download " + "warning size (10000000 B)." + ), + ), + ) + + def test_download_warnsize_request_meta_br(self): + try: + import brotli # noqa: F401 + except ImportError: + raise SkipTest("no brotli") + self._test_download_warnsize_request_meta("br") + + def test_download_warnsize_request_meta_deflate(self): + self._test_download_warnsize_request_meta("deflate") + + def test_download_warnsize_request_meta_gzip(self): + self._test_download_warnsize_request_meta("gzip") + + def test_download_warnsize_request_meta_zstd(self): + try: + import zstandard # noqa: F401 + except ImportError: + raise SkipTest("no zstd support (zstandard)") + self._test_download_warnsize_request_meta("zstd") + + +class HttpCompressionSubclassTest(TestCase): + def test_init_missing_stats(self): + class HttpCompressionMiddlewareSubclass(HttpCompressionMiddleware): + def __init__(self): + super().__init__() + + crawler = get_crawler(Spider) + with catch_warnings(record=True) as caught_warnings: + HttpCompressionMiddlewareSubclass.from_crawler(crawler) + messages = tuple( + str(warning.message) + for warning in caught_warnings + if warning.category is ScrapyDeprecationWarning + ) + self.assertEqual( + messages, + ( + ( + "HttpCompressionMiddleware subclasses must either modify " + "their '__init__' method to support a 'crawler' parameter " + "or reimplement their 'from_crawler' method." + ), + ), + ) diff --git a/tests/test_downloadermiddleware_redirect.py b/tests/test_downloadermiddleware_redirect.py index dc15b672c..10b8ca9af 100644 --- a/tests/test_downloadermiddleware_redirect.py +++ b/tests/test_downloadermiddleware_redirect.py @@ -247,6 +247,37 @@ class RedirectMiddlewareTest(unittest.TestCase): perc_encoded_utf8_url = "http://scrapytest.org/a%C3%A7%C3%A3o" self.assertEqual(perc_encoded_utf8_url, req_result.url) + def test_cross_domain_header_dropping(self): + safe_headers = {"A": "B"} + original_request = Request( + "https://example.com", + headers={"Cookie": "a=b", "Authorization": "a", **safe_headers}, + ) + + internal_response = Response( + "https://example.com", + headers={"Location": "https://example.com/a"}, + status=301, + ) + internal_redirect_request = self.mw.process_response( + original_request, internal_response, self.spider + ) + self.assertIsInstance(internal_redirect_request, Request) + self.assertEqual(original_request.headers, internal_redirect_request.headers) + + external_response = Response( + "https://example.com", + headers={"Location": "https://example.org/a"}, + status=301, + ) + external_redirect_request = self.mw.process_response( + original_request, external_response, self.spider + ) + self.assertIsInstance(external_redirect_request, Request) + self.assertEqual( + safe_headers, external_redirect_request.headers.to_unicode_dict() + ) + class MetaRefreshMiddlewareTest(unittest.TestCase): def setUp(self): diff --git a/tests/test_exporters.py b/tests/test_exporters.py index c11913365..fa9389044 100644 --- a/tests/test_exporters.py +++ b/tests/test_exporters.py @@ -121,7 +121,9 @@ class BaseItemExporterTest(unittest.TestCase): self.assertEqual(name, "John\xa3") ie = self._get_exporter(fields_to_export={"name": "名稱"}) - self.assertEqual(list(ie._get_serialized_fields(self.i)), [("名稱", "John\xa3")]) + self.assertEqual( + list(ie._get_serialized_fields(self.i)), [("名稱", "John\xa3")] + ) def test_field_custom_serializer(self): i = self.custom_field_item_class(name="John\xa3", age="22") @@ -150,7 +152,7 @@ class PythonItemExporterTest(BaseItemExporterTest): def test_nested_item(self): i1 = self.item_class(name="Joseph", age="22") - i2 = dict(name="Maria", age=i1) + i2 = {"name": "Maria", "age": i1} i3 = self.item_class(name="Jesus", age=i2) ie = self._get_exporter() exported = ie.export_item(i3) @@ -183,7 +185,7 @@ class PythonItemExporterTest(BaseItemExporterTest): def test_export_item_dict_list(self): i1 = self.item_class(name="Joseph", age="22") - i2 = dict(name="Maria", age=[i1]) + i2 = {"name": "Maria", "age": [i1]} i3 = self.item_class(name="Jesus", age=[i2]) ie = self._get_exporter() exported = ie.export_item(i3) @@ -371,7 +373,7 @@ class CsvItemExporterTest(BaseItemExporterTest): def test_join_multivalue_not_strings(self): self.assertExportResult( - item=dict(name="John", friends=[4, 8]), + item={"name": "John", "friends": [4, 8]}, include_headers_line=False, expected='"[4, 8]",John\r\n', ) @@ -386,14 +388,14 @@ class CsvItemExporterTest(BaseItemExporterTest): def test_errors_default(self): with self.assertRaises(UnicodeEncodeError): self.assertExportResult( - item=dict(text="W\u0275\u200Brd"), + item={"text": "W\u0275\u200Brd"}, expected=None, encoding="windows-1251", ) def test_errors_xmlcharrefreplace(self): self.assertExportResult( - item=dict(text="W\u0275\u200Brd"), + item={"text": "W\u0275\u200Brd"}, include_headers_line=False, expected="Wɵ​rd\r\n", encoding="windows-1251", @@ -453,8 +455,8 @@ class XmlItemExporterTest(BaseItemExporterTest): ) def test_nested_item(self): - i1 = dict(name="foo\xa3hoo", age="22") - i2 = dict(name="bar", age=i1) + i1 = {"name": "foo\xa3hoo", "age": "22"} + i2 = {"name": "bar", "age": i1} i3 = self.item_class(name="buz", age=i2) self.assertExportResult( @@ -476,8 +478,8 @@ class XmlItemExporterTest(BaseItemExporterTest): ) def test_nested_list_item(self): - i1 = dict(name="foo") - i2 = dict(name="bar", v2={"egg": ["spam"]}) + i1 = {"name": "foo"} + i2 = {"name": "bar", "v2": {"egg": ["spam"]}} i3 = self.item_class(name="buz", age=[i1, i2]) self.assertExportResult( @@ -532,7 +534,7 @@ class JsonLinesItemExporterTest(BaseItemExporterTest): def test_nested_item(self): i1 = self.item_class(name="Joseph", age="22") - i2 = dict(name="Maria", age=i1) + i2 = {"name": "Maria", "age": i1} i3 = self.item_class(name="Jesus", age=i2) self.ie.start_exporting() self.ie.export_item(i3) @@ -620,9 +622,9 @@ class JsonItemExporterTest(JsonLinesItemExporterTest): self.assertEqual(exported, [expected]) def test_nested_dict_item(self): - i1 = dict(name="Joseph\xa3", age="22") + i1 = {"name": "Joseph\xa3", "age": "22"} i2 = self.item_class(name="Maria", age=i1) - i3 = dict(name="Jesus", age=i2) + i3 = {"name": "Jesus", "age": i2} self.ie.start_exporting() self.ie.export_item(i3) self.ie.finish_exporting() diff --git a/tests/test_extension_periodic_log.py b/tests/test_extension_periodic_log.py index 502ada6be..b7312bbcd 100644 --- a/tests/test_extension_periodic_log.py +++ b/tests/test_extension_periodic_log.py @@ -67,7 +67,7 @@ def extension(settings=None): class TestPeriodicLog(unittest.TestCase): def test_extension_enabled(self): - # Expected that settings for this extension loaded succesfully + # Expected that settings for this extension loaded successfully # And on certain conditions - extension raising NotConfigured # "PERIODIC_LOG_STATS": True -> set to {"enabled": True} diff --git a/tests/test_extension_throttle.py b/tests/test_extension_throttle.py new file mode 100644 index 000000000..dae4ea966 --- /dev/null +++ b/tests/test_extension_throttle.py @@ -0,0 +1,340 @@ +from logging import INFO +from unittest.mock import Mock + +import pytest + +from scrapy import Request, Spider +from scrapy.exceptions import NotConfigured +from scrapy.extensions.throttle import AutoThrottle +from scrapy.http.response import Response +from scrapy.settings.default_settings import ( + AUTOTHROTTLE_MAX_DELAY, + AUTOTHROTTLE_START_DELAY, + DOWNLOAD_DELAY, +) +from scrapy.utils.misc import build_from_crawler +from scrapy.utils.test import get_crawler as _get_crawler + +UNSET = object() + + +class TestSpider(Spider): + name = "test" + + +def get_crawler(settings=None, spidercls=None): + settings = settings or {} + settings["AUTOTHROTTLE_ENABLED"] = True + return _get_crawler(settings_dict=settings, spidercls=spidercls) + + +@pytest.mark.parametrize( + ("value", "expected"), + ( + (UNSET, False), + (False, False), + (True, True), + ), +) +def test_enabled(value, expected): + settings = {} + if value is not UNSET: + settings["AUTOTHROTTLE_ENABLED"] = value + crawler = _get_crawler(settings_dict=settings) + if expected: + build_from_crawler(AutoThrottle, crawler) + else: + with pytest.raises(NotConfigured): + build_from_crawler(AutoThrottle, crawler) + + +@pytest.mark.parametrize( + "value", + ( + 0.0, + -1.0, + ), +) +def test_target_concurrency_invalid(value): + settings = {"AUTOTHROTTLE_TARGET_CONCURRENCY": value} + crawler = get_crawler(settings) + with pytest.raises(NotConfigured): + build_from_crawler(AutoThrottle, crawler) + + +@pytest.mark.parametrize( + ("spider", "setting", "expected"), + ( + (UNSET, UNSET, DOWNLOAD_DELAY), + (1.0, UNSET, 1.0), + (UNSET, 1.0, 1.0), + (1.0, 2.0, 1.0), + (3.0, 2.0, 3.0), + ), +) +def test_mindelay_definition(spider, setting, expected): + settings = {} + if setting is not UNSET: + settings["DOWNLOAD_DELAY"] = setting + + class _TestSpider(Spider): + name = "test" + + if spider is not UNSET: + _TestSpider.download_delay = spider + + crawler = get_crawler(settings, _TestSpider) + at = build_from_crawler(AutoThrottle, crawler) + at._spider_opened(_TestSpider()) + assert at.mindelay == expected + + +@pytest.mark.parametrize( + ("value", "expected"), + ( + (UNSET, AUTOTHROTTLE_MAX_DELAY), + (1.0, 1.0), + ), +) +def test_maxdelay_definition(value, expected): + settings = {} + if value is not UNSET: + settings["AUTOTHROTTLE_MAX_DELAY"] = value + crawler = get_crawler(settings) + at = build_from_crawler(AutoThrottle, crawler) + at._spider_opened(TestSpider()) + assert at.maxdelay == expected + + +@pytest.mark.parametrize( + ("min_spider", "min_setting", "start_setting", "expected"), + ( + (UNSET, UNSET, UNSET, AUTOTHROTTLE_START_DELAY), + (AUTOTHROTTLE_START_DELAY - 1.0, UNSET, UNSET, AUTOTHROTTLE_START_DELAY), + (AUTOTHROTTLE_START_DELAY + 1.0, UNSET, UNSET, AUTOTHROTTLE_START_DELAY + 1.0), + (UNSET, AUTOTHROTTLE_START_DELAY - 1.0, UNSET, AUTOTHROTTLE_START_DELAY), + (UNSET, AUTOTHROTTLE_START_DELAY + 1.0, UNSET, AUTOTHROTTLE_START_DELAY + 1.0), + (UNSET, UNSET, AUTOTHROTTLE_START_DELAY - 1.0, AUTOTHROTTLE_START_DELAY - 1.0), + (UNSET, UNSET, AUTOTHROTTLE_START_DELAY + 1.0, AUTOTHROTTLE_START_DELAY + 1.0), + ( + AUTOTHROTTLE_START_DELAY + 1.0, + AUTOTHROTTLE_START_DELAY + 2.0, + UNSET, + AUTOTHROTTLE_START_DELAY + 1.0, + ), + ( + AUTOTHROTTLE_START_DELAY + 2.0, + UNSET, + AUTOTHROTTLE_START_DELAY + 1.0, + AUTOTHROTTLE_START_DELAY + 2.0, + ), + ( + AUTOTHROTTLE_START_DELAY + 1.0, + UNSET, + AUTOTHROTTLE_START_DELAY + 2.0, + AUTOTHROTTLE_START_DELAY + 2.0, + ), + ), +) +def test_startdelay_definition(min_spider, min_setting, start_setting, expected): + settings = {} + if min_setting is not UNSET: + settings["DOWNLOAD_DELAY"] = min_setting + if start_setting is not UNSET: + settings["AUTOTHROTTLE_START_DELAY"] = start_setting + + class _TestSpider(Spider): + name = "test" + + if min_spider is not UNSET: + _TestSpider.download_delay = min_spider + + crawler = get_crawler(settings, _TestSpider) + at = build_from_crawler(AutoThrottle, crawler) + spider = _TestSpider() + at._spider_opened(spider) + assert spider.download_delay == expected + + +@pytest.mark.parametrize( + ("meta", "slot"), + ( + ({}, None), + ({"download_latency": 1.0}, None), + ({"download_slot": "foo"}, None), + ({"download_slot": "foo"}, "foo"), + ({"download_latency": 1.0, "download_slot": "foo"}, None), + ), +) +def test_skipped(meta, slot): + crawler = get_crawler() + at = build_from_crawler(AutoThrottle, crawler) + spider = TestSpider() + at._spider_opened(spider) + request = Request("https://example.com", meta=meta) + + crawler.engine = Mock() + crawler.engine.downloader = Mock() + crawler.engine.downloader.slots = {} + if slot is not None: + crawler.engine.downloader.slots[slot] = object() + at._adjust_delay = None # Raise exception if called. + + at._response_downloaded(None, request, spider) + + +@pytest.mark.parametrize( + ("download_latency", "target_concurrency", "slot_delay", "expected"), + ( + (2.0, 2.0, 1.0, 1.0), + (1.0, 2.0, 1.0, 0.75), + (4.0, 2.0, 1.0, 2.0), + (2.0, 1.0, 1.0, 2.0), + (2.0, 4.0, 1.0, 0.75), + (2.0, 2.0, 0.5, 1.0), + (2.0, 2.0, 2.0, 1.5), + ), +) +def test_adjustment(download_latency, target_concurrency, slot_delay, expected): + settings = {"AUTOTHROTTLE_TARGET_CONCURRENCY": target_concurrency} + crawler = get_crawler(settings) + at = build_from_crawler(AutoThrottle, crawler) + spider = TestSpider() + at._spider_opened(spider) + meta = {"download_latency": download_latency, "download_slot": "foo"} + request = Request("https://example.com", meta=meta) + response = Response(request.url) + + crawler.engine = Mock() + crawler.engine.downloader = Mock() + crawler.engine.downloader.slots = {} + slot = Mock() + slot.delay = slot_delay + crawler.engine.downloader.slots["foo"] = slot + + at._response_downloaded(response, request, spider) + + assert slot.delay == expected, f"{slot.delay} != {expected}" + + +@pytest.mark.parametrize( + ("mindelay", "maxdelay", "expected"), + ( + (0.5, 2.0, 1.0), + (0.25, 0.5, 0.5), + (2.0, 4.0, 2.0), + ), +) +def test_adjustment_limits(mindelay, maxdelay, expected): + download_latency, target_concurrency, slot_delay = (2.0, 2.0, 1.0) + # expected adjustment without limits with these values: 1.0 + settings = { + "AUTOTHROTTLE_MAX_DELAY": maxdelay, + "AUTOTHROTTLE_TARGET_CONCURRENCY": target_concurrency, + "DOWNLOAD_DELAY": mindelay, + } + crawler = get_crawler(settings) + at = build_from_crawler(AutoThrottle, crawler) + spider = TestSpider() + at._spider_opened(spider) + meta = {"download_latency": download_latency, "download_slot": "foo"} + request = Request("https://example.com", meta=meta) + response = Response(request.url) + + crawler.engine = Mock() + crawler.engine.downloader = Mock() + crawler.engine.downloader.slots = {} + slot = Mock() + slot.delay = slot_delay + crawler.engine.downloader.slots["foo"] = slot + + at._response_downloaded(response, request, spider) + + assert slot.delay == expected, f"{slot.delay} != {expected}" + + +@pytest.mark.parametrize( + ("download_latency", "target_concurrency", "slot_delay", "expected"), + ( + (2.0, 2.0, 1.0, 1.0), + (1.0, 2.0, 1.0, 1.0), # Instead of 0.75 + (4.0, 2.0, 1.0, 2.0), + ), +) +def test_adjustment_bad_response( + download_latency, target_concurrency, slot_delay, expected +): + settings = {"AUTOTHROTTLE_TARGET_CONCURRENCY": target_concurrency} + crawler = get_crawler(settings) + at = build_from_crawler(AutoThrottle, crawler) + spider = TestSpider() + at._spider_opened(spider) + meta = {"download_latency": download_latency, "download_slot": "foo"} + request = Request("https://example.com", meta=meta) + response = Response(request.url, status=400) + + crawler.engine = Mock() + crawler.engine.downloader = Mock() + crawler.engine.downloader.slots = {} + slot = Mock() + slot.delay = slot_delay + crawler.engine.downloader.slots["foo"] = slot + + at._response_downloaded(response, request, spider) + + assert slot.delay == expected, f"{slot.delay} != {expected}" + + +def test_debug(caplog): + settings = {"AUTOTHROTTLE_DEBUG": True} + crawler = get_crawler(settings) + at = build_from_crawler(AutoThrottle, crawler) + spider = TestSpider() + at._spider_opened(spider) + meta = {"download_latency": 1.0, "download_slot": "foo"} + request = Request("https://example.com", meta=meta) + response = Response(request.url, body=b"foo") + + crawler.engine = Mock() + crawler.engine.downloader = Mock() + crawler.engine.downloader.slots = {} + slot = Mock() + slot.delay = 2.0 + slot.transferring = (None, None) + crawler.engine.downloader.slots["foo"] = slot + + caplog.clear() + with caplog.at_level(INFO): + at._response_downloaded(response, request, spider) + + assert caplog.record_tuples == [ + ( + "scrapy.extensions.throttle", + INFO, + "slot: foo | conc: 2 | delay: 1500 ms (-500) | latency: 1000 ms | size: 3 bytes", + ), + ] + + +def test_debug_disabled(caplog): + crawler = get_crawler() + at = build_from_crawler(AutoThrottle, crawler) + spider = TestSpider() + at._spider_opened(spider) + meta = {"download_latency": 1.0, "download_slot": "foo"} + request = Request("https://example.com", meta=meta) + response = Response(request.url, body=b"foo") + + crawler.engine = Mock() + crawler.engine.downloader = Mock() + crawler.engine.downloader.slots = {} + slot = Mock() + slot.delay = 2.0 + slot.transferring = (None, None) + crawler.engine.downloader.slots["foo"] = slot + + caplog.clear() + with caplog.at_level(INFO): + at._response_downloaded(response, request, spider) + + assert caplog.record_tuples == [] diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 89169fd7c..d7560b5ff 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -673,8 +673,7 @@ class FeedExportTestBase(ABC, unittest.TestCase): name = "testspider" def parse(self, response): - for item in items: - yield item + yield from items data = yield self.run_and_export(TestSpider, settings) return data @@ -1732,6 +1731,7 @@ class FeedExportTest(FeedExportTestBase): def store(self, file): Storage.store_file = file + Storage.file_was_closed = file.closed file.close() settings = { @@ -1747,6 +1747,7 @@ class FeedExportTest(FeedExportTestBase): } yield self.exported_no_data(settings) self.assertIs(Storage.open_file, Storage.store_file) + self.assertFalse(Storage.file_was_closed) class FeedPostProcessedExportsTest(FeedExportTestBase): @@ -2300,7 +2301,7 @@ class BatchDeliveriesTest(FeedExportTestBase): content[feed["format"]].append(file.read_bytes()) finally: self.tearDown() - defer.returnValue(content) + return content @defer.inlineCallbacks def assertExportedJsonLines(self, items, rows, settings=None): @@ -2696,8 +2697,7 @@ class BatchDeliveriesTest(FeedExportTestBase): name = "testspider" def parse(self, response): - for item in items: - yield item + yield from items with MockServer() as server: TestSpider.start_urls = [server.url("/")] diff --git a/tests/test_http2_client_protocol.py b/tests/test_http2_client_protocol.py index 8fdf3d56f..995c02a1a 100644 --- a/tests/test_http2_client_protocol.py +++ b/tests/test_http2_client_protocol.py @@ -5,6 +5,7 @@ import shutil import string from ipaddress import IPv4Address from pathlib import Path +from tempfile import mkdtemp from typing import Dict from unittest import mock, skipIf from urllib.parse import urlencode @@ -185,8 +186,7 @@ class Https2ClientProtocolTestCase(TestCase): certificate_file = Path(__file__).parent / "keys" / "localhost.crt" def _init_resource(self): - self.temp_directory = self.mktemp() - Path(self.temp_directory).mkdir() + self.temp_directory = mkdtemp() r = File(self.temp_directory) r.putChild(b"get-data-html-small", GetDataHtmlSmall()) r.putChild(b"get-data-html-large", GetDataHtmlLarge()) diff --git a/tests/test_http_cookies.py b/tests/test_http_cookies.py index 9e43b72b0..8b5554914 100644 --- a/tests/test_http_cookies.py +++ b/tests/test_http_cookies.py @@ -1,8 +1,8 @@ from unittest import TestCase -from urllib.parse import urlparse from scrapy.http import Request, Response from scrapy.http.cookies import WrappedRequest, WrappedResponse +from scrapy.utils.httpobj import urlparse_cached class WrappedRequestTest(TestCase): @@ -17,12 +17,12 @@ class WrappedRequestTest(TestCase): self.assertEqual(self.wrapped.full_url, self.request.url) def test_get_host(self): - self.assertEqual(self.wrapped.get_host(), urlparse(self.request.url).netloc) - self.assertEqual(self.wrapped.host, urlparse(self.request.url).netloc) + self.assertEqual(self.wrapped.get_host(), urlparse_cached(self.request).netloc) + self.assertEqual(self.wrapped.host, urlparse_cached(self.request).netloc) def test_get_type(self): - self.assertEqual(self.wrapped.get_type(), urlparse(self.request.url).scheme) - self.assertEqual(self.wrapped.type, urlparse(self.request.url).scheme) + self.assertEqual(self.wrapped.get_type(), urlparse_cached(self.request).scheme) + self.assertEqual(self.wrapped.type, urlparse_cached(self.request).scheme) def test_is_unverifiable(self): self.assertFalse(self.wrapped.is_unverifiable()) diff --git a/tests/test_http_request.py b/tests/test_http_request.py index 6dc9ec8b7..7ce73e6ff 100644 --- a/tests/test_http_request.py +++ b/tests/test_http_request.py @@ -5,7 +5,7 @@ import warnings import xmlrpc.client from typing import Any, Dict, List from unittest import mock -from urllib.parse import parse_qs, unquote_to_bytes, urlparse +from urllib.parse import parse_qs, unquote_to_bytes from scrapy.http import ( FormRequest, @@ -16,6 +16,7 @@ from scrapy.http import ( XmlRpcRequest, ) from scrapy.http.request import NO_CALLBACK +from scrapy.utils.httpobj import urlparse_cached from scrapy.utils.python import to_bytes, to_unicode @@ -617,8 +618,8 @@ class FormRequestTest(RequestTest): method="GET", formdata=(("foo", "bar"), ("foo", "baz")), ) - self.assertEqual(urlparse(req.url).hostname, "www.example.com") - self.assertEqual(urlparse(req.url).query, "foo=bar&foo=baz") + self.assertEqual(urlparse_cached(req).hostname, "www.example.com") + self.assertEqual(urlparse_cached(req).query, "foo=bar&foo=baz") def test_from_response_override_duplicate_form_key(self): response = _buildresponse( @@ -666,8 +667,8 @@ class FormRequestTest(RequestTest): response, formdata={"one": ["two", "three"], "six": "seven"} ) self.assertEqual(r1.method, "GET") - self.assertEqual(urlparse(r1.url).hostname, "www.example.com") - self.assertEqual(urlparse(r1.url).path, "/this/get.php") + self.assertEqual(urlparse_cached(r1).hostname, "www.example.com") + self.assertEqual(urlparse_cached(r1).path, "/this/get.php") fs = _qs(r1) self.assertEqual(set(fs[b"test"]), {b"val1", b"val2"}) self.assertEqual(set(fs[b"one"]), {b"two", b"three"}) @@ -1426,6 +1427,58 @@ class FormRequestTest(RequestTest): r = self.request_class.from_response(response) self.assertEqual(r.method, expected) + def test_form_response_with_invalid_formdata_type_error(self): + """Test that a ValueError is raised for non-iterable and non-dict formdata input""" + response = _buildresponse( + """ +
+ +
+ """ + ) + with self.assertRaises(ValueError) as context: + FormRequest.from_response(response, formdata=123) + + self.assertIn( + "formdata should be a dict or iterable of tuples", str(context.exception) + ) + + def test_form_response_with_custom_invalid_formdata_value_error(self): + """Test that a ValueError is raised for fault-inducing iterable formdata input""" + response = _buildresponse( + """ +
+ +
+ """ + ) + + with self.assertRaises(ValueError) as context: + FormRequest.from_response(response, formdata=("a",)) + + self.assertIn( + "formdata should be a dict or iterable of tuples", str(context.exception) + ) + + def test_get_form_with_xpath_no_form_parent(self): + """Test that _get_from raised a ValueError when an XPath selects an element + not nested within a
and no parent is found""" + response = _buildresponse( + """ +
+

This paragraph is not inside a form.

+
+ + +
+ """ + ) + + with self.assertRaises(ValueError) as context: + FormRequest.from_response(response, formxpath='//div[@id="outside-form"]/p') + + self.assertIn("No
element found with", str(context.exception)) + def _buildresponse(body, **kwargs): kwargs.setdefault("body", body) @@ -1642,6 +1695,25 @@ class JsonRequestTest(RequestTest): self.assertEqual(kwargs["ensure_ascii"], True) self.assertEqual(kwargs["allow_nan"], True) + def test_replacement_both_body_and_data_warns(self): + """Test that we get a warning if both body and data are passed""" + body1 = None + body2 = b"body" + data1 = { + "name1": "value1", + } + data2 = { + "name2": "value2", + } + r1 = self.request_class(url="http://www.example.com/", data=data1, body=body1) + + with warnings.catch_warnings(record=True) as _warnings: + r1.replace(data=data2, body=body2) + self.assertIn( + "Both body and data passed. data will be ignored", + str(_warnings[0].message), + ) + def tearDown(self): warnings.resetwarnings() super().tearDown() diff --git a/tests/test_item.py b/tests/test_item.py index ce2b4fd15..daf5d4f59 100644 --- a/tests/test_item.py +++ b/tests/test_item.py @@ -290,7 +290,9 @@ class ItemMetaTest(unittest.TestCase): class ItemMetaClassCellRegression(unittest.TestCase): def test_item_meta_classcell_regression(self): class MyItem(Item, metaclass=ItemMeta): - def __init__(self, *args, **kwargs): + def __init__( + self, *args, **kwargs + ): # pylint: disable=useless-parent-delegation # This call to super() trigger the __classcell__ propagation # requirement. When not done properly raises an error: # TypeError: __class__ set to diff --git a/tests/test_linkextractors.py b/tests/test_linkextractors.py index 18e9608c1..217c7a299 100644 --- a/tests/test_linkextractors.py +++ b/tests/test_linkextractors.py @@ -37,7 +37,7 @@ class Base: page4_url = "http://example.com/page%204.html" self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -55,7 +55,7 @@ class Base: def test_extract_filter_allow(self): lx = self.extractor_cls(allow=("sample",)) self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -70,7 +70,7 @@ class Base: def test_extract_filter_allow_with_duplicates(self): lx = self.extractor_cls(allow=("sample",), unique=False) self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -93,7 +93,7 @@ class Base: def test_extract_filter_allow_with_duplicates_canonicalize(self): lx = self.extractor_cls(allow=("sample",), unique=False, canonicalize=True) self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -116,7 +116,7 @@ class Base: def test_extract_filter_allow_no_duplicates_canonicalize(self): lx = self.extractor_cls(allow=("sample",), unique=True, canonicalize=True) self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -127,7 +127,7 @@ class Base: def test_extract_filter_allow_and_deny(self): lx = self.extractor_cls(allow=("sample",), deny=("3",)) self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -137,7 +137,7 @@ class Base: def test_extract_filter_allowed_domains(self): lx = self.extractor_cls(allow_domains=("google.com",)) self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://www.google.com/something", text=""), ], @@ -148,7 +148,7 @@ class Base: lx = self.extractor_cls(allow="sample") self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -162,7 +162,7 @@ class Base: lx = self.extractor_cls(allow="sample", deny="3") self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -171,7 +171,7 @@ class Base: lx = self.extractor_cls(allow_domains="google.com") self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://www.google.com/something", text=""), ], @@ -179,7 +179,7 @@ class Base: lx = self.extractor_cls(deny_domains="example.com") self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://www.google.com/something", text=""), ], @@ -265,7 +265,7 @@ class Base: def test_restrict_xpaths(self): lx = self.extractor_cls(restrict_xpaths=('//div[@id="subwrapper"]',)) self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -337,7 +337,7 @@ class Base: restrict_css=("#subwrapper + a",), ) self.assertEqual( - [link for link in lx.extract_links(self.response)], + list(lx.extract_links(self.response)), [ Link(url="http://example.com/sample1.html", text=""), Link(url="http://example.com/sample2.html", text="sample 2"), @@ -705,7 +705,7 @@ class Base: response = HtmlResponse("http://example.org/index.html", body=html) lx = self.extractor_cls() self.assertEqual( - [link for link in lx.extract_links(response)], + list(lx.extract_links(response)), [ Link( url="http://example.org/item1.html", @@ -758,7 +758,7 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): response = HtmlResponse("http://example.org/index.html", body=html) lx = self.extractor_cls() self.assertEqual( - [link for link in lx.extract_links(response)], + list(lx.extract_links(response)), [ Link( url="http://example.org/item1.html", text="Item 1", nofollow=False @@ -779,7 +779,7 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): # Simple text inclusion test lx = self.extractor_cls(restrict_text="dog") self.assertEqual( - [link for link in lx.extract_links(response)], + list(lx.extract_links(response)), [ Link( url="http://example.org/item2.html", @@ -791,7 +791,7 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): # Unique regex test lx = self.extractor_cls(restrict_text=r"of.*dog") self.assertEqual( - [link for link in lx.extract_links(response)], + list(lx.extract_links(response)), [ Link( url="http://example.org/item2.html", @@ -803,7 +803,7 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): # Multiple regex test lx = self.extractor_cls(restrict_text=[r"of.*dog", r"of.*cat"]) self.assertEqual( - [link for link in lx.extract_links(response)], + list(lx.extract_links(response)), [ Link( url="http://example.org/item1.html", @@ -818,9 +818,6 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): ], ) - def test_restrict_xpaths_with_html_entities(self): - super().test_restrict_xpaths_with_html_entities() - @mark.skipif( Version(w3lib_version) < Version("2.0.0"), reason=( @@ -837,7 +834,7 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): response = HtmlResponse("http://example.org/index.html", body=html) lx = self.extractor_cls() self.assertEqual( - [link for link in lx.extract_links(response)], + list(lx.extract_links(response)), [ Link( url="http://example.org/item2.html", @@ -851,3 +848,15 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase): ), ], ) + + def test_link_allowed_is_false_with_empty_url(self): + bad_link = Link("") + self.assertFalse(LxmlLinkExtractor()._link_allowed(bad_link)) + + def test_link_allowed_is_false_with_bad_url_prefix(self): + bad_link = Link("htp://should_be_http.example") + self.assertFalse(LxmlLinkExtractor()._link_allowed(bad_link)) + + def test_link_allowed_is_false_with_missing_url_prefix(self): + bad_link = Link("should_have_prefix.example") + self.assertFalse(LxmlLinkExtractor()._link_allowed(bad_link)) diff --git a/tests/test_loader_deprecated.py b/tests/test_loader_deprecated.py index d7f773d5c..528efa142 100644 --- a/tests/test_loader_deprecated.py +++ b/tests/test_loader_deprecated.py @@ -565,37 +565,37 @@ class NoInputReprocessingFromDictTest(unittest.TestCase): """ def test_avoid_reprocessing_with_initial_values_single(self): - il = NoInputReprocessingDictLoader(item=dict(title="foo")) + il = NoInputReprocessingDictLoader(item={"title": "foo"}) il_loaded = il.load_item() - self.assertEqual(il_loaded, dict(title="foo")) + self.assertEqual(il_loaded, {"title": "foo"}) self.assertEqual( - NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title="foo") + NoInputReprocessingDictLoader(item=il_loaded).load_item(), {"title": "foo"} ) def test_avoid_reprocessing_with_initial_values_list(self): - il = NoInputReprocessingDictLoader(item=dict(title=["foo", "bar"])) + il = NoInputReprocessingDictLoader(item={"title": ["foo", "bar"]}) il_loaded = il.load_item() - self.assertEqual(il_loaded, dict(title="foo")) + self.assertEqual(il_loaded, {"title": "foo"}) self.assertEqual( - NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title="foo") + NoInputReprocessingDictLoader(item=il_loaded).load_item(), {"title": "foo"} ) def test_avoid_reprocessing_without_initial_values_single(self): il = NoInputReprocessingDictLoader() il.add_value("title", "foo") il_loaded = il.load_item() - self.assertEqual(il_loaded, dict(title="FOO")) + self.assertEqual(il_loaded, {"title": "FOO"}) self.assertEqual( - NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title="FOO") + NoInputReprocessingDictLoader(item=il_loaded).load_item(), {"title": "FOO"} ) def test_avoid_reprocessing_without_initial_values_list(self): il = NoInputReprocessingDictLoader() il.add_value("title", ["foo", "bar"]) il_loaded = il.load_item() - self.assertEqual(il_loaded, dict(title="FOO")) + self.assertEqual(il_loaded, {"title": "FOO"}) self.assertEqual( - NoInputReprocessingDictLoader(item=il_loaded).load_item(), dict(title="FOO") + NoInputReprocessingDictLoader(item=il_loaded).load_item(), {"title": "FOO"} ) @@ -678,11 +678,11 @@ class SelectJmesTestCase(unittest.TestCase): } def test_output(self): - for tl in self.test_list_equals: - expr, test_list, expected = self.test_list_equals[tl] + for k, v in self.test_list_equals.items(): + expr, test_list, expected = v test = SelectJmes(expr)(test_list) self.assertEqual( - test, expected, msg=f'test "{tl}" got {test} expected {expected}' + test, expected, msg=f'test "{k}" got {test} expected {expected}' ) diff --git a/tests/test_logstats.py b/tests/test_logstats.py new file mode 100644 index 000000000..d87285df7 --- /dev/null +++ b/tests/test_logstats.py @@ -0,0 +1,62 @@ +import unittest +from datetime import datetime + +from scrapy.extensions.logstats import LogStats +from scrapy.utils.test import get_crawler +from tests.spiders import SimpleSpider + + +class TestLogStats(unittest.TestCase): + def setUp(self): + self.crawler = get_crawler(SimpleSpider) + self.spider = self.crawler._create_spider("spidey") + self.stats = self.crawler.stats + + self.stats.set_value("response_received_count", 4802) + self.stats.set_value("item_scraped_count", 3201) + + def test_stats_calculations(self): + logstats = LogStats.from_crawler(self.crawler) + + with self.assertRaises(AttributeError): + logstats.pagesprev + logstats.itemsprev + + logstats.spider_opened(self.spider) + self.assertEqual(logstats.pagesprev, 4802) + self.assertEqual(logstats.itemsprev, 3201) + + logstats.calculate_stats() + self.assertEqual(logstats.items, 3201) + self.assertEqual(logstats.pages, 4802) + self.assertEqual(logstats.irate, 0.0) + self.assertEqual(logstats.prate, 0.0) + self.assertEqual(logstats.pagesprev, 4802) + self.assertEqual(logstats.itemsprev, 3201) + + # Simulate what happens after a minute + self.stats.set_value("response_received_count", 5187) + self.stats.set_value("item_scraped_count", 3492) + logstats.calculate_stats() + self.assertEqual(logstats.items, 3492) + self.assertEqual(logstats.pages, 5187) + self.assertEqual(logstats.irate, 291.0) + self.assertEqual(logstats.prate, 385.0) + self.assertEqual(logstats.pagesprev, 5187) + self.assertEqual(logstats.itemsprev, 3492) + + # Simulate when spider closes after running for 30 mins + self.stats.set_value("start_time", datetime.fromtimestamp(1655100172)) + self.stats.set_value("finished_time", datetime.fromtimestamp(1655101972)) + logstats.spider_closed(self.spider, "test reason") + self.assertEqual(self.stats.get_value("responses_per_minute"), 172.9) + self.assertEqual(self.stats.get_value("items_per_minute"), 116.4) + + def test_stats_calculations_no_time(self): + """The stat values should be None since the start and finish time are + not available. + """ + logstats = LogStats.from_crawler(self.crawler) + logstats.spider_closed(self.spider, "test reason") + self.assertIsNone(self.stats.get_value("responses_per_minute")) + self.assertIsNone(self.stats.get_value("items_per_minute")) diff --git a/tests/test_mail.py b/tests/test_mail.py index 2535e58db..ff1505397 100644 --- a/tests/test_mail.py +++ b/tests/test_mail.py @@ -91,7 +91,7 @@ class MailSenderTest(unittest.TestCase): self.assertEqual(attach.get_payload(decode=True), b"content") def _catch_mail_sent(self, **kwargs): - self.catched_msg = dict(**kwargs) + self.catched_msg = {**kwargs} def test_send_utf8(self): subject = "sübjèçt" diff --git a/tests/test_pipeline_crawl.py b/tests/test_pipeline_crawl.py index ed8483483..5a9a217ce 100644 --- a/tests/test_pipeline_crawl.py +++ b/tests/test_pipeline_crawl.py @@ -1,5 +1,6 @@ import shutil from pathlib import Path +from tempfile import mkdtemp from typing import Optional, Set from testfixtures import LogCapture @@ -9,6 +10,7 @@ from w3lib.url import add_or_replace_parameter from scrapy import signals from scrapy.crawler import CrawlerRunner +from scrapy.utils.misc import load_object from tests.mockserver import MockServer from tests.spiders import SimpleSpider @@ -66,8 +68,7 @@ class FileDownloadCrawlTestCase(TestCase): self.mockserver.__enter__() # prepare a directory for storing files - self.tmpmediastore = Path(self.mktemp()) - self.tmpmediastore.mkdir() + self.tmpmediastore = Path(mkdtemp()) self.settings = { "REQUEST_FINGERPRINTER_IMPLEMENTATION": "2.7", "ITEM_PIPELINES": {self.pipeline_class: 1}, @@ -139,7 +140,7 @@ class FileDownloadCrawlTestCase(TestCase): self.assertEqual(logs.count(file_dl_failure), 3) # check that no files were written to the media store - self.assertEqual([x for x in self.tmpmediastore.iterdir()], []) + self.assertEqual(list(self.tmpmediastore.iterdir()), []) @defer.inlineCallbacks def test_download_media(self): @@ -193,6 +194,29 @@ class FileDownloadCrawlTestCase(TestCase): crawler.stats.get_value("downloader/response_status_count/302"), 3 ) + @defer.inlineCallbacks + def test_download_media_file_path_error(self): + cls = load_object(self.pipeline_class) + + class ExceptionRaisingMediaPipeline(cls): + def file_path(self, request, response=None, info=None, *, item=None): + return 1 / 0 + + settings = { + **self.settings, + "ITEM_PIPELINES": {ExceptionRaisingMediaPipeline: 1}, + } + runner = CrawlerRunner(settings) + crawler = self._create_crawler(MediaDownloadSpider, runner=runner) + with LogCapture() as log: + yield crawler.crawl( + self.mockserver.url("/files/images/"), + media_key=self.media_key, + media_urls_key=self.media_urls_key, + mockserver=self.mockserver, + ) + self.assertIn("ZeroDivisionError", str(log)) + skip_pillow: Optional[str] try: diff --git a/tests/test_pipeline_files.py b/tests/test_pipeline_files.py index e7000e314..0babde4d9 100644 --- a/tests/test_pipeline_files.py +++ b/tests/test_pipeline_files.py @@ -221,7 +221,7 @@ class FilesPipelineTestCase(unittest.TestCase): file_path = CustomFilesPipeline.from_settings( Settings({"FILES_STORE": self.tempdir}) ).file_path - item = dict(path="path-to-store-file") + item = {"path": "path-to-store-file"} request = Request("http://example.com") self.assertEqual(file_path(request, item=item), "full/path-to-store-file") diff --git a/tests/test_pipeline_images.py b/tests/test_pipeline_images.py index 2e2e06b89..18a2454b3 100644 --- a/tests/test_pipeline_images.py +++ b/tests/test_pipeline_images.py @@ -132,7 +132,7 @@ class ImagesPipelineTestCase(unittest.TestCase): thumb_path = CustomImagesPipeline.from_settings( Settings({"IMAGES_STORE": self.tempdir}) ).thumb_path - item = dict(path="path-to-store-file") + item = {"path": "path-to-store-file"} request = Request("http://example.com") self.assertEqual( thumb_path(request, "small", item=item), "thumb/small/path-to-store-file" @@ -433,14 +433,14 @@ class ImagesPipelineTestCaseCustomSettings(unittest.TestCase): ] # This should match what is defined in ImagesPipeline. - default_pipeline_settings = dict( - MIN_WIDTH=0, - MIN_HEIGHT=0, - EXPIRES=90, - THUMBS={}, - IMAGES_URLS_FIELD="image_urls", - IMAGES_RESULT_FIELD="images", - ) + default_pipeline_settings = { + "MIN_WIDTH": 0, + "MIN_HEIGHT": 0, + "EXPIRES": 90, + "THUMBS": {}, + "IMAGES_URLS_FIELD": "image_urls", + "IMAGES_RESULT_FIELD": "images", + } def setUp(self): self.tempdir = mkdtemp() diff --git a/tests/test_pipeline_media.py b/tests/test_pipeline_media.py index 820484565..d4dde4a40 100644 --- a/tests/test_pipeline_media.py +++ b/tests/test_pipeline_media.py @@ -22,9 +22,9 @@ from scrapy.utils.test import get_crawler try: from PIL import Image # noqa: imported just to check for the import error except ImportError: - skip_pillow: Optional[ - str - ] = "Missing Python Imaging Library, install https://pypi.python.org/pypi/Pillow" + skip_pillow: Optional[str] = ( + "Missing Python Imaging Library, install https://pypi.python.org/pypi/Pillow" + ) else: skip_pillow = None @@ -59,7 +59,7 @@ class BaseMediaPipelineTestCase(unittest.TestCase): assert self.pipe.media_to_download(request, self.info) is None def test_default_get_media_requests(self): - item = dict(name="name") + item = {"name": "name"} assert self.pipe.get_media_requests(item, self.info) is None def test_default_media_downloaded(self): @@ -73,7 +73,7 @@ class BaseMediaPipelineTestCase(unittest.TestCase): assert self.pipe.media_failed(fail, request, self.info) is fail def test_default_item_completed(self): - item = dict(name="name") + item = {"name": "name"} assert self.pipe.item_completed([], item, self.info) is item # Check that failures are logged by default @@ -98,7 +98,7 @@ class BaseMediaPipelineTestCase(unittest.TestCase): @inlineCallbacks def test_default_process_item(self): - item = dict(name="name") + item = {"name": "name"} new_item = yield self.pipe.process_item(item, self.spider) assert new_item is item @@ -226,11 +226,11 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): rsp = Response("http://url1") req = Request( "http://url1", - meta=dict(response=rsp), + meta={"response": rsp}, callback=self._callback, errback=self._errback, ) - item = dict(requests=req) + item = {"requests": req} new_item = yield self.pipe.process_item(item, self.spider) self.assertEqual(new_item["results"], [(True, rsp)]) self.assertEqual( @@ -250,11 +250,11 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): fail = Failure(Exception()) req = Request( "http://url1", - meta=dict(response=fail), + meta={"response": fail}, callback=self._callback, errback=self._errback, ) - item = dict(requests=req) + item = {"requests": req} new_item = yield self.pipe.process_item(item, self.spider) self.assertEqual(new_item["results"], [(False, fail)]) self.assertEqual( @@ -272,10 +272,10 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): def test_mix_of_success_and_failure(self): self.pipe.LOG_FAILED_RESULTS = False rsp1 = Response("http://url1") - req1 = Request("http://url1", meta=dict(response=rsp1)) + req1 = Request("http://url1", meta={"response": rsp1}) fail = Failure(Exception()) - req2 = Request("http://url2", meta=dict(response=fail)) - item = dict(requests=[req1, req2]) + req2 = Request("http://url2", meta={"response": fail}) + item = {"requests": [req1, req2]} new_item = yield self.pipe.process_item(item, self.spider) self.assertEqual(new_item["results"], [(True, rsp1), (False, fail)]) m = self.pipe._mockcalled @@ -294,7 +294,7 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): def test_get_media_requests(self): # returns single Request (without callback) req = Request("http://url") - item = dict(requests=req) # pass a single item + item = {"requests": req} # pass a single item new_item = yield self.pipe.process_item(item, self.spider) assert new_item is item self.assertIn(self.fingerprint(req), self.info.downloaded) @@ -302,7 +302,7 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): # returns iterable of Requests req1 = Request("http://url1") req2 = Request("http://url2") - item = dict(requests=iter([req1, req2])) + item = {"requests": iter([req1, req2])} new_item = yield self.pipe.process_item(item, self.spider) assert new_item is item assert self.fingerprint(req1) in self.info.downloaded @@ -311,17 +311,17 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): @inlineCallbacks def test_results_are_cached_across_multiple_items(self): rsp1 = Response("http://url1") - req1 = Request("http://url1", meta=dict(response=rsp1)) - item = dict(requests=req1) + req1 = Request("http://url1", meta={"response": rsp1}) + item = {"requests": req1} new_item = yield self.pipe.process_item(item, self.spider) self.assertTrue(new_item is item) self.assertEqual(new_item["results"], [(True, rsp1)]) # rsp2 is ignored, rsp1 must be in results because request fingerprints are the same req2 = Request( - req1.url, meta=dict(response=Response("http://donot.download.me")) + req1.url, meta={"response": Response("http://donot.download.me")} ) - item = dict(requests=req2) + item = {"requests": req2} new_item = yield self.pipe.process_item(item, self.spider) self.assertTrue(new_item is item) self.assertEqual(self.fingerprint(req1), self.fingerprint(req2)) @@ -330,11 +330,11 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): @inlineCallbacks def test_results_are_cached_for_requests_of_single_item(self): rsp1 = Response("http://url1") - req1 = Request("http://url1", meta=dict(response=rsp1)) + req1 = Request("http://url1", meta={"response": rsp1}) req2 = Request( - req1.url, meta=dict(response=Response("http://donot.download.me")) + req1.url, meta={"response": Response("http://donot.download.me")} ) - item = dict(requests=[req1, req2]) + item = {"requests": [req1, req2]} new_item = yield self.pipe.process_item(item, self.spider) self.assertTrue(new_item is item) self.assertEqual(new_item["results"], [(True, rsp1), (True, rsp1)]) @@ -359,16 +359,16 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): def rsp2_func(): self.fail("it must cache rsp1 result and must not try to redownload") - req1 = Request("http://url", meta=dict(response=rsp1_func)) - req2 = Request(req1.url, meta=dict(response=rsp2_func)) - item = dict(requests=[req1, req2]) + req1 = Request("http://url", meta={"response": rsp1_func}) + req2 = Request(req1.url, meta={"response": rsp2_func}) + item = {"requests": [req1, req2]} new_item = yield self.pipe.process_item(item, self.spider) self.assertEqual(new_item["results"], [(True, rsp1), (True, rsp1)]) @inlineCallbacks def test_use_media_to_download_result(self): - req = Request("http://url", meta=dict(result="ITSME", response=self.fail)) - item = dict(requests=req) + req = Request("http://url", meta={"result": "ITSME", "response": self.fail}) + item = {"requests": req} new_item = yield self.pipe.process_item(item, self.spider) self.assertEqual(new_item["results"], [(True, "ITSME")]) self.assertEqual( diff --git a/tests/test_proxy_connect.py b/tests/test_proxy_connect.py index dc0a82086..46d42e9f6 100644 --- a/tests/test_proxy_connect.py +++ b/tests/test_proxy_connect.py @@ -31,6 +31,7 @@ sys.exit(mitmdump()) self.proc = Popen( [ sys.executable, + "-u", "-c", script, "--listen-host", @@ -46,7 +47,7 @@ sys.exit(mitmdump()) stdout=PIPE, ) line = self.proc.stdout.readline().decode("utf-8") - host_port = re.search(r"listening at http://([^:]+:\d+)", line).group(1) + host_port = re.search(r"listening at (?:http://)?([^:]+:\d+)", line).group(1) address = f"http://{self.auth_user}:{self.auth_pass}@{host_port}" return address diff --git a/tests/test_responsetypes.py b/tests/test_responsetypes.py index 6e1ed82f0..2633cca5b 100644 --- a/tests/test_responsetypes.py +++ b/tests/test_responsetypes.py @@ -1,6 +1,13 @@ import unittest -from scrapy.http import Headers, HtmlResponse, Response, TextResponse, XmlResponse +from scrapy.http import ( + Headers, + HtmlResponse, + JsonResponse, + Response, + TextResponse, + XmlResponse, +) from scrapy.responsetypes import responsetypes @@ -26,7 +33,10 @@ class ResponseTypesTest(unittest.TestCase): ("attachment;filename=dataµ.tar.gz".encode("latin-1"), Response), ("attachment;filename=data高.doc".encode("gbk"), Response), ("attachment;filename=دورهdata.html".encode("cp720"), HtmlResponse), - ("attachment;filename=日本語版Wikipedia.xml".encode("iso2022_jp"), XmlResponse), + ( + "attachment;filename=日本語版Wikipedia.xml".encode("iso2022_jp"), + XmlResponse, + ), ] for source, cls in mappings: retcls = responsetypes.from_content_disposition(source) @@ -40,8 +50,9 @@ class ResponseTypesTest(unittest.TestCase): ("application/vnd.wap.xhtml+xml; charset=utf-8", HtmlResponse), ("application/xml; charset=UTF-8", XmlResponse), ("application/octet-stream", Response), - ("application/x-json; encoding=UTF8;charset=UTF-8", TextResponse), - ("application/json-amazonui-streaming;charset=UTF-8", TextResponse), + ("application/json; encoding=UTF8;charset=UTF-8", JsonResponse), + ("application/x-json; encoding=UTF8;charset=UTF-8", JsonResponse), + ("application/json-amazonui-streaming;charset=UTF-8", JsonResponse), (b"application/x-download; filename=\x80dummy.txt", Response), ] for source, cls in mappings: diff --git a/tests/test_scheduler.py b/tests/test_scheduler.py index f8465a5ff..37099dae6 100644 --- a/tests/test_scheduler.py +++ b/tests/test_scheduler.py @@ -45,15 +45,15 @@ class MockDownloader: class MockCrawler(Crawler): def __init__(self, priority_queue_cls, jobdir): - settings = dict( - SCHEDULER_DEBUG=False, - SCHEDULER_DISK_QUEUE="scrapy.squeues.PickleLifoDiskQueue", - SCHEDULER_MEMORY_QUEUE="scrapy.squeues.LifoMemoryQueue", - SCHEDULER_PRIORITY_QUEUE=priority_queue_cls, - JOBDIR=jobdir, - DUPEFILTER_CLASS="scrapy.dupefilters.BaseDupeFilter", - REQUEST_FINGERPRINTER_IMPLEMENTATION="2.7", - ) + settings = { + "SCHEDULER_DEBUG": False, + "SCHEDULER_DISK_QUEUE": "scrapy.squeues.PickleLifoDiskQueue", + "SCHEDULER_MEMORY_QUEUE": "scrapy.squeues.LifoMemoryQueue", + "SCHEDULER_PRIORITY_QUEUE": priority_queue_cls, + "JOBDIR": jobdir, + "DUPEFILTER_CLASS": "scrapy.dupefilters.BaseDupeFilter", + "REQUEST_FINGERPRINTER_IMPLEMENTATION": "2.7", + } super().__init__(Spider, settings) self.engine = MockEngine(downloader=MockDownloader()) self.stats = load_object(self.settings["STATS_CLASS"])(self) @@ -338,10 +338,10 @@ class TestIntegrationWithDownloaderAwareInMemory(TestCase): class TestIncompatibility(unittest.TestCase): def _incompatible(self): - settings = dict( - SCHEDULER_PRIORITY_QUEUE="scrapy.pqueues.DownloaderAwarePriorityQueue", - CONCURRENT_REQUESTS_PER_IP=1, - ) + settings = { + "SCHEDULER_PRIORITY_QUEUE": "scrapy.pqueues.DownloaderAwarePriorityQueue", + "CONCURRENT_REQUESTS_PER_IP": 1, + } crawler = get_crawler(Spider, settings) scheduler = Scheduler.from_crawler(crawler) spider = Spider(name="spider") diff --git a/tests/test_scheduler_base.py b/tests/test_scheduler_base.py index 76ca777a8..5db2e4e50 100644 --- a/tests/test_scheduler_base.py +++ b/tests/test_scheduler_base.py @@ -1,6 +1,6 @@ from typing import Dict, Optional from unittest import TestCase -from urllib.parse import urljoin, urlparse +from urllib.parse import urljoin from testfixtures import LogCapture from twisted.internet import defer @@ -9,6 +9,7 @@ from twisted.trial.unittest import TestCase as TwistedTestCase from scrapy.core.scheduler import BaseScheduler from scrapy.http import Request from scrapy.spiders import Spider +from scrapy.utils.httpobj import urlparse_cached from scrapy.utils.request import fingerprint from scrapy.utils.test import get_crawler from tests.mockserver import MockServer @@ -57,7 +58,7 @@ class TestSpider(Spider): self.start_urls = map(mockserver.url, PATHS) def parse(self, response): - return {"path": urlparse(response.url).path} + return {"path": urlparse_cached(response).path} class InterfaceCheckMixin: diff --git a/tests/test_settings/__init__.py b/tests/test_settings/__init__.py index e7799737f..9ee248538 100644 --- a/tests/test_settings/__init__.py +++ b/tests/test_settings/__init__.py @@ -426,7 +426,7 @@ class SettingsTest(unittest.TestCase): mydict = settings.get("TEST_DICT") self.assertIsInstance(mydict, BaseSettings) self.assertIn("key", mydict) - self.assertEqual(mydict["key"], "val") + self.assertEqual(mydict["key"], "val") # pylint: disable=unsubscriptable-object self.assertEqual(mydict.getpriority("key"), 0) @mock.patch("scrapy.settings.default_settings", default_settings) @@ -440,7 +440,7 @@ class SettingsTest(unittest.TestCase): def test_passing_objects_as_values(self): from scrapy.core.downloader.handlers.file import FileDownloadHandler - from scrapy.utils.misc import create_instance + from scrapy.utils.misc import build_from_crawler from scrapy.utils.test import get_crawler class TestPipeline: @@ -468,7 +468,7 @@ class SettingsTest(unittest.TestCase): myhandler = settings.getdict("DOWNLOAD_HANDLERS").pop("ftp") self.assertEqual(myhandler, FileDownloadHandler) - myhandler_instance = create_instance(myhandler, None, get_crawler()) + myhandler_instance = build_from_crawler(myhandler, get_crawler()) self.assertIsInstance(myhandler_instance, FileDownloadHandler) self.assertTrue(hasattr(myhandler_instance, "download_request")) diff --git a/tests/test_spider.py b/tests/test_spider.py index 00da3d485..d629d33af 100644 --- a/tests/test_spider.py +++ b/tests/test_spider.py @@ -2,6 +2,8 @@ import gzip import inspect import warnings from io import BytesIO +from logging import WARNING +from pathlib import Path from typing import Any from unittest import mock @@ -25,7 +27,7 @@ from scrapy.spiders import ( ) from scrapy.spiders.init import InitSpider from scrapy.utils.test import get_crawler -from tests import get_testdata +from tests import get_testdata, tests_datadir class SpiderTest(unittest.TestCase): @@ -149,10 +151,10 @@ class XMLFeedSpiderTest(SpiderTest): body = b""" - http://www.example.com/Special-Offers.html2009-08-16 + http://www.example.com/Special-Offers.html2009-08-16 - http://www.example.com/2009-08-16 + http://www.example.com/2009-08-16 """ response = XmlResponse(url="http://example.com/sitemap.xml", body=body) @@ -317,8 +319,7 @@ class CrawlSpiderTest(SpiderTest): rules = (Rule(LinkExtractor(), process_links="dummy_process_links"),) def dummy_process_links(self, links): - for link in links: - yield link + yield from links spider = _CrawlSpider() output = list(spider._requests_to_follow(response)) @@ -489,7 +490,8 @@ class SitemapSpiderTest(SpiderTest): GZBODY = f.getvalue() def assertSitemapBody(self, response, body): - spider = self.spider_class("example.com") + crawler = get_crawler() + spider = self.spider_class.from_crawler(crawler, "example.com") self.assertEqual(spider._get_sitemap_body(response), body) def test_get_sitemap_body(self): @@ -507,6 +509,7 @@ class SitemapSpiderTest(SpiderTest): url="http://www.example.com/sitemap", body=self.GZBODY, headers={"content-type": "application/gzip"}, + request=Request("http://www.example.com/sitemap"), ) self.assertSitemapBody(r, self.BODY) @@ -515,7 +518,11 @@ class SitemapSpiderTest(SpiderTest): self.assertSitemapBody(r, self.BODY) def test_get_sitemap_body_xml_url_compressed(self): - r = Response(url="http://www.example.com/sitemap.xml.gz", body=self.GZBODY) + r = Response( + url="http://www.example.com/sitemap.xml.gz", + body=self.GZBODY, + request=Request("http://www.example.com/sitemap"), + ) self.assertSitemapBody(r, self.BODY) # .xml.gz but body decoded by HttpCompression middleware already @@ -692,6 +699,116 @@ Sitemap: /sitemap-relative-url.xml ["http://www.example.com/sitemap2.xml"], ) + def test_compression_bomb_setting(self): + settings = {"DOWNLOAD_MAXSIZE": 10_000_000} + crawler = get_crawler(settings_dict=settings) + spider = self.spider_class.from_crawler(crawler, "example.com") + body_path = Path(tests_datadir, "compressed", "bomb-gzip.bin") + body = body_path.read_bytes() + request = Request(url="https://example.com") + response = Response(url="https://example.com", body=body, request=request) + self.assertIsNone(spider._get_sitemap_body(response)) + + def test_compression_bomb_spider_attr(self): + class DownloadMaxSizeSpider(self.spider_class): + download_maxsize = 10_000_000 + + crawler = get_crawler() + spider = DownloadMaxSizeSpider.from_crawler(crawler, "example.com") + body_path = Path(tests_datadir, "compressed", "bomb-gzip.bin") + body = body_path.read_bytes() + request = Request(url="https://example.com") + response = Response(url="https://example.com", body=body, request=request) + self.assertIsNone(spider._get_sitemap_body(response)) + + def test_compression_bomb_request_meta(self): + crawler = get_crawler() + spider = self.spider_class.from_crawler(crawler, "example.com") + body_path = Path(tests_datadir, "compressed", "bomb-gzip.bin") + body = body_path.read_bytes() + request = Request( + url="https://example.com", meta={"download_maxsize": 10_000_000} + ) + response = Response(url="https://example.com", body=body, request=request) + self.assertIsNone(spider._get_sitemap_body(response)) + + def test_download_warnsize_setting(self): + settings = {"DOWNLOAD_WARNSIZE": 10_000_000} + crawler = get_crawler(settings_dict=settings) + spider = self.spider_class.from_crawler(crawler, "example.com") + body_path = Path(tests_datadir, "compressed", "bomb-gzip.bin") + body = body_path.read_bytes() + request = Request(url="https://example.com") + response = Response(url="https://example.com", body=body, request=request) + with LogCapture( + "scrapy.spiders.sitemap", propagate=False, level=WARNING + ) as log: + spider._get_sitemap_body(response) + log.check( + ( + "scrapy.spiders.sitemap", + "WARNING", + ( + "<200 https://example.com> body size after decompression " + "(11511612 B) is larger than the download warning size " + "(10000000 B)." + ), + ), + ) + + def test_download_warnsize_spider_attr(self): + class DownloadWarnSizeSpider(self.spider_class): + download_warnsize = 10_000_000 + + crawler = get_crawler() + spider = DownloadWarnSizeSpider.from_crawler(crawler, "example.com") + body_path = Path(tests_datadir, "compressed", "bomb-gzip.bin") + body = body_path.read_bytes() + request = Request( + url="https://example.com", meta={"download_warnsize": 10_000_000} + ) + response = Response(url="https://example.com", body=body, request=request) + with LogCapture( + "scrapy.spiders.sitemap", propagate=False, level=WARNING + ) as log: + spider._get_sitemap_body(response) + log.check( + ( + "scrapy.spiders.sitemap", + "WARNING", + ( + "<200 https://example.com> body size after decompression " + "(11511612 B) is larger than the download warning size " + "(10000000 B)." + ), + ), + ) + + def test_download_warnsize_request_meta(self): + crawler = get_crawler() + spider = self.spider_class.from_crawler(crawler, "example.com") + body_path = Path(tests_datadir, "compressed", "bomb-gzip.bin") + body = body_path.read_bytes() + request = Request( + url="https://example.com", meta={"download_warnsize": 10_000_000} + ) + response = Response(url="https://example.com", body=body, request=request) + with LogCapture( + "scrapy.spiders.sitemap", propagate=False, level=WARNING + ) as log: + spider._get_sitemap_body(response) + log.check( + ( + "scrapy.spiders.sitemap", + "WARNING", + ( + "<200 https://example.com> body size after decompression " + "(11511612 B) is larger than the download warning size " + "(10000000 B)." + ), + ), + ) + class DeprecationTest(unittest.TestCase): def test_crawl_spider(self): diff --git a/tests/test_spiderloader/__init__.py b/tests/test_spiderloader/__init__.py index 04025d30d..f950739f2 100644 --- a/tests/test_spiderloader/__init__.py +++ b/tests/test_spiderloader/__init__.py @@ -3,6 +3,7 @@ import sys import tempfile import warnings from pathlib import Path +from tempfile import mkdtemp from twisted.trial import unittest from zope.interface.verify import verifyObject @@ -139,8 +140,7 @@ class SpiderLoaderTest(unittest.TestCase): class DuplicateSpiderNameLoaderTest(unittest.TestCase): def setUp(self): orig_spiders_dir = module_dir / "test_spiders" - self.tmpdir = Path(self.mktemp()) - self.tmpdir.mkdir() + self.tmpdir = Path(mkdtemp()) self.spiders_dir = self.tmpdir / "test_spiders_xxx" _copytree(orig_spiders_dir, self.spiders_dir) sys.path.append(str(self.tmpdir)) diff --git a/tests/test_spidermiddleware.py b/tests/test_spidermiddleware.py index d167adbb7..38ca8d950 100644 --- a/tests/test_spidermiddleware.py +++ b/tests/test_spidermiddleware.py @@ -170,8 +170,7 @@ class BaseAsyncSpiderMiddlewareTestCase(SpiderMiddlewareTestCase): class ProcessSpiderOutputSimpleMiddleware: def process_spider_output(self, response, result, spider): - for r in result: - yield r + yield from result class ProcessSpiderOutputAsyncGenMiddleware: @@ -182,8 +181,7 @@ class ProcessSpiderOutputAsyncGenMiddleware: class ProcessSpiderOutputUniversalMiddleware: def process_spider_output(self, response, result, spider): - for r in result: - yield r + yield from result async def process_spider_output_async(self, response, result, spider): async for r in result: @@ -324,8 +322,7 @@ class ProcessSpiderOutputInvalidResult(BaseAsyncSpiderMiddlewareTestCase): class ProcessStartRequestsSimpleMiddleware: def process_start_requests(self, start_requests, spider): - for r in start_requests: - yield r + yield from start_requests class ProcessStartRequestsSimple(BaseAsyncSpiderMiddlewareTestCase): diff --git a/tests/test_spidermiddleware_offsite.py b/tests/test_spidermiddleware_offsite.py index ea45b7698..837f1c2c8 100644 --- a/tests/test_spidermiddleware_offsite.py +++ b/tests/test_spidermiddleware_offsite.py @@ -16,10 +16,10 @@ class TestOffsiteMiddleware(TestCase): self.mw.spider_opened(self.spider) def _get_spiderargs(self): - return dict( - name="foo", - allowed_domains=["scrapytest.org", "scrapy.org", "scrapy.test.org"], - ) + return { + "name": "foo", + "allowed_domains": ["scrapytest.org", "scrapy.org", "scrapy.test.org"], + } def test_process_spider_output(self): res = Response("http://scrapytest.org") @@ -50,7 +50,7 @@ class TestOffsiteMiddleware(TestCase): class TestOffsiteMiddleware2(TestOffsiteMiddleware): def _get_spiderargs(self): - return dict(name="foo", allowed_domains=None) + return {"name": "foo", "allowed_domains": None} def test_process_spider_output(self): res = Response("http://scrapytest.org") @@ -61,13 +61,16 @@ class TestOffsiteMiddleware2(TestOffsiteMiddleware): class TestOffsiteMiddleware3(TestOffsiteMiddleware2): def _get_spiderargs(self): - return dict(name="foo") + return {"name": "foo"} class TestOffsiteMiddleware4(TestOffsiteMiddleware3): def _get_spiderargs(self): bad_hostname = urlparse("http:////scrapytest.org").hostname - return dict(name="foo", allowed_domains=["scrapytest.org", None, bad_hostname]) + return { + "name": "foo", + "allowed_domains": ["scrapytest.org", None, bad_hostname], + } def test_process_spider_output(self): res = Response("http://scrapytest.org") diff --git a/tests/test_spiderstate.py b/tests/test_spiderstate.py index f97125b76..59d18d92e 100644 --- a/tests/test_spiderstate.py +++ b/tests/test_spiderstate.py @@ -1,6 +1,6 @@ import shutil from datetime import datetime, timezone -from pathlib import Path +from tempfile import mkdtemp from twisted.trial import unittest @@ -12,8 +12,7 @@ from scrapy.utils.test import get_crawler class SpiderStateTest(unittest.TestCase): def test_store_load(self): - jobdir = self.mktemp() - Path(jobdir).mkdir() + jobdir = mkdtemp() try: spider = Spider(name="default") dt = datetime.now(tz=timezone.utc) diff --git a/tests/test_squeues_request.py b/tests/test_squeues_request.py index b444c32b7..499ca46b8 100644 --- a/tests/test_squeues_request.py +++ b/tests/test_squeues_request.py @@ -25,7 +25,7 @@ class BaseQueueTestCase(unittest.TestCase): def setUp(self): self.tmpdir = tempfile.mkdtemp(prefix="scrapy-queue-tests-") self.qpath = self.tempfilename() - self.qdir = self.mkdtemp() + self.qdir = tempfile.mkdtemp() self.crawler = get_crawler(Spider) def tearDown(self): diff --git a/tests/test_utils_datatypes.py b/tests/test_utils_datatypes.py index 9e5f88f48..be5c6de81 100644 --- a/tests/test_utils_datatypes.py +++ b/tests/test_utils_datatypes.py @@ -353,7 +353,7 @@ class LocalWeakReferencedCacheTest(unittest.TestCase): for i, r in enumerate(refs): self.assertIn(r, cache) self.assertEqual(cache[r], i) - del r # delete reference to the last object in the list + del r # delete reference to the last object in the list # pylint: disable=undefined-loop-variable # delete half of the objects, make sure that is reflected in the cache for _ in range(max // 2): diff --git a/tests/test_utils_defer.py b/tests/test_utils_defer.py index bb0ebc2a4..a7d54b565 100644 --- a/tests/test_utils_defer.py +++ b/tests/test_utils_defer.py @@ -107,8 +107,7 @@ class DeferUtilsTest(unittest.TestCase): class IterErrbackTest(unittest.TestCase): def test_iter_errback_good(self): def itergood(): - for x in range(10): - yield x + yield from range(10) errors = [] out = list(iter_errback(itergood(), errors.append)) diff --git a/tests/test_utils_iterators.py b/tests/test_utils_iterators.py index 3598fa0bb..ec377bb19 100644 --- a/tests/test_utils_iterators.py +++ b/tests/test_utils_iterators.py @@ -1,14 +1,14 @@ -from pytest import mark +import pytest from twisted.trial import unittest +from scrapy.exceptions import ScrapyDeprecationWarning from scrapy.http import Response, TextResponse, XmlResponse from scrapy.utils.iterators import _body_or_str, csviter, xmliter, xmliter_lxml from tests import get_testdata -class XmliterTestCase(unittest.TestCase): - xmliter = staticmethod(xmliter) - +class XmliterBaseTestCase: + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter(self): body = b""" @@ -40,6 +40,7 @@ class XmliterTestCase(unittest.TestCase): attrs, [("001", ["Name 1"], ["Type 1"]), ("002", ["Name 2"], ["Type 2"])] ) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_unusual_node(self): body = b""" @@ -53,6 +54,7 @@ class XmliterTestCase(unittest.TestCase): ] self.assertEqual(nodenames, [["matchme..."]]) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_unicode(self): # example taken from https://github.com/scrapy/scrapy/issues/1665 body = """ @@ -112,6 +114,7 @@ class XmliterTestCase(unittest.TestCase): [("26", ["-"], ["80"]), ("21", ["Ab"], ["76"]), ("27", ["A"], ["27"])], ) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_text(self): body = ( '' @@ -123,6 +126,7 @@ class XmliterTestCase(unittest.TestCase): [["one"], ["two"]], ) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_namespaces(self): body = b""" @@ -162,6 +166,7 @@ class XmliterTestCase(unittest.TestCase): self.assertEqual(node.xpath("id/text()").getall(), []) self.assertEqual(node.xpath("price/text()").getall(), []) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_namespaced_nodename(self): body = b""" @@ -190,6 +195,7 @@ class XmliterTestCase(unittest.TestCase): ["http://www.mydummycompany.com/images/item1.jpg"], ) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_namespaced_nodename_missing(self): body = b""" @@ -214,6 +220,7 @@ class XmliterTestCase(unittest.TestCase): with self.assertRaises(StopIteration): next(my_iter) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_exception(self): body = ( '' @@ -226,10 +233,12 @@ class XmliterTestCase(unittest.TestCase): self.assertRaises(StopIteration, next, iter) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_objtype_exception(self): i = self.xmliter(42, "product") self.assertRaises(TypeError, next, i) + @pytest.mark.filterwarnings("ignore::scrapy.exceptions.ScrapyDeprecationWarning") def test_xmliter_encoding(self): body = ( b'\n' @@ -244,12 +253,25 @@ class XmliterTestCase(unittest.TestCase): ) -class LxmlXmliterTestCase(XmliterTestCase): - xmliter = staticmethod(xmliter_lxml) +class XmliterTestCase(XmliterBaseTestCase, unittest.TestCase): + xmliter = staticmethod(xmliter) - @mark.xfail(reason="known bug of the current implementation") - def test_xmliter_namespaced_nodename(self): - super().test_xmliter_namespaced_nodename() + def test_deprecation(self): + body = b""" + + + + + """ + with pytest.warns( + ScrapyDeprecationWarning, + match="xmliter", + ): + next(self.xmliter(body, "product")) + + +class LxmlXmliterTestCase(XmliterBaseTestCase, unittest.TestCase): + xmliter = staticmethod(xmliter_lxml) def test_xmliter_iterate_namespace(self): body = b""" @@ -333,7 +355,7 @@ class UtilsCsvTestCase(unittest.TestCase): response = TextResponse(url="http://example.com/", body=body) csv = csviter(response) - result = [row for row in csv] + result = list(csv) self.assertEqual( result, [ @@ -355,7 +377,7 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response, delimiter="\t") self.assertEqual( - [row for row in csv], + list(csv), [ {"id": "1", "name": "alpha", "value": "foobar"}, {"id": "2", "name": "unicode", "value": "\xfan\xedc\xf3d\xe9\u203d"}, @@ -372,7 +394,7 @@ class UtilsCsvTestCase(unittest.TestCase): csv1 = csviter(response1, quotechar="'") self.assertEqual( - [row for row in csv1], + list(csv1), [ {"id": "1", "name": "alpha", "value": "foobar"}, {"id": "2", "name": "unicode", "value": "\xfan\xedc\xf3d\xe9\u203d"}, @@ -385,7 +407,7 @@ class UtilsCsvTestCase(unittest.TestCase): csv2 = csviter(response2, delimiter="|", quotechar="'") self.assertEqual( - [row for row in csv2], + list(csv2), [ {"id": "1", "name": "alpha", "value": "foobar"}, {"id": "2", "name": "unicode", "value": "\xfan\xedc\xf3d\xe9\u203d"}, @@ -400,7 +422,7 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response) self.assertEqual( - [row for row in csv], + list(csv), [ {"'id'": "1", "'name'": "'alpha'", "'value'": "'foobar'"}, { @@ -419,7 +441,7 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response, delimiter="\t") self.assertEqual( - [row for row in csv], + list(csv), [ {"id": "1", "name": "alpha", "value": "foobar"}, {"id": "2", "name": "unicode", "value": "\xfan\xedc\xf3d\xe9\u203d"}, @@ -436,7 +458,7 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response, headers=[h.decode("utf-8") for h in headers]) self.assertEqual( - [row for row in csv], + list(csv), [ {"id": "1", "name": "alpha", "value": "foobar"}, {"id": "2", "name": "unicode", "value": "\xfan\xedc\xf3d\xe9\u203d"}, @@ -453,7 +475,7 @@ class UtilsCsvTestCase(unittest.TestCase): csv = csviter(response) self.assertEqual( - [row for row in csv], + list(csv), [ {"id": "1", "name": "alpha", "value": "foobar"}, {"id": "2", "name": "unicode", "value": "\xfan\xedc\xf3d\xe9\u203d"}, @@ -524,6 +546,6 @@ class TestHelper(unittest.TestCase): def _assert_type_and_value(self, a, b, obj): self.assertTrue( - type(a) is type(b), f"Got {type(a)}, expected {type(b)} for { obj!r}" + type(a) is type(b), f"Got {type(a)}, expected {type(b)} for {obj!r}" ) self.assertEqual(a, b) diff --git a/tests/test_utils_misc/__init__.py b/tests/test_utils_misc/__init__.py index 69793ee75..ee3314d8e 100644 --- a/tests/test_utils_misc/__init__.py +++ b/tests/test_utils_misc/__init__.py @@ -7,6 +7,8 @@ from unittest import mock from scrapy.item import Field, Item from scrapy.utils.misc import ( arg_to_iter, + build_from_crawler, + build_from_settings, create_instance, load_object, rel_has_nofollow, @@ -153,6 +155,78 @@ class UtilsMiscTestCase(unittest.TestCase): with self.assertRaises(TypeError): create_instance(m, settings, None) + def test_build_from_crawler(self): + settings = mock.MagicMock() + crawler = mock.MagicMock(spec_set=["settings"]) + args = (True, 100.0) + kwargs = {"key": "val"} + + def _test_with_crawler(mock, settings, crawler): + build_from_crawler(mock, crawler, *args, **kwargs) + if hasattr(mock, "from_crawler"): + mock.from_crawler.assert_called_once_with(crawler, *args, **kwargs) + if hasattr(mock, "from_settings"): + self.assertEqual(mock.from_settings.call_count, 0) + self.assertEqual(mock.call_count, 0) + elif hasattr(mock, "from_settings"): + mock.from_settings.assert_called_once_with(settings, *args, **kwargs) + self.assertEqual(mock.call_count, 0) + else: + mock.assert_called_once_with(*args, **kwargs) + + # Check usage of correct constructor using three mocks: + # 1. with no alternative constructors + # 2. with from_crawler() constructor + # 3. with from_settings() and from_crawler() constructor + spec_sets = ( + ["__qualname__"], + ["__qualname__", "from_crawler"], + ["__qualname__", "from_settings", "from_crawler"], + ) + for specs in spec_sets: + m = mock.MagicMock(spec_set=specs) + _test_with_crawler(m, settings, crawler) + m.reset_mock() + + # Check adoption of crawler + m = mock.MagicMock(spec_set=["__qualname__", "from_crawler"]) + m.from_crawler.return_value = None + with self.assertRaises(TypeError): + build_from_crawler(m, crawler, *args, **kwargs) + + def test_build_from_settings(self): + settings = mock.MagicMock() + args = (True, 100.0) + kwargs = {"key": "val"} + + def _test_with_settings(mock, settings): + build_from_settings(mock, settings, *args, **kwargs) + if hasattr(mock, "from_settings"): + mock.from_settings.assert_called_once_with(settings, *args, **kwargs) + self.assertEqual(mock.call_count, 0) + else: + mock.assert_called_once_with(*args, **kwargs) + + # Check usage of correct constructor using three mocks: + # 1. with no alternative constructors + # 2. with from_settings() constructor + # 3. with from_settings() and from_crawler() constructor + spec_sets = ( + ["__qualname__"], + ["__qualname__", "from_settings"], + ["__qualname__", "from_settings", "from_crawler"], + ) + for specs in spec_sets: + m = mock.MagicMock(spec_set=specs) + _test_with_settings(m, settings) + m.reset_mock() + + # Check adoption of crawler settings + m = mock.MagicMock(spec_set=["__qualname__", "from_settings"]) + m.from_settings.return_value = None + with self.assertRaises(TypeError): + build_from_settings(m, settings, *args, **kwargs) + def test_set_environ(self): assert os.environ.get("some_test_environ") is None with set_environ(some_test_environ="test_value"): diff --git a/tests/test_utils_request.py b/tests/test_utils_request.py index e6d1abe3f..633077eec 100644 --- a/tests/test_utils_request.py +++ b/tests/test_utils_request.py @@ -2,22 +2,15 @@ import json import unittest import warnings from hashlib import sha1 -from typing import Dict, Mapping, Optional, Tuple, Union +from typing import Dict, Optional, Tuple, Union from weakref import WeakKeyDictionary -import pytest -from w3lib.url import canonicalize_url - from scrapy.http import Request -from scrapy.utils.deprecate import ScrapyDeprecationWarning from scrapy.utils.python import to_bytes from scrapy.utils.request import ( - _deprecated_fingerprint_cache, _fingerprint_cache, - _request_fingerprint_as_bytes, fingerprint, request_authenticate, - request_fingerprint, request_httprepr, request_to_curl, ) @@ -233,168 +226,6 @@ class FingerprintTest(unittest.TestCase): self.assertEqual(actual, expected) -class RequestFingerprintTest(FingerprintTest): - function = staticmethod(request_fingerprint) - cache = _deprecated_fingerprint_cache - known_hashes: Tuple[Tuple[Request, Union[bytes, str], Dict], ...] = ( - ( - Request("http://example.org"), - "b2e5245ef826fd9576c93bd6e392fce3133fab62", - {}, - ), - ( - Request("https://example.org"), - "bd10a0a89ea32cdee77917320f1309b0da87e892", - {}, - ), - ( - Request("https://example.org?a"), - "2fb7d48ae02f04b749f40caa969c0bc3c43204ce", - {}, - ), - ( - Request("https://example.org?a=b"), - "42e5fe149b147476e3f67ad0670c57b4cc57856a", - {}, - ), - ( - Request("https://example.org?a=b&a"), - "d23a9787cb56c6375c2cae4453c5a8c634526942", - {}, - ), - ( - Request("https://example.org?a=b&a=c"), - "9a18a7a8552a9182b7f1e05d33876409e421e5c5", - {}, - ), - ( - Request("https://example.org", method="POST"), - "ba20a80cb5c5ca460021ceefb3c2467b2bfd1bc6", - {}, - ), - ( - Request("https://example.org", body=b"a"), - "4bb136e54e715a4ea7a9dd1101831765d33f2d60", - {}, - ), - ( - Request("https://example.org", method="POST", body=b"a"), - "6c6595374a304b293be762f7b7be3f54e9947c65", - {}, - ), - ( - Request("https://example.org#a", headers={"A": b"B"}), - "bd10a0a89ea32cdee77917320f1309b0da87e892", - {}, - ), - ( - Request("https://example.org#a", headers={"A": b"B"}), - "515b633cb3ca502a33a9d8c890e889ec1e425e65", - {"include_headers": ["A"]}, - ), - ( - Request("https://example.org#a", headers={"A": b"B"}), - "505c96e7da675920dfef58725e8c957dfdb38f47", - {"keep_fragments": True}, - ), - ( - Request("https://example.org#a", headers={"A": b"B"}), - "d6f673cdcb661b7970c2b9a00ee63e87d1e2e5da", - {"include_headers": ["A"], "keep_fragments": True}, - ), - ( - Request("https://example.org/ab"), - "4e2870fee58582d6f81755e9b8fdefe3cba0c951", - {}, - ), - ( - Request("https://example.org/a", body=b"b"), - "4e2870fee58582d6f81755e9b8fdefe3cba0c951", - {}, - ), - ) - - def setUp(self) -> None: - warnings.simplefilter("ignore", ScrapyDeprecationWarning) - - def tearDown(self) -> None: - warnings.simplefilter("default", ScrapyDeprecationWarning) - - @pytest.mark.xfail(reason="known bug kept for backward compatibility", strict=True) - def test_part_separation(self): - super().test_part_separation() - - -class RequestFingerprintDeprecationTest(unittest.TestCase): - def test_deprecation_default_parameters(self): - with pytest.warns(ScrapyDeprecationWarning) as warnings: - request_fingerprint(Request("http://www.example.com")) - messages = [str(warning.message) for warning in warnings] - self.assertTrue( - any("Call to deprecated function" in message for message in messages) - ) - self.assertFalse(any("non-default" in message for message in messages)) - - def test_deprecation_non_default_parameters(self): - with pytest.warns(ScrapyDeprecationWarning) as warnings: - request_fingerprint(Request("http://www.example.com"), keep_fragments=True) - messages = [str(warning.message) for warning in warnings] - self.assertTrue( - any("Call to deprecated function" in message for message in messages) - ) - self.assertTrue(any("non-default" in message for message in messages)) - - -class RequestFingerprintAsBytesTest(FingerprintTest): - function = staticmethod(_request_fingerprint_as_bytes) - cache = _deprecated_fingerprint_cache - known_hashes = RequestFingerprintTest.known_hashes - - def test_caching(self): - r1 = Request("http://www.example.com/hnnoticiaj1.aspx?78160,199") - self.assertEqual( - self.function(r1), bytes.fromhex(self.cache[r1][self.default_cache_key]) - ) - - @pytest.mark.xfail(reason="known bug kept for backward compatibility", strict=True) - def test_part_separation(self): - super().test_part_separation() - - def test_hashes(self): - actual = [ - self.function(request, **kwargs) for request, _, kwargs in self.known_hashes - ] - expected = [ - bytes.fromhex(_fingerprint) for _, _fingerprint, _ in self.known_hashes - ] - self.assertEqual(actual, expected) - - -_fingerprint_cache_2_6: Mapping[Request, Tuple[None, bool]] = WeakKeyDictionary() - - -def request_fingerprint_2_6(request, include_headers=None, keep_fragments=False): - if include_headers: - include_headers = tuple(to_bytes(h.lower()) for h in sorted(include_headers)) - cache = _fingerprint_cache_2_6.setdefault(request, {}) - cache_key = (include_headers, keep_fragments) - if cache_key not in cache: - fp = sha1() - fp.update(to_bytes(request.method)) - fp.update( - to_bytes(canonicalize_url(request.url, keep_fragments=keep_fragments)) - ) - fp.update(request.body or b"") - if include_headers: - for hdr in include_headers: - if hdr in request.headers: - fp.update(hdr) - for v in request.headers.getlist(hdr): - fp.update(v) - cache[cache_key] = fp.hexdigest() - return cache[cache_key] - - REQUEST_OBJECTS_TO_TEST = ( Request("http://www.example.com/"), Request("http://www.example.com/query?id=111&cat=222"), @@ -424,94 +255,16 @@ REQUEST_OBJECTS_TO_TEST = ( ) -class BackwardCompatibilityTestCase(unittest.TestCase): - def test_function_backward_compatibility(self): - include_headers_to_test = ( - None, - ["Accept-Language"], - ["accept-language", "sessionid"], - ["SESSIONID", "Accept-Language"], - ) - for request_object in REQUEST_OBJECTS_TO_TEST: - for include_headers in include_headers_to_test: - for keep_fragments in (False, True): - with warnings.catch_warnings(): - warnings.simplefilter("ignore") - fp = request_fingerprint( - request_object, - include_headers=include_headers, - keep_fragments=keep_fragments, - ) - old_fp = request_fingerprint_2_6( - request_object, - include_headers=include_headers, - keep_fragments=keep_fragments, - ) - self.assertEqual(fp, old_fp) - - def test_component_backward_compatibility(self): - for request_object in REQUEST_OBJECTS_TO_TEST: - with warnings.catch_warnings(): - warnings.simplefilter("ignore") - crawler = get_crawler(prevent_warnings=False) - fp = crawler.request_fingerprinter.fingerprint(request_object) - old_fp = request_fingerprint_2_6(request_object) - self.assertEqual(fp.hex(), old_fp) - - def test_custom_component_backward_compatibility(self): - """Tests that the backward-compatible request fingerprinting class featured - in the documentation is indeed backward compatible and does not cause a - warning to be logged.""" - - class RequestFingerprinter: - cache = WeakKeyDictionary() - - def fingerprint(self, request): - if request not in self.cache: - fp = sha1() - fp.update(to_bytes(request.method)) - fp.update(to_bytes(canonicalize_url(request.url))) - fp.update(request.body or b"") - self.cache[request] = fp.digest() - return self.cache[request] - - for request_object in REQUEST_OBJECTS_TO_TEST: - with warnings.catch_warnings() as logged_warnings: - settings = { - "REQUEST_FINGERPRINTER_CLASS": RequestFingerprinter, - } - crawler = get_crawler(settings_dict=settings) - fp = crawler.request_fingerprinter.fingerprint(request_object) - old_fp = request_fingerprint_2_6(request_object) - self.assertEqual(fp.hex(), old_fp) - self.assertFalse(logged_warnings) - - class RequestFingerprinterTestCase(unittest.TestCase): def test_default_implementation(self): - with warnings.catch_warnings(record=True) as logged_warnings: - crawler = get_crawler(prevent_warnings=False) + crawler = get_crawler() request = Request("https://example.com") self.assertEqual( crawler.request_fingerprinter.fingerprint(request), - _request_fingerprint_as_bytes(request), + fingerprint(request), ) - self.assertTrue(logged_warnings) def test_deprecated_implementation(self): - settings = { - "REQUEST_FINGERPRINTER_IMPLEMENTATION": "2.6", - } - with warnings.catch_warnings(record=True) as logged_warnings: - crawler = get_crawler(settings_dict=settings) - request = Request("https://example.com") - self.assertEqual( - crawler.request_fingerprinter.fingerprint(request), - _request_fingerprint_as_bytes(request), - ) - self.assertTrue(logged_warnings) - - def test_recommended_implementation(self): settings = { "REQUEST_FINGERPRINTER_IMPLEMENTATION": "2.7", } @@ -522,14 +275,7 @@ class RequestFingerprinterTestCase(unittest.TestCase): crawler.request_fingerprinter.fingerprint(request), fingerprint(request), ) - self.assertFalse(logged_warnings) - - def test_unknown_implementation(self): - settings = { - "REQUEST_FINGERPRINTER_IMPLEMENTATION": "2.5", - } - with self.assertRaises(ValueError): - get_crawler(settings_dict=settings) + self.assertTrue(logged_warnings) class CustomRequestFingerprinterTestCase(unittest.TestCase): diff --git a/tests/test_utils_response.py b/tests/test_utils_response.py index 661fb47a3..7ad86127b 100644 --- a/tests/test_utils_response.py +++ b/tests/test_utils_response.py @@ -1,10 +1,14 @@ import unittest from pathlib import Path +from time import process_time from urllib.parse import urlparse +import pytest + from scrapy.http import HtmlResponse, Response, TextResponse from scrapy.utils.python import to_bytes from scrapy.utils.response import ( + _remove_html_comments, get_base_url, get_meta_refresh, open_in_browser, @@ -166,3 +170,76 @@ class ResponseUtilsTest(unittest.TestCase): assert open_in_browser( r5, _openfunc=check_base_url ), "Inject unique base url with conditional comment" + + def test_open_in_browser_redos_comment(self): + MAX_CPU_TIME = 0.02 + + # Exploit input from + # https://makenowjust-labs.github.io/recheck/playground/ + # for // (old pattern to remove comments). + body = b"->" + + response = HtmlResponse("https://example.com", body=body) + + start_time = process_time() + + open_in_browser(response, lambda url: True) + + end_time = process_time() + self.assertLess(end_time - start_time, MAX_CPU_TIME) + + def test_open_in_browser_redos_head(self): + MAX_CPU_TIME = 0.02 + + # Exploit input from + # https://makenowjust-labs.github.io/recheck/playground/ + # for /(|\s.*?>))/ (old pattern to find the head element). + body = b"b", + b"ab", + ), + ( + b"ac", + b"ac", + ), + ( + b"acccd", + b"acd", + ), + ( + b"ad", + b"ad", + ), + ), +) +def test_remove_html_comments(input_body, output_body): + assert ( + _remove_html_comments(input_body) == output_body + ), f"{_remove_html_comments(input_body)=} == {output_body=}" diff --git a/tests/test_utils_signal.py b/tests/test_utils_signal.py index 65b99e0c4..60232f10b 100644 --- a/tests/test_utils_signal.py +++ b/tests/test_utils_signal.py @@ -75,9 +75,6 @@ class SendCatchLogDeferredAsyncDefTest(SendCatchLogDeferredTest): await defer.succeed(42) return "OK" - def test_send_catch_log(self): - return super().test_send_catch_log() - @mark.only_asyncio() class SendCatchLogDeferredAsyncioTest(SendCatchLogDeferredTest): @@ -87,9 +84,6 @@ class SendCatchLogDeferredAsyncioTest(SendCatchLogDeferredTest): await asyncio.sleep(0.2) return await get_from_asyncio_queue("OK") - def test_send_catch_log(self): - return super().test_send_catch_log() - class SendCatchLogTest2(unittest.TestCase): def test_error_logged_if_deferred_not_supported(self): diff --git a/tests/test_utils_spider.py b/tests/test_utils_spider.py index 460ae40c3..dd1d26448 100644 --- a/tests/test_utils_spider.py +++ b/tests/test_utils_spider.py @@ -26,7 +26,7 @@ class UtilsSpidersTestCase(unittest.TestCase): self.assertEqual(list(iterate_spider_output([r, i, o])), [r, i, o]) def test_iter_spider_classes(self): - import tests.test_utils_spider + import tests.test_utils_spider # pylint: disable=import-self it = iter_spider_classes(tests.test_utils_spider) self.assertEqual(set(it), {MySpider1, MySpider2}) diff --git a/tests/test_utils_template.py b/tests/test_utils_template.py index cbe80e157..fc42c0d2f 100644 --- a/tests/test_utils_template.py +++ b/tests/test_utils_template.py @@ -16,7 +16,7 @@ class UtilsRenderTemplateFileTestCase(unittest.TestCase): rmtree(self.tmp_path) def test_simple_render(self): - context = dict(project_name="proj", name="spi", classname="TheSpider") + context = {"project_name": "proj", "name": "spi", "classname": "TheSpider"} template = "from ${project_name}.spiders.${name} import ${classname}" rendered = "from proj.spiders.spi import TheSpider" diff --git a/tests/test_webclient.py b/tests/test_webclient.py index 0042fe8f0..cce119001 100644 --- a/tests/test_webclient.py +++ b/tests/test_webclient.py @@ -2,8 +2,10 @@ from twisted.internet import defer Tests borrowed from the twisted.web.client tests. """ + import shutil from pathlib import Path +from tempfile import mkdtemp import OpenSSL.SSL from twisted.internet import defer, reactor @@ -24,7 +26,7 @@ from scrapy.core.downloader import webclient as client from scrapy.core.downloader.contextfactory import ScrapyClientContextFactory from scrapy.http import Headers, Request from scrapy.settings import Settings -from scrapy.utils.misc import create_instance +from scrapy.utils.misc import build_from_settings from scrapy.utils.python import to_bytes, to_unicode from tests.mockserver import ( BrokenDownloadResource, @@ -274,8 +276,7 @@ class WebClientTestCase(unittest.TestCase): return reactor.listenTCP(0, site, interface="127.0.0.1") def setUp(self): - self.tmpname = Path(self.mktemp()) - self.tmpname.mkdir() + self.tmpname = Path(mkdtemp()) (self.tmpname / "file").write_bytes(b"0123456789") r = static.File(str(self.tmpname)) r.putChild(b"redirect", util.Redirect(b"/file")) @@ -440,8 +441,7 @@ class WebClientSSLTestCase(unittest.TestCase): return f"https://127.0.0.1:{self.portno}/{path}" def setUp(self): - self.tmpname = Path(self.mktemp()) - self.tmpname.mkdir() + self.tmpname = Path(mkdtemp()) (self.tmpname / "file").write_bytes(b"0123456789") r = static.File(str(self.tmpname)) r.putChild(b"payload", PayloadResource()) @@ -470,8 +470,8 @@ class WebClientCustomCiphersSSLTestCase(WebClientSSLTestCase): def testPayload(self): s = "0123456789" * 10 settings = Settings({"DOWNLOADER_CLIENT_TLS_CIPHERS": self.custom_ciphers}) - client_context_factory = create_instance( - ScrapyClientContextFactory, settings=settings, crawler=None + client_context_factory = build_from_settings( + ScrapyClientContextFactory, settings ) return getPage( self.getURL("payload"), body=s, contextFactory=client_context_factory @@ -482,8 +482,8 @@ class WebClientCustomCiphersSSLTestCase(WebClientSSLTestCase): settings = Settings( {"DOWNLOADER_CLIENT_TLS_CIPHERS": "ECDHE-RSA-AES256-GCM-SHA384"} ) - client_context_factory = create_instance( - ScrapyClientContextFactory, settings=settings, crawler=None + client_context_factory = build_from_settings( + ScrapyClientContextFactory, settings ) d = getPage( self.getURL("payload"), body=s, contextFactory=client_context_factory diff --git a/tox.ini b/tox.ini index 8996b12a4..c43bd73d1 100644 --- a/tox.ini +++ b/tox.ini @@ -11,11 +11,7 @@ minversion = 1.7.0 deps = -rtests/requirements.txt # mitmproxy does not support PyPy - # Python 3.9+ requires mitmproxy >= 5.3.0 - # mitmproxy >= 5.3.0 requires h2 >= 4.0, Twisted 21.2 requires h2 < 4.0 - #mitmproxy >= 5.3.0; python_version >= '3.9' and implementation_name != 'pypy' - # The tests hang with mitmproxy 8.0.0: https://github.com/scrapy/scrapy/issues/5454 - mitmproxy >= 4.0.4, < 8; python_version < '3.9' and implementation_name != 'pypy' + mitmproxy; implementation_name != 'pypy' passenv = S3_TEST_FILE_URI AWS_ACCESS_KEY_ID @@ -34,13 +30,13 @@ install_command = basepython = python3 deps = mypy==1.8.0 - typing-extensions==4.9.0 + typing-extensions==4.10.0 types-attrs==19.1.0 - types-lxml==2023.10.21 - types-Pillow==10.1.0.2 - types-Pygments==2.17.0.0 - types-pyOpenSSL==23.3.0.0 - types-setuptools==69.0.0.0 + types-lxml==2024.2.9 + types-Pillow==10.2.0.20240213 + types-Pygments==2.17.0.20240106 + types-pyOpenSSL==24.0.0.20240130 + types-setuptools==69.1.0.20240223 # 2.1.2 fixes a typing bug: https://github.com/scrapy/w3lib/pull/211 w3lib >= 2.1.2 commands = @@ -66,7 +62,7 @@ commands = basepython = python3 deps = {[testenv:extra-deps]deps} - pylint==3.0.1 + pylint==3.1.0 commands = pylint conftest.py docs extras scrapy setup.py tests @@ -96,7 +92,7 @@ deps = lxml==4.4.1 -rtests/requirements.txt - # mitmproxy 4.0.4+ requires upgrading some of the pinned dependencies + # mitmproxy 8.0.0 requires upgrading some of the pinned dependencies # above, hence we do not install it in pinned environments at the moment setenv = _SCRAPY_PINNED=true @@ -137,6 +133,8 @@ deps = robotexclusionrulesparser Pillow Twisted[http2] + brotli + zstandard [testenv:extra-deps-pinned] basepython = python3.8