From 59fcb9b93c4971602b4a4afd4afdf08db7a7f2b7 Mon Sep 17 00:00:00 2001 From: Andrey Rakhmatullin Date: Tue, 7 Jan 2025 15:18:18 +0400 Subject: [PATCH] Improve internal refs to scrapy.Request and scrapy.Selector (#6526) * Improve internal refs to scrapy.Selector. * Improve internal refs to scrapy.Request. * More scrapy.http fixes. * Fix FormRequest refs. * More fixes. * Simplifications. * Last fixes. * Add the parsel intersphinx. --- docs/conf.py | 1 + docs/news.rst | 139 +++++++++++++------------- docs/topics/downloader-middleware.rst | 2 +- docs/topics/dynamic-content.rst | 5 +- docs/topics/exceptions.rst | 2 +- docs/topics/request-response.rst | 137 ++++++++++++------------- docs/topics/selectors.rst | 16 +-- scrapy/core/scheduler.py | 4 +- scrapy/http/request/__init__.py | 12 +-- scrapy/http/response/__init__.py | 8 +- scrapy/http/response/text.py | 14 +-- scrapy/loader/__init__.py | 4 +- scrapy/utils/request.py | 10 +- 13 files changed, 176 insertions(+), 178 deletions(-) diff --git a/docs/conf.py b/docs/conf.py index d06828bcc..fd8165db3 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -284,6 +284,7 @@ intersphinx_mapping = { "cryptography": ("https://cryptography.io/en/latest/", None), "cssselect": ("https://cssselect.readthedocs.io/en/latest", None), "itemloaders": ("https://itemloaders.readthedocs.io/en/latest/", None), + "parsel": ("https://parsel.readthedocs.io/en/latest/", None), "pytest": ("https://docs.pytest.org/en/latest", None), "python": ("https://docs.python.org/3", None), "sphinx": ("https://www.sphinx-doc.org/en/master", None), diff --git a/docs/news.rst b/docs/news.rst index 2bf65272f..924abb7a1 100644 --- a/docs/news.rst +++ b/docs/news.rst @@ -635,7 +635,7 @@ Bug fixes exception if ``default`` is ``None``. (:issue:`6308`, :issue:`6310`) -- :class:`~scrapy.selector.Selector` now uses +- :class:`~scrapy.Selector` now uses :func:`scrapy.utils.response.get_base_url` to determine the base URL of a given :class:`~scrapy.http.Response`. (:issue:`6265`) @@ -653,7 +653,7 @@ Documentation - Add a FAQ entry about :ref:`creating blank requests `. (:issue:`6203`, :issue:`6208`) -- Document that :attr:`scrapy.selector.Selector.type` can be ``"json"``. +- Document that :attr:`scrapy.Selector.type` can be ``"json"``. (:issue:`6328`, :issue:`6334`) Quality assurance @@ -734,7 +734,7 @@ 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 `. +- Extended documentation for :attr:`.Request.meta`. (:issue:`5565`) - Fixed the :reqmeta:`dont_merge_cookies` documentation. (:issue:`5936`, @@ -1095,7 +1095,7 @@ New features :setting:`RANDOMIZE_DOWNLOAD_DELAY` can now be set on a per-domain basis via the new :setting:`DOWNLOAD_SLOTS` setting. (:issue:`5328`) -- Added :meth:`TextResponse.jmespath`, a shortcut for JMESPath selectors +- Added :meth:`.TextResponse.jmespath`, a shortcut for JMESPath selectors available since parsel_ 1.8.1. (:issue:`5894`, :issue:`5915`) - Added :signal:`feed_slot_closed` and :signal:`feed_exporter_closed` @@ -1275,7 +1275,7 @@ New features avoid confusion. (:issue:`5717`, :issue:`5722`, :issue:`5727`) -- The ``callback`` parameter of :class:`~scrapy.http.Request` can now be set +- The ``callback`` parameter of :class:`~scrapy.Request` can now be set to :func:`scrapy.http.request.NO_CALLBACK`, to distinguish it from ``None``, as the latter indicates that the default spider callback (:meth:`~scrapy.Spider.parse`) is to be used. @@ -1772,17 +1772,17 @@ Highlights: Security bug fixes ~~~~~~~~~~~~~~~~~~ -- When a :class:`~scrapy.http.Request` object with cookies defined gets a - redirect response causing a new :class:`~scrapy.http.Request` object to be +- When a :class:`~scrapy.Request` object with cookies defined gets a + redirect response causing a new :class:`~scrapy.Request` object to be scheduled, the cookies defined in the original - :class:`~scrapy.http.Request` object are no longer copied into the new - :class:`~scrapy.http.Request` object. + :class:`~scrapy.Request` object are no longer copied into the new + :class:`~scrapy.Request` object. If you manually set the ``Cookie`` header on a - :class:`~scrapy.http.Request` object and the domain name of the redirect + :class:`~scrapy.Request` object and the domain name of the redirect URL is not an exact match for the domain of the URL of the original - :class:`~scrapy.http.Request` object, your ``Cookie`` header is now dropped - from the new :class:`~scrapy.http.Request` object. + :class:`~scrapy.Request` object, your ``Cookie`` header is now dropped + from the new :class:`~scrapy.Request` object. The old behavior could be exploited by an attacker to gain access to your cookies. Please, see the `cjvr-mfj7-j4j8 security advisory`_ for more @@ -1795,10 +1795,10 @@ Security bug fixes ``example.com`` and any subdomain) by defining the shared domain suffix (e.g. ``example.com``) as the cookie domain when defining your cookies. See the documentation of the - :class:`~scrapy.http.Request` class for more information. + :class:`~scrapy.Request` class for more information. - When the domain of a cookie, either received in the ``Set-Cookie`` header - of a response or defined in a :class:`~scrapy.http.Request` object, is set + of a response or defined in a :class:`~scrapy.Request` object, is set to a `public suffix `_, the cookie is now ignored unless the cookie domain is the same as the request domain. @@ -1849,7 +1849,7 @@ Backward-incompatible changes meet expectations, :exc:`TypeError` is now raised at startup time. Before, other exceptions would be raised at run time. (:issue:`3559`) -- The ``_encoding`` field of serialized :class:`~scrapy.http.Request` objects +- The ``_encoding`` field of serialized :class:`~scrapy.Request` objects is now named ``encoding``, in line with all other fields (:issue:`5130`) @@ -1879,7 +1879,7 @@ Deprecations - :mod:`scrapy.utils.reqser` is deprecated. (:issue:`5130`) - Instead of :func:`~scrapy.utils.reqser.request_to_dict`, use the new - :meth:`Request.to_dict ` method. + :meth:`.Request.to_dict` method. - Instead of :func:`~scrapy.utils.reqser.request_from_dict`, use the new :func:`scrapy.utils.request.request_from_dict` function. @@ -1984,9 +1984,9 @@ New features using ``queuelib`` 1.6.1 or later), the ``peek`` method raises :exc:`NotImplementedError`. -- :class:`~scrapy.http.Request` and :class:`~scrapy.http.Response` now have +- :class:`~scrapy.Request` and :class:`~scrapy.http.Response` now have an ``attributes`` attribute that makes subclassing easier. For - :class:`~scrapy.http.Request`, it also allows subclasses to work with + :class:`~scrapy.Request`, it also allows subclasses to work with :func:`scrapy.utils.request.request_from_dict`. (:issue:`1877`, :issue:`5130`, :issue:`5218`) @@ -2452,14 +2452,13 @@ Backward-incompatible changes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * :class:`~scrapy.downloadermiddlewares.cookies.CookiesMiddleware` once again - discards cookies defined in :attr:`Request.headers - `. + discards cookies defined in :attr:`.Request.headers`. We decided to revert this bug fix, introduced in Scrapy 2.2.0, because it was reported that the current implementation could break existing code. If you need to set cookies for a request, use the :class:`Request.cookies - ` parameter. + ` parameter. A future version of Scrapy will include a new, better implementation of the reverted bug fix. @@ -2580,16 +2579,16 @@ New features :meth:`~scrapy.downloadermiddlewares.DownloaderMiddleware.process_response` or :meth:`~scrapy.downloadermiddlewares.DownloaderMiddleware.process_exception` - with a custom :class:`~scrapy.http.Request` object assigned to + with a custom :class:`~scrapy.Request` object assigned to :class:`response.request `: - The response is handled by the callback of that custom - :class:`~scrapy.http.Request` object, instead of being handled by the - callback of the original :class:`~scrapy.http.Request` object + :class:`~scrapy.Request` object, instead of being handled by the + callback of the original :class:`~scrapy.Request` object - - That custom :class:`~scrapy.http.Request` object is now sent as the + - That custom :class:`~scrapy.Request` object is now sent as the ``request`` argument to the :signal:`response_received` signal, instead - of the original :class:`~scrapy.http.Request` object + of the original :class:`~scrapy.Request` object (:issue:`4529`, :issue:`4632`) @@ -2760,7 +2759,7 @@ New features * The :command:`parse` command now allows specifying an output file (:issue:`4317`, :issue:`4377`) -* :meth:`Request.from_curl ` and +* :meth:`.Request.from_curl` and :func:`~scrapy.utils.curl.curl_to_request_kwargs` now also support ``--data-raw`` (:issue:`4612`) @@ -2776,7 +2775,7 @@ Bug fixes :ref:`dataclass items ` and :ref:`attr.s items ` (:issue:`4667`, :issue:`4668`) -* :meth:`Request.from_curl ` and +* :meth:`.Request.from_curl` and :func:`~scrapy.utils.curl.curl_to_request_kwargs` now set the request method to ``POST`` when a request body is specified and no request method is specified (:issue:`4612`) @@ -2861,8 +2860,7 @@ Backward-incompatible changes Deprecations ~~~~~~~~~~~~ -* :meth:`TextResponse.body_as_unicode - ` is now deprecated, use +* ``TextResponse.body_as_unicode()`` is now deprecated, use :attr:`TextResponse.text ` instead (:issue:`4546`, :issue:`4555`, :issue:`4579`) @@ -2901,9 +2899,8 @@ New features * :ref:`Link extractors ` are now serializable, as long as you do not use :ref:`lambdas ` for parameters; for - example, you can now pass link extractors in :attr:`Request.cb_kwargs - ` or - :attr:`Request.meta ` when :ref:`persisting + example, you can now pass link extractors in :attr:`.Request.cb_kwargs` + or :attr:`.Request.meta` when :ref:`persisting scheduled requests ` (:issue:`4554`) * Upgraded the :ref:`pickle protocol ` that Scrapy uses @@ -2922,11 +2919,11 @@ Bug fixes * :class:`~scrapy.downloadermiddlewares.cookies.CookiesMiddleware` no longer discards cookies defined in :attr:`Request.headers - ` (:issue:`1992`, :issue:`2400`) + ` (:issue:`1992`, :issue:`2400`) * :class:`~scrapy.downloadermiddlewares.cookies.CookiesMiddleware` no longer re-encodes cookies defined as :class:`bytes` in the ``cookies`` parameter - of the ``__init__`` method of :class:`~scrapy.http.Request` + of the ``__init__`` method of :class:`~scrapy.Request` (:issue:`2400`, :issue:`3575`) * When :setting:`FEEDS` defines multiple URIs, :setting:`FEED_STORE_EMPTY` is @@ -2935,7 +2932,7 @@ Bug fixes * :class:`~scrapy.spiders.Spider` callbacks defined using :doc:`coroutine syntax ` no longer need to return an iterable, and may - instead return a :class:`~scrapy.http.Request` object, an + instead return a :class:`~scrapy.Request` object, an :ref:`item `, or ``None`` (:issue:`4609`) * The :command:`startproject` command now ensures that the generated project @@ -2976,8 +2973,8 @@ Documentation :issue:`4587`) * The display-on-hover behavior of internal documentation references now also - covers links to :ref:`commands `, :attr:`Request.meta - ` keys, :ref:`settings ` and + covers links to :ref:`commands `, :attr:`.Request.meta` + keys, :ref:`settings ` and :ref:`signals ` (:issue:`4495`, :issue:`4563`) * It is again possible to download the documentation for offline reading @@ -3262,7 +3259,7 @@ Deprecation removals ~~~~~~~~~~~~~~~~~~~~ * The :ref:`Scrapy shell ` no longer provides a `sel` proxy - object, use :meth:`response.selector ` + object, use :meth:`response.selector ` instead (:issue:`4347`) * LevelDB support has been removed (:issue:`4112`) @@ -3332,10 +3329,10 @@ New features * The new :attr:`Response.cb_kwargs ` attribute serves as a shortcut for :attr:`Response.request.cb_kwargs - ` (:issue:`4331`) + ` (:issue:`4331`) * :meth:`Response.follow ` now supports a - ``flags`` parameter, for consistency with :class:`~scrapy.http.Request` + ``flags`` parameter, for consistency with :class:`~scrapy.Request` (:issue:`4277`, :issue:`4279`) * :ref:`Item loader processors ` can now be @@ -3344,7 +3341,7 @@ New features * :class:`~scrapy.spiders.Rule` now accepts an ``errback`` parameter (:issue:`4000`) -* :class:`~scrapy.http.Request` no longer requires a ``callback`` parameter +* :class:`~scrapy.Request` no longer requires a ``callback`` parameter when an ``errback`` parameter is specified (:issue:`3586`, :issue:`4008`) * :class:`~scrapy.logformatter.LogFormatter` now supports some additional @@ -3416,7 +3413,7 @@ Bug fixes * Redirects to URLs starting with 3 slashes (``///``) are now supported (:issue:`4032`, :issue:`4042`) -* :class:`~scrapy.http.Request` no longer accepts strings as ``url`` simply +* :class:`~scrapy.Request` no longer accepts strings as ``url`` simply because they have a colon (:issue:`2552`, :issue:`4094`) * The correct encoding is now used for attach names in @@ -3462,7 +3459,7 @@ Documentation using :class:`~scrapy.crawler.CrawlerProcess` (:issue:`2149`, :issue:`2352`, :issue:`3146`, :issue:`3960`) -* Clarified the requirements for :class:`~scrapy.http.Request` objects +* Clarified the requirements for :class:`~scrapy.Request` objects :ref:`when using persistence ` (:issue:`4124`, :issue:`4139`) @@ -3731,17 +3728,17 @@ Scrapy 1.8.2 (2022-03-01) **Security bug fixes:** -- When a :class:`~scrapy.http.Request` object with cookies defined gets a - redirect response causing a new :class:`~scrapy.http.Request` object to be +- When a :class:`~scrapy.Request` object with cookies defined gets a + redirect response causing a new :class:`~scrapy.Request` object to be scheduled, the cookies defined in the original - :class:`~scrapy.http.Request` object are no longer copied into the new - :class:`~scrapy.http.Request` object. + :class:`~scrapy.Request` object are no longer copied into the new + :class:`~scrapy.Request` object. If you manually set the ``Cookie`` header on a - :class:`~scrapy.http.Request` object and the domain name of the redirect + :class:`~scrapy.Request` object and the domain name of the redirect URL is not an exact match for the domain of the URL of the original - :class:`~scrapy.http.Request` object, your ``Cookie`` header is now dropped - from the new :class:`~scrapy.http.Request` object. + :class:`~scrapy.Request` object, your ``Cookie`` header is now dropped + from the new :class:`~scrapy.Request` object. The old behavior could be exploited by an attacker to gain access to your cookies. Please, see the `cjvr-mfj7-j4j8 security advisory`_ for more @@ -3754,10 +3751,10 @@ Scrapy 1.8.2 (2022-03-01) ``example.com`` and any subdomain) by defining the shared domain suffix (e.g. ``example.com``) as the cookie domain when defining your cookies. See the documentation of the - :class:`~scrapy.http.Request` class for more information. + :class:`~scrapy.Request` class for more information. - When the domain of a cookie, either received in the ``Set-Cookie`` header - of a response or defined in a :class:`~scrapy.http.Request` object, is set + of a response or defined in a :class:`~scrapy.Request` object, is set to a `public suffix `_, the cookie is now ignored unless the cookie domain is the same as the request domain. @@ -3815,7 +3812,7 @@ Highlights: * Dropped Python 3.4 support and updated minimum requirements; made Python 3.8 support official -* New :meth:`Request.from_curl ` class method +* New :meth:`.Request.from_curl` class method * New :setting:`ROBOTSTXT_PARSER` and :setting:`ROBOTSTXT_USER_AGENT` settings * New :setting:`DOWNLOADER_CLIENT_TLS_CIPHERS` and :setting:`DOWNLOADER_CLIENT_TLS_VERBOSE_LOGGING` settings @@ -3869,7 +3866,7 @@ See also :ref:`1.8-deprecation-removals` below. New features ~~~~~~~~~~~~ -* A new :meth:`Request.from_curl ` class +* A new :meth:`Request.from_curl ` class method allows :ref:`creating a request from a cURL command ` (:issue:`2985`, :issue:`3862`) @@ -3898,9 +3895,8 @@ New features ``True`` to enable debug-level messages about TLS connection parameters after establishing HTTPS connections (:issue:`2111`, :issue:`3450`) -* Callbacks that receive keyword arguments - (see :attr:`Request.cb_kwargs `) can now be - tested using the new :class:`@cb_kwargs +* Callbacks that receive keyword arguments (see :attr:`.Request.cb_kwargs`) + can now be tested using the new :class:`@cb_kwargs ` :ref:`spider contract ` (:issue:`3985`, :issue:`3988`) @@ -4089,7 +4085,7 @@ Backward-incompatible changes * Non-default values for the :setting:`SCHEDULER_PRIORITY_QUEUE` setting may stop working. Scheduler priority queue classes now need to handle - :class:`~scrapy.http.Request` objects instead of arbitrary Python data + :class:`~scrapy.Request` objects instead of arbitrary Python data structures. * An additional ``crawler`` parameter has been added to the ``__init__`` @@ -4111,7 +4107,7 @@ New features scheduling improvement on crawls targeting multiple web domains, at the cost of no :setting:`CONCURRENT_REQUESTS_PER_IP` support (:issue:`3520`) -* A new :attr:`Request.cb_kwargs ` attribute +* A new :attr:`.Request.cb_kwargs` attribute provides a cleaner way to pass keyword arguments to callback methods (:issue:`1138`, :issue:`3563`) @@ -4192,7 +4188,7 @@ Bug fixes * Requests with private callbacks are now correctly unserialized from disk (:issue:`3790`) -* :meth:`FormRequest.from_response() ` +* :meth:`.FormRequest.from_response` now handles invalid methods like major web browsers (:issue:`3777`, :issue:`3794`) @@ -4272,13 +4268,13 @@ The following deprecated APIs have been removed (:issue:`3578`): * From both ``scrapy.selector`` and ``scrapy.selector.lxmlsel``: - * ``HtmlXPathSelector`` (use :class:`~scrapy.selector.Selector`) + * ``HtmlXPathSelector`` (use :class:`~scrapy.Selector`) - * ``XmlXPathSelector`` (use :class:`~scrapy.selector.Selector`) + * ``XmlXPathSelector`` (use :class:`~scrapy.Selector`) - * ``XPathSelector`` (use :class:`~scrapy.selector.Selector`) + * ``XPathSelector`` (use :class:`~scrapy.Selector`) - * ``XPathSelectorList`` (use :class:`~scrapy.selector.Selector`) + * ``XPathSelectorList`` (use :class:`~scrapy.Selector`) * From ``scrapy.selector.csstranslator``: @@ -4288,7 +4284,7 @@ The following deprecated APIs have been removed (:issue:`3578`): * ``ScrapyXPathExpr`` (use parsel.csstranslator.XPathExpr_) -* From :class:`~scrapy.selector.Selector`: +* From :class:`~scrapy.Selector`: * ``_root`` (both the ``__init__`` method argument and the object property, use ``root``) @@ -4818,7 +4814,7 @@ New Features (:issue:`2535`) - New :ref:`response.follow ` shortcut for creating requests (:issue:`1940`) -- Added ``flags`` argument and attribute to :class:`Request ` +- Added ``flags`` argument and attribute to :class:`~scrapy.Request` objects (:issue:`2047`) - Support Anonymous FTP (:issue:`2342`) - Added ``retry/count``, ``retry/max_reached`` and ``retry/reason_count/`` @@ -4860,7 +4856,7 @@ Bug fixes - LinkExtractor now strips leading and trailing whitespaces from attributes (:issue:`2547`, fixes :issue:`1614`) - Properly handle whitespaces in action attribute in - :class:`~scrapy.http.FormRequest` (:issue:`2548`) + :class:`~scrapy.FormRequest` (:issue:`2548`) - Buffer CONNECT response bytes from proxy until all HTTP headers are received (:issue:`2495`, fixes :issue:`2491`) - FTP downloader now works on Python 3, provided you use Twisted>=17.1 @@ -4902,8 +4898,7 @@ Documentation ~~~~~~~~~~~~~ - Binary mode is required for exporters (:issue:`2564`, fixes :issue:`2553`) -- Mention issue with :meth:`FormRequest.from_response - ` due to bug in lxml (:issue:`2572`) +- Mention issue with :meth:`.FormRequest.from_response` due to bug in lxml (:issue:`2572`) - Use single quotes uniformly in templates (:issue:`2596`) - Document :reqmeta:`ftp_user` and :reqmeta:`ftp_password` meta keys (:issue:`2587`) - Removed section on deprecated ``contrib/`` (:issue:`2636`) @@ -5442,7 +5437,7 @@ Bugfixes - Support empty password for http_proxy config (:issue:`1274`). - Interpret ``application/x-json`` as ``TextResponse`` (:issue:`1333`). - Support link rel attribute with multiple values (:issue:`1201`). -- Fixed ``scrapy.http.FormRequest.from_response`` when there is a ```` +- Fixed ``scrapy.FormRequest.from_response`` when there is a ```` tag (:issue:`1564`). - Fixed :setting:`TEMPLATES_DIR` handling (:issue:`1575`). - Various ``FormRequest`` fixes (:issue:`1595`, :issue:`1596`, :issue:`1597`). @@ -6369,7 +6364,7 @@ Scrapy 0.18.0 (released 2013-08-09) - Moved persistent (on disk) queues to a separate project (queuelib_) which Scrapy now depends on - Add Scrapy commands using external libraries (:issue:`260`) - Added ``--pdb`` option to ``scrapy`` command line tool -- Added :meth:`XPathSelector.remove_namespaces ` which allows to remove all namespaces from XML documents for convenience (to work with namespace-less XPaths). Documented in :ref:`topics-selectors`. +- Added :meth:`XPathSelector.remove_namespaces ` which allows to remove all namespaces from XML documents for convenience (to work with namespace-less XPaths). Documented in :ref:`topics-selectors`. - Several improvements to spider contracts - New default middleware named MetaRefreshMiddleware that handles meta-refresh html tag redirections, - MetaRefreshMiddleware and RedirectMiddleware have different priorities to address #62 diff --git a/docs/topics/downloader-middleware.rst b/docs/topics/downloader-middleware.rst index 11a3fcb94..af7885a45 100644 --- a/docs/topics/downloader-middleware.rst +++ b/docs/topics/downloader-middleware.rst @@ -80,7 +80,7 @@ object gives you access, for example, to the :ref:`settings `. middleware. :meth:`process_request` should either: return ``None``, return a - :class:`~scrapy.Response` object, return a :class:`~scrapy.http.Request` + :class:`~scrapy.http.Response` object, return a :class:`~scrapy.Request` object, or raise :exc:`~scrapy.exceptions.IgnoreRequest`. If it returns ``None``, Scrapy will continue processing this request, executing all diff --git a/docs/topics/dynamic-content.rst b/docs/topics/dynamic-content.rst index 75d980835..801f6d06d 100644 --- a/docs/topics/dynamic-content.rst +++ b/docs/topics/dynamic-content.rst @@ -117,7 +117,8 @@ data from it depends on the type of response: - If the response is HTML, XML or JSON, use :ref:`selectors ` as usual. -- If the response is JSON, use :func:`response.json()` to load the desired data: +- If the response is JSON, use :func:`response.json() + ` to load the desired data: .. code-block:: python @@ -143,7 +144,7 @@ data from it depends on the type of response: - If the response is an image or another format based on images (e.g. PDF), read the response as bytes from - :attr:`response.body ` and use an OCR + :attr:`response.body ` and use an OCR solution to extract the desired data as text. For example, you can use pytesseract_. To read a table from a PDF, diff --git a/docs/topics/exceptions.rst b/docs/topics/exceptions.rst index ea64edbe6..0b572ff95 100644 --- a/docs/topics/exceptions.rst +++ b/docs/topics/exceptions.rst @@ -105,7 +105,7 @@ response: In both cases, the response could have its body truncated: the body contains all bytes received up until the exception is raised, including the bytes received in the signal handler that raises the exception. Also, the response -object is marked with ``"download_stopped"`` in its :attr:`Response.flags` +object is marked with ``"download_stopped"`` in its :attr:`~scrapy.http.Response.flags` attribute. .. note:: ``fail`` is a keyword-only parameter, i.e. raising diff --git a/docs/topics/request-response.rst b/docs/topics/request-response.rst index 710e2e131..1bb1a10a4 100644 --- a/docs/topics/request-response.rst +++ b/docs/topics/request-response.rst @@ -7,15 +7,15 @@ Requests and Responses .. module:: scrapy.http :synopsis: Request and Response classes -Scrapy uses :class:`Request` and :class:`Response` objects for crawling web +Scrapy uses :class:`~scrapy.Request` and :class:`Response` objects for crawling web sites. -Typically, :class:`Request` objects are generated in the spiders and pass +Typically, :class:`~scrapy.Request` objects are generated in the spiders and pass across the system until they reach the Downloader, which executes the request and returns a :class:`Response` object which travels back to the spider that issued the request. -Both :class:`Request` and :class:`Response` classes have subclasses which add +Both :class:`~scrapy.Request` and :class:`Response` classes have subclasses which add functionality not required in the base classes. These are described below in :ref:`topics-request-response-ref-request-subclasses` and :ref:`topics-request-response-ref-response-subclasses`. @@ -24,7 +24,7 @@ below in :ref:`topics-request-response-ref-request-subclasses` and Request objects =============== -.. autoclass:: Request +.. autoclass:: scrapy.Request :param url: the URL of this request @@ -52,7 +52,7 @@ Request objects :param method: the HTTP method of this request. Defaults to ``'GET'``. :type method: str - :param meta: the initial values for the :attr:`Request.meta` attribute. If + :param meta: the initial values for the :attr:`.Request.meta` attribute. If given, the dict passed in this parameter will be shallow copied. :type meta: dict @@ -67,10 +67,10 @@ Request objects (for single valued headers) or lists (for multi-valued headers). If ``None`` is passed as value, the HTTP header will not be sent at all. - .. caution:: Cookies set via the ``Cookie`` header are not considered by the - :ref:`cookies-mw`. If you need to set cookies for a request, use the - :class:`Request.cookies ` parameter. This is a known - current limitation that is being worked on. + .. caution:: Cookies set via the ``Cookie`` header are not considered by the + :ref:`cookies-mw`. If you need to set cookies for a request, use the + ``cookies`` argument. This is a known current limitation that is being + worked on. :type headers: dict @@ -124,7 +124,7 @@ Request objects .. caution:: Cookies set via the ``Cookie`` header are not considered by the :ref:`cookies-mw`. If you need to set cookies for a request, use the - :class:`Request.cookies ` parameter. This is a known + :class:`scrapy.Request.cookies ` parameter. This is a known current limitation that is being worked on. .. versionadded:: 2.6.0 @@ -172,7 +172,7 @@ Request objects A string containing the URL of this request. Keep in mind that this attribute contains the escaped URL, so it can differ from the URL passed in - the ``__init__`` method. + the ``__init__()`` method. This attribute is read-only. To change the URL of a Request use :meth:`replace`. @@ -184,7 +184,8 @@ Request objects .. attribute:: Request.headers - A dictionary-like object which contains the request headers. + A dictionary-like (:class:`scrapy.http.headers.Headers`) object which contains + the request headers. .. attribute:: Request.body @@ -240,8 +241,8 @@ Request objects A dictionary that contains arbitrary metadata for this request. Its contents will be passed to the Request's callback as keyword arguments. It is empty - for new Requests, which means by default callbacks only get a :class:`Response` - object as argument. + for new Requests, which means by default callbacks only get a + :class:`~scrapy.http.Response` object as argument. This dict is :doc:`shallow copied ` when the request is cloned using the ``copy()`` or ``replace()`` methods, and can also be @@ -262,7 +263,7 @@ Request objects Return a Request object with the same members, except for those members given new values by whichever keyword arguments are specified. The - :attr:`Request.cb_kwargs` and :attr:`Request.meta` attributes are shallow + :attr:`~scrapy.Request.cb_kwargs` and :attr:`~scrapy.Request.meta` attributes are shallow copied by default (unless new values are given as arguments). See also :ref:`topics-request-response-ref-request-callback-arguments`. @@ -305,7 +306,7 @@ Example: In some cases you may be interested in passing arguments to those callback functions so you can receive the arguments later, in the second callback. The following example shows how to achieve this by using the -:attr:`Request.cb_kwargs` attribute: +:attr:`.Request.cb_kwargs` attribute: .. code-block:: python @@ -326,10 +327,10 @@ The following example shows how to achieve this by using the foo=foo, ) -.. caution:: :attr:`Request.cb_kwargs` was introduced in version ``1.7``. - Prior to that, using :attr:`Request.meta` was recommended for passing - information around callbacks. After ``1.7``, :attr:`Request.cb_kwargs` - became the preferred way for handling user information, leaving :attr:`Request.meta` +.. caution:: :attr:`.Request.cb_kwargs` was introduced in version ``1.7``. + Prior to that, using :attr:`.Request.meta` was recommended for passing + information around callbacks. After ``1.7``, :attr:`.Request.cb_kwargs` + became the preferred way for handling user information, leaving :attr:`.Request.meta` for communication with components like middlewares and extensions. .. _topics-request-response-ref-errbacks: @@ -441,7 +442,7 @@ Request fingerprints There are some aspects of scraping, such as filtering out duplicate requests (see :setting:`DUPEFILTER_CLASS`) or caching responses (see :setting:`HTTPCACHE_POLICY`), where you need the ability to generate a short, -unique identifier from a :class:`~scrapy.http.Request` object: a request +unique identifier from a :class:`~scrapy.Request` object: a request fingerprint. You often do not need to worry about request fingerprints, the default request @@ -486,7 +487,7 @@ A request fingerprinter is a class that must implement the following method: See also :ref:`request-fingerprint-restrictions`. :param request: request to fingerprint - :type request: scrapy.http.Request + :type request: scrapy.Request Additionally, it may also implement the following method: @@ -566,7 +567,7 @@ URL canonicalization or taking the request method or body into account: If you need to be able to override the request fingerprinting for arbitrary requests from your spider callbacks, you may implement a request fingerprinter -that reads fingerprints from :attr:`request.meta ` +that reads fingerprints from :attr:`request.meta ` when available, and then falls back to :func:`scrapy.utils.request.fingerprint`. For example: @@ -581,10 +582,8 @@ when available, and then falls back to return request.meta["fingerprint"] return fingerprint(request) -If you need to reproduce the same fingerprinting algorithm as Scrapy 2.6 -without using the deprecated ``'2.6'`` value of the -:setting:`REQUEST_FINGERPRINTER_IMPLEMENTATION` setting, use the following -request fingerprinter: +If you need to reproduce the same fingerprinting algorithm as Scrapy 2.6, use +the following request fingerprinter: .. code-block:: python @@ -628,7 +627,7 @@ The following built-in Scrapy components have such restrictions: :setting:`HTTPCACHE_DIR` also apply. Inside :setting:`HTTPCACHE_DIR`, the following directory structure is created: - - :attr:`Spider.name ` + - :attr:`.Spider.name` - first byte of a request fingerprint as hexadecimal @@ -656,7 +655,7 @@ The following built-in Scrapy components have such restrictions: Request.meta special keys ========================= -The :attr:`Request.meta` attribute can contain any arbitrary data, but there +The :attr:`.Request.meta` attribute can contain any arbitrary data, but there are some special keys recognized by Scrapy and its built-in extensions. Those are: @@ -780,24 +779,25 @@ call their callback instead, like in this example, pass ``fail=False`` to the Request subclasses ================== -Here is the list of built-in :class:`Request` subclasses. You can also subclass +Here is the list of built-in :class:`~scrapy.Request` subclasses. You can also subclass it to implement your own custom functionality. FormRequest objects ------------------- -The FormRequest class extends the base :class:`Request` with functionality for +The FormRequest class extends the base :class:`~scrapy.Request` with functionality for dealing with HTML forms. It uses `lxml.html forms`_ to pre-populate form fields with form data from :class:`Response` objects. .. _lxml.html forms: https://lxml.de/lxmlhtml.html#forms -.. class:: scrapy.http.request.form.FormRequest -.. class:: scrapy.http.FormRequest -.. class:: scrapy.FormRequest(url, [formdata, ...]) +.. currentmodule:: None - The :class:`FormRequest` class adds a new keyword parameter to the ``__init__`` method. The - remaining arguments are the same as for the :class:`Request` class and are +.. class:: scrapy.FormRequest(url, [formdata, ...]) + :canonical: scrapy.http.request.form.FormRequest + + The :class:`~scrapy.FormRequest` class adds a new keyword parameter to the ``__init__()`` method. The + remaining arguments are the same as for the :class:`~scrapy.Request` class and are not documented here. :param formdata: is a dictionary (or iterable of (key, value) tuples) @@ -805,12 +805,12 @@ fields with form data from :class:`Response` objects. body of the request. :type formdata: dict or collections.abc.Iterable - The :class:`FormRequest` objects support the following class method in - addition to the standard :class:`Request` methods: + The :class:`~scrapy.FormRequest` objects support the following class method in + addition to the standard :class:`~scrapy.Request` methods: - .. classmethod:: FormRequest.from_response(response, [formname=None, formid=None, formnumber=0, formdata=None, formxpath=None, formcss=None, clickdata=None, dont_click=False, ...]) + .. classmethod:: from_response(response, [formname=None, formid=None, formnumber=0, formdata=None, formxpath=None, formcss=None, clickdata=None, dont_click=False, ...]) - Returns a new :class:`FormRequest` object with its form field values + Returns a new :class:`~scrapy.FormRequest` object with its form field values pre-populated with those found in the HTML ``
`` element contained in the given response. For an example see :ref:`topics-request-response-ref-request-userlogin`. @@ -832,7 +832,7 @@ fields with form data from :class:`Response` objects. :param response: the response containing a HTML form which will be used to pre-populate the form fields - :type response: :class:`Response` object + :type response: :class:`~scrapy.http.Response` object :param formname: if given, the form with name attribute set to this value will be used. :type formname: str @@ -869,7 +869,9 @@ fields with form data from :class:`Response` objects. :type dont_click: bool The other parameters of this class method are passed directly to the - :class:`FormRequest` ``__init__`` method. + :class:`~scrapy.FormRequest` ``__init__()`` method. + +.. currentmodule:: scrapy.http Request usage examples ---------------------- @@ -878,7 +880,7 @@ Using FormRequest to send data via HTTP POST ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ If you want to simulate a HTML Form POST in your spider and send a couple of -key-value fields, you can return a :class:`FormRequest` object (from your +key-value fields, you can return a :class:`~scrapy.FormRequest` object (from your spider) like this: .. skip: next @@ -901,7 +903,7 @@ It is usual for web sites to provide pre-populated form fields through ```` elements, such as session related data or authentication tokens (for login pages). When scraping, you'll want these fields to be automatically pre-populated and only override a couple of them, such as the -user name and password. You can use the :meth:`FormRequest.from_response` +user name and password. You can use the :meth:`.FormRequest.from_response()` method for this job. Here's an example spider which uses it: .. code-block:: python @@ -936,21 +938,22 @@ method for this job. Here's an example spider which uses it: JsonRequest ----------- -The JsonRequest class extends the base :class:`Request` class with functionality for +The JsonRequest class extends the base :class:`~scrapy.Request` class with functionality for dealing with JSON requests. .. class:: JsonRequest(url, [... data, dumps_kwargs]) - The :class:`JsonRequest` class adds two new keyword parameters to the ``__init__`` method. The - remaining arguments are the same as for the :class:`Request` class and are + The :class:`JsonRequest` class adds two new keyword parameters to the ``__init__()`` method. The + remaining arguments are the same as for the :class:`~scrapy.Request` class and are not documented here. Using the :class:`JsonRequest` will set the ``Content-Type`` header to ``application/json`` and ``Accept`` header to ``application/json, text/javascript, */*; q=0.01`` :param data: is any JSON serializable object that needs to be JSON encoded and assigned to body. - if :attr:`Request.body` argument is provided this parameter will be ignored. - if :attr:`Request.body` argument is not provided and data argument is provided :attr:`Request.method` will be + If the :attr:`~scrapy.Request.body` argument is provided this parameter will be ignored. + If the :attr:`~scrapy.Request.body` argument is not provided and the + ``data`` argument is provided the :attr:`~scrapy.Request.method` will be set to ``'POST'`` automatically. :type data: object @@ -1002,7 +1005,7 @@ Response objects :type flags: list :param request: the initial value of the :attr:`Response.request` attribute. - This represents the :class:`Request` that generated this response. + This represents the :class:`~scrapy.Request` that generated this response. :type request: scrapy.Request :param certificate: an object representing the server's SSL certificate. @@ -1038,11 +1041,12 @@ Response objects .. attribute:: Response.headers - A dictionary-like object which contains the response headers. Values can - be accessed using :meth:`get` to return the first header value with the - specified name or :meth:`getlist` to return all header values with the - specified name. For example, this call will give you all cookies in the - headers:: + A dictionary-like (:class:`scrapy.http.headers.Headers`) object which contains + the response headers. Values can be accessed using + :meth:`~scrapy.http.headers.Headers.get` to return the first header value with + the specified name or :meth:`~scrapy.http.headers.Headers.getlist` to return + all header values with the specified name. For example, this call will give you + all cookies in the headers:: response.headers.getlist('Set-Cookie') @@ -1058,7 +1062,7 @@ Response objects .. attribute:: Response.request - The :class:`Request` object that generated this response. This attribute is + The :class:`~scrapy.Request` object that generated this response. This attribute is assigned in the Scrapy engine, after the response and the request have passed through all :ref:`Downloader Middlewares `. In particular, this means that: @@ -1077,34 +1081,33 @@ Response objects .. attribute:: Response.meta - A shortcut to the :attr:`Request.meta` attribute of the + A shortcut to the :attr:`~scrapy.Request.meta` attribute of the :attr:`Response.request` object (i.e. ``self.request.meta``). Unlike the :attr:`Response.request` attribute, the :attr:`Response.meta` attribute is propagated along redirects and retries, so you will get - the original :attr:`Request.meta` sent from your spider. + the original :attr:`.Request.meta` sent from your spider. - .. seealso:: :attr:`Request.meta` attribute + .. seealso:: :attr:`.Request.meta` attribute .. attribute:: Response.cb_kwargs .. versionadded:: 2.0 - A shortcut to the :attr:`Request.cb_kwargs` attribute of the + A shortcut to the :attr:`~scrapy.Request.cb_kwargs` attribute of the :attr:`Response.request` object (i.e. ``self.request.cb_kwargs``). Unlike the :attr:`Response.request` attribute, the :attr:`Response.cb_kwargs` attribute is propagated along redirects and - retries, so you will get the original :attr:`Request.cb_kwargs` sent - from your spider. + retries, so you will get the original :attr:`.Request.cb_kwargs` sent from your spider. - .. seealso:: :attr:`Request.cb_kwargs` attribute + .. seealso:: :attr:`.Request.cb_kwargs` attribute .. attribute:: Response.flags A list that contains flags for this response. Flags are labels used for tagging Responses. For example: ``'cached'``, ``'redirected``', etc. And - they're shown on the string representation of the Response (`__str__` + they're shown on the string representation of the Response (``__str__()`` method) which is used by the engine for logging. .. attribute:: Response.certificate @@ -1181,7 +1184,7 @@ TextResponse objects :class:`Response` class, which is meant to be used only for binary data, such as images, sounds or any media file. - :class:`TextResponse` objects support a new ``__init__`` method argument, in + :class:`TextResponse` objects support a new ``__init__()`` method argument, in addition to the base :class:`Response` objects. The remaining functionality is the same as for the :class:`Response` class and is not documented here. @@ -1219,7 +1222,7 @@ TextResponse objects A string with the encoding of this response. The encoding is resolved by trying the following mechanisms, in order: - 1. the encoding passed in the ``__init__`` method ``encoding`` argument + 1. the encoding passed in the ``__init__()`` method ``encoding`` argument 2. the encoding declared in the Content-Type HTTP header. If this encoding is not valid (i.e. unknown), it is ignored and the next @@ -1273,7 +1276,7 @@ TextResponse objects Constructs an absolute url by combining the Response's base url with a possible relative url. The base url shall be extracted from the - ```` tag, or just the Response's :attr:`url` if there is no such + ```` tag, or just :attr:`Response.url` if there is no such tag. diff --git a/docs/topics/selectors.rst b/docs/topics/selectors.rst index 202b0823a..b95e6eab3 100644 --- a/docs/topics/selectors.rst +++ b/docs/topics/selectors.rst @@ -777,7 +777,7 @@ Removing namespaces When dealing with scraping projects, it is often quite convenient to get rid of namespaces altogether and just work with element names, to write more simple/convenient XPaths. You can use the -:meth:`Selector.remove_namespaces` method for that. +:meth:`.Selector.remove_namespaces` method for that. Let's show an example that illustrates this with the Python Insider blog atom feed. @@ -814,7 +814,7 @@ doesn't work (because the Atom XML namespace is obfuscating those nodes): >>> response.xpath("//link") [] -But once we call the :meth:`Selector.remove_namespaces` method, all +But once we call the :meth:`.Selector.remove_namespaces` method, all nodes can be accessed directly by their names: .. code-block:: pycon @@ -1046,7 +1046,7 @@ Built-in Selectors reference Selector objects ---------------- -.. autoclass:: Selector +.. autoclass:: scrapy.Selector .. automethod:: xpath @@ -1126,8 +1126,8 @@ Examples Selector examples on HTML response ---------------------------------- -Here are some :class:`Selector` examples to illustrate several concepts. -In all cases, we assume there is already a :class:`Selector` instantiated with +Here are some :class:`~scrapy.Selector` examples to illustrate several concepts. +In all cases, we assume there is already a :class:`~scrapy.Selector` instantiated with a :class:`~scrapy.http.HtmlResponse` object like this: .. code-block:: python @@ -1135,7 +1135,7 @@ a :class:`~scrapy.http.HtmlResponse` object like this: sel = Selector(html_response) 1. Select all ``

`` elements from an HTML response body, returning a list of - :class:`Selector` objects (i.e. a :class:`SelectorList` object): + :class:`~scrapy.Selector` objects (i.e. a :class:`SelectorList` object): .. code-block:: python @@ -1165,7 +1165,7 @@ Selector examples on XML response .. skip: start -Here are some examples to illustrate concepts for :class:`Selector` objects +Here are some examples to illustrate concepts for :class:`~scrapy.Selector` objects instantiated with an :class:`~scrapy.http.XmlResponse` object: .. code-block:: python @@ -1173,7 +1173,7 @@ instantiated with an :class:`~scrapy.http.XmlResponse` object: sel = Selector(xml_response) 1. Select all ```` elements from an XML response body, returning a list - of :class:`Selector` objects (i.e. a :class:`SelectorList` object): + of :class:`~scrapy.Selector` objects (i.e. a :class:`SelectorList` object): .. code-block:: python diff --git a/scrapy/core/scheduler.py b/scrapy/core/scheduler.py index fcc94879a..4bb143dfd 100644 --- a/scrapy/core/scheduler.py +++ b/scrapy/core/scheduler.py @@ -115,7 +115,7 @@ class BaseScheduler(metaclass=BaseSchedulerMeta): @abstractmethod def next_request(self) -> Request | None: """ - Return the next :class:`~scrapy.http.Request` to be processed, or ``None`` + Return the next :class:`~scrapy.Request` to be processed, or ``None`` to indicate that there are no requests to be considered ready at the moment. Returning ``None`` implies that no request from the scheduler will be sent @@ -263,7 +263,7 @@ class Scheduler(BaseScheduler): def next_request(self) -> Request | None: """ - Return a :class:`~scrapy.http.Request` object from the memory queue, + Return a :class:`~scrapy.Request` object from the memory queue, falling back to the disk queue if the memory queue is empty. Return ``None`` if there are no more enqueued requests. diff --git a/scrapy/http/request/__init__.py b/scrapy/http/request/__init__.py index 3d6cf4816..4eee5ffbb 100644 --- a/scrapy/http/request/__init__.py +++ b/scrapy/http/request/__init__.py @@ -59,7 +59,7 @@ RequestTypeVar = TypeVar("RequestTypeVar", bound="Request") def NO_CALLBACK(*args: Any, **kwargs: Any) -> NoReturn: """When assigned to the ``callback`` parameter of - :class:`~scrapy.http.Request`, it indicates that the request is not meant + :class:`~scrapy.Request`, it indicates that the request is not meant to have a spider callback at all. For example: @@ -83,7 +83,7 @@ def NO_CALLBACK(*args: Any, **kwargs: Any) -> NoReturn: class Request(object_ref): """Represents an HTTP request, which is usually generated in a Spider and - executed by the Downloader, thus generating a :class:`Response`. + executed by the Downloader, thus generating a :class:`~scrapy.http.Response`. """ attributes: tuple[str, ...] = ( @@ -103,9 +103,9 @@ class Request(object_ref): ) """A tuple of :class:`str` objects containing the name of all public attributes of the class that are also keyword parameters of the - ``__init__`` method. + ``__init__()`` method. - Currently used by :meth:`Request.replace`, :meth:`Request.to_dict` and + Currently used by :meth:`.Request.replace`, :meth:`.Request.to_dict` and :func:`~scrapy.utils.request.request_from_dict`. """ @@ -233,7 +233,7 @@ class Request(object_ref): finding unknown options call this method by passing ``ignore_unknown_options=False``. - .. caution:: Using :meth:`from_curl` from :class:`~scrapy.http.Request` + .. caution:: Using :meth:`from_curl` from :class:`~scrapy.Request` subclasses, such as :class:`~scrapy.http.JsonRequest`, or :class:`~scrapy.http.XmlRpcRequest`, as well as having :ref:`downloader middlewares ` @@ -244,7 +244,7 @@ class Request(object_ref): :class:`~scrapy.downloadermiddlewares.useragent.UserAgentMiddleware`, or :class:`~scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware`, - may modify the :class:`~scrapy.http.Request` object. + may modify the :class:`~scrapy.Request` object. To translate a cURL command into a Scrapy request, you may use `curl2scrapy `_. diff --git a/scrapy/http/response/__init__.py b/scrapy/http/response/__init__.py index 387805f57..b84110b29 100644 --- a/scrapy/http/response/__init__.py +++ b/scrapy/http/response/__init__.py @@ -51,7 +51,7 @@ class Response(object_ref): ) """A tuple of :class:`str` objects containing the name of all public attributes of the class that are also keyword parameters of the - ``__init__`` method. + ``__init__()`` method. Currently used by :meth:`Response.replace`. """ @@ -199,8 +199,8 @@ class Response(object_ref): ) -> Request: """ Return a :class:`~.Request` instance to follow a link ``url``. - It accepts the same arguments as ``Request.__init__`` method, - but ``url`` can be a relative URL or a ``scrapy.link.Link`` object, + It accepts the same arguments as ``Request.__init__()`` method, + but ``url`` can be a relative URL or a :class:`~scrapy.link.Link` object, not only an absolute URL. :class:`~.TextResponse` provides a :meth:`~.TextResponse.follow` @@ -254,7 +254,7 @@ class Response(object_ref): .. versionadded:: 2.0 Return an iterable of :class:`~.Request` instances to follow all links - in ``urls``. It accepts the same arguments as ``Request.__init__`` method, + in ``urls``. It accepts the same arguments as ``Request.__init__()`` method, but elements of ``urls`` can be relative URLs or :class:`~scrapy.link.Link` objects, not only absolute URLs. diff --git a/scrapy/http/response/text.py b/scrapy/http/response/text.py index 476f1754e..081223882 100644 --- a/scrapy/http/response/text.py +++ b/scrapy/http/response/text.py @@ -185,15 +185,15 @@ class TextResponse(Response): ) -> Request: """ Return a :class:`~.Request` instance to follow a link ``url``. - It accepts the same arguments as ``Request.__init__`` method, + It accepts the same arguments as ``Request.__init__()`` method, but ``url`` can be not only an absolute URL, but also * a relative URL * a :class:`~scrapy.link.Link` object, e.g. the result of :ref:`topics-link-extractors` - * a :class:`~scrapy.selector.Selector` object for a ```` or ```` element, e.g. + * a :class:`~scrapy.Selector` object for a ```` or ```` element, e.g. ``response.css('a.my_link')[0]`` - * an attribute :class:`~scrapy.selector.Selector` (not SelectorList), e.g. + * an attribute :class:`~scrapy.Selector` (not SelectorList), e.g. ``response.css('a::attr(href)')[0]`` or ``response.xpath('//img/@src')[0]`` @@ -241,20 +241,20 @@ class TextResponse(Response): """ A generator that produces :class:`~.Request` instances to follow all links in ``urls``. It accepts the same arguments as the :class:`~.Request`'s - ``__init__`` method, except that each ``urls`` element does not need to be + ``__init__()`` method, except that each ``urls`` element does not need to be an absolute URL, it can be any of the following: * a relative URL * a :class:`~scrapy.link.Link` object, e.g. the result of :ref:`topics-link-extractors` - * a :class:`~scrapy.selector.Selector` object for a ```` or ```` element, e.g. + * a :class:`~scrapy.Selector` object for a ```` or ```` element, e.g. ``response.css('a.my_link')[0]`` - * an attribute :class:`~scrapy.selector.Selector` (not SelectorList), e.g. + * an attribute :class:`~scrapy.Selector` (not SelectorList), e.g. ``response.css('a::attr(href)')[0]`` or ``response.xpath('//img/@src')[0]`` In addition, ``css`` and ``xpath`` arguments are accepted to perform the link extraction - within the ``follow_all`` method (only one of ``urls``, ``css`` and ``xpath`` is accepted). + within the ``follow_all()`` method (only one of ``urls``, ``css`` and ``xpath`` is accepted). Note that when passing a ``SelectorList`` as argument for the ``urls`` parameter or using the ``css`` or ``xpath`` parameters, this method will not produce requests for diff --git a/scrapy/loader/__init__.py b/scrapy/loader/__init__.py index d35720a45..2f5c0343b 100644 --- a/scrapy/loader/__init__.py +++ b/scrapy/loader/__init__.py @@ -32,7 +32,7 @@ class ItemLoader(itemloaders.ItemLoader): :param selector: The selector to extract data from, when using the :meth:`add_xpath`, :meth:`add_css`, :meth:`replace_xpath`, or :meth:`replace_css` method. - :type selector: :class:`~scrapy.selector.Selector` object + :type selector: :class:`~scrapy.Selector` object :param response: The response used to construct the selector using the :attr:`default_selector_class`, unless the selector argument is given, @@ -79,7 +79,7 @@ class ItemLoader(itemloaders.ItemLoader): .. attribute:: selector - The :class:`~scrapy.selector.Selector` object to extract data from. + The :class:`~scrapy.Selector` object to extract data from. It's either the selector given in the ``__init__`` method or one created from the response given in the ``__init__`` method using the :attr:`default_selector_class`. This attribute is meant to be diff --git a/scrapy/utils/request.py b/scrapy/utils/request.py index 7f2b178f5..9c1161968 100644 --- a/scrapy/utils/request.py +++ b/scrapy/utils/request.py @@ -1,6 +1,6 @@ """ This module provides some useful functions for working with -scrapy.http.Request objects +scrapy.Request objects """ from __future__ import annotations @@ -109,12 +109,10 @@ class RequestFingerprinter: It takes into account a canonical version (:func:`w3lib.url.canonicalize_url`) of :attr:`request.url - ` and the values of :attr:`request.method - ` and :attr:`request.body - `. It then generates an `SHA1 + ` and the values of :attr:`request.method + ` and :attr:`request.body + `. It then generates an `SHA1 `_ hash. - - .. seealso:: :setting:`REQUEST_FINGERPRINTER_IMPLEMENTATION`. """ @classmethod