diff --git a/.github/workflows/checks.yml b/.github/workflows/checks.yml index 6bdfcb5dc..80df9469d 100644 --- a/.github/workflows/checks.yml +++ b/.github/workflows/checks.yml @@ -8,10 +8,10 @@ jobs: fail-fast: false matrix: include: - - python-version: 3.9 + - python-version: "3.10" env: TOXENV: security - - python-version: 3.9 + - python-version: "3.10" env: TOXENV: flake8 # Pylint requires installing reppy, which does not support Python 3.9 @@ -20,10 +20,10 @@ jobs: env: TOXENV: pylint TOX_PIP_VERSION: 20.3.3 - - python-version: 3.9 + - python-version: 3.6 env: TOXENV: typing - - python-version: 3.8 # Keep in sync with .readthedocs.yml + - python-version: "3.10" # Keep in sync with .readthedocs.yml env: TOXENV: docs diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml index b48066ea4..44b682830 100644 --- a/.github/workflows/publish.yml +++ b/.github/workflows/publish.yml @@ -9,10 +9,10 @@ jobs: steps: - uses: actions/checkout@v2 - - name: Set up Python 3.9 + - name: Set up Python uses: actions/setup-python@v2 with: - python-version: 3.9 + python-version: "3.10" - name: Check Tag id: check-release-tag diff --git a/.github/workflows/tests-macos.yml b/.github/workflows/tests-macos.yml index 095ca1013..3aaf688c7 100644 --- a/.github/workflows/tests-macos.yml +++ b/.github/workflows/tests-macos.yml @@ -7,7 +7,7 @@ jobs: strategy: fail-fast: false matrix: - python-version: [3.6, 3.7, 3.8, 3.9] + python-version: ["3.6", "3.7", "3.8", "3.9", "3.10"] steps: - uses: actions/checkout@v2 diff --git a/.github/workflows/tests-ubuntu.yml b/.github/workflows/tests-ubuntu.yml index ef1c8362f..5ea50e644 100644 --- a/.github/workflows/tests-ubuntu.yml +++ b/.github/workflows/tests-ubuntu.yml @@ -17,6 +17,12 @@ jobs: - python-version: 3.9 env: TOXENV: py + - python-version: "3.10" + env: + TOXENV: py + - python-version: "3.10" + env: + TOXENV: asyncio - python-version: pypy3 env: TOXENV: pypy3 @@ -42,14 +48,6 @@ jobs: TOXENV: extra-deps TOX_PIP_VERSION: 20.3.3 - # 3.10-pre - - python-version: "3.10.0-beta.4" - env: - TOXENV: py - - python-version: "3.10.0-beta.4" - env: - TOXENV: asyncio - steps: - uses: actions/checkout@v2 diff --git a/.readthedocs.yml b/.readthedocs.yml index 80a1cd036..390be3749 100644 --- a/.readthedocs.yml +++ b/.readthedocs.yml @@ -5,12 +5,13 @@ sphinx: fail_on_warning: true build: - image: latest + os: ubuntu-20.04 + tools: + # For available versions, see: + # https://docs.readthedocs.io/en/stable/config-file/v2.html#build-tools-python + python: "3.10" # Keep in sync with .github/workflows/checks.yml python: - # For available versions, see: - # https://docs.readthedocs.io/en/stable/config-file/v2.html#build-image - version: 3.8 # Keep in sync with .github/workflows/checks.yml install: - requirements: docs/requirements.txt - path: . diff --git a/docs/intro/overview.rst b/docs/intro/overview.rst index dd80c7bd0..405bf845d 100644 --- a/docs/intro/overview.rst +++ b/docs/intro/overview.rst @@ -4,7 +4,7 @@ Scrapy at a glance ================== -Scrapy is an application framework for crawling web sites and extracting +Scrapy (/ˈskreɪpaɪ/) is an application framework for crawling web sites and extracting structured data which can be used for a wide range of useful applications, like data mining, information processing or historical archival. diff --git a/docs/intro/tutorial.rst b/docs/intro/tutorial.rst index 438f3d6df..ca5856881 100644 --- a/docs/intro/tutorial.rst +++ b/docs/intro/tutorial.rst @@ -277,9 +277,19 @@ As an alternative, you could've written: >>> response.css('title::text')[0].get() 'Quotes to Scrape' -However, using ``.get()`` directly on a :class:`~scrapy.selector.SelectorList` -instance avoids an ``IndexError`` and returns ``None`` when it doesn't -find any element matching the selection. +Accessing an index on a :class:`~scrapy.selector.SelectorList` instance will +raise an :exc:`IndexError` exception if there are no results:: + + >>> response.css('noelement')[0].get() + Traceback (most recent call last): + ... + IndexError: list index out of range + +You might want to use ``.get()`` directly on the +:class:`~scrapy.selector.SelectorList` instance instead, which returns ``None`` +if there are no results:: + +>>> response.css("noelement").get() There's a lesson here: for most scraping code, you want it to be resilient to errors due to things not being found on a page, so that even if some parts fail diff --git a/docs/news.rst b/docs/news.rst index 5e590f027..509366c17 100644 --- a/docs/news.rst +++ b/docs/news.rst @@ -1830,7 +1830,7 @@ New features * A new scheduler priority queue, ``scrapy.pqueues.DownloaderAwarePriorityQueue``, may be :ref:`enabled ` for a significant - scheduling improvement on crawls targetting multiple web domains, at the + 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 @@ -2868,7 +2868,7 @@ Bug fixes - Fix for selected callbacks when using ``CrawlSpider`` with :command:`scrapy parse ` (:issue:`2225`). - Fix for invalid JSON and XML files when spider yields no items (:issue:`872`). -- Implement ``flush()`` fpr ``StreamLogger`` avoiding a warning in logs (:issue:`2125`). +- Implement ``flush()`` for ``StreamLogger`` avoiding a warning in logs (:issue:`2125`). Refactoring ~~~~~~~~~~~ @@ -3731,7 +3731,7 @@ Scrapy 0.24.3 (2014-08-09) - adding some xpath tips to selectors docs (:commit:`2d103e0`) - fix tests to account for https://github.com/scrapy/w3lib/pull/23 (:commit:`f8d366a`) - get_func_args maximum recursion fix #728 (:commit:`81344ea`) -- Updated input/ouput processor example according to #560. (:commit:`f7c4ea8`) +- Updated input/output processor example according to #560. (:commit:`f7c4ea8`) - Fixed Python syntax in tutorial. (:commit:`db59ed9`) - Add test case for tunneling proxy (:commit:`f090260`) - Bugfix for leaking Proxy-Authorization header to remote host when using tunneling (:commit:`d8793af`) @@ -4393,7 +4393,7 @@ Scrapyd changes ~~~~~~~~~~~~~~~ - Scrapyd now uses one process per spider -- It stores one log file per spider run, and rotate them keeping the lastest 5 logs per spider (by default) +- It stores one log file per spider run, and rotate them keeping the latest 5 logs per spider (by default) - A minimal web ui was added, available at http://localhost:6800 by default - There is now a ``scrapy server`` command to start a Scrapyd server of the current project @@ -4429,7 +4429,7 @@ New features and improvements - Added two new methods to item pipeline open_spider(), close_spider() with deferred support (#195) - Support for overriding default request headers per spider (#181) - Replaced default Spider Manager with one with similar functionality but not depending on Twisted Plugins (#186) -- Splitted Debian package into two packages - the library and the service (#187) +- Split Debian package into two packages - the library and the service (#187) - Scrapy log refactoring (#188) - New extension for keeping persistent spider contexts among different runs (#203) - Added ``dont_redirect`` request.meta key for avoiding redirects (#233) diff --git a/docs/topics/asyncio.rst b/docs/topics/asyncio.rst index 2bf4f56b6..28241ae24 100644 --- a/docs/topics/asyncio.rst +++ b/docs/topics/asyncio.rst @@ -47,20 +47,14 @@ Awaiting on Deferreds When the asyncio reactor isn't installed, you can await on Deferreds in the coroutines directly. When it is installed, this is not possible anymore, due to specifics of the Scrapy coroutine integration (the coroutines are wrapped into -asyncio Futures, not into Deferreds directly), and you need to wrap them into +:class:`asyncio.Future` objects, not into +:class:`~twisted.internet.defer.Deferred` directly), and you need to wrap them into Futures. Scrapy provides two helpers for this: .. autofunction:: scrapy.utils.defer.deferred_to_future .. autofunction:: scrapy.utils.defer.maybe_deferred_to_future - -If you want to write universal code that works on any reactors, -you should use ``maybe_deferred_to_future`` on all Deferreds:: - - from scrapy.utils.defer import maybe_deferred_to_future - - class MySpider(Spider): - # ... - async def parse_with_deferred(self, response): - additional_response = await maybe_deferred_to_future(treq.get('https://additional.url')) - additional_data = await maybe_deferred_to_future(treq.content(additional_response)) - # ... use response and additional_data to yield items and requests +.. tip:: If you need to use these functions in code that aims to be compatible + with lower versions of Scrapy that do not provide these functions, + down to Scrapy 2.0 (earlier versions do not support + :mod:`asyncio`), you can copy the implementation of these functions + into your own code. diff --git a/docs/topics/coroutines.rst b/docs/topics/coroutines.rst index 067a97a55..c514fc00a 100644 --- a/docs/topics/coroutines.rst +++ b/docs/topics/coroutines.rst @@ -96,8 +96,8 @@ This means you can use many useful Python libraries providing such code:: :mod:`asyncio` loop and to use them you need to :doc:`enable asyncio support in Scrapy`. -.. note:: If you want to ``await`` on Deferreds, you may need to - :ref:`wrap them`. +.. note:: If you want to ``await`` on Deferreds while using the asyncio reactor, + you need to :ref:`wrap them`. Common use cases for asynchronous code include: diff --git a/docs/topics/exporters.rst b/docs/topics/exporters.rst index 8c30122b6..923336769 100644 --- a/docs/topics/exporters.rst +++ b/docs/topics/exporters.rst @@ -122,7 +122,7 @@ Example:: class ProductXmlExporter(XmlItemExporter): def serialize_field(self, field, name, value): - if field == 'price': + if name == 'price': return f'$ {str(value)}' return super().serialize_field(field, name, value) diff --git a/docs/topics/item-pipeline.rst b/docs/topics/item-pipeline.rst index 5351a2293..391751364 100644 --- a/docs/topics/item-pipeline.rst +++ b/docs/topics/item-pipeline.rst @@ -190,6 +190,8 @@ item. import scrapy from itemadapter import ItemAdapter + from scrapy.utils.defer import maybe_deferred_to_future + class ScreenshotPipeline: """Pipeline that uses Splash to render screenshot of @@ -202,7 +204,7 @@ item. encoded_item_url = quote(adapter["url"]) screenshot_url = self.SPLASH_URL.format(encoded_item_url) request = scrapy.Request(screenshot_url) - response = await spider.crawler.engine.download(request, spider) + response = await maybe_deferred_to_future(spider.crawler.engine.download(request, spider)) if response.status != 200: # Error happened, return item. diff --git a/docs/topics/loaders.rst b/docs/topics/loaders.rst index c0f534493..0d63700c8 100644 --- a/docs/topics/loaders.rst +++ b/docs/topics/loaders.rst @@ -56,7 +56,7 @@ chapter `:: l.add_xpath('name', '//div[@class="product_name"]') l.add_xpath('name', '//div[@class="product_title"]') l.add_xpath('price', '//p[@id="price"]') - l.add_css('stock', 'p#stock]') + l.add_css('stock', 'p#stock') l.add_value('last_updated', 'today') # you can also use literal values return l.load_item() diff --git a/docs/topics/logging.rst b/docs/topics/logging.rst index dda04dc4d..d593c74c6 100644 --- a/docs/topics/logging.rst +++ b/docs/topics/logging.rst @@ -143,6 +143,7 @@ Logging settings These settings can be used to configure the logging: * :setting:`LOG_FILE` +* :setting:`LOG_FILE_APPEND` * :setting:`LOG_ENABLED` * :setting:`LOG_ENCODING` * :setting:`LOG_LEVEL` @@ -155,7 +156,9 @@ The first couple of settings define a destination for log messages. If :setting:`LOG_FILE` is set, messages sent through the root logger will be redirected to a file named :setting:`LOG_FILE` with encoding :setting:`LOG_ENCODING`. If unset and :setting:`LOG_ENABLED` is ``True``, log -messages will be displayed on the standard error. Lastly, if +messages will be displayed on the standard error. If :setting:`LOG_FILE` is set +and :setting:`LOG_FILE_APPEND` is ``False``, the file will be overwritten +(discarding the output from previous runs, if any). Lastly, if :setting:`LOG_ENABLED` is ``False``, there won't be any visible log output. :setting:`LOG_LEVEL` determines the minimum level of severity to display, those diff --git a/docs/topics/media-pipeline.rst b/docs/topics/media-pipeline.rst index 46bd2859b..10d2ac990 100644 --- a/docs/topics/media-pipeline.rst +++ b/docs/topics/media-pipeline.rst @@ -383,6 +383,9 @@ class name. E.g. given pipeline class called MyPipeline you can set setting key: and pipeline class MyPipeline will have expiration time set to 180. +The last modified time from the file is used to determine the age of the file in days, +which is then compared to the set expiration time to determine if the file is expired. + .. _topics-images-thumbnails: Thumbnail generation for images diff --git a/docs/topics/settings.rst b/docs/topics/settings.rst index 2ab2020fa..210c1def7 100644 --- a/docs/topics/settings.rst +++ b/docs/topics/settings.rst @@ -1026,6 +1026,16 @@ Default: ``None`` File name to use for logging output. If ``None``, standard error will be used. +.. setting:: LOG_FILE_APPEND + +LOG_FILE_APPEND +--------------- + +Default: ``True`` + +If ``False``, the log file specified with :setting:`LOG_FILE` will be +overwritten (discarding the output from previous runs, if any). + .. setting:: LOG_FORMAT LOG_FORMAT @@ -1566,7 +1576,7 @@ If a reactor is already installed, :meth:`CrawlerRunner.__init__ ` raises :exc:`Exception` if the installed reactor does not match the -:setting:`TWISTED_REACTOR` setting; therfore, having top-level +:setting:`TWISTED_REACTOR` setting; therefore, having top-level :mod:`~twisted.internet.reactor` imports in project files and imported third-party libraries will make Scrapy raise :exc:`Exception` when it checks which reactor is installed. @@ -1645,8 +1655,19 @@ Default: ``2083`` Scope: ``spidermiddlewares.urllength`` -The maximum URL length to allow for crawled URLs. For more information about -the default value for this setting see: https://support.microsoft.com/en-us/topic/maximum-url-length-is-2-083-characters-in-internet-explorer-174e7c8a-6666-f4e0-6fd6-908b53c12246 +The maximum URL length to allow for crawled URLs. + +This setting can act as a stopping condition in case of URLs of ever-increasing +length, which may be caused for example by a programming error either in the +target server or in your code. See also :setting:`REDIRECT_MAX_TIMES` and +:setting:`DEPTH_LIMIT`. + +Use ``0`` to allow URLs of any length. + +The default value is copied from the `Microsoft Internet Explorer maximum URL +length`_, even though this setting exists for different reasons. + +.. _Microsoft Internet Explorer maximum URL length: https://support.microsoft.com/en-us/topic/maximum-url-length-is-2-083-characters-in-internet-explorer-174e7c8a-6666-f4e0-6fd6-908b53c12246 .. setting:: USER_AGENT @@ -1658,7 +1679,7 @@ Default: ``"Scrapy/VERSION (+https://scrapy.org)"`` The default User-Agent to use when crawling, unless overridden. This user agent is also used by :class:`~scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware` if :setting:`ROBOTSTXT_USER_AGENT` setting is ``None`` and -there is no overridding User-Agent header specified for the request. +there is no overriding User-Agent header specified for the request. Settings documented elsewhere: diff --git a/docs/topics/shell.rst b/docs/topics/shell.rst index 8c90a506c..007e9fc2f 100644 --- a/docs/topics/shell.rst +++ b/docs/topics/shell.rst @@ -99,7 +99,7 @@ Available Shortcuts shortcuts - ``fetch(url[, redirect=True])`` - fetch a new response from the given URL - and update all related objects accordingly. You can optionaly ask for HTTP + and update all related objects accordingly. You can optionally ask for HTTP 3xx redirections to not be followed by passing ``redirect=False`` - ``fetch(request)`` - fetch a new response from the given request and update diff --git a/docs/topics/spider-middleware.rst b/docs/topics/spider-middleware.rst index c2651debb..f8d4a356f 100644 --- a/docs/topics/spider-middleware.rst +++ b/docs/topics/spider-middleware.rst @@ -447,4 +447,3 @@ UrlLengthMiddleware settings (see the settings documentation for more info): * :setting:`URLLENGTH_LIMIT` - The maximum URL length to allow for crawled URLs. - diff --git a/docs/topics/spiders.rst b/docs/topics/spiders.rst index 4d3d32941..99e74233a 100644 --- a/docs/topics/spiders.rst +++ b/docs/topics/spiders.rst @@ -372,7 +372,7 @@ CrawlSpider described below. If multiple rules match the same link, the first one will be used, according to the order they're defined in this attribute. - This spider also exposes an overrideable method: + This spider also exposes an overridable method: .. method:: parse_start_url(response, **kwargs) @@ -534,7 +534,7 @@ XMLFeedSpider itertag = 'n:url' # ... - Apart from these new attributes, this spider has the following overrideable + Apart from these new attributes, this spider has the following overridable methods too: .. method:: adapt_response(response) diff --git a/docs/versioning.rst b/docs/versioning.rst index 57643ea9a..9d02757b0 100644 --- a/docs/versioning.rst +++ b/docs/versioning.rst @@ -13,7 +13,7 @@ There are 3 numbers in a Scrapy version: *A.B.C* large changes. * *B* is the release number. This will include many changes including features and things that possibly break backward compatibility, although we strive to - keep theses cases at a minimum. + keep these cases at a minimum. * *C* is the bugfix release number. Backward-incompatibilities are explicitly mentioned in the :ref:`release notes `, diff --git a/extras/qpsclient.py b/extras/qpsclient.py index f9fb70342..28703650d 100644 --- a/extras/qpsclient.py +++ b/extras/qpsclient.py @@ -1,5 +1,5 @@ """ -A spider that generate light requests to meassure QPS troughput +A spider that generate light requests to meassure QPS throughput usage: diff --git a/scrapy/downloadermiddlewares/retry.py b/scrapy/downloadermiddlewares/retry.py index f1fdc3858..c6cc7c56d 100644 --- a/scrapy/downloadermiddlewares/retry.py +++ b/scrapy/downloadermiddlewares/retry.py @@ -2,7 +2,7 @@ An extension to retry failed requests that are potentially caused by temporary problems such as a connection timeout or HTTP 500 error. -You can change the behaviour of this middleware by modifing the scraping settings: +You can change the behaviour of this middleware by modifying the scraping settings: RETRY_TIMES - how many times to retry a failed page RETRY_HTTP_CODES - which HTTP response codes to retry diff --git a/scrapy/exporters.py b/scrapy/exporters.py index fb4b565cf..36cca2d05 100644 --- a/scrapy/exporters.py +++ b/scrapy/exporters.py @@ -30,7 +30,7 @@ class BaseItemExporter: self._configure(kwargs, dont_fail=dont_fail) def _configure(self, options, dont_fail=False): - """Configure the exporter by poping options from the ``options`` dict. + """Configure the exporter by popping options from the ``options`` dict. If dont_fail is set, it won't raise an exception on unexpected options (useful for using with keyword arguments in subclasses ``__init__`` methods) """ diff --git a/scrapy/linkextractors/lxmlhtml.py b/scrapy/linkextractors/lxmlhtml.py index e941c4321..b5d2585a8 100644 --- a/scrapy/linkextractors/lxmlhtml.py +++ b/scrapy/linkextractors/lxmlhtml.py @@ -88,7 +88,7 @@ class LxmlParserLinkExtractor: def _process_links(self, links): """ Normalize and filter extracted links - The subclass should override it if neccessary + The subclass should override it if necessary """ return self._deduplicate_if_needed(links) diff --git a/scrapy/loader/__init__.py b/scrapy/loader/__init__.py index 014951a8e..91337b949 100644 --- a/scrapy/loader/__init__.py +++ b/scrapy/loader/__init__.py @@ -83,6 +83,9 @@ class ItemLoader(itemloaders.ItemLoader): def __init__(self, item=None, selector=None, response=None, parent=None, **context): if selector is None and response is not None: - selector = self.default_selector_class(response) + try: + selector = self.default_selector_class(response) + except AttributeError: + selector = None context.update(response=response) super().__init__(item=item, selector=selector, parent=parent, **context) diff --git a/scrapy/pipelines/files.py b/scrapy/pipelines/files.py index 8766ef66f..5c52c6c28 100644 --- a/scrapy/pipelines/files.py +++ b/scrapy/pipelines/files.py @@ -85,7 +85,7 @@ class S3FilesStore: AWS_USE_SSL = None AWS_VERIFY = None - POLICY = 'private' # Overriden from settings.FILES_STORE_S3_ACL in FilesPipeline.from_settings + POLICY = 'private' # Overridden from settings.FILES_STORE_S3_ACL in FilesPipeline.from_settings HEADERS = { 'Cache-Control': 'max-age=172800', } @@ -142,7 +142,7 @@ class S3FilesStore: **extra) def _headers_to_botocore_kwargs(self, headers): - """ Convert headers to botocore keyword agruments. + """ Convert headers to botocore keyword arguments. """ # This is required while we need to support both boto and botocore. mapping = CaselessDict({ @@ -190,7 +190,7 @@ class GCSFilesStore: CACHE_CONTROL = 'max-age=172800' # The bucket's default object ACL will be applied to the object. - # Overriden from settings.FILES_STORE_GCS_ACL in FilesPipeline.from_settings. + # Overridden from settings.FILES_STORE_GCS_ACL in FilesPipeline.from_settings. POLICY = None def __init__(self, uri): @@ -291,7 +291,7 @@ class FilesPipeline(MediaPipeline): """Abstract pipeline that implement the file downloading This pipeline tries to minimize network transfers and file processing, - doing stat of the files and determining if file is new, uptodate or + doing stat of the files and determining if file is new, up-to-date or expired. ``new`` files are those that pipeline never processed and needs to be diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index 4ef330dd2..8389a70cb 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -207,6 +207,7 @@ LOG_DATEFORMAT = '%Y-%m-%d %H:%M:%S' LOG_STDOUT = False LOG_LEVEL = 'DEBUG' LOG_FILE = None +LOG_FILE_APPEND = True LOG_SHORT_NAMES = False SCHEDULER_DEBUG = False diff --git a/scrapy/spiders/feed.py b/scrapy/spiders/feed.py index 6ed17e4dd..bef2d6b24 100644 --- a/scrapy/spiders/feed.py +++ b/scrapy/spiders/feed.py @@ -43,7 +43,7 @@ class XMLFeedSpider(Spider): return response def parse_node(self, response, selector): - """This method must be overriden with your custom spider functionality""" + """This method must be overridden with your custom spider functionality""" if hasattr(self, 'parse_item'): # backward compatibility return self.parse_item(response, selector) raise NotImplementedError @@ -113,7 +113,7 @@ class CSVFeedSpider(Spider): return response def parse_row(self, response, row): - """This method must be overriden with your custom spider functionality""" + """This method must be overridden with your custom spider functionality""" raise NotImplementedError def parse_rows(self, response): diff --git a/scrapy/utils/console.py b/scrapy/utils/console.py index 133261fd7..1bc0bd45f 100644 --- a/scrapy/utils/console.py +++ b/scrapy/utils/console.py @@ -14,7 +14,7 @@ def _embed_ipython_shell(namespace={}, banner=''): @wraps(_embed_ipython_shell) def wrapper(namespace=namespace, banner=''): config = load_default_config() - # Always use .instace() to ensure _instance propagation to all parents + # Always use .instance() to ensure _instance propagation to all parents # this is needed for completion works well for new imports # and clear the instance to always have the fresh env # on repeated breaks like with inspect_response() diff --git a/scrapy/utils/datatypes.py b/scrapy/utils/datatypes.py index e31284a7f..47df8a717 100644 --- a/scrapy/utils/datatypes.py +++ b/scrapy/utils/datatypes.py @@ -41,7 +41,7 @@ class CaselessDict(dict): return key.lower() def normvalue(self, value): - """Method to normalize values prior to be setted""" + """Method to normalize values prior to be set""" return value def get(self, key, def_val=None): diff --git a/scrapy/utils/defer.py b/scrapy/utils/defer.py index 39c8a85e9..faa39bb12 100644 --- a/scrapy/utils/defer.py +++ b/scrapy/utils/defer.py @@ -46,7 +46,7 @@ def defer_succeed(result) -> Deferred: """Same as twisted.internet.defer.succeed but delay calling callback until next reactor loop - It delays by 100ms so reactor has a chance to go trough readers and writers + It delays by 100ms so reactor has a chance to go through readers and writers before attending pending delayed calls, so do not set delay to zero. """ from twisted.internet import reactor @@ -303,17 +303,50 @@ def maybeDeferred_coro(f: Callable, *args, **kw) -> Deferred: def deferred_to_future(d: Deferred) -> Future: - """ Wraps a Deferred into a Future. Requires the asyncio reactor. + """ + .. versionadded:: VERSION + + Return an :class:`asyncio.Future` object that wraps *d*. + + When :ref:`using the asyncio reactor `, you cannot await + on :class:`~twisted.internet.defer.Deferred` objects from :ref:`Scrapy + callables defined as coroutines `, you can only await on + ``Future`` objects. Wrapping ``Deferred`` objects into ``Future`` objects + allows you to wait on them:: + + class MySpider(Spider): + ... + async def parse(self, response): + d = treq.get('https://example.com/additional') + additional_response = await deferred_to_future(d) """ return d.asFuture(asyncio.get_event_loop()) def maybe_deferred_to_future(d: Deferred) -> Union[Deferred, Future]: - """ Converts a Deferred to something that can be awaited in a callback or other user coroutine. + """ + .. versionadded:: VERSION - If the asyncio reactor is installed, coroutines are wrapped into Futures, and only Futures can be - awaited inside them. Otherwise, coroutines are wrapped into Deferreds and Deferreds can be awaited - directly inside them. + Return *d* as an object that can be awaited from a :ref:`Scrapy callable + defined as a coroutine `. + + What you can await in Scrapy callables defined as coroutines depends on the + value of :setting:`TWISTED_REACTOR`: + + - When not using the asyncio reactor, you can only await on + :class:`~twisted.internet.defer.Deferred` objects. + + - When :ref:`using the asyncio reactor `, you can only + await on :class:`asyncio.Future` objects. + + If you want to write code that uses ``Deferred`` objects but works with any + reactor, use this function on all ``Deferred`` objects:: + + class MySpider(Spider): + ... + async def parse(self, response): + d = treq.get('https://example.com/additional') + extra_response = await maybe_deferred_to_future(d) """ if not is_asyncio_reactor_installed(): return d diff --git a/scrapy/utils/log.py b/scrapy/utils/log.py index 6c456ed60..0441c0358 100644 --- a/scrapy/utils/log.py +++ b/scrapy/utils/log.py @@ -124,8 +124,9 @@ def _get_handler(settings): """ Return a log handler object according to settings """ filename = settings.get('LOG_FILE') if filename: + mode = 'a' if settings.getbool('LOG_FILE_APPEND') else 'w' encoding = settings.get('LOG_ENCODING') - handler = logging.FileHandler(filename, encoding=encoding) + handler = logging.FileHandler(filename, mode=mode, encoding=encoding) elif settings.getbool('LOG_ENABLED'): handler = logging.StreamHandler() else: diff --git a/scrapy/utils/request.py b/scrapy/utils/request.py index 57dcc5f2c..70ef3ba2b 100644 --- a/scrapy/utils/request.py +++ b/scrapy/utils/request.py @@ -48,7 +48,7 @@ def request_fingerprint( the fingerprint. For this reason, request headers are ignored by default when calculating - the fingeprint. If you want to include specific headers use the + 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, @@ -78,7 +78,7 @@ def request_fingerprint( def request_authenticate(request: Request, username: str, password: str) -> None: - """Autenticate the given request (in place) using the HTTP basic access + """Authenticate the given request (in place) using the HTTP basic access authentication mechanism (RFC 2617) and the given username and password """ request.headers['Authorization'] = basic_auth_header(username, password) diff --git a/sep/sep-001.rst b/sep/sep-001.rst index 00226283f..f704e113f 100644 --- a/sep/sep-001.rst +++ b/sep/sep-001.rst @@ -260,7 +260,7 @@ ItemForm ia['width'] = x.x('//p[@class="width"]') ia['volume'] = x.x('//p[@class="volume"]') - # another example passing parametes on instance + # another example passing parameters on instance ia = NewsForm(response, encoding='utf-8') ia['name'] = x.x('//p[@class="name"]') diff --git a/sep/sep-005.rst b/sep/sep-005.rst index e795838e4..08ed367b3 100644 --- a/sep/sep-005.rst +++ b/sep/sep-005.rst @@ -107,7 +107,7 @@ gUsing default_builder This will use default_builder as the builder for every field in the item class. -As a reducer is not set reducers will be set based on Item Field classess. +As a reducer is not set reducers will be set based on Item Field classes. gReset default_builder for a field ================================== diff --git a/sep/sep-014.rst b/sep/sep-014.rst index 8ca81824d..0859e3f7c 100644 --- a/sep/sep-014.rst +++ b/sep/sep-014.rst @@ -64,7 +64,7 @@ Request Processors takes requests objects and can perform any action to them, like filtering or modifying on the fly. The current ``LinkExtractor`` had integrated link processing, like -canonicalize. Request Processors can be reutilized and applied in serie. +canonicalize. Request Processors can be reutilized and applied in series. Request Generator ----------------- diff --git a/sep/sep-021.rst b/sep/sep-021.rst index 372429791..c1ec16f7f 100644 --- a/sep/sep-021.rst +++ b/sep/sep-021.rst @@ -22,7 +22,7 @@ Instead, the hooks are spread over: * Downloader handlers (DOWNLOADER_HANDLERS) * Item pipelines (ITEM_PIPELINES) * Feed exporters and storages (FEED_EXPORTERS, FEED_STORAGES) -* Overrideable components (DUPEFILTER_CLASS, STATS_CLASS, SCHEDULER, SPIDER_MANAGER_CLASS, ITEM_PROCESSOR, etc) +* Overridable components (DUPEFILTER_CLASS, STATS_CLASS, SCHEDULER, SPIDER_MANAGER_CLASS, ITEM_PROCESSOR, etc) * Generic extensions (EXTENSIONS) * CLI commands (COMMANDS_MODULE) diff --git a/setup.py b/setup.py index ed2b6e347..3a6ff2836 100644 --- a/setup.py +++ b/setup.py @@ -87,6 +87,7 @@ setup( 'Programming Language :: Python :: 3.7', 'Programming Language :: Python :: 3.8', 'Programming Language :: Python :: 3.9', + 'Programming Language :: Python :: 3.10', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: PyPy', 'Topic :: Internet :: WWW/HTTP', diff --git a/tests/test_crawler.py b/tests/test_crawler.py index dec517bb6..be067155e 100644 --- a/tests/test_crawler.py +++ b/tests/test_crawler.py @@ -98,6 +98,8 @@ class CrawlerLoggingTestCase(unittest.TestCase): def test_spider_custom_settings_log_level(self): log_file = self.mktemp() + with open(log_file, 'wb') as fo: + fo.write('previous message\n'.encode('utf-8')) class MySpider(scrapy.Spider): name = 'spider' @@ -119,8 +121,9 @@ class CrawlerLoggingTestCase(unittest.TestCase): logging.error('error message') with open(log_file, 'rb') as fo: - logged = fo.read().decode('utf8') + logged = fo.read().decode('utf-8') + self.assertIn('previous message', logged) self.assertNotIn('debug message', logged) self.assertIn('info message', logged) self.assertIn('warning message', logged) @@ -131,6 +134,30 @@ class CrawlerLoggingTestCase(unittest.TestCase): crawler.stats.get_value('log_count/INFO') - info_count, 1) self.assertEqual(crawler.stats.get_value('log_count/DEBUG', 0), 0) + def test_spider_custom_settings_log_append(self): + log_file = self.mktemp() + with open(log_file, 'wb') as fo: + fo.write('previous message\n'.encode('utf-8')) + + class MySpider(scrapy.Spider): + name = 'spider' + custom_settings = { + 'LOG_FILE': log_file, + 'LOG_FILE_APPEND': False, + # disable telnet if not available to avoid an extra warning + 'TELNETCONSOLE_ENABLED': telnet.TWISTED_CONCH_AVAILABLE, + } + + configure_logging() + Crawler(MySpider, {}) + logging.debug('debug message') + + with open(log_file, 'rb') as fo: + logged = fo.read().decode('utf-8') + + self.assertNotIn('previous message', logged) + self.assertIn('debug message', logged) + class SpiderLoaderWithWrongInterface: diff --git a/tests/test_http_response.py b/tests/test_http_response.py index c376a46cd..0ec5257e1 100644 --- a/tests/test_http_response.py +++ b/tests/test_http_response.py @@ -19,7 +19,7 @@ class BaseResponseTest(unittest.TestCase): response_class = Response def test_init(self): - # Response requires url in the consturctor + # Response requires url in the constructor self.assertRaises(Exception, self.response_class) self.assertTrue(isinstance(self.response_class('http://example.com/'), self.response_class)) self.assertRaises(TypeError, self.response_class, b"http://example.com") @@ -392,7 +392,7 @@ class TextResponseTest(BaseResponseTest): def test_declared_encoding_invalid(self): """Check that unknown declared encodings are ignored""" r = self.response_class("http://www.example.com", - headers={"Content-type": ["text/html; charset=UKNOWN"]}, + headers={"Content-type": ["text/html; charset=UNKNOWN"]}, body=b"\xc2\xa3") self.assertEqual(r._declared_encoding(), None) self._assert_response_values(r, 'utf-8', "\xa3") diff --git a/tests/test_loader.py b/tests/test_loader.py index b0bc82f4e..f7ab1f236 100644 --- a/tests/test_loader.py +++ b/tests/test_loader.py @@ -4,7 +4,7 @@ import attr from itemadapter import ItemAdapter from itemloaders.processors import Compose, Identity, MapCompose, TakeFirst -from scrapy.http import HtmlResponse +from scrapy.http import HtmlResponse, Response from scrapy.item import Item, Field from scrapy.loader import ItemLoader from scrapy.selector import Selector @@ -304,6 +304,12 @@ class SelectortemLoaderTest(unittest.TestCase): l.add_css('name', 'div::text') self.assertEqual(l.get_output_value('name'), ['Marta']) + + def test_init_method_with_base_response(self): + """Selector should be None after initialization""" + response = Response("https://scrapy.org") + l = TestItemLoader(response=response) + self.assertIs(l.selector, None) def test_init_method_with_response(self): l = TestItemLoader(response=self.response) diff --git a/tests/test_pipelines.py b/tests/test_pipelines.py index ff3af9a74..8e432b913 100644 --- a/tests/test_pipelines.py +++ b/tests/test_pipelines.py @@ -6,6 +6,7 @@ from twisted.internet.defer import Deferred from twisted.trial import unittest from scrapy import Spider, signals, Request +from scrapy.utils.defer import maybe_deferred_to_future, deferred_to_future from scrapy.utils.test import get_crawler, get_from_asyncio_queue from tests.mockserver import MockServer @@ -31,18 +32,38 @@ class DeferredPipeline: class AsyncDefPipeline: async def process_item(self, item, spider): - await defer.succeed(42) + d = Deferred() + from twisted.internet import reactor + reactor.callLater(0, d.callback, None) + await maybe_deferred_to_future(d) item['pipeline_passed'] = True return item class AsyncDefAsyncioPipeline: async def process_item(self, item, spider): + d = Deferred() + from twisted.internet import reactor + reactor.callLater(0, d.callback, None) + await deferred_to_future(d) await asyncio.sleep(0.2) item['pipeline_passed'] = await get_from_asyncio_queue(True) return item +class AsyncDefNotAsyncioPipeline: + async def process_item(self, item, spider): + d1 = Deferred() + from twisted.internet import reactor + reactor.callLater(0, d1.callback, None) + await d1 + d2 = Deferred() + reactor.callLater(0, d2.callback, None) + await maybe_deferred_to_future(d2) + item['pipeline_passed'] = True + return item + + class ItemSpider(Spider): name = 'itemspider' @@ -99,3 +120,10 @@ class PipelineTestCase(unittest.TestCase): crawler = self._create_crawler(AsyncDefAsyncioPipeline) yield crawler.crawl(mockserver=self.mockserver) self.assertEqual(len(self.items), 1) + + @mark.only_not_asyncio() + @defer.inlineCallbacks + def test_asyncdef_not_asyncio_pipeline(self): + crawler = self._create_crawler(AsyncDefNotAsyncioPipeline) + yield crawler.crawl(mockserver=self.mockserver) + self.assertEqual(len(self.items), 1) diff --git a/tests/test_request_attribute_binding.py b/tests/test_request_attribute_binding.py index 00c532c41..25d9657d5 100644 --- a/tests/test_request_attribute_binding.py +++ b/tests/test_request_attribute_binding.py @@ -106,9 +106,9 @@ class CrawlTestCase(TestCase): """ Downloader middleware which returns a response with an specific 'request' attribute. - * The spider callback should receive the overriden response.request - * Handlers listening to the response_received signal should receive the overriden response.request - * The "crawled" log message should show the overriden response.request + * The spider callback should receive the overridden response.request + * Handlers listening to the response_received signal should receive the overridden response.request + * The "crawled" log message should show the overridden response.request """ signal_params = {} @@ -144,7 +144,7 @@ class CrawlTestCase(TestCase): An exception is raised but caught by the next middleware, which returns a Response with a specific 'request' attribute. - The spider callback should receive the overriden response.request + The spider callback should receive the overridden response.request """ url = self.mockserver.url("/status?n=200") runner = CrawlerRunner(settings={ diff --git a/tests/test_utils_defer.py b/tests/test_utils_defer.py index 543bbee09..d39de7430 100644 --- a/tests/test_utils_defer.py +++ b/tests/test_utils_defer.py @@ -29,7 +29,7 @@ class MustbeDeferredTest(unittest.TestCase): dfd = mustbe_deferred(_append, 1) dfd.addCallback(self.assertEqual, [1, 2]) # it is [1] with maybeDeferred - steps.append(2) # add another value, that should be catched by assertEqual + steps.append(2) # add another value, that should be caught by assertEqual return dfd def test_unfired_deferred(self): @@ -43,7 +43,7 @@ class MustbeDeferredTest(unittest.TestCase): dfd = mustbe_deferred(_append, 1) dfd.addCallback(self.assertEqual, [1, 2]) # it is [1] with maybeDeferred - steps.append(2) # add another value, that should be catched by assertEqual + steps.append(2) # add another value, that should be caught by assertEqual return dfd diff --git a/tests/test_utils_template.py b/tests/test_utils_template.py index 5ff2e41ef..1d5e63363 100644 --- a/tests/test_utils_template.py +++ b/tests/test_utils_template.py @@ -36,7 +36,7 @@ class UtilsRenderTemplateFileTestCase(unittest.TestCase): self.assertEqual(result.read().decode('utf8'), rendered) os.remove(render_path) - assert not os.path.exists(render_path) # Failure of test iself + assert not os.path.exists(render_path) # Failure of test itself if '__main__' == __name__: diff --git a/tox.ini b/tox.ini index e274fc8d2..021dd9988 100644 --- a/tox.ini +++ b/tox.ini @@ -41,6 +41,7 @@ deps = types-pyOpenSSL==20.0.3 types-setuptools==57.0.0 commands = + pip install types-dataclasses # remove once py36 support is dropped mypy --show-error-codes {posargs: scrapy tests} [testenv:security] @@ -57,6 +58,7 @@ deps = # Twisted[http2] is required to import some files Twisted[http2]>=17.9.0 pytest-flake8 + flake8==3.9.2 # https://github.com/tholo/pytest-flake8/issues/81 commands = py.test --flake8 {posargs:docs scrapy tests}