diff --git a/.readthedocs.yml b/.readthedocs.yml index 17eba34f3..e4d3f02cc 100644 --- a/.readthedocs.yml +++ b/.readthedocs.yml @@ -1,4 +1,5 @@ version: 2 +formats: all sphinx: configuration: docs/conf.py fail_on_warning: true diff --git a/docs/README.rst b/docs/README.rst index 0a343cd19..0b7afa548 100644 --- a/docs/README.rst +++ b/docs/README.rst @@ -57,3 +57,12 @@ There is a way to recreate the doc automatically when you make changes, you need to install watchdog (``pip install watchdog``) and then use:: make watch + +Alternative method using tox +---------------------------- + +To compile the documentation to HTML run the following command:: + + tox -e docs + +Documentation will be generated (in HTML format) inside the ``.tox/docs/tmp/html`` dir. diff --git a/docs/conf.py b/docs/conf.py index 8ab38a090..29b2fc406 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -100,6 +100,9 @@ exclude_trees = ['.build'] # The name of the Pygments (syntax highlighting) style to use. pygments_style = 'sphinx' +# List of Sphinx warnings that will not be raised +suppress_warnings = ['epub.unknown_project_files'] + # Options for HTML output # ----------------------- @@ -300,3 +303,4 @@ hoverxref_role_types = { "mod": "tooltip", "ref": "tooltip", } +hoverxref_roles = ['command', 'reqmeta', 'setting', 'signal'] diff --git a/docs/faq.rst b/docs/faq.rst index 0b6bd6a86..c06cb945b 100644 --- a/docs/faq.rst +++ b/docs/faq.rst @@ -371,6 +371,19 @@ Twisted reactor is :class:`twisted.internet.selectreactor.SelectReactor`. Switch different reactor is possible by using the :setting:`TWISTED_REACTOR` setting. +.. _faq-stop-response-download: + +How can I cancel the download of a given response? +-------------------------------------------------- + +In some situations, it might be useful to stop the download of a certain response. +For instance, if you only need the first part of a large response and you would like +to save resources by avoiding the download of the whole body. +In that case, you could attach a handler to the :class:`~scrapy.signals.bytes_received` +signal and raise a :exc:`~scrapy.exceptions.StopDownload` exception. Please refer to +the :ref:`topics-stop-response-download` topic for additional information and examples. + + .. _has been reported: https://github.com/scrapy/scrapy/issues/2905 .. _user agents: https://en.wikipedia.org/wiki/User_agent .. _LIFO: https://en.wikipedia.org/wiki/Stack_(abstract_data_type) diff --git a/docs/topics/api.rst b/docs/topics/api.rst index 1c461a511..52509ffdf 100644 --- a/docs/topics/api.rst +++ b/docs/topics/api.rst @@ -91,7 +91,7 @@ how you :ref:`configure the downloader middlewares provided while constructing the crawler, and it is created after the arguments given in the :meth:`crawl` method. - .. method:: crawl(\*args, \**kwargs) + .. method:: crawl(*args, **kwargs) Starts the crawler by instantiating its spider class with the given ``args`` and ``kwargs`` arguments, while setting the execution engine in diff --git a/docs/topics/contracts.rst b/docs/topics/contracts.rst index 319f577bc..b8b3078c4 100644 --- a/docs/topics/contracts.rst +++ b/docs/topics/contracts.rst @@ -78,7 +78,7 @@ override three methods: .. module:: scrapy.contracts -.. class:: Contract(method, \*args) +.. class:: Contract(method, *args) :param method: callback function to which the contract is associated :type method: function diff --git a/docs/topics/downloader-middleware.rst b/docs/topics/downloader-middleware.rst index 1a87d07b6..323e553e5 100644 --- a/docs/topics/downloader-middleware.rst +++ b/docs/topics/downloader-middleware.rst @@ -202,6 +202,11 @@ CookiesMiddleware sends them back on subsequent requests (from that spider), just like web browsers do. + .. caution:: When non-UTF8 encoded byte sequences are passed to a + :class:`~scrapy.http.Request`, the ``CookiesMiddleware`` will log + a warning. Refer to :ref:`topics-logging-advanced-customization` + to customize the logging behaviour. + The following settings can be used to configure the cookie middleware: * :setting:`COOKIES_ENABLED` diff --git a/docs/topics/exceptions.rst b/docs/topics/exceptions.rst index 09cb8ed66..583a50ab8 100644 --- a/docs/topics/exceptions.rst +++ b/docs/topics/exceptions.rst @@ -14,13 +14,6 @@ Built-in Exceptions reference Here's a list of all exceptions included in Scrapy and their usage. -DropItem --------- - -.. exception:: DropItem - -The exception that must be raised by item pipeline stages to stop processing an -Item. For more information see :ref:`topics-item-pipeline`. CloseSpider ----------- @@ -47,6 +40,14 @@ DontCloseSpider This exception can be raised in a :signal:`spider_idle` signal handler to prevent the spider from being closed. +DropItem +-------- + +.. exception:: DropItem + +The exception that must be raised by item pipeline stages to stop processing an +Item. For more information see :ref:`topics-item-pipeline`. + IgnoreRequest ------------- @@ -77,3 +78,37 @@ NotSupported This exception is raised to indicate an unsupported feature. +StopDownload +------------- + +.. versionadded:: 2.2 + +.. exception:: StopDownload(fail=True) + +Raised from a :class:`~scrapy.signals.bytes_received` signal handler to +indicate that no further bytes should be downloaded for a response. + +The ``fail`` boolean parameter controls which method will handle the resulting +response: + +* If ``fail=True`` (default), the request errback is called. The response object is + available as the ``response`` attribute of the ``StopDownload`` exception, + which is in turn stored as the ``value`` attribute of the received + :class:`~twisted.python.failure.Failure` object. This means that in an errback + defined as ``def errback(self, failure)``, the response can be accessed though + ``failure.value.response``. + +* If ``fail=False``, the request callback is called instead. + +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` +attribute. + +.. note:: ``fail`` is a keyword-only parameter, i.e. raising + ``StopDownload(False)`` or ``StopDownload(True)`` will raise + a :class:`TypeError`. + +See the documentation for the :class:`~scrapy.signals.bytes_received` signal +and the :ref:`topics-stop-response-download` topic for additional information and examples. diff --git a/docs/topics/exporters.rst b/docs/topics/exporters.rst index de8b51195..7daf25ab3 100644 --- a/docs/topics/exporters.rst +++ b/docs/topics/exporters.rst @@ -236,7 +236,7 @@ PythonItemExporter XmlItemExporter --------------- -.. class:: XmlItemExporter(file, item_element='item', root_element='items', \**kwargs) +.. class:: XmlItemExporter(file, item_element='item', root_element='items', **kwargs) Exports Items in XML format to the specified file object. @@ -290,7 +290,7 @@ XmlItemExporter CsvItemExporter --------------- -.. class:: CsvItemExporter(file, include_headers_line=True, join_multivalued=',', \**kwargs) +.. class:: CsvItemExporter(file, include_headers_line=True, join_multivalued=',', **kwargs) Exports Items in CSV format to the given file-like object. If the :attr:`fields_to_export` attribute is set, it will be used to define the @@ -323,7 +323,7 @@ CsvItemExporter PickleItemExporter ------------------ -.. class:: PickleItemExporter(file, protocol=0, \**kwargs) +.. class:: PickleItemExporter(file, protocol=0, **kwargs) Exports Items in pickle format to the given file-like object. @@ -343,7 +343,7 @@ PickleItemExporter PprintItemExporter ------------------ -.. class:: PprintItemExporter(file, \**kwargs) +.. class:: PprintItemExporter(file, **kwargs) Exports Items in pretty print format to the specified file object. @@ -363,7 +363,7 @@ PprintItemExporter JsonItemExporter ---------------- -.. class:: JsonItemExporter(file, \**kwargs) +.. class:: JsonItemExporter(file, **kwargs) Exports Items in JSON format to the specified file-like object, writing all objects as a list of objects. The additional ``__init__`` method arguments are @@ -392,7 +392,7 @@ JsonItemExporter JsonLinesItemExporter --------------------- -.. class:: JsonLinesItemExporter(file, \**kwargs) +.. class:: JsonLinesItemExporter(file, **kwargs) Exports Items in JSON format to the specified file-like object, writing one JSON-encoded item per line. The additional ``__init__`` method arguments are passed diff --git a/docs/topics/item-pipeline.rst b/docs/topics/item-pipeline.rst index 533f84630..c9194caa1 100644 --- a/docs/topics/item-pipeline.rst +++ b/docs/topics/item-pipeline.rst @@ -167,11 +167,13 @@ method and how to clean up the resources properly.:: Take screenshot of item ----------------------- -This example demonstrates how to return a -:class:`~twisted.internet.defer.Deferred` from the :meth:`process_item` method. -It uses Splash_ to render screenshot of item url. Pipeline -makes request to locally running instance of Splash_. After request is downloaded, -it saves the screenshot to a file and adds filename to the item. +This example demonstrates how to use :doc:`coroutine syntax ` in +the :meth:`process_item` method. + +This item pipeline makes a request to a locally-running instance of Splash_ to +render a screenshot of the item URL. After the request response is downloaded, +the item pipeline saves the screenshot to a file and adds the filename to the +item. :: diff --git a/docs/topics/loaders.rst b/docs/topics/loaders.rst index 5f75ccbff..eb804f1db 100644 --- a/docs/topics/loaders.rst +++ b/docs/topics/loaders.rst @@ -273,7 +273,7 @@ There are several ways to modify Item Loader context values: ItemLoader objects ================== -.. class:: ItemLoader([item, selector, response], \**kwargs) +.. class:: ItemLoader([item, selector, response], **kwargs) Return a new Item Loader for populating the given Item. If no item is given, one is instantiated automatically using the class in @@ -303,7 +303,7 @@ ItemLoader objects :class:`ItemLoader` instances have the following methods: - .. method:: get_value(value, \*processors, \**kwargs) + .. method:: get_value(value, *processors, **kwargs) Process the given ``value`` by the given ``processors`` and keyword arguments. @@ -321,7 +321,7 @@ ItemLoader objects >>> loader.get_value(u'name: foo', TakeFirst(), unicode.upper, re='name: (.+)') 'FOO` - .. method:: add_value(field_name, value, \*processors, \**kwargs) + .. method:: add_value(field_name, value, *processors, **kwargs) Process and then add the given ``value`` for the given field. @@ -343,11 +343,11 @@ ItemLoader objects loader.add_value('name', u'name: foo', TakeFirst(), re='name: (.+)') loader.add_value(None, {'name': u'foo', 'sex': u'male'}) - .. method:: replace_value(field_name, value, \*processors, \**kwargs) + .. method:: replace_value(field_name, value, *processors, **kwargs) Similar to :meth:`add_value` but replaces the collected data with the new value instead of adding it. - .. method:: get_xpath(xpath, \*processors, \**kwargs) + .. method:: get_xpath(xpath, *processors, **kwargs) Similar to :meth:`ItemLoader.get_value` but receives an XPath instead of a value, which is used to extract a list of unicode strings from the @@ -367,7 +367,7 @@ ItemLoader objects # HTML snippet:

the price is $1200

loader.get_xpath('//p[@id="price"]', TakeFirst(), re='the price is (.*)') - .. method:: add_xpath(field_name, xpath, \*processors, \**kwargs) + .. method:: add_xpath(field_name, xpath, *processors, **kwargs) Similar to :meth:`ItemLoader.add_value` but receives an XPath instead of a value, which is used to extract a list of unicode strings from the @@ -385,12 +385,12 @@ ItemLoader objects # HTML snippet:

the price is $1200

loader.add_xpath('price', '//p[@id="price"]', re='the price is (.*)') - .. method:: replace_xpath(field_name, xpath, \*processors, \**kwargs) + .. method:: replace_xpath(field_name, xpath, *processors, **kwargs) Similar to :meth:`add_xpath` but replaces collected data instead of adding it. - .. method:: get_css(css, \*processors, \**kwargs) + .. method:: get_css(css, *processors, **kwargs) Similar to :meth:`ItemLoader.get_value` but receives a CSS selector instead of a value, which is used to extract a list of unicode strings @@ -410,7 +410,7 @@ ItemLoader objects # HTML snippet:

the price is $1200

loader.get_css('p#price', TakeFirst(), re='the price is (.*)') - .. method:: add_css(field_name, css, \*processors, \**kwargs) + .. method:: add_css(field_name, css, *processors, **kwargs) Similar to :meth:`ItemLoader.add_value` but receives a CSS selector instead of a value, which is used to extract a list of unicode strings @@ -428,7 +428,7 @@ ItemLoader objects # HTML snippet:

the price is $1200

loader.add_css('price', 'p#price', re='the price is (.*)') - .. method:: replace_css(field_name, css, \*processors, \**kwargs) + .. method:: replace_css(field_name, css, *processors, **kwargs) Similar to :meth:`add_css` but replaces collected data instead of adding it. @@ -678,7 +678,7 @@ Here is a list of all built-in processors: >>> proc(['one', 'two', 'three']) 'one
two
three' -.. class:: Compose(\*functions, \**default_loader_context) +.. class:: Compose(*functions, **default_loader_context) A processor which is constructed from the composition of the given functions. This means that each input value of this processor is passed to @@ -706,7 +706,7 @@ Here is a list of all built-in processors: active Loader context accessible through the :meth:`ItemLoader.context` attribute. -.. class:: MapCompose(\*functions, \**default_loader_context) +.. class:: MapCompose(*functions, **default_loader_context) A processor which is constructed from the composition of the given functions, similar to the :class:`Compose` processor. The difference with diff --git a/docs/topics/logging.rst b/docs/topics/logging.rst index 675e65ef1..55065a1a3 100644 --- a/docs/topics/logging.rst +++ b/docs/topics/logging.rst @@ -202,6 +202,9 @@ A custom log format can be set for different actions by extending .. autoclass:: scrapy.logformatter.LogFormatter :members: + +.. _topics-logging-advanced-customization: + Advanced customization ---------------------- @@ -262,7 +265,6 @@ scrapy.utils.log module This is an example on how to redirect ``INFO`` or higher messages to a file:: import logging - from scrapy.utils.log import configure_logging logging.basicConfig( filename='log.txt', diff --git a/docs/topics/request-response.rst b/docs/topics/request-response.rst index 15a83f453..bbd715766 100644 --- a/docs/topics/request-response.rst +++ b/docs/topics/request-response.rst @@ -385,6 +385,51 @@ The meta key is used set retry times per request. When initialized, the :reqmeta:`max_retry_times` meta key takes higher precedence over the :setting:`RETRY_TIMES` setting. + +.. _topics-stop-response-download: + +Stopping the download of a Response +=================================== + +Raising a :exc:`~scrapy.exceptions.StopDownload` exception from a +:class:`~scrapy.signals.bytes_received` signal handler will stop the +download of a given response. See the following example:: + + import scrapy + + + class StopSpider(scrapy.Spider): + name = "stop" + start_urls = ["https://docs.scrapy.org/en/latest/"] + + @classmethod + def from_crawler(cls, crawler): + spider = super().from_crawler(crawler) + crawler.signals.connect(spider.on_bytes_received, signal=scrapy.signals.bytes_received) + return spider + + def parse(self, response): + # 'last_chars' show that the full response was not downloaded + yield {"len": len(response.text), "last_chars": response.text[-40:]} + + def on_bytes_received(self, data, request, spider): + raise scrapy.exceptions.StopDownload(fail=False) + +which produces the following output:: + + 2020-05-19 17:26:12 [scrapy.core.engine] INFO: Spider opened + 2020-05-19 17:26:12 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min) + 2020-05-19 17:26:13 [scrapy.core.downloader.handlers.http11] DEBUG: Download stopped for from signal handler StopSpider.on_bytes_received + 2020-05-19 17:26:13 [scrapy.core.engine] DEBUG: Crawled (200) (referer: None) ['download_stopped'] + 2020-05-19 17:26:13 [scrapy.core.scraper] DEBUG: Scraped from <200 https://docs.scrapy.org/en/latest/> + {'len': 279, 'last_chars': 'dth, initial-scale=1.0">\n \n Scr'} + 2020-05-19 17:26:13 [scrapy.core.engine] INFO: Closing spider (finished) + +By default, resulting responses are handled by their corresponding errbacks. To +call their callback instead, like in this example, pass ``fail=False`` to the +:exc:`~scrapy.exceptions.StopDownload` exception. + + .. _topics-request-response-ref-request-subclasses: Request subclasses @@ -716,9 +761,9 @@ Response objects .. versionadded:: 2.1.0 The IP address of the server from which the Response originated. - + This attribute is currently only populated by the HTTP 1.1 download - handler, i.e. for ``http(s)`` responses. For other handlers, + handler, i.e. for ``http(s)`` responses. For other handlers, :attr:`ip_address` is always ``None``. .. method:: Response.copy() @@ -834,6 +879,11 @@ TextResponse objects .. automethod:: TextResponse.follow_all + .. automethod:: TextResponse.json() + + Returns a Python object from deserialized JSON document. + The result is cached after the first call. + HtmlResponse objects -------------------- diff --git a/docs/topics/signals.rst b/docs/topics/signals.rst index 7fe63a7b0..fe4fb0834 100644 --- a/docs/topics/signals.rst +++ b/docs/topics/signals.rst @@ -373,6 +373,8 @@ request_left_downloader bytes_received ~~~~~~~~~~~~~~ +.. versionadded:: 2.2 + .. signal:: bytes_received .. function:: bytes_received(data, request, spider) @@ -385,14 +387,19 @@ bytes_received This signal does not support returning deferreds from its handlers. :param data: the data received by the download handler - :type spider: :class:`bytes` object + :type data: :class:`bytes` object - :param request: the request that generated the response + :param request: the request that generated the download :type request: :class:`~scrapy.http.Request` object :param spider: the spider associated with the response :type spider: :class:`~scrapy.spiders.Spider` object +.. note:: Handlers of this signal can stop the download of a response while it + is in progress by raising the :exc:`~scrapy.exceptions.StopDownload` + exception. Please refer to the :ref:`topics-stop-response-download` topic + for additional information and examples. + Response signals ---------------- diff --git a/docs/topics/spiders.rst b/docs/topics/spiders.rst index 231db6cea..8ff5e7292 100644 --- a/docs/topics/spiders.rst +++ b/docs/topics/spiders.rst @@ -121,7 +121,7 @@ scrapy.Spider send log messages through it as described on :ref:`topics-logging-from-spiders`. - .. method:: from_crawler(crawler, \*args, \**kwargs) + .. method:: from_crawler(crawler, *args, **kwargs) This is the class method used by Scrapy to create your spiders. diff --git a/pytest.ini b/pytest.ini index 0e289866c..663c5cc78 100644 --- a/pytest.ini +++ b/pytest.ini @@ -27,18 +27,16 @@ flake8-ignore = # Exclude files that are meant to provide top-level imports # E402: Module level import not at top of file # F401: Module imported but unused + scrapy/__init__.py E402 scrapy/core/downloader/handlers/http.py F401 scrapy/http/__init__.py F401 scrapy/linkextractors/__init__.py E402 F401 + scrapy/selector/__init__.py F401 scrapy/spiders/__init__.py E402 F401 # Issues pending a review: - scrapy/__init__.py E402 - scrapy/selector/__init__.py F403 - scrapy/spiders/__init__.py E402 scrapy/utils/http.py F403 scrapy/utils/markup.py F403 scrapy/utils/multipart.py F403 scrapy/utils/url.py F403 F405 tests/test_loader.py E741 - tests/test_webclient.py E402 diff --git a/scrapy/__init__.py b/scrapy/__init__.py index fb8357f3c..e791deaa6 100644 --- a/scrapy/__init__.py +++ b/scrapy/__init__.py @@ -2,33 +2,11 @@ Scrapy - a web crawling and web scraping framework written for Python """ -__all__ = ['__version__', 'version_info', 'twisted_version', - 'Spider', 'Request', 'FormRequest', 'Selector', 'Item', 'Field'] - -# Scrapy version import pkgutil -__version__ = pkgutil.get_data(__package__, 'VERSION').decode('ascii').strip() -version_info = tuple(int(v) if v.isdigit() else v - for v in __version__.split('.')) -del pkgutil - -# Check minimum required Python version import sys -if sys.version_info < (3, 5): - print("Scrapy %s requires Python 3.5" % __version__) - sys.exit(1) - -# Ignore noisy twisted deprecation warnings import warnings -warnings.filterwarnings('ignore', category=DeprecationWarning, module='twisted') -del warnings - -# Apply monkey patches to fix issues in external libraries -from scrapy import _monkeypatches -del _monkeypatches from twisted import version as _txv -twisted_version = (_txv.major, _txv.minor, _txv.micro) # Declare top-level shortcuts from scrapy.spiders import Spider @@ -36,4 +14,29 @@ from scrapy.http import Request, FormRequest from scrapy.selector import Selector from scrapy.item import Item, Field + +__all__ = [ + '__version__', 'version_info', 'twisted_version', 'Spider', + 'Request', 'FormRequest', 'Selector', 'Item', 'Field', +] + + +# Scrapy and Twisted versions +__version__ = pkgutil.get_data(__package__, 'VERSION').decode('ascii').strip() +version_info = tuple(int(v) if v.isdigit() else v for v in __version__.split('.')) +twisted_version = (_txv.major, _txv.minor, _txv.micro) + + +# Check minimum required Python version +if sys.version_info < (3, 5): + print("Scrapy %s requires Python 3.5" % __version__) + sys.exit(1) + + +# Ignore noisy twisted deprecation warnings +warnings.filterwarnings('ignore', category=DeprecationWarning, module='twisted') + + +del pkgutil del sys +del warnings diff --git a/scrapy/_monkeypatches.py b/scrapy/_monkeypatches.py deleted file mode 100644 index f74f89bda..000000000 --- a/scrapy/_monkeypatches.py +++ /dev/null @@ -1,11 +0,0 @@ -import copyreg - - -# Undo what Twisted's perspective broker adds to pickle register -# to prevent bugs like Twisted#7989 while serializing requests -import twisted.persisted.styles # NOQA -# Remove only entries with twisted serializers for non-twisted types. -for k, v in frozenset(copyreg.dispatch_table.items()): - if not str(getattr(k, '__module__', '')).startswith('twisted') \ - and str(getattr(v, '__module__', '')).startswith('twisted'): - copyreg.dispatch_table.pop(k) diff --git a/scrapy/commands/__init__.py b/scrapy/commands/__init__.py index 97f818cb2..ab850dcb3 100644 --- a/scrapy/commands/__init__.py +++ b/scrapy/commands/__init__.py @@ -5,7 +5,7 @@ import os from optparse import OptionGroup from twisted.python import failure -from scrapy.utils.conf import arglist_to_dict +from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli from scrapy.exceptions import UsageError @@ -104,3 +104,27 @@ class ScrapyCommand: Entry point for running commands """ raise NotImplementedError + + +class BaseRunSpiderCommand(ScrapyCommand): + """ + Common class used to share functionality between the crawl and runspider commands + """ + def add_options(self, parser): + ScrapyCommand.add_options(self, parser) + parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE", + help="set spider argument (may be repeated)") + parser.add_option("-o", "--output", metavar="FILE", action="append", + help="dump scraped items into FILE (use - for stdout)") + parser.add_option("-t", "--output-format", metavar="FORMAT", + help="format to use for dumping items with -o") + + def process_options(self, args, opts): + ScrapyCommand.process_options(self, args, opts) + try: + opts.spargs = arglist_to_dict(opts.spargs) + except ValueError: + raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False) + if opts.output: + feeds = feed_process_params_from_cli(self.settings, opts.output, opts.output_format) + self.settings.set('FEEDS', feeds, priority='cmdline') diff --git a/scrapy/commands/crawl.py b/scrapy/commands/crawl.py index 4b2f9484b..e1724c1e6 100644 --- a/scrapy/commands/crawl.py +++ b/scrapy/commands/crawl.py @@ -1,9 +1,8 @@ -from scrapy.commands import ScrapyCommand -from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli +from scrapy.commands import BaseRunSpiderCommand from scrapy.exceptions import UsageError -class Command(ScrapyCommand): +class Command(BaseRunSpiderCommand): requires_project = True @@ -13,25 +12,6 @@ class Command(ScrapyCommand): def short_desc(self): return "Run a spider" - def add_options(self, parser): - ScrapyCommand.add_options(self, parser) - parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE", - help="set spider argument (may be repeated)") - parser.add_option("-o", "--output", metavar="FILE", action="append", - help="dump scraped items into FILE (use - for stdout)") - parser.add_option("-t", "--output-format", metavar="FORMAT", - help="format to use for dumping items with -o") - - def process_options(self, args, opts): - ScrapyCommand.process_options(self, args, opts) - try: - opts.spargs = arglist_to_dict(opts.spargs) - except ValueError: - raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False) - if opts.output: - feeds = feed_process_params_from_cli(self.settings, opts.output, opts.output_format) - self.settings.set('FEEDS', feeds, priority='cmdline') - def run(self, args, opts): if len(args) < 1: raise UsageError() diff --git a/scrapy/commands/runspider.py b/scrapy/commands/runspider.py index 62510609a..befee021b 100644 --- a/scrapy/commands/runspider.py +++ b/scrapy/commands/runspider.py @@ -3,9 +3,8 @@ import os from importlib import import_module from scrapy.utils.spider import iter_spider_classes -from scrapy.commands import ScrapyCommand from scrapy.exceptions import UsageError -from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli +from scrapy.commands import BaseRunSpiderCommand def _import_file(filepath): @@ -24,7 +23,7 @@ def _import_file(filepath): return module -class Command(ScrapyCommand): +class Command(BaseRunSpiderCommand): requires_project = False default_settings = {'SPIDER_LOADER_WARN_ONLY': True} @@ -38,25 +37,6 @@ class Command(ScrapyCommand): def long_desc(self): return "Run the spider defined in the given file" - def add_options(self, parser): - ScrapyCommand.add_options(self, parser) - parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE", - help="set spider argument (may be repeated)") - parser.add_option("-o", "--output", metavar="FILE", action="append", - help="dump scraped items into FILE (use - for stdout)") - parser.add_option("-t", "--output-format", metavar="FORMAT", - help="format to use for dumping items with -o") - - def process_options(self, args, opts): - ScrapyCommand.process_options(self, args, opts) - try: - opts.spargs = arglist_to_dict(opts.spargs) - except ValueError: - raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False) - if opts.output: - feeds = feed_process_params_from_cli(self.settings, opts.output, opts.output_format) - self.settings.set('FEEDS', feeds, priority='cmdline') - def run(self, args, opts): if len(args) != 1: raise UsageError() diff --git a/scrapy/core/downloader/handlers/http11.py b/scrapy/core/downloader/handlers/http11.py index c21491f52..22c9ac520 100644 --- a/scrapy/core/downloader/handlers/http11.py +++ b/scrapy/core/downloader/handlers/http11.py @@ -12,6 +12,7 @@ from urllib.parse import urldefrag from twisted.internet import defer, protocol, ssl from twisted.internet.endpoints import TCP4ClientEndpoint from twisted.internet.error import TimeoutError +from twisted.python.failure import Failure from twisted.web.client import Agent, HTTPConnectionPool, ResponseDone, ResponseFailed, URI from twisted.web.http import _DataLoss, PotentialDataLoss from twisted.web.http_headers import Headers as TxHeaders @@ -21,7 +22,7 @@ from zope.interface import implementer from scrapy import signals from scrapy.core.downloader.tls import openssl_methods from scrapy.core.downloader.webclient import _parse -from scrapy.exceptions import ScrapyDeprecationWarning +from scrapy.exceptions import ScrapyDeprecationWarning, StopDownload from scrapy.http import Headers from scrapy.responsetypes import responsetypes from scrapy.utils.misc import create_instance, load_object @@ -431,7 +432,7 @@ class ScrapyAgent: def _cb_bodydone(self, result, request, url): headers = Headers(result["txresponse"].headers.getAllRawHeaders()) respcls = responsetypes.from_args(headers=headers, url=url, body=result["body"]) - return respcls( + response = respcls( url=url, status=int(result["txresponse"].code), headers=headers, @@ -440,6 +441,10 @@ class ScrapyAgent: certificate=result["certificate"], ip_address=result["ip_address"], ) + if result.get("failure"): + result["failure"].value.response = response + return result["failure"] + return response @implementer(IBodyProducer) @@ -477,6 +482,16 @@ class _ResponseReader(protocol.Protocol): self._ip_address = None self._crawler = crawler + def _finish_response(self, flags=None, failure=None): + self._finished.callback({ + "txresponse": self._txresponse, + "body": self._bodybuf.getvalue(), + "flags": flags, + "certificate": self._certificate, + "ip_address": self._ip_address, + "failure": failure, + }) + def connectionMade(self): if self._certificate is None: with suppress(AttributeError): @@ -493,12 +508,19 @@ class _ResponseReader(protocol.Protocol): self._bodybuf.write(bodyBytes) self._bytes_received += len(bodyBytes) - self._crawler.signals.send_catch_log( + bytes_received_result = self._crawler.signals.send_catch_log( signal=signals.bytes_received, data=bodyBytes, request=self._request, spider=self._crawler.spider, ) + for handler, result in bytes_received_result: + if isinstance(result, Failure) and isinstance(result.value, StopDownload): + logger.debug("Download stopped for %(request)s from signal handler %(handler)s", + {"request": self._request, "handler": handler.__qualname__}) + self.transport._producer.loseConnection() + failure = result if result.value.fail else None + self._finish_response(flags=["download_stopped"], failure=failure) if self._maxsize and self._bytes_received > self._maxsize: logger.error("Received (%(bytes)s) bytes larger than download " @@ -521,36 +543,17 @@ class _ResponseReader(protocol.Protocol): if self._finished.called: return - body = self._bodybuf.getvalue() if reason.check(ResponseDone): - self._finished.callback({ - "txresponse": self._txresponse, - "body": body, - "flags": None, - "certificate": self._certificate, - "ip_address": self._ip_address, - }) + self._finish_response() return if reason.check(PotentialDataLoss): - self._finished.callback({ - "txresponse": self._txresponse, - "body": body, - "flags": ["partial"], - "certificate": self._certificate, - "ip_address": self._ip_address, - }) + self._finish_response(flags=["partial"]) return if reason.check(ResponseFailed) and any(r.check(_DataLoss) for r in reason.value.reasons): if not self._fail_on_dataloss: - self._finished.callback({ - "txresponse": self._txresponse, - "body": body, - "flags": ["dataloss"], - "certificate": self._certificate, - "ip_address": self._ip_address, - }) + self._finish_response(flags=["dataloss"]) return elif not self._fail_on_dataloss_warned: diff --git a/scrapy/downloadermiddlewares/cookies.py b/scrapy/downloadermiddlewares/cookies.py index d57f04bc3..77048f389 100644 --- a/scrapy/downloadermiddlewares/cookies.py +++ b/scrapy/downloadermiddlewares/cookies.py @@ -29,8 +29,7 @@ class CookiesMiddleware: cookiejarkey = request.meta.get("cookiejar") jar = self.jars[cookiejarkey] - cookies = self._get_request_cookies(jar, request) - for cookie in cookies: + for cookie in self._get_request_cookies(jar, request): jar.set_cookie_if_ok(cookie, request) # set Cookie header @@ -68,28 +67,65 @@ class CookiesMiddleware: msg = "Received cookies from: {}\n{}".format(response, cookies) logger.debug(msg, extra={'spider': spider}) - def _format_cookie(self, cookie): - # build cookie string - cookie_str = '%s=%s' % (cookie['name'], cookie['value']) - - if cookie.get('path', None): - cookie_str += '; Path=%s' % cookie['path'] - if cookie.get('domain', None): - cookie_str += '; Domain=%s' % cookie['domain'] + def _format_cookie(self, cookie, request): + """ + Given a dict consisting of cookie components, return its string representation. + Decode from bytes if necessary. + """ + decoded = {} + for key in ("name", "value", "path", "domain"): + if not cookie.get(key): + if key in ("name", "value"): + msg = "Invalid cookie found in request {}: {} ('{}' is missing)" + logger.warning(msg.format(request, cookie, key)) + return + continue + if isinstance(cookie[key], str): + decoded[key] = cookie[key] + else: + try: + decoded[key] = cookie[key].decode("utf8") + except UnicodeDecodeError: + logger.warning("Non UTF-8 encoded cookie found in request %s: %s", + request, cookie) + decoded[key] = cookie[key].decode("latin1", errors="replace") + cookie_str = "{}={}".format(decoded.pop("name"), decoded.pop("value")) + for key, value in decoded.items(): # path, domain + cookie_str += "; {}={}".format(key.capitalize(), value) return cookie_str def _get_request_cookies(self, jar, request): - if isinstance(request.cookies, dict): - cookie_list = [ - {'name': k, 'value': v} - for k, v in request.cookies.items() - ] - else: - cookie_list = request.cookies + """ + Extract cookies from a Request. Values from the `Request.cookies` attribute + take precedence over values from the `Cookie` request header. + """ + def get_cookies_from_header(jar, request): + cookie_header = request.headers.get("Cookie") + if not cookie_header: + return [] + cookie_gen_bytes = (s.strip() for s in cookie_header.split(b";")) + cookie_list_unicode = [] + for cookie_bytes in cookie_gen_bytes: + try: + cookie_unicode = cookie_bytes.decode("utf8") + except UnicodeDecodeError: + logger.warning("Non UTF-8 encoded cookie found in request %s: %s", + request, cookie_bytes) + cookie_unicode = cookie_bytes.decode("latin1", errors="replace") + cookie_list_unicode.append(cookie_unicode) + response = Response(request.url, headers={"Set-Cookie": cookie_list_unicode}) + return jar.make_cookies(response, request) - cookies = [self._format_cookie(x) for x in cookie_list] - headers = {'Set-Cookie': cookies} - response = Response(request.url, headers=headers) + def get_cookies_from_attribute(jar, request): + if not request.cookies: + return [] + elif isinstance(request.cookies, dict): + cookies = ({"name": k, "value": v} for k, v in request.cookies.items()) + else: + cookies = request.cookies + formatted = filter(None, (self._format_cookie(c, request) for c in cookies)) + response = Response(request.url, headers={"Set-Cookie": formatted}) + return jar.make_cookies(response, request) - return jar.make_cookies(response, request) + return get_cookies_from_header(jar, request) + get_cookies_from_attribute(jar, request) diff --git a/scrapy/exceptions.py b/scrapy/exceptions.py index 7c4bb3d00..45f152321 100644 --- a/scrapy/exceptions.py +++ b/scrapy/exceptions.py @@ -41,6 +41,18 @@ class CloseSpider(Exception): self.reason = reason +class StopDownload(Exception): + """ + Stop the download of the body for a given response. + The 'fail' boolean parameter indicates whether or not the resulting partial response + should be handled by the request errback. Note that 'fail' is a keyword-only argument. + """ + + def __init__(self, *, fail=True): + super().__init__() + self.fail = fail + + # Items @@ -59,6 +71,7 @@ class NotSupported(Exception): class UsageError(Exception): """To indicate a command-line usage error""" + def __init__(self, *a, **kw): self.print_help = kw.pop('print_help', True) super(UsageError, self).__init__(*a, **kw) diff --git a/scrapy/http/response/text.py b/scrapy/http/response/text.py index 0603b6653..40cf3f483 100644 --- a/scrapy/http/response/text.py +++ b/scrapy/http/response/text.py @@ -5,6 +5,7 @@ discovering (through HTTP headers) to base Response class. See documentation in docs/topics/request-response.rst """ +import json import warnings from contextlib import suppress from typing import Generator @@ -21,10 +22,13 @@ from scrapy.http.response import Response from scrapy.utils.python import memoizemethod_noargs, to_unicode from scrapy.utils.response import get_base_url +_NONE = object() + class TextResponse(Response): _DEFAULT_ENCODING = 'ascii' + _cached_decoded_json = _NONE def __init__(self, *args, **kwargs): self._encoding = kwargs.pop('encoding', None) @@ -68,6 +72,14 @@ class TextResponse(Response): ScrapyDeprecationWarning, stacklevel=2) return self.text + def json(self): + """ + Deserialize a JSON document to a Python object. + """ + if self._cached_decoded_json is _NONE: + self._cached_decoded_json = json.loads(self.text) + return self._cached_decoded_json + @property def text(self): """ Body as unicode """ diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.py index ae019c70f..984a5c4e1 100644 --- a/scrapy/linkextractors/__init__.py +++ b/scrapy/linkextractors/__init__.py @@ -133,4 +133,4 @@ class FilteringLinkExtractor: # Top-level imports -from scrapy.linkextractors.lxmlhtml import LxmlLinkExtractor as LinkExtractor # noqa: F401 +from scrapy.linkextractors.lxmlhtml import LxmlLinkExtractor as LinkExtractor diff --git a/scrapy/selector/__init__.py b/scrapy/selector/__init__.py index a9240c1f6..85c500d66 100644 --- a/scrapy/selector/__init__.py +++ b/scrapy/selector/__init__.py @@ -1,4 +1,6 @@ """ Selectors """ -from scrapy.selector.unified import * # noqa: F401 + +# top-level imports +from scrapy.selector.unified import Selector, SelectorList diff --git a/scrapy/spiders/__init__.py b/scrapy/spiders/__init__.py index ba1c866f8..02f87f8f5 100644 --- a/scrapy/spiders/__init__.py +++ b/scrapy/spiders/__init__.py @@ -110,6 +110,6 @@ class Spider(object_ref): # Top-level imports -from scrapy.spiders.crawl import CrawlSpider, Rule # noqa: F401 -from scrapy.spiders.feed import XMLFeedSpider, CSVFeedSpider # noqa: F401 -from scrapy.spiders.sitemap import SitemapSpider # noqa: F401 +from scrapy.spiders.crawl import CrawlSpider, Rule +from scrapy.spiders.feed import XMLFeedSpider, CSVFeedSpider +from scrapy.spiders.sitemap import SitemapSpider diff --git a/scrapy/utils/datatypes.py b/scrapy/utils/datatypes.py index f59f4cc55..2a92d0588 100644 --- a/scrapy/utils/datatypes.py +++ b/scrapy/utils/datatypes.py @@ -105,8 +105,8 @@ class LocalWeakReferencedCache(weakref.WeakKeyDictionary): def __getitem__(self, key): try: return super(LocalWeakReferencedCache, self).__getitem__(key) - except TypeError: - return None # key is not weak-referenceable, it's not cached + except (TypeError, KeyError): + return None # key is either not weak-referenceable or not cached class SequenceExclude: diff --git a/scrapy/utils/signal.py b/scrapy/utils/signal.py index a311e9257..115707182 100644 --- a/scrapy/utils/signal.py +++ b/scrapy/utils/signal.py @@ -5,13 +5,14 @@ import logging from twisted.internet.defer import DeferredList, Deferred from twisted.python.failure import Failure -from pydispatch.dispatcher import Any, Anonymous, liveReceivers, \ - getAllReceivers, disconnect +from pydispatch.dispatcher import Anonymous, Any, disconnect, getAllReceivers, liveReceivers from pydispatch.robustapply import robustApply +from scrapy.exceptions import StopDownload from scrapy.utils.defer import maybeDeferred_coro from scrapy.utils.log import failure_to_exc_info + logger = logging.getLogger(__name__) @@ -23,7 +24,7 @@ def send_catch_log(signal=Any, sender=Anonymous, *arguments, **named): """Like pydispatcher.robust.sendRobust but it also logs errors and returns Failures instead of exceptions. """ - dont_log = named.pop('dont_log', _IgnoredException) + dont_log = (named.pop('dont_log', _IgnoredException), StopDownload) spider = named.get('spider', None) responses = [] for receiver in liveReceivers(getAllReceivers(sender, signal)): diff --git a/scrapy/utils/spider.py b/scrapy/utils/spider.py index 346ad772f..5bfeae2ef 100644 --- a/scrapy/utils/spider.py +++ b/scrapy/utils/spider.py @@ -1,5 +1,5 @@ -import logging import inspect +import logging from scrapy.spiders import Spider from scrapy.utils.defer import deferred_from_coro, _isasyncgen @@ -18,7 +18,11 @@ def iterate_spider_output(result): d = deferred_from_coro(collect_asyncgen(result)) d.addCallback(iterate_spider_output) return d - return arg_to_iter(deferred_from_coro(result)) + elif inspect.iscoroutine(result): + d = deferred_from_coro(result) + d.addCallback(iterate_spider_output) + return d + return arg_to_iter(result) def iter_spider_classes(module): diff --git a/tests/requirements-py3.txt b/tests/requirements-py3.txt index d207c5fb0..91fa1c5b5 100644 --- a/tests/requirements-py3.txt +++ b/tests/requirements-py3.txt @@ -2,7 +2,8 @@ jmespath mitmproxy; python_version >= '3.6' mitmproxy<4.0.0; python_version < '3.6' -pytest < 5.4 +# https://github.com/pytest-dev/pytest-twisted/issues/93 +pytest != 5.4, != 5.4.1 pytest-cov pytest-twisted >= 1.11 pytest-xdist diff --git a/tests/spiders.py b/tests/spiders.py index 33d5d02e1..a360d8206 100644 --- a/tests/spiders.py +++ b/tests/spiders.py @@ -7,6 +7,8 @@ from urllib.parse import urlencode from twisted.internet import defer +from scrapy import signals +from scrapy.exceptions import StopDownload from scrapy.http import Request from scrapy.item import Item from scrapy.linkextractors import LinkExtractor @@ -117,6 +119,17 @@ class AsyncDefAsyncioReturnSpider(SimpleSpider): return [{'id': 1}, {'id': 2}] +class AsyncDefAsyncioReturnSingleElementSpider(SimpleSpider): + + name = "asyncdef_asyncio_return_single_element" + + async def parse(self, response): + await asyncio.sleep(0.1) + status = await get_from_asyncio_queue(response.status) + self.logger.info("Got response %d" % status) + return {"foo": 42} + + class AsyncDefAsyncioReqsReturnSpider(SimpleSpider): name = 'asyncdef_asyncio_reqs_return' @@ -267,3 +280,36 @@ class CrawlSpiderWithErrback(MockServerSpider, CrawlSpider): def errback(self, failure): self.logger.info('[errback] status %i', failure.value.response.status) + + +class BytesReceivedCallbackSpider(MetaSpider): + + full_response_length = 2**18 + + @classmethod + def from_crawler(cls, crawler, *args, **kwargs): + spider = super().from_crawler(crawler, *args, **kwargs) + crawler.signals.connect(spider.bytes_received, signals.bytes_received) + return spider + + def start_requests(self): + body = b"a" * self.full_response_length + url = self.mockserver.url("/alpayload") + yield Request(url, method="POST", body=body, errback=self.errback) + + def parse(self, response): + self.meta["response"] = response + + def errback(self, failure): + self.meta["failure"] = failure + + def bytes_received(self, data, request, spider): + self.meta["bytes_received"] = data + raise StopDownload(fail=False) + + +class BytesReceivedErrbackSpider(BytesReceivedCallbackSpider): + + def bytes_received(self, data, request, spider): + self.meta["bytes_received"] = data + raise StopDownload(fail=True) diff --git a/tests/test_crawl.py b/tests/test_crawl.py index 84f80d103..df920f2a2 100644 --- a/tests/test_crawl.py +++ b/tests/test_crawl.py @@ -9,17 +9,32 @@ from pytest import mark from testfixtures import LogCapture from twisted.internet import defer from twisted.internet.ssl import Certificate +from twisted.python.failure import Failure from twisted.trial.unittest import TestCase from scrapy import signals from scrapy.crawler import CrawlerRunner +from scrapy.exceptions import StopDownload from scrapy.http import Request +from scrapy.http.response import Response from scrapy.utils.python import to_unicode from tests.mockserver import MockServer -from tests.spiders import (FollowAllSpider, DelaySpider, SimpleSpider, BrokenStartRequestsSpider, - SingleRequestSpider, DuplicateStartRequestsSpider, CrawlSpiderWithErrback, - AsyncDefSpider, AsyncDefAsyncioSpider, AsyncDefAsyncioReturnSpider, - AsyncDefAsyncioReqsReturnSpider) +from tests.spiders import ( + AsyncDefAsyncioReqsReturnSpider, + AsyncDefAsyncioReturnSingleElementSpider, + AsyncDefAsyncioReturnSpider, + AsyncDefAsyncioSpider, + AsyncDefSpider, + BrokenStartRequestsSpider, + BytesReceivedCallbackSpider, + BytesReceivedErrbackSpider, + CrawlSpiderWithErrback, + DelaySpider, + DuplicateStartRequestsSpider, + FollowAllSpider, + SimpleSpider, + SingleRequestSpider, +) class CrawlTestCase(TestCase): @@ -350,6 +365,21 @@ with multiples lines self.assertIn({'id': 1}, items) self.assertIn({'id': 2}, items) + @mark.only_asyncio() + @defer.inlineCallbacks + def test_async_def_asyncio_parse_items_single_element(self): + items = [] + + def _on_item_scraped(item): + items.append(item) + + crawler = self.runner.create_crawler(AsyncDefAsyncioReturnSingleElementSpider) + crawler.signals.connect(_on_item_scraped, signals.item_scraped) + with LogCapture() as log: + yield crawler.crawl(self.mockserver.url("/status?n=200"), mockserver=self.mockserver) + self.assertIn("Got response 200", str(log)) + self.assertIn({"foo": 42}, items) + @mark.skipif(sys.version_info < (3, 6), reason="Async generators require Python 3.6 or higher") @mark.only_asyncio() @defer.inlineCallbacks @@ -457,3 +487,27 @@ with multiples lines ip_address = crawler.spider.meta['responses'][0].ip_address self.assertIsInstance(ip_address, IPv4Address) self.assertEqual(str(ip_address), gethostbyname(expected_netloc)) + + @defer.inlineCallbacks + def test_stop_download_callback(self): + crawler = self.runner.create_crawler(BytesReceivedCallbackSpider) + yield crawler.crawl(mockserver=self.mockserver) + self.assertIsNone(crawler.spider.meta.get("failure")) + self.assertIsInstance(crawler.spider.meta["response"], Response) + self.assertEqual(crawler.spider.meta["response"].body, crawler.spider.meta.get("bytes_received")) + self.assertLess(len(crawler.spider.meta["response"].body), crawler.spider.full_response_length) + + @defer.inlineCallbacks + def test_stop_download_errback(self): + crawler = self.runner.create_crawler(BytesReceivedErrbackSpider) + yield crawler.crawl(mockserver=self.mockserver) + self.assertIsNone(crawler.spider.meta.get("response")) + self.assertIsInstance(crawler.spider.meta["failure"], Failure) + self.assertIsInstance(crawler.spider.meta["failure"].value, StopDownload) + self.assertIsInstance(crawler.spider.meta["failure"].value.response, Response) + self.assertEqual( + crawler.spider.meta["failure"].value.response.body, + crawler.spider.meta.get("bytes_received")) + self.assertLess( + len(crawler.spider.meta["failure"].value.response.body), + crawler.spider.full_response_length) diff --git a/tests/test_downloadermiddleware_cookies.py b/tests/test_downloadermiddleware_cookies.py index d54434c8f..9ccc2110b 100644 --- a/tests/test_downloadermiddleware_cookies.py +++ b/tests/test_downloadermiddleware_cookies.py @@ -1,20 +1,21 @@ -import re import logging -from unittest import TestCase from testfixtures import LogCapture +from unittest import TestCase +from scrapy.downloadermiddlewares.cookies import CookiesMiddleware +from scrapy.downloadermiddlewares.defaultheaders import DefaultHeadersMiddleware +from scrapy.exceptions import NotConfigured from scrapy.http import Response, Request from scrapy.spiders import Spider +from scrapy.utils.python import to_bytes from scrapy.utils.test import get_crawler -from scrapy.exceptions import NotConfigured -from scrapy.downloadermiddlewares.cookies import CookiesMiddleware class CookiesMiddlewareTest(TestCase): def assertCookieValEqual(self, first, second, msg=None): def split_cookies(cookies): - return sorted(re.split(r";\s*", cookies.decode("latin1"))) + return sorted([s.strip() for s in to_bytes(cookies).split(b";")]) return self.assertEqual(split_cookies(first), split_cookies(second), msg=msg) def setUp(self): @@ -61,12 +62,13 @@ class CookiesMiddlewareTest(TestCase): def test_setting_enabled_cookies_debug(self): crawler = get_crawler(settings_dict={'COOKIES_DEBUG': True}) mw = CookiesMiddleware.from_crawler(crawler) - with LogCapture('scrapy.downloadermiddlewares.cookies', - propagate=False, - level=logging.DEBUG) as log: + with LogCapture( + 'scrapy.downloadermiddlewares.cookies', + propagate=False, + level=logging.DEBUG, + ) as log: req = Request('http://scrapytest.org/') - res = Response('http://scrapytest.org/', - headers={'Set-Cookie': 'C1=value1; path=/'}) + res = Response('http://scrapytest.org/', headers={'Set-Cookie': 'C1=value1; path=/'}) mw.process_response(req, res, crawler.spider) req2 = Request('http://scrapytest.org/sub1/') mw.process_request(req2, crawler.spider) @@ -85,12 +87,13 @@ class CookiesMiddlewareTest(TestCase): def test_setting_disabled_cookies_debug(self): crawler = get_crawler(settings_dict={'COOKIES_DEBUG': False}) mw = CookiesMiddleware.from_crawler(crawler) - with LogCapture('scrapy.downloadermiddlewares.cookies', - propagate=False, - level=logging.DEBUG) as log: + with LogCapture( + 'scrapy.downloadermiddlewares.cookies', + propagate=False, + level=logging.DEBUG, + ) as log: req = Request('http://scrapytest.org/') - res = Response('http://scrapytest.org/', - headers={'Set-Cookie': 'C1=value1; path=/'}) + res = Response('http://scrapytest.org/', headers={'Set-Cookie': 'C1=value1; path=/'}) mw.process_response(req, res, crawler.spider) req2 = Request('http://scrapytest.org/sub1/') mw.process_request(req2, crawler.spider) @@ -102,8 +105,7 @@ class CookiesMiddlewareTest(TestCase): assert self.mw.process_request(req, self.spider) is None assert 'Cookie' not in req.headers - headers = {'Set-Cookie': b'C1=in\xa3valid; path=/', - 'Other': b'ignore\xa3me'} + headers = {'Set-Cookie': b'C1=in\xa3valid; path=/', 'Other': b'ignore\xa3me'} res = Response('http://scrapytest.org/', headers=headers) assert self.mw.process_response(req, res, self.spider) is res @@ -124,7 +126,10 @@ class CookiesMiddlewareTest(TestCase): assert 'Cookie' not in req.headers # check that returned cookies are not merged back to jar - res = Response('http://scrapytest.org/dontmerge', headers={'Set-Cookie': 'dont=mergeme; path=/'}) + res = Response( + 'http://scrapytest.org/dontmerge', + headers={'Set-Cookie': 'dont=mergeme; path=/'}, + ) assert self.mw.process_response(req, res, self.spider) is res # check that cookies are merged back @@ -179,7 +184,11 @@ class CookiesMiddlewareTest(TestCase): self.assertCookieValEqual(req2.headers.get('Cookie'), b"C1=value1; galleta=salada") def test_cookiejar_key(self): - req = Request('http://scrapytest.org/', cookies={'galleta': 'salada'}, meta={'cookiejar': "store1"}) + req = Request( + 'http://scrapytest.org/', + cookies={'galleta': 'salada'}, + meta={'cookiejar': "store1"}, + ) assert self.mw.process_request(req, self.spider) is None self.assertEqual(req.headers.get('Cookie'), b'galleta=salada') @@ -191,7 +200,11 @@ class CookiesMiddlewareTest(TestCase): assert self.mw.process_request(req2, self.spider) is None self.assertCookieValEqual(req2.headers.get('Cookie'), b'C1=value1; galleta=salada') - req3 = Request('http://scrapytest.org/', cookies={'galleta': 'dulce'}, meta={'cookiejar': "store2"}) + req3 = Request( + 'http://scrapytest.org/', + cookies={'galleta': 'dulce'}, + meta={'cookiejar': "store2"}, + ) assert self.mw.process_request(req3, self.spider) is None self.assertEqual(req3.headers.get('Cookie'), b'galleta=dulce') @@ -229,3 +242,95 @@ class CookiesMiddlewareTest(TestCase): assert self.mw.process_request(request, self.spider) is None self.assertIn('Cookie', request.headers) self.assertEqual(b'currencyCookie=USD', request.headers['Cookie']) + + def test_keep_cookie_from_default_request_headers_middleware(self): + DEFAULT_REQUEST_HEADERS = dict(Cookie='default=value; asdf=qwerty') + mw_default_headers = DefaultHeadersMiddleware(DEFAULT_REQUEST_HEADERS.items()) + # overwrite with values from 'cookies' request argument + req1 = Request('http://example.org', cookies={'default': 'something'}) + assert mw_default_headers.process_request(req1, self.spider) is None + assert self.mw.process_request(req1, self.spider) is None + self.assertCookieValEqual(req1.headers['Cookie'], b'default=something; asdf=qwerty') + # keep both + req2 = Request('http://example.com', cookies={'a': 'b'}) + assert mw_default_headers.process_request(req2, self.spider) is None + assert self.mw.process_request(req2, self.spider) is None + self.assertCookieValEqual(req2.headers['Cookie'], b'default=value; a=b; asdf=qwerty') + + def test_keep_cookie_header(self): + # keep only cookies from 'Cookie' request header + req1 = Request('http://scrapytest.org', headers={'Cookie': 'a=b; c=d'}) + assert self.mw.process_request(req1, self.spider) is None + self.assertCookieValEqual(req1.headers['Cookie'], 'a=b; c=d') + # keep cookies from both 'Cookie' request header and 'cookies' keyword + req2 = Request('http://scrapytest.org', headers={'Cookie': 'a=b; c=d'}, cookies={'e': 'f'}) + assert self.mw.process_request(req2, self.spider) is None + self.assertCookieValEqual(req2.headers['Cookie'], 'a=b; c=d; e=f') + # overwrite values from 'Cookie' request header with 'cookies' keyword + req3 = Request( + 'http://scrapytest.org', + headers={'Cookie': 'a=b; c=d'}, + cookies={'a': 'new', 'e': 'f'}, + ) + assert self.mw.process_request(req3, self.spider) is None + self.assertCookieValEqual(req3.headers['Cookie'], 'a=new; c=d; e=f') + + def test_request_cookies_encoding(self): + # 1) UTF8-encoded bytes + req1 = Request('http://example.org', cookies={'a': u'á'.encode('utf8')}) + assert self.mw.process_request(req1, self.spider) is None + self.assertCookieValEqual(req1.headers['Cookie'], b'a=\xc3\xa1') + + # 2) Non UTF8-encoded bytes + req2 = Request('http://example.org', cookies={'a': u'á'.encode('latin1')}) + assert self.mw.process_request(req2, self.spider) is None + self.assertCookieValEqual(req2.headers['Cookie'], b'a=\xc3\xa1') + + # 3) Unicode string + req3 = Request('http://example.org', cookies={'a': u'á'}) + assert self.mw.process_request(req3, self.spider) is None + self.assertCookieValEqual(req3.headers['Cookie'], b'a=\xc3\xa1') + + def test_request_headers_cookie_encoding(self): + # 1) UTF8-encoded bytes + req1 = Request('http://example.org', headers={'Cookie': u'a=á'.encode('utf8')}) + assert self.mw.process_request(req1, self.spider) is None + self.assertCookieValEqual(req1.headers['Cookie'], b'a=\xc3\xa1') + + # 2) Non UTF8-encoded bytes + req2 = Request('http://example.org', headers={'Cookie': u'a=á'.encode('latin1')}) + assert self.mw.process_request(req2, self.spider) is None + self.assertCookieValEqual(req2.headers['Cookie'], b'a=\xc3\xa1') + + # 3) Unicode string + req3 = Request('http://example.org', headers={'Cookie': u'a=á'}) + assert self.mw.process_request(req3, self.spider) is None + self.assertCookieValEqual(req3.headers['Cookie'], b'a=\xc3\xa1') + + def test_invalid_cookies(self): + """ + Invalid cookies are logged as warnings and discarded + """ + with LogCapture( + 'scrapy.downloadermiddlewares.cookies', + propagate=False, + level=logging.INFO, + ) as lc: + cookies1 = [{'value': 'bar'}, {'name': 'key', 'value': 'value1'}] + req1 = Request('http://example.org/1', cookies=cookies1) + assert self.mw.process_request(req1, self.spider) is None + cookies2 = [{'name': 'foo'}, {'name': 'key', 'value': 'value2'}] + req2 = Request('http://example.org/2', cookies=cookies2) + assert self.mw.process_request(req2, self.spider) is None + lc.check( + ("scrapy.downloadermiddlewares.cookies", + "WARNING", + "Invalid cookie found in request <GET http://example.org/1>:" + " {'value': 'bar'} ('name' is missing)"), + ("scrapy.downloadermiddlewares.cookies", + "WARNING", + "Invalid cookie found in request <GET http://example.org/2>:" + " {'name': 'foo'} ('value' is missing)"), + ) + self.assertCookieValEqual(req1.headers['Cookie'], 'key=value1') + self.assertCookieValEqual(req2.headers['Cookie'], 'key=value2') diff --git a/tests/test_engine.py b/tests/test_engine.py index 827f803a4..4c6a88116 100644 --- a/tests/test_engine.py +++ b/tests/test_engine.py @@ -16,14 +16,16 @@ import sys from collections import defaultdict from urllib.parse import urlparse +from pydispatch import dispatcher from pytest import mark +from testfixtures import LogCapture from twisted.internet import reactor, defer from twisted.trial import unittest from twisted.web import server, static, util -from pydispatch import dispatcher from scrapy import signals from scrapy.core.engine import ExecutionEngine +from scrapy.exceptions import StopDownload from scrapy.http import Request from scrapy.item import Item, Field from scrapy.linkextractors import LinkExtractor @@ -96,7 +98,7 @@ def start_test_site(debug=False): r = static.File(root_dir) r.putChild(b"redirect", util.Redirect(b"/redirected")) r.putChild(b"redirected", static.Data(b"Redirected here", "text/plain")) - numbers = [str(x).encode("utf8") for x in range(2**14)] + numbers = [str(x).encode("utf8") for x in range(2**18)] r.putChild(b"numbers", static.Data(b"".join(numbers), "text/plain")) port = reactor.listenTCP(0, server.Site(r), interface="127.0.0.1") @@ -194,6 +196,16 @@ class CrawlerRun: self.signals_caught[sig] = signalargs +class StopDownloadCrawlerRun(CrawlerRun): + """ + Make sure raising the StopDownload exception stops the download of the response body + """ + + def bytes_received(self, data, request, spider): + super().bytes_received(data, request, spider) + raise StopDownload(fail=False) + + class EngineTest(unittest.TestCase): @defer.inlineCallbacks @@ -345,7 +357,7 @@ class EngineTest(unittest.TestCase): # signal was fired multiple times self.assertTrue(len(data) > 1) # bytes were received in order - numbers = [str(x).encode("utf8") for x in range(2**14)] + numbers = [str(x).encode("utf8") for x in range(2**18)] self.assertEqual(joined_data, b"".join(numbers)) def _assert_signals_caught(self): @@ -386,6 +398,45 @@ class EngineTest(unittest.TestCase): self.assertEqual(len(e.open_spiders), 0) +class StopDownloadEngineTest(EngineTest): + + @defer.inlineCallbacks + def test_crawler(self): + for spider in TestSpider, DictItemsSpider: + self.run = StopDownloadCrawlerRun(spider) + with LogCapture() as log: + yield self.run.run() + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + "Download stopped for <GET http://localhost:{}/redirected> from signal handler" + " StopDownloadCrawlerRun.bytes_received".format(self.run.portno))) + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + "Download stopped for <GET http://localhost:{}/> from signal handler" + " StopDownloadCrawlerRun.bytes_received".format(self.run.portno))) + log.check_present(("scrapy.core.downloader.handlers.http11", + "DEBUG", + "Download stopped for <GET http://localhost:{}/numbers> from signal handler" + " StopDownloadCrawlerRun.bytes_received".format(self.run.portno))) + self._assert_visited_urls() + self._assert_scheduled_requests(urls_to_visit=9) + self._assert_downloaded_responses() + self._assert_signals_caught() + self._assert_bytes_received() + + def _assert_bytes_received(self): + self.assertEqual(9, len(self.run.bytes)) + for request, data in self.run.bytes.items(): + joined_data = b"".join(data) + self.assertTrue(len(data) == 1) # signal was fired only once + if self.run.getpath(request.url) == "/numbers": + # Received bytes are not the complete response. The exact amount depends + # on the buffer size, which can vary, so we only check that the amount + # of received bytes is strictly less than the full response. + numbers = [str(x).encode("utf8") for x in range(2**18)] + self.assertTrue(len(joined_data) < len(b"".join(numbers))) + + if __name__ == "__main__": if len(sys.argv) > 1 and sys.argv[1] == 'runserver': start_test_site(debug=True) diff --git a/tests/test_http_response.py b/tests/test_http_response.py index 039e863f4..e0ca3c0e6 100644 --- a/tests/test_http_response.py +++ b/tests/test_http_response.py @@ -1,4 +1,5 @@ import unittest +from unittest import mock from warnings import catch_warnings from w3lib.encoding import resolve_encoding @@ -685,6 +686,26 @@ class TextResponseTest(BaseResponseTest): self.assertEqual(len(warnings), 1) self.assertEqual(warnings[0].category, ScrapyDeprecationWarning) + def test_json_response(self): + json_body = b"""{"ip": "109.187.217.200"}""" + json_response = self.response_class("http://www.example.com", body=json_body) + self.assertEqual(json_response.json(), {'ip': '109.187.217.200'}) + + text_body = b"""<html><body>text</body></html>""" + text_response = self.response_class("http://www.example.com", body=text_body) + with self.assertRaises(ValueError): + text_response.json() + + def test_cache_json_response(self): + json_valid_bodies = [b"""{"ip": "109.187.217.200"}""", b"""null"""] + for json_body in json_valid_bodies: + json_response = self.response_class("http://www.example.com", body=json_body) + + with mock.patch('json.loads') as mock_json: + for _ in range(2): + json_response.json() + mock_json.assert_called_once_with(json_body.decode()) + class HtmlResponseTest(TextResponseTest): diff --git a/tests/test_utils_datatypes.py b/tests/test_utils_datatypes.py index 0a4c6034a..aa18ef1f3 100644 --- a/tests/test_utils_datatypes.py +++ b/tests/test_utils_datatypes.py @@ -271,6 +271,7 @@ class LocalWeakReferencedCacheTest(unittest.TestCase): self.assertNotIn(r1, cache) self.assertIn(r2, cache) self.assertIn(r3, cache) + self.assertEqual(cache[r1], None) self.assertEqual(cache[r2], 2) self.assertEqual(cache[r3], 3) del r2