Merge remote-tracking branch 'origin/master' into asyncio-startrequests-asyncgen

.travis.yml

@@ -11,16 +11,22 @@ matrix:
       python: 3.8
     - env: TOXENV=flake8
       python: 3.8
+    - env: TOXENV=pylint
+      python: 3.8
     - env: TOXENV=docs
       python: 3.7  # Keep in sync with .readthedocs.yml
 
     - env: TOXENV=pypy3
+    - env: TOXENV=pinned
+      python: 3.5.1
+      dist: trusty
+    - env: TOXENV=asyncio
+      python: 3.5.1  # We use additional code to support 3.5.3 and earlier
+      dist: trusty
     - env: TOXENV=py
       python: 3.5
-    - env: TOXENV=pinned
-      python: 3.5
     - env: TOXENV=asyncio
-      python: 3.5.2
+      python: 3.5  # We use specific code to support >= 3.5.4, < 3.6
     - env: TOXENV=py
       python: 3.6
     - env: TOXENV=py

README.rst

@@ -40,7 +40,7 @@ including a list of features.
 Requirements
 ============
 
-* Python 3.5+
+* Python 3.5.1+
 * Works on Linux, Windows, macOS, BSD
 
 Install

docs/faq.rst

@@ -69,7 +69,7 @@ Here's an example spider using BeautifulSoup API, with ``lxml`` as the HTML pars
 What Python versions does Scrapy support?
 -----------------------------------------
 
-Scrapy is supported under Python 3.5+
+Scrapy is supported under Python 3.5.1+
 under CPython (default Python implementation) and PyPy (starting with PyPy 5.9).
 Python 3 support was added in Scrapy 1.1.
 PyPy support was added in Scrapy 1.4, PyPy3 support was added in Scrapy 1.5.
@@ -342,14 +342,14 @@ method for this purpose. For example::
 
     from copy import deepcopy
 
-    from scrapy.item import BaseItem
+    from scrapy.item import Item
 
 
     class MultiplyItemsMiddleware:
 
         def process_spider_output(self, response, result, spider):
             for item in result:
-                if isinstance(item, (BaseItem, dict)):
+                if isinstance(item, (Item, dict)):
                     for _ in range(item['multiply_by']):
                         yield deepcopy(item)
 

docs/intro/install.rst

@@ -7,7 +7,7 @@ Installation guide
 Installing Scrapy
 =================
 
-Scrapy runs on Python 3.5 or above under CPython (default Python
+Scrapy runs on Python 3.5.1 or above under CPython (default Python
 implementation) and PyPy (starting with PyPy 5.9).
 
 If you're using `Anaconda`_ or `Miniconda`_, you can install the package from

docs/topics/dynamic-content.rst

@@ -184,6 +184,18 @@ data from it:
     >>> json.loads(json_data)
     {'field': 'value'}
 
+-   chompjs_ provides an API to parse JavaScript objects into a :class:`dict`.
+
+    For example, if the JavaScript code contains
+    ``var data = {field: "value", secondField: "second value"};``
+    you can extract that data as follows:
+
+    >>> import chompjs
+    >>> javascript = response.css('script::text').get()
+    >>> data = chompjs.parse_js_object(javascript)
+    >>> data
+    {'field': 'value', 'secondField': 'second value'}
+
 -   Otherwise, use js2xml_ to convert the JavaScript code into an XML document
     that you can parse using :ref:`selectors <topics-selectors>`.
 
@@ -241,6 +253,7 @@ along with `scrapy-selenium`_ for seamless integration.
 
 
 .. _AJAX: https://en.wikipedia.org/wiki/Ajax_%28programming%29
+.. _chompjs: https://github.com/Nykakin/chompjs
 .. _CSS: https://en.wikipedia.org/wiki/Cascading_Style_Sheets
 .. _curl: https://curl.haxx.se/
 .. _headless browser: https://en.wikipedia.org/wiki/Headless_browser

docs/topics/items.rst

@@ -257,6 +257,4 @@ Field objects
 Other classes related to Item
 =============================
 
-.. autoclass:: BaseItem
-
 .. autoclass:: ItemMeta

docs/topics/media-pipeline.rst

@@ -50,7 +50,7 @@ this:
 4. When the files are downloaded, another field (``files``) will be populated
    with the results. This field will contain a list of dicts with information
    about the downloaded files, such as the downloaded path, the original
-   scraped url (taken from the ``file_urls`` field) , and the file checksum.
+   scraped url (taken from the ``file_urls`` field), the file checksum and the file status.
    The files in the list of the ``files`` field will retain the same order of
    the original ``file_urls`` field. If some file failed downloading, an
    error will be logged and the file won't be present in the ``files`` field.
@@ -470,6 +470,14 @@ See here the methods that you can override in your custom Files Pipeline:
 
         * ``checksum`` - a `MD5 hash`_ of the image contents
 
+        * ``status`` - the file status indication. It can be one of the following:
+
+          * ``downloaded`` - file was downloaded.
+          * ``uptodate`` - file was not downloaded, as it was downloaded recently,
+            according to the file expiration policy.
+          * ``cached`` - file was already scheduled for download, by another item
+            sharing the same file.
+
       The list of tuples received by :meth:`~item_completed` is
       guaranteed to retain the same order of the requests returned from the
       :meth:`~get_media_requests` method.
@@ -479,7 +487,8 @@ See here the methods that you can override in your custom Files Pipeline:
           [(True,
             {'checksum': '2b00042f7481c7b056c4b410d28f33cf',
              'path': 'full/0a79c461a4062ac383dc4fade7bc09f1384a3910.jpg',
-             'url': 'http://www.example.com/files/product1.pdf'}),
+             'url': 'http://www.example.com/files/product1.pdf',
+             'status': 'downloaded'}),
            (False,
             Failure(...))]
 

docs/topics/request-response.rst

@@ -834,11 +834,6 @@ TextResponse objects
 
     .. automethod:: TextResponse.follow_all
 
-    .. method:: TextResponse.body_as_unicode()
-
-        The same as :attr:`text`, but available as a method. This method is
-        kept for backward compatibility; please prefer ``response.text``.
-
 
 HtmlResponse objects
 --------------------

docs/topics/signals.rst

@@ -112,7 +112,7 @@ engine_started
 
     Sent when the Scrapy engine has started crawling.
 
-    This signal supports returning deferreds from their handlers.
+    This signal supports returning deferreds from its handlers.
 
 .. note:: This signal may be fired *after* the :signal:`spider_opened` signal,
     depending on how the spider was started. So **don't** rely on this signal
@@ -127,7 +127,7 @@ engine_stopped
     Sent when the Scrapy engine is stopped (for example, when a crawling
     process has finished).
 
-    This signal supports returning deferreds from their handlers.
+    This signal supports returning deferreds from its handlers.
 
 Item signals
 ------------
@@ -149,7 +149,7 @@ item_scraped
     Sent when an item has been scraped, after it has passed all the
     :ref:`topics-item-pipeline` stages (without being dropped).
 
-    This signal supports returning deferreds from their handlers.
+    This signal supports returning deferreds from its handlers.
 
     :param item: the item scraped
     :type item: dict or :class:`~scrapy.item.Item` object
@@ -169,7 +169,7 @@ item_dropped
     Sent after an item has been dropped from the :ref:`topics-item-pipeline`
     when some stage raised a :exc:`~scrapy.exceptions.DropItem` exception.
 
-    This signal supports returning deferreds from their handlers.
+    This signal supports returning deferreds from its handlers.
 
     :param item: the item dropped from the :ref:`topics-item-pipeline`
     :type item: dict or :class:`~scrapy.item.Item` object
@@ -194,7 +194,7 @@ item_error
     Sent when a :ref:`topics-item-pipeline` generates an error (i.e. raises
     an exception), except :exc:`~scrapy.exceptions.DropItem` exception.
 
-    This signal supports returning deferreds from their handlers.
+    This signal supports returning deferreds from its handlers.
 
     :param item: the item dropped from the :ref:`topics-item-pipeline`
     :type item: dict or :class:`~scrapy.item.Item` object
@@ -220,7 +220,7 @@ spider_closed
     Sent after a spider has been closed. This can be used to release per-spider
     resources reserved on :signal:`spider_opened`.
 
-    This signal supports returning deferreds from their handlers.
+    This signal supports returning deferreds from its handlers.
 
     :param spider: the spider which has been closed
     :type spider: :class:`~scrapy.spiders.Spider` object
@@ -244,7 +244,7 @@ spider_opened
     reserve per-spider resources, but can be used for any task that needs to be
     performed when a spider is opened.
 
-    This signal supports returning deferreds from their handlers.
+    This signal supports returning deferreds from its handlers.
 
     :param spider: the spider which has been opened
     :type spider: :class:`~scrapy.spiders.Spider` object
@@ -268,7 +268,7 @@ spider_idle
     You may raise a :exc:`~scrapy.exceptions.DontCloseSpider` exception to
     prevent the spider from being closed.
 
-    This signal does not support returning deferreds from their handlers.
+    This signal does not support returning deferreds from its handlers.
 
     :param spider: the spider which has gone idle
     :type spider: :class:`~scrapy.spiders.Spider` object
@@ -287,7 +287,7 @@ spider_error
 
     Sent when a spider callback generates an error (i.e. raises an exception).
 
-    This signal does not support returning deferreds from their handlers.
+    This signal does not support returning deferreds from its handlers.
 
     :param failure: the exception raised
     :type failure: twisted.python.failure.Failure
@@ -310,7 +310,7 @@ request_scheduled
     Sent when the engine schedules a :class:`~scrapy.http.Request`, to be
     downloaded later.
 
-    The signal does not support returning deferreds from their handlers.
+    This signal does not support returning deferreds from its handlers.
 
     :param request: the request that reached the scheduler
     :type request: :class:`~scrapy.http.Request` object
@@ -327,7 +327,7 @@ request_dropped
     Sent when a :class:`~scrapy.http.Request`, scheduled by the engine to be
     downloaded later, is rejected by the scheduler.
 
-    The signal does not support returning deferreds from their handlers.
+    This signal does not support returning deferreds from its handlers.
 
     :param request: the request that reached the scheduler
     :type request: :class:`~scrapy.http.Request` object
@@ -343,7 +343,7 @@ request_reached_downloader
 
     Sent when a :class:`~scrapy.http.Request` reached downloader.
 
-    The signal does not support returning deferreds from their handlers.
+    This signal does not support returning deferreds from its handlers.
 
     :param request: the request that reached downloader
     :type request: :class:`~scrapy.http.Request` object
@@ -370,6 +370,29 @@ request_left_downloader
     :param spider: the spider that yielded the request
     :type spider: :class:`~scrapy.spiders.Spider` object
 
+bytes_received
+~~~~~~~~~~~~~~
+
+.. signal:: bytes_received
+.. function:: bytes_received(data, request, spider)
+
+    Sent by the HTTP 1.1 and S3 download handlers when a group of bytes is
+    received for a specific request. This signal might be fired multiple
+    times for the same request, with partial data each time. For instance,
+    a possible scenario for a 25 kb response would be two signals fired
+    with 10 kb of data, and a final one with 5 kb of data.
+
+    This signal does not support returning deferreds from its handlers.
+
+    :param data: the data received by the download handler
+    :type spider: :class:`bytes` object
+
+    :param request: the request that generated the response
+    :type request: :class:`~scrapy.http.Request` object
+
+    :param spider: the spider associated with the response
+    :type spider: :class:`~scrapy.spiders.Spider` object
+
 Response signals
 ----------------
 
@@ -382,7 +405,7 @@ response_received
     Sent when the engine receives a new :class:`~scrapy.http.Response` from the
     downloader.
 
-    This signal does not support returning deferreds from their handlers.
+    This signal does not support returning deferreds from its handlers.
 
     :param response: the response received
     :type response: :class:`~scrapy.http.Response` object
@@ -401,7 +424,7 @@ response_downloaded
 
     Sent by the downloader right after a ``HTTPResponse`` is downloaded.
 
-    This signal does not support returning deferreds from their handlers.
+    This signal does not support returning deferreds from its handlers.
 
     :param response: the response downloaded
     :type response: :class:`~scrapy.http.Response` object

docs/utils/linkfix.py

@@ -14,50 +14,57 @@ Author: dufferzafar
 
 import re
 
-# Used for remembering the file (and its contents)
-# so we don't have to open the same file again.
-_filename = None
-_contents = None
 
-# A regex that matches standard linkcheck output lines
-line_re = re.compile(u'(.*)\:\d+\:\s\[(.*)\]\s(?:(.*)\sto\s(.*)|(.*))')
+def main():
 
-# Read lines from the linkcheck output file
-try:
-    with open("build/linkcheck/output.txt") as out:
-        output_lines = out.readlines()
-except IOError:
-    print("linkcheck output not found; please run linkcheck first.")
-    exit(1)
+    # Used for remembering the file (and its contents)
+    # so we don't have to open the same file again.
+    _filename = None
+    _contents = None
 
-# For every line, fix the respective file
-for line in output_lines:
-    match = re.match(line_re, line)
+    # A regex that matches standard linkcheck output lines
+    line_re = re.compile(u'(.*)\:\d+\:\s\[(.*)\]\s(?:(.*)\sto\s(.*)|(.*))')
 
-    if match:
-        newfilename = match.group(1)
-        errortype = match.group(2)
+    # Read lines from the linkcheck output file
+    try:
+        with open("build/linkcheck/output.txt") as out:
+            output_lines = out.readlines()
+    except IOError:
+        print("linkcheck output not found; please run linkcheck first.")
+        exit(1)
 
-        # Broken links can't be fixed and
-        # I am not sure what do with the local ones.
-        if errortype.lower() in ["broken", "local"]:
-            print("Not Fixed: " + line)
+    # For every line, fix the respective file
+    for line in output_lines:
+        match = re.match(line_re, line)
+
+        if match:
+            newfilename = match.group(1)
+            errortype = match.group(2)
+
+            # Broken links can't be fixed and
+            # I am not sure what do with the local ones.
+            if errortype.lower() in ["broken", "local"]:
+                print("Not Fixed: " + line)
+            else:
+                # If this is a new file
+                if newfilename != _filename:
+
+                    # Update the previous file
+                    if _filename:
+                        with open(_filename, "w") as _file:
+                            _file.write(_contents)
+
+                    _filename = newfilename
+
+                    # Read the new file to memory
+                    with open(_filename) as _file:
+                        _contents = _file.read()
+
+                _contents = _contents.replace(match.group(3), match.group(4))
         else:
-            # If this is a new file
-            if newfilename != _filename:
+            # We don't understand what the current line means!
+            print("Not Understood: " + line)
 
-                # Update the previous file
-                if _filename:
-                    with open(_filename, "w") as _file:
-                        _file.write(_contents)
 
-                _filename = newfilename
-
-                # Read the new file to memory
-                with open(_filename) as _file:
-                    _contents = _file.read()
-
-            _contents = _contents.replace(match.group(3), match.group(4))
-    else:
-        # We don't understand what the current line means!
-        print("Not Understood: " + line)
+if __name__ == '__main__':
+    main()

pylintrc

@@ -0,0 +1,113 @@
+[MASTER]
+persistent=no
+jobs=1  # >1 hides results
+
+[MESSAGES CONTROL]
+disable=abstract-method,
+        anomalous-backslash-in-string,
+        arguments-differ,
+        attribute-defined-outside-init,
+        bad-classmethod-argument,
+        bad-continuation,
+        bad-indentation,
+        bad-mcs-classmethod-argument,
+        bad-super-call,
+        bad-whitespace,
+        bare-except,
+        blacklisted-name,
+        broad-except,
+        c-extension-no-member,
+        catching-non-exception,
+        cell-var-from-loop,
+        comparison-with-callable,
+        consider-iterating-dictionary,
+        consider-using-in,
+        consider-using-set-comprehension,
+        consider-using-sys-exit,
+        cyclic-import,
+        dangerous-default-value,
+        deprecated-method,
+        deprecated-module,
+        duplicate-code,  # https://github.com/PyCQA/pylint/issues/214
+        eval-used,
+        expression-not-assigned,
+        fixme,
+        function-redefined,
+        global-statement,
+        import-error,
+        import-outside-toplevel,
+        import-self,
+        inconsistent-return-statements,
+        inherit-non-class,
+        invalid-name,
+        invalid-overridden-method,
+        isinstance-second-argument-not-valid-type,
+        keyword-arg-before-vararg,
+        line-too-long,
+        logging-format-interpolation,
+        logging-not-lazy,
+        lost-exception,
+        method-hidden,
+        misplaced-comparison-constant,
+        missing-docstring,
+        missing-final-newline,
+        multiple-imports,
+        multiple-statements,
+        no-else-continue,
+        no-else-raise,
+        no-else-return,
+        no-init,
+        no-member,
+        no-method-argument,
+        no-name-in-module,
+        no-self-argument,
+        no-self-use,
+        no-value-for-parameter,
+        not-an-iterable,
+        not-callable,
+        pointless-statement,
+        pointless-string-statement,
+        protected-access,
+        redefined-argument-from-local,
+        redefined-builtin,
+        redefined-outer-name,
+        reimported,
+        signature-differs,
+        singleton-comparison,
+        super-init-not-called,
+        superfluous-parens,
+        too-few-public-methods,
+        too-many-ancestors,
+        too-many-arguments,
+        too-many-branches,
+        too-many-format-args,
+        too-many-function-args,
+        too-many-instance-attributes,
+        too-many-lines,
+        too-many-locals,
+        too-many-public-methods,
+        too-many-return-statements,
+        trailing-newlines,
+        trailing-whitespace,
+        unbalanced-tuple-unpacking,
+        undefined-variable,
+        undefined-loop-variable,
+        unexpected-special-method-signature,
+        ungrouped-imports,
+        unidiomatic-typecheck,
+        unnecessary-comprehension,
+        unnecessary-lambda,
+        unnecessary-pass,
+        unreachable,
+        unsubscriptable-object,
+        unused-argument,
+        unused-import,
+        unused-variable,
+        unused-wildcard-import,
+        used-before-assignment,
+        useless-object-inheritance,  # Required for Python 2 support
+        useless-return,
+        useless-super-delegation,
+        wildcard-import,
+        wrong-import-order,
+        wrong-import-position

pytest.ini

@@ -20,235 +20,25 @@ addopts =
 twisted = 1
 markers =
     only_asyncio: marks tests as only enabled when --reactor=asyncio is passed
+flake8-max-line-length = 119
 flake8-ignore =
     W503
-    # Files that are only meant to provide top-level imports are expected not
-    # to use any of their imports:
+
+    # 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/core/downloader/handlers/http.py F401
     scrapy/http/__init__.py F401
+    scrapy/linkextractors/__init__.py E402 F401
+    scrapy/spiders/__init__.py E402 F401
+
     # Issues pending a review:
-    # extras
-    extras/qps-bench-server.py E501
-    extras/qpsclient.py E501 E501
-    # scrapy/commands
-    scrapy/commands/__init__.py E128 E501
-    scrapy/commands/check.py E501
-    scrapy/commands/crawl.py E501
-    scrapy/commands/edit.py E501
-    scrapy/commands/fetch.py E501 E128
-    scrapy/commands/genspider.py E128 E501
-    scrapy/commands/parse.py E128 E501
-    scrapy/commands/runspider.py E501
-    scrapy/commands/settings.py E128
-    scrapy/commands/shell.py E128 E501
-    scrapy/commands/startproject.py E501 E128
-    scrapy/commands/version.py E501 E128
-    # scrapy/contracts
-    scrapy/contracts/__init__.py E501
-    scrapy/contracts/default.py E128
-    # scrapy/core
-    scrapy/core/engine.py E501 E128
-    scrapy/core/scheduler.py E501
-    scrapy/core/scraper.py E501 E128
-    scrapy/core/spidermw.py E501
-    scrapy/core/downloader/__init__.py E501
-    scrapy/core/downloader/contextfactory.py E501 E128
-    scrapy/core/downloader/middleware.py E501
-    scrapy/core/downloader/tls.py E501
-    scrapy/core/downloader/webclient.py E501 E128
-    scrapy/core/downloader/handlers/__init__.py E501
-    scrapy/core/downloader/handlers/ftp.py E501 E128
-    scrapy/core/downloader/handlers/http10.py E501
-    scrapy/core/downloader/handlers/http11.py E501
-    scrapy/core/downloader/handlers/s3.py E501 E128
-    # scrapy/downloadermiddlewares
-    scrapy/downloadermiddlewares/ajaxcrawl.py E501
-    scrapy/downloadermiddlewares/decompression.py E501
-    scrapy/downloadermiddlewares/defaultheaders.py E501
-    scrapy/downloadermiddlewares/httpcache.py E501
-    scrapy/downloadermiddlewares/httpcompression.py E501 E128
-    scrapy/downloadermiddlewares/httpproxy.py E501
-    scrapy/downloadermiddlewares/redirect.py E501
-    scrapy/downloadermiddlewares/retry.py E501
-    scrapy/downloadermiddlewares/robotstxt.py E501
-    scrapy/downloadermiddlewares/stats.py E501
-    # scrapy/extensions
-    scrapy/extensions/closespider.py E501 E128
-    scrapy/extensions/corestats.py E501
-    scrapy/extensions/feedexport.py E128 E501
-    scrapy/extensions/httpcache.py E128 E501
-    scrapy/extensions/memdebug.py E501
-    scrapy/extensions/spiderstate.py E501
-    scrapy/extensions/telnet.py E501
-    scrapy/extensions/throttle.py E501
-    # scrapy/http
-    scrapy/http/common.py E501
-    scrapy/http/cookies.py E501
-    scrapy/http/request/__init__.py E501
-    scrapy/http/request/form.py E501
-    scrapy/http/request/json_request.py E501
-    scrapy/http/response/__init__.py E501 E128
-    scrapy/http/response/text.py E501 E128
-    # scrapy/linkextractors
-    scrapy/linkextractors/__init__.py E501 E402
-    scrapy/linkextractors/lxmlhtml.py E501
-    # scrapy/loader
-    scrapy/loader/__init__.py E501 E128
-    scrapy/loader/processors.py E501
-    # scrapy/pipelines
-    scrapy/pipelines/__init__.py E501
-    scrapy/pipelines/files.py E116 E501
-    scrapy/pipelines/images.py E501
-    scrapy/pipelines/media.py E501
-    # scrapy/selector
+    scrapy/__init__.py E402
     scrapy/selector/__init__.py F403
-    scrapy/selector/unified.py E501 E111
-    # scrapy/settings
-    scrapy/settings/__init__.py E501
-    scrapy/settings/default_settings.py E501 E114 E116
-    scrapy/settings/deprecated.py E501
-    # scrapy/spidermiddlewares
-    scrapy/spidermiddlewares/httperror.py E501
-    scrapy/spidermiddlewares/offsite.py E501
-    scrapy/spidermiddlewares/referer.py E501
-    scrapy/spidermiddlewares/urllength.py E501
-    # scrapy/spiders
-    scrapy/spiders/__init__.py E501 E402
-    scrapy/spiders/crawl.py E501
-    scrapy/spiders/feed.py E501
-    scrapy/spiders/sitemap.py E501
-    # scrapy/utils
-    scrapy/utils/asyncio.py E501
-    scrapy/utils/asyncgen.py E501
-    scrapy/utils/benchserver.py E501
-    scrapy/utils/conf.py E402 E501
-    scrapy/utils/datatypes.py E501
-    scrapy/utils/decorators.py E501
-    scrapy/utils/defer.py E501 E128
-    scrapy/utils/deprecate.py E501
-    scrapy/utils/gz.py E501
+    scrapy/spiders/__init__.py E402
     scrapy/utils/http.py F403
-    scrapy/utils/httpobj.py E501
-    scrapy/utils/iterators.py E501
-    scrapy/utils/log.py E128 E501
     scrapy/utils/markup.py F403
-    scrapy/utils/middlewares.py E501
-    scrapy/utils/misc.py E501
     scrapy/utils/multipart.py F403
-    scrapy/utils/project.py E501
-    scrapy/utils/python.py E501
-    scrapy/utils/reactor.py E501
-    scrapy/utils/reqser.py E501
-    scrapy/utils/request.py E501
-    scrapy/utils/response.py E501 E128
-    scrapy/utils/signal.py E501 E128
-    scrapy/utils/sitemap.py E501
-    scrapy/utils/spider.py E501
-    scrapy/utils/ssl.py E501
-    scrapy/utils/test.py E501
-    scrapy/utils/url.py E501 F403 E128 F405
-    # scrapy
-    scrapy/__init__.py E402 E501
-    scrapy/cmdline.py E501
-    scrapy/crawler.py E501
-    scrapy/dupefilters.py E501
-    scrapy/exceptions.py E501
-    scrapy/exporters.py E501
-    scrapy/interfaces.py E501
-    scrapy/item.py E501 E128
-    scrapy/link.py E501
-    scrapy/logformatter.py E501
-    scrapy/mail.py E402 E128 E501
-    scrapy/middleware.py E128 E501
-    scrapy/pqueues.py E501
-    scrapy/resolver.py E501
-    scrapy/responsetypes.py E128 E501
-    scrapy/robotstxt.py E501
-    scrapy/shell.py E501
-    scrapy/signalmanager.py E501
-    scrapy/spiderloader.py F841 E501
-    scrapy/squeues.py E128
-    scrapy/statscollectors.py E501
-    # tests
-    tests/__init__.py E402 E501
-    tests/mockserver.py E501
-    tests/pipelines.py F841
-    tests/spiders.py E501
-    tests/test_closespider.py E501
-    tests/test_command_fetch.py E501
-    tests/test_command_parse.py E501 E128
-    tests/test_command_shell.py E501 E128
-    tests/test_commands.py E128 E501
-    tests/test_contracts.py E501 E128
-    tests/test_crawl.py E501 E741
-    tests/test_crawler.py F841 E501
-    tests/test_dependencies.py F841 E501
-    tests/test_downloader_handlers.py E128 E501
-    tests/test_downloadermiddleware.py E501
-    tests/test_downloadermiddleware_ajaxcrawlable.py E501
-    tests/test_downloadermiddleware_cookies.py E741 E501 E128
-    tests/test_downloadermiddleware_defaultheaders.py E501
-    tests/test_downloadermiddleware_downloadtimeout.py E501
-    tests/test_downloadermiddleware_httpcache.py E501
-    tests/test_downloadermiddleware_httpcompression.py E501
-    tests/test_downloadermiddleware_decompression.py E501
-    tests/test_downloadermiddleware_httpproxy.py E501 E128
-    tests/test_downloadermiddleware_redirect.py E501 E128
-    tests/test_downloadermiddleware_retry.py E501 E128
-    tests/test_downloadermiddleware_robotstxt.py E501
-    tests/test_downloadermiddleware_stats.py E501
-    tests/test_dupefilters.py E501 E741 E128
-    tests/test_engine.py E501 E128
-    tests/test_exporters.py E501 E128
-    tests/test_extension_telnet.py F841
-    tests/test_feedexport.py E501 F841
-    tests/test_http_cookies.py E501
-    tests/test_http_headers.py E501
-    tests/test_http_request.py E402 E501 E128 E128
-    tests/test_http_response.py E501 E128
-    tests/test_item.py E128 F841
-    tests/test_link.py E501
-    tests/test_linkextractors.py E501 E128
-    tests/test_loader.py E501 E741 E128 E117
-    tests/test_logformatter.py E128 E501
-    tests/test_mail.py E128 E501
-    tests/test_middleware.py E501 E128
-    tests/test_pipeline_crawl.py E501 E128
-    tests/test_pipeline_files.py E501
-    tests/test_pipeline_images.py F841 E501
-    tests/test_pipeline_media.py E501 E741 E128
-    tests/test_proxy_connect.py E501 E741
-    tests/test_request_cb_kwargs.py E501
-    tests/test_responsetypes.py E501
-    tests/test_robotstxt_interface.py E501 E501
-    tests/test_scheduler.py E501
-    tests/test_selector.py E501
-    tests/test_spider.py E501
-    tests/test_spidermiddleware.py E501
-    tests/test_spidermiddleware_httperror.py E128 E501 E121
-    tests/test_spidermiddleware_offsite.py E501 E128 E111
-    tests/test_spidermiddleware_output_chain.py E501
-    tests/test_spidermiddleware_referer.py E501 F841 E501 E121
-    tests/test_squeues.py E501 E741
-    tests/test_utils_asyncio.py E501
-    tests/test_utils_asyncgen.py E501
-    tests/test_utils_conf.py E501 E128
-    tests/test_utils_curl.py E501
-    tests/test_utils_datatypes.py E402 E501
-    tests/test_utils_defer.py E501 F841
-    tests/test_utils_deprecate.py F841 E501
-    tests/test_utils_http.py E501 E128
-    tests/test_utils_iterators.py E501 E128
-    tests/test_utils_log.py E741
-    tests/test_utils_python.py E501
-    tests/test_utils_reqser.py E501 E128
-    tests/test_utils_request.py E501 E128
-    tests/test_utils_response.py E501
-    tests/test_utils_signal.py E741 F841
-    tests/test_utils_sitemap.py E128 E501
-    tests/test_utils_url.py E501 E501
-    tests/test_webclient.py E501 E128 E402
-    tests/test_cmdline/__init__.py E501
-    tests/test_settings/__init__.py E501 E128
-    tests/test_spiderloader/__init__.py E128 E501
-    tests/test_utils_misc/__init__.py E501
+    scrapy/utils/url.py F403 F405
+    tests/test_loader.py E741
+    tests/test_webclient.py E402

scrapy/cmdline.py

@@ -165,6 +165,7 @@ if __name__ == '__main__':
     try:
         execute()
     finally:
-        # Twisted prints errors in DebugInfo.__del__, but PyPy does not run gc.collect()
-        # on exit: http://doc.pypy.org/en/latest/cpython_differences.html?highlight=gc.collect#differences-related-to-garbage-collection-strategies
+        # Twisted prints errors in DebugInfo.__del__, but PyPy does not run gc.collect() on exit:
+        # http://doc.pypy.org/en/latest/cpython_differences.html
+        # ?highlight=gc.collect#differences-related-to-garbage-collection-strategies
         garbage_collect()

scrapy/commands/__init__.py

@@ -59,17 +59,17 @@ class ScrapyCommand:
         """
         group = OptionGroup(parser, "Global Options")
         group.add_option("--logfile", metavar="FILE",
-            help="log file. if omitted stderr will be used")
+                         help="log file. if omitted stderr will be used")
         group.add_option("-L", "--loglevel", metavar="LEVEL", default=None,
-            help="log level (default: %s)" % self.settings['LOG_LEVEL'])
+                         help="log level (default: %s)" % self.settings['LOG_LEVEL'])
         group.add_option("--nolog", action="store_true",
-            help="disable logging completely")
+                         help="disable logging completely")
         group.add_option("--profile", metavar="FILE", default=None,
-            help="write python cProfile stats to FILE")
+                         help="write python cProfile stats to FILE")
         group.add_option("--pidfile", metavar="FILE",
-            help="write process ID to FILE")
+                         help="write process ID to FILE")
         group.add_option("-s", "--set", action="append", default=[], metavar="NAME=VALUE",
-            help="set/override setting (may be repeated)")
+                         help="set/override setting (may be repeated)")
         group.add_option("--pdb", action="store_true", help="enable pdb on failure")
 
         parser.add_option_group(group)

scrapy/commands/fetch.py

@@ -27,8 +27,8 @@ class Command(ScrapyCommand):
         parser.add_option("--spider", dest="spider", help="use this spider")
         parser.add_option("--headers", dest="headers", action="store_true",
                           help="print response HTTP headers instead of body")
-        parser.add_option("--no-redirect", dest="no_redirect", action="store_true",
-                          default=False, help="do not handle HTTP 3xx status codes and print response as-is")
+        parser.add_option("--no-redirect", dest="no_redirect", action="store_true", default=False,
+                          help="do not handle HTTP 3xx status codes and print response as-is")
 
     def _print_headers(self, headers, prefix):
         for key, values in headers.items():

scrapy/commands/genspider.py

@@ -36,15 +36,15 @@ class Command(ScrapyCommand):
     def add_options(self, parser):
         ScrapyCommand.add_options(self, parser)
         parser.add_option("-l", "--list", dest="list", action="store_true",
-            help="List available templates")
+                          help="List available templates")
         parser.add_option("-e", "--edit", dest="edit", action="store_true",
-            help="Edit spider after creating it")
+                          help="Edit spider after creating it")
         parser.add_option("-d", "--dump", dest="dump", metavar="TEMPLATE",
-            help="Dump template to standard output")
+                          help="Dump template to standard output")
         parser.add_option("-t", "--template", dest="template", default="basic",
-            help="Uses a custom template.")
+                          help="Uses a custom template.")
         parser.add_option("--force", dest="force", action="store_true",
-            help="If the spider already exists, overwrite it with the template")
+                          help="If the spider already exists, overwrite it with the template")
 
     def run(self, args, opts):
         if opts.list:

scrapy/commands/parse.py

@@ -5,7 +5,7 @@ from w3lib.url import is_url
 
 from scrapy.commands import ScrapyCommand
 from scrapy.http import Request
-from scrapy.item import BaseItem
+from scrapy.item import _BaseItem
 from scrapy.utils import display
 from scrapy.utils.conf import arglist_to_dict
 from scrapy.utils.spider import iterate_spider_output, spidercls_for_request
@@ -33,29 +33,29 @@ class Command(ScrapyCommand):
     def add_options(self, parser):
         ScrapyCommand.add_options(self, parser)
         parser.add_option("--spider", dest="spider", default=None,
-            help="use this spider without looking for one")
+                          help="use this spider without looking for one")
         parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE",
-            help="set spider argument (may be repeated)")
+                          help="set spider argument (may be repeated)")
         parser.add_option("--pipelines", action="store_true",
-            help="process items through pipelines")
+                          help="process items through pipelines")
         parser.add_option("--nolinks", dest="nolinks", action="store_true",
-            help="don't show links to follow (extracted requests)")
+                          help="don't show links to follow (extracted requests)")
         parser.add_option("--noitems", dest="noitems", action="store_true",
-            help="don't show scraped items")
+                          help="don't show scraped items")
         parser.add_option("--nocolour", dest="nocolour", action="store_true",
-            help="avoid using pygments to colorize the output")
+                          help="avoid using pygments to colorize the output")
         parser.add_option("-r", "--rules", dest="rules", action="store_true",
-            help="use CrawlSpider rules to discover the callback")
+                          help="use CrawlSpider rules to discover the callback")
         parser.add_option("-c", "--callback", dest="callback",
-            help="use this callback for parsing, instead looking for a callback")
+                          help="use this callback for parsing, instead looking for a callback")
         parser.add_option("-m", "--meta", dest="meta",
-            help="inject extra meta into the Request, it must be a valid raw json string")
+                          help="inject extra meta into the Request, it must be a valid raw json string")
         parser.add_option("--cbkwargs", dest="cbkwargs",
-            help="inject extra callback kwargs into the Request, it must be a valid raw json string")
+                          help="inject extra callback kwargs into the Request, it must be a valid raw json string")
         parser.add_option("-d", "--depth", dest="depth", type="int", default=1,
-            help="maximum depth for parsing requests [default: %default]")
+                          help="maximum depth for parsing requests [default: %default]")
         parser.add_option("-v", "--verbose", dest="verbose", action="store_true",
-            help="print each depth level one by one")
+                          help="print each depth level one by one")
 
     @property
     def max_level(self):
@@ -117,7 +117,7 @@ class Command(ScrapyCommand):
         items, requests = [], []
 
         for x in iterate_spider_output(callback(response, **cb_kwargs)):
-            if isinstance(x, (BaseItem, dict)):
+            if isinstance(x, (_BaseItem, dict)):
                 items.append(x)
             elif isinstance(x, Request):
                 requests.append(x)

scrapy/commands/settings.py

@@ -19,15 +19,15 @@ class Command(ScrapyCommand):
     def add_options(self, parser):
         ScrapyCommand.add_options(self, parser)
         parser.add_option("--get", dest="get", metavar="SETTING",
-            help="print raw setting value")
+                          help="print raw setting value")
         parser.add_option("--getbool", dest="getbool", metavar="SETTING",
-            help="print setting value, interpreted as a boolean")
+                          help="print setting value, interpreted as a boolean")
         parser.add_option("--getint", dest="getint", metavar="SETTING",
-            help="print setting value, interpreted as an integer")
+                          help="print setting value, interpreted as an integer")
         parser.add_option("--getfloat", dest="getfloat", metavar="SETTING",
-            help="print setting value, interpreted as a float")
+                          help="print setting value, interpreted as a float")
         parser.add_option("--getlist", dest="getlist", metavar="SETTING",
-            help="print setting value, interpreted as a list")
+                          help="print setting value, interpreted as a list")
 
     def run(self, args, opts):
         settings = self.crawler_process.settings

scrapy/commands/shell.py

@@ -34,11 +34,11 @@ class Command(ScrapyCommand):
     def add_options(self, parser):
         ScrapyCommand.add_options(self, parser)
         parser.add_option("-c", dest="code",
-            help="evaluate the code in the shell, print the result and exit")
+                          help="evaluate the code in the shell, print the result and exit")
         parser.add_option("--spider", dest="spider",
-            help="use this spider")
-        parser.add_option("--no-redirect", dest="no_redirect", action="store_true",
-            default=False, help="do not handle HTTP 3xx status codes and print response as-is")
+                          help="use this spider")
+        parser.add_option("--no-redirect", dest="no_redirect", action="store_true", default=False,
+                          help="do not handle HTTP 3xx status codes and print response as-is")
 
     def update_vars(self, vars):
         """You can use this function to update the Scrapy objects that will be

scrapy/commands/startproject.py

@@ -102,10 +102,8 @@ class Command(ScrapyCommand):
         move(join(project_dir, 'module'), join(project_dir, project_name))
         for paths in TEMPLATES_TO_RENDER:
             path = join(*paths)
-            tplfile = join(project_dir,
-                string.Template(path).substitute(project_name=project_name))
-            render_templatefile(tplfile, project_name=project_name,
-                ProjectName=string_camelcase(project_name))
+            tplfile = join(project_dir, string.Template(path).substitute(project_name=project_name))
+            render_templatefile(tplfile, project_name=project_name, ProjectName=string_camelcase(project_name))
         print("New Scrapy project '%s', using template directory '%s', "
               "created in:" % (project_name, self.templates_dir))
         print("    %s\n" % abspath(project_dir))

scrapy/commands/version.py

@@ -17,7 +17,7 @@ class Command(ScrapyCommand):
     def add_options(self, parser):
         ScrapyCommand.add_options(self, parser)
         parser.add_option("--verbose", "-v", dest="verbose", action="store_true",
-            help="also display twisted/python/platform info (useful for bug reports)")
+                          help="also display twisted/python/platform info (useful for bug reports)")
 
     def run(self, args, opts):
         if opts.verbose:

scrapy/contracts/default.py

@@ -1,6 +1,6 @@
 import json
 
-from scrapy.item import BaseItem
+from scrapy.item import _BaseItem
 from scrapy.http import Request
 from scrapy.exceptions import ContractFail
 
@@ -51,8 +51,8 @@ class ReturnsContract(Contract):
     objects = {
         'request': Request,
         'requests': Request,
-        'item': (BaseItem, dict),
-        'items': (BaseItem, dict),
+        'item': (_BaseItem, dict),
+        'items': (_BaseItem, dict),
     }
 
     def __init__(self, *args, **kwargs):
@@ -103,7 +103,7 @@ class ScrapesContract(Contract):
 
     def post_process(self, output):
         for x in output:
-            if isinstance(x, (BaseItem, dict)):
+            if isinstance(x, (_BaseItem, dict)):
                 missing = [arg for arg in self.args if arg not in x]
                 if missing:
                     raise ContractFail(

scrapy/core/downloader/contextfactory.py

@@ -46,11 +46,12 @@ class ScrapyClientContextFactory(BrowserLikePolicyForHTTPS):
         #
         # * getattr() for `_ssl_method` attribute for context factories
         #   not calling super(..., self).__init__
-        return CertificateOptions(verify=False,
-                    method=getattr(self, 'method',
-                                   getattr(self, '_ssl_method', None)),
-                    fixBrokenPeers=True,
-                    acceptableCiphers=self.tls_ciphers)
+        return CertificateOptions(
+            verify=False,
+            method=getattr(self, 'method', getattr(self, '_ssl_method', None)),
+            fixBrokenPeers=True,
+            acceptableCiphers=self.tls_ciphers,
+        )
 
     # kept for old-style HTTP/1.0 downloader context twisted calls,
     # e.g. connectSSL()

scrapy/core/downloader/handlers/ftp.py

@@ -86,10 +86,9 @@ class FTPDownloadHandler:
         password = request.meta.get("ftp_password", self.default_password)
         passive_mode = 1 if bool(request.meta.get("ftp_passive",
                                                   self.passive_mode)) else 0
-        creator = ClientCreator(reactor, FTPClient, user, password,
-            passive=passive_mode)
-        return creator.connectTCP(parsed_url.hostname, parsed_url.port or 21).addCallback(self.gotClient,
-                                request, unquote(parsed_url.path))
+        creator = ClientCreator(reactor, FTPClient, user, password, passive=passive_mode)
+        dfd = creator.connectTCP(parsed_url.hostname, parsed_url.port or 21)
+        return dfd.addCallback(self.gotClient, request, unquote(parsed_url.path))
 
     def gotClient(self, client, request, filepath):
         self.client = client

scrapy/core/downloader/handlers/http11.py

@@ -18,6 +18,7 @@ from twisted.web.http_headers import Headers as TxHeaders
 from twisted.web.iweb import IBodyProducer, UNKNOWN_LENGTH
 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
@@ -34,6 +35,8 @@ class HTTP11DownloadHandler:
     lazy = False
 
     def __init__(self, settings, crawler=None):
+        self._crawler = crawler
+
         from twisted.internet import reactor
         self._pool = HTTPConnectionPool(reactor, persistent=True)
         self._pool.maxPersistentPerHost = settings.getint('CONCURRENT_REQUESTS_PER_DOMAIN')
@@ -79,6 +82,7 @@ class HTTP11DownloadHandler:
             maxsize=getattr(spider, 'download_maxsize', self._default_maxsize),
             warnsize=getattr(spider, 'download_warnsize', self._default_warnsize),
             fail_on_dataloss=self._fail_on_dataloss,
+            crawler=self._crawler,
         )
         return agent.download_request(request)
 
@@ -276,7 +280,7 @@ class ScrapyAgent:
     _TunnelingAgent = TunnelingAgent
 
     def __init__(self, contextFactory=None, connectTimeout=10, bindAddress=None, pool=None,
-                 maxsize=0, warnsize=0, fail_on_dataloss=True):
+                 maxsize=0, warnsize=0, fail_on_dataloss=True, crawler=None):
         self._contextFactory = contextFactory
         self._connectTimeout = connectTimeout
         self._bindAddress = bindAddress
@@ -285,6 +289,7 @@ class ScrapyAgent:
         self._warnsize = warnsize
         self._fail_on_dataloss = fail_on_dataloss
         self._txresponse = None
+        self._crawler = crawler
 
     def _get_agent(self, request, timeout):
         from twisted.internet import reactor
@@ -407,7 +412,15 @@ class ScrapyAgent:
 
         d = defer.Deferred(_cancel)
         txresponse.deliverBody(
-            _ResponseReader(d, txresponse, request, maxsize, warnsize, fail_on_dataloss)
+            _ResponseReader(
+                finished=d,
+                txresponse=txresponse,
+                request=request,
+                maxsize=maxsize,
+                warnsize=warnsize,
+                fail_on_dataloss=fail_on_dataloss,
+                crawler=self._crawler,
+            )
         )
 
         # save response for timeouts
@@ -449,7 +462,7 @@ class _RequestBodyProducer:
 
 class _ResponseReader(protocol.Protocol):
 
-    def __init__(self, finished, txresponse, request, maxsize, warnsize, fail_on_dataloss):
+    def __init__(self, finished, txresponse, request, maxsize, warnsize, fail_on_dataloss, crawler):
         self._finished = finished
         self._txresponse = txresponse
         self._request = request
@@ -462,6 +475,7 @@ class _ResponseReader(protocol.Protocol):
         self._bytes_received = 0
         self._certificate = None
         self._ip_address = None
+        self._crawler = crawler
 
     def connectionMade(self):
         if self._certificate is None:
@@ -479,6 +493,13 @@ class _ResponseReader(protocol.Protocol):
         self._bodybuf.write(bodyBytes)
         self._bytes_received += len(bodyBytes)
 
+        self._crawler.signals.send_catch_log(
+            signal=signals.bytes_received,
+            data=bodyBytes,
+            request=self._request,
+            spider=self._crawler.spider,
+        )
+
         if self._maxsize and self._bytes_received > self._maxsize:
             logger.error("Received (%(bytes)s) bytes larger than download "
                          "max size (%(maxsize)s) in request %(request)s.",

scrapy/core/engine.py

@@ -228,11 +228,9 @@ class ExecutionEngine:
         self.slot.nextcall.schedule()
 
     def schedule(self, request, spider):
-        self.signals.send_catch_log(signal=signals.request_scheduled,
-                request=request, spider=spider)
+        self.signals.send_catch_log(signals.request_scheduled, request=request, spider=spider)
         if not self.slot.scheduler.enqueue_request(request):
-            self.signals.send_catch_log(signal=signals.request_dropped,
-                                        request=request, spider=spider)
+            self.signals.send_catch_log(signals.request_dropped, request=request, spider=spider)
 
     def download(self, request, spider):
         d = self._download(request, spider)
@@ -258,8 +256,8 @@ class ExecutionEngine:
                 logkws = self.logformatter.crawled(request, response, spider)
                 if logkws is not None:
                     logger.log(*logformatter_adapter(logkws), extra={'spider': spider})
-                self.signals.send_catch_log(signal=signals.response_received,
-                    response=response, request=request, spider=spider)
+                self.signals.send_catch_log(signals.response_received,
+                                            response=response, request=request, spider=spider)
             return response
 
         def _on_complete(_):
@@ -297,8 +295,7 @@ class ExecutionEngine:
         next loop and this function is guaranteed to be called (at least) once
         again for this spider.
         """
-        res = self.signals.send_catch_log(signal=signals.spider_idle,
-            spider=spider, dont_log=DontCloseSpider)
+        res = self.signals.send_catch_log(signals.spider_idle, spider=spider, dont_log=DontCloseSpider)
         if any(isinstance(x, Failure) and isinstance(x.value, DontCloseSpider) for _, x in res):
             return
 

scrapy/core/scraper.py

@@ -14,7 +14,7 @@ from scrapy.utils.log import logformatter_adapter, failure_to_exc_info
 from scrapy.exceptions import CloseSpider, DropItem, IgnoreRequest
 from scrapy import signals
 from scrapy.http import Request, Response
-from scrapy.item import BaseItem
+from scrapy.item import _BaseItem
 from scrapy.core.spidermw import SpiderMiddlewareManager
 
 
@@ -191,7 +191,7 @@ class Scraper:
         """
         if isinstance(output, Request):
             self.crawler.engine.crawl(request=output, spider=spider)
-        elif isinstance(output, (BaseItem, dict)):
+        elif isinstance(output, (_BaseItem, dict)):
             self.slot.itemproc_size += 1
             dfd = self.itemproc.process_item(output, spider)
             dfd.addBoth(self._itemproc_finished, output, response, spider)

scrapy/core/spidermw.py

@@ -19,7 +19,7 @@ def _isiterable(possible_iterator):
 
 
 def _fname(f):
-    return "%s.%s".format(
+    return "{}.{}".format(
         f.__self__.__class__.__name__,
         f.__func__.__name__
     )

scrapy/exporters.py

@@ -12,7 +12,7 @@ from xml.sax.saxutils import XMLGenerator
 
 from scrapy.utils.serialize import ScrapyJSONEncoder
 from scrapy.utils.python import to_bytes, to_unicode, is_listlike
-from scrapy.item import BaseItem
+from scrapy.item import _BaseItem
 from scrapy.exceptions import ScrapyDeprecationWarning
 
 
@@ -250,7 +250,7 @@ class CsvItemExporter(BaseItemExporter):
 
 class PickleItemExporter(BaseItemExporter):
 
-    def __init__(self, file, protocol=2, **kwargs):
+    def __init__(self, file, protocol=4, **kwargs):
         super().__init__(**kwargs)
         self.file = file
         self.protocol = protocol
@@ -312,7 +312,7 @@ class PythonItemExporter(BaseItemExporter):
         return serializer(value)
 
     def _serialize_value(self, value):
-        if isinstance(value, BaseItem):
+        if isinstance(value, _BaseItem):
             return self.export_item(value)
         if isinstance(value, dict):
             return dict(self._serialize_dict(value))

scrapy/extensions/httpcache.py

@@ -46,9 +46,10 @@ class RFC2616Policy:
     def __init__(self, settings):
         self.always_store = settings.getbool('HTTPCACHE_ALWAYS_STORE')
         self.ignore_schemes = settings.getlist('HTTPCACHE_IGNORE_SCHEMES')
-        self.ignore_response_cache_controls = [to_bytes(cc) for cc in
-            settings.getlist('HTTPCACHE_IGNORE_RESPONSE_CACHE_CONTROLS')]
         self._cc_parsed = WeakKeyDictionary()
+        self.ignore_response_cache_controls = [
+            to_bytes(cc) for cc in settings.getlist('HTTPCACHE_IGNORE_RESPONSE_CACHE_CONTROLS')
+        ]
 
     def _parse_cachecontrol(self, r):
         if r not in self._cc_parsed:
@@ -250,7 +251,7 @@ class DbmCacheStorage:
             'headers': dict(response.headers),
             'body': response.body,
         }
-        self.db['%s_data' % key] = pickle.dumps(data, protocol=2)
+        self.db['%s_data' % key] = pickle.dumps(data, protocol=4)
         self.db['%s_time' % key] = str(time())
 
     def _read_data(self, spider, request):
@@ -317,7 +318,7 @@ class FilesystemCacheStorage:
         with self._open(os.path.join(rpath, 'meta'), 'wb') as f:
             f.write(to_bytes(repr(metadata)))
         with self._open(os.path.join(rpath, 'pickled_meta'), 'wb') as f:
-            pickle.dump(metadata, f, protocol=2)
+            pickle.dump(metadata, f, protocol=4)
         with self._open(os.path.join(rpath, 'response_headers'), 'wb') as f:
             f.write(headers_dict_to_raw(response.headers))
         with self._open(os.path.join(rpath, 'response_body'), 'wb') as f:

scrapy/extensions/spiderstate.py

@@ -26,7 +26,7 @@ class SpiderState:
     def spider_closed(self, spider):
         if self.jobdir:
             with open(self.statefn, 'wb') as f:
-                pickle.dump(spider.state, f, protocol=2)
+                pickle.dump(spider.state, f, protocol=4)
 
     def spider_opened(self, spider):
         if self.jobdir and os.path.exists(self.statefn):

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 warnings
 from contextlib import suppress
 from typing import Generator
 from urllib.parse import urljoin
@@ -14,6 +15,7 @@ from w3lib.encoding import (html_body_declared_encoding, html_to_unicode,
                             http_content_type_encoding, resolve_encoding)
 from w3lib.html import strip_html5_whitespace
 
+from scrapy.exceptions import ScrapyDeprecationWarning
 from scrapy.http import Request
 from scrapy.http.response import Response
 from scrapy.utils.python import memoizemethod_noargs, to_unicode
@@ -61,6 +63,9 @@ class TextResponse(Response):
 
     def body_as_unicode(self):
         """Return body as unicode"""
+        warnings.warn('Response.body_as_unicode() is deprecated, '
+                      'please use Response.text instead.',
+                      ScrapyDeprecationWarning, stacklevel=2)
         return self.text
 
     @property

scrapy/item.py

@@ -14,28 +14,39 @@ from scrapy.utils.deprecate import ScrapyDeprecationWarning
 from scrapy.utils.trackref import object_ref
 
 
-class BaseItem(object_ref):
-    """Base class for all scraped items.
-
-    In Scrapy, an object is considered an *item* if it is an instance of either
-    :class:`BaseItem` or :class:`dict`. For example, when the output of a
-    spider callback is evaluated, only instances of :class:`BaseItem` or
-    :class:`dict` are passed to :ref:`item pipelines <topics-item-pipeline>`.
-
-    If you need instances of a custom class to be considered items by Scrapy,
-    you must inherit from either :class:`BaseItem` or :class:`dict`.
-
-    Unlike instances of :class:`dict`, instances of :class:`BaseItem` may be
-    :ref:`tracked <topics-leaks-trackrefs>` to debug memory leaks.
+class _BaseItem(object_ref):
+    """
+    Temporary class used internally to avoid the deprecation
+    warning raised by isinstance checks using BaseItem.
     """
     pass
 
 
+class _BaseItemMeta(ABCMeta):
+    def __instancecheck__(cls, instance):
+        if cls is BaseItem:
+            warn('scrapy.item.BaseItem is deprecated, please use scrapy.item.Item instead',
+                 ScrapyDeprecationWarning, stacklevel=2)
+        return super().__instancecheck__(instance)
+
+
+class BaseItem(_BaseItem, metaclass=_BaseItemMeta):
+    """
+    Deprecated, please use :class:`scrapy.item.Item` instead
+    """
+
+    def __new__(cls, *args, **kwargs):
+        if issubclass(cls, BaseItem) and not (issubclass(cls, Item) or issubclass(cls, DictItem)):
+            warn('scrapy.item.BaseItem is deprecated, please use scrapy.item.Item instead',
+                 ScrapyDeprecationWarning, stacklevel=2)
+        return super(BaseItem, cls).__new__(cls, *args, **kwargs)
+
+
 class Field(dict):
     """Container of field metadata"""
 
 
-class ItemMeta(ABCMeta):
+class ItemMeta(_BaseItemMeta):
     """Metaclass_ of :class:`Item` that handles field definitions.
 
     .. _metaclass: https://realpython.com/python-metaclasses
@@ -68,8 +79,7 @@ class DictItem(MutableMapping, BaseItem):
 
     def __new__(cls, *args, **kwargs):
         if issubclass(cls, DictItem) and not issubclass(cls, Item):
-            warn('scrapy.item.DictItem is deprecated, please use '
-                 'scrapy.item.Item instead',
+            warn('scrapy.item.DictItem is deprecated, please use scrapy.item.Item instead',
                  ScrapyDeprecationWarning, stacklevel=2)
         return super(DictItem, cls).__new__(cls, *args, **kwargs)
 
@@ -86,8 +96,7 @@ class DictItem(MutableMapping, BaseItem):
         if key in self.fields:
             self._values[key] = value
         else:
-            raise KeyError("%s does not support field: %s" %
-                (self.__class__.__name__, key))
+            raise KeyError("%s does not support field: %s" % (self.__class__.__name__, key))
 
     def __delitem__(self, key):
         del self._values[key]
@@ -99,8 +108,7 @@ class DictItem(MutableMapping, BaseItem):
 
     def __setattr__(self, name, value):
         if not name.startswith('_'):
-            raise AttributeError("Use item[%r] = %r to set field value" %
-                (name, value))
+            raise AttributeError("Use item[%r] = %r to set field value" % (name, value))
         super(DictItem, self).__setattr__(name, value)
 
     def __len__(self):
@@ -127,4 +135,24 @@ class DictItem(MutableMapping, BaseItem):
 
 
 class Item(DictItem, metaclass=ItemMeta):
-    pass
+    """
+    Base class for scraped items.
+
+    In Scrapy, an object is considered an ``item`` if it is an instance of either
+    :class:`Item` or :class:`dict`, or any subclass. For example, when the output of a
+    spider callback is evaluated, only instances of :class:`Item` or
+    :class:`dict` are passed to :ref:`item pipelines <topics-item-pipeline>`.
+
+    If you need instances of a custom class to be considered items by Scrapy,
+    you must inherit from either :class:`Item` or :class:`dict`.
+
+    Items must declare :class:`Field` attributes, which are processed and stored
+    in the ``fields`` attribute. This restricts the set of allowed field names
+    and prevents typos, raising ``KeyError`` when referring to undefined fields.
+    Additionally, fields can be used to define metadata and control the way
+    data is processed internally. Please refer to the :ref:`documentation
+    about fields <topics-items-fields>` for additional information.
+
+    Unlike instances of :class:`dict`, instances of :class:`Item` may be
+    :ref:`tracked <topics-leaks-trackrefs>` to debug memory leaks.
+    """

scrapy/linkextractors/lxmlhtml.py

@@ -1,6 +1,8 @@
 """
 Link extractor based on lxml.html
 """
+import operator
+from functools import partial
 from urllib.parse import urljoin
 
 import lxml.etree as etree
@@ -8,10 +10,10 @@ from w3lib.html import strip_html5_whitespace
 from w3lib.url import canonicalize_url, safe_url_string
 
 from scrapy.link import Link
+from scrapy.linkextractors import FilteringLinkExtractor
 from scrapy.utils.misc import arg_to_iter, rel_has_nofollow
 from scrapy.utils.python import unique as unique_list
 from scrapy.utils.response import get_base_url
-from scrapy.linkextractors import FilteringLinkExtractor
 
 
 # from lxml/src/lxml/html/__init__.py
@@ -27,19 +29,24 @@ def _nons(tag):
     return tag
 
 
+def _identity(x):
+    return x
+
+
+def _canonicalize_link_url(link):
+    return canonicalize_url(link.url, keep_fragments=True)
+
+
 class LxmlParserLinkExtractor:
-    def __init__(self, tag="a", attr="href", process=None, unique=False,
-                 strip=True, canonicalized=False):
-        self.scan_tag = tag if callable(tag) else lambda t: t == tag
-        self.scan_attr = attr if callable(attr) else lambda a: a == attr
-        self.process_attr = process if callable(process) else lambda v: v
+    def __init__(
+        self, tag="a", attr="href", process=None, unique=False, strip=True, canonicalized=False
+    ):
+        self.scan_tag = tag if callable(tag) else partial(operator.eq, tag)
+        self.scan_attr = attr if callable(attr) else partial(operator.eq, attr)
+        self.process_attr = process if callable(process) else _identity
         self.unique = unique
         self.strip = strip
-        if canonicalized:
-            self.link_key = lambda link: link.url
-        else:
-            self.link_key = lambda link: canonicalize_url(link.url,
-                                                          keep_fragments=True)
+        self.link_key = operator.attrgetter("url") if canonicalized else _canonicalize_link_url
 
     def _iter_links(self, document):
         for el in document.iter(etree.Element):
@@ -93,25 +100,44 @@ class LxmlParserLinkExtractor:
 
 class LxmlLinkExtractor(FilteringLinkExtractor):
 
-    def __init__(self, allow=(), deny=(), allow_domains=(), deny_domains=(), restrict_xpaths=(),
-                 tags=('a', 'area'), attrs=('href',), canonicalize=False,
-                 unique=True, process_value=None, deny_extensions=None, restrict_css=(),
-                 strip=True, restrict_text=None):
+    def __init__(
+        self,
+        allow=(),
+        deny=(),
+        allow_domains=(),
+        deny_domains=(),
+        restrict_xpaths=(),
+        tags=('a', 'area'),
+        attrs=('href',),
+        canonicalize=False,
+        unique=True,
+        process_value=None,
+        deny_extensions=None,
+        restrict_css=(),
+        strip=True,
+        restrict_text=None,
+    ):
         tags, attrs = set(arg_to_iter(tags)), set(arg_to_iter(attrs))
         lx = LxmlParserLinkExtractor(
-            tag=lambda x: x in tags,
-            attr=lambda x: x in attrs,
+            tag=partial(operator.contains, tags),
+            attr=partial(operator.contains, attrs),
             unique=unique,
             process=process_value,
             strip=strip,
             canonicalized=canonicalize
         )
-
-        super(LxmlLinkExtractor, self).__init__(lx, allow=allow, deny=deny,
-                                                allow_domains=allow_domains, deny_domains=deny_domains,
-                                                restrict_xpaths=restrict_xpaths, restrict_css=restrict_css,
-                                                canonicalize=canonicalize, deny_extensions=deny_extensions,
-                                                restrict_text=restrict_text)
+        super(LxmlLinkExtractor, self).__init__(
+            link_extractor=lx,
+            allow=allow,
+            deny=deny,
+            allow_domains=allow_domains,
+            deny_domains=deny_domains,
+            restrict_xpaths=restrict_xpaths,
+            restrict_css=restrict_css,
+            canonicalize=canonicalize,
+            deny_extensions=deny_extensions,
+            restrict_text=restrict_text,
+        )
 
     def extract_links(self, response):
         """Returns a list of :class:`~scrapy.link.Link` objects from the
@@ -124,9 +150,11 @@ class LxmlLinkExtractor(FilteringLinkExtractor):
         """
         base_url = get_base_url(response)
         if self.restrict_xpaths:
-            docs = [subdoc
-                    for x in self.restrict_xpaths
-                    for subdoc in response.xpath(x)]
+            docs = [
+                subdoc
+                for x in self.restrict_xpaths
+                for subdoc in response.xpath(x)
+            ]
         else:
             docs = [response.selector]
         all_links = []

scrapy/mail.py

@@ -28,8 +28,10 @@ def _to_bytes_or_none(text):
 
 
 class MailSender:
-    def __init__(self, smtphost='localhost', mailfrom='scrapy@localhost',
-            smtpuser=None, smtppass=None, smtpport=25, smtptls=False, smtpssl=False, debug=False):
+    def __init__(
+        self, smtphost='localhost', mailfrom='scrapy@localhost', smtpuser=None,
+        smtppass=None, smtpport=25, smtptls=False, smtpssl=False, debug=False
+    ):
         self.smtphost = smtphost
         self.smtpport = smtpport
         self.smtpuser = _to_bytes_or_none(smtpuser)
@@ -41,9 +43,15 @@ class MailSender:
 
     @classmethod
     def from_settings(cls, settings):
-        return cls(settings['MAIL_HOST'], settings['MAIL_FROM'], settings['MAIL_USER'],
-            settings['MAIL_PASS'], settings.getint('MAIL_PORT'),
-            settings.getbool('MAIL_TLS'), settings.getbool('MAIL_SSL'))
+        return cls(
+            smtphost=settings['MAIL_HOST'],
+            mailfrom=settings['MAIL_FROM'],
+            smtpuser=settings['MAIL_USER'],
+            smtppass=settings['MAIL_PASS'],
+            smtpport=settings.getint('MAIL_PORT'),
+            smtptls=settings.getbool('MAIL_TLS'),
+            smtpssl=settings.getbool('MAIL_SSL'),
+        )
 
     def send(self, to, subject, body, cc=None, attachs=(), mimetype='text/plain', charset=None, _callback=None):
         from twisted.internet import reactor
@@ -89,9 +97,12 @@ class MailSender:
             return
 
         dfd = self._sendmail(rcpts, msg.as_string().encode(charset or 'utf-8'))
-        dfd.addCallbacks(self._sent_ok, self._sent_failed,
+        dfd.addCallbacks(
+            callback=self._sent_ok,
+            errback=self._sent_failed,
             callbackArgs=[to, cc, subject, len(attachs)],
-            errbackArgs=[to, cc, subject, len(attachs)])
+            errbackArgs=[to, cc, subject, len(attachs)],
+        )
         reactor.addSystemEventTrigger('before', 'shutdown', lambda: dfd)
         return dfd
 
@@ -115,9 +126,10 @@ class MailSender:
         from twisted.mail.smtp import ESMTPSenderFactory
         msg = BytesIO(msg)
         d = defer.Deferred()
-        factory = ESMTPSenderFactory(self.smtpuser, self.smtppass, self.mailfrom,
-            to_addrs, msg, d, heloFallback=True, requireAuthentication=False,
-            requireTransportSecurity=self.smtptls)
+        factory = ESMTPSenderFactory(
+            self.smtpuser, self.smtppass, self.mailfrom, to_addrs, msg, d,
+            heloFallback=True, requireAuthentication=False, requireTransportSecurity=self.smtptls,
+        )
         factory.noisy = False
 
         if self.smtpssl:

scrapy/pipelines/files.py

@@ -83,8 +83,7 @@ class S3FilesStore:
     AWS_USE_SSL = None
     AWS_VERIFY = None
 
-    POLICY = 'private'  # Overriden from settings.FILES_STORE_S3_ACL in
-                        # FilesPipeline.from_settings.
+    POLICY = 'private'  # Overriden from settings.FILES_STORE_S3_ACL in FilesPipeline.from_settings
     HEADERS = {
         'Cache-Control': 'max-age=172800',
     }
@@ -433,7 +432,7 @@ class FilesPipeline(MediaPipeline):
             self.inc_stats(info.spider, 'uptodate')
 
             checksum = result.get('checksum', None)
-            return {'url': request.url, 'path': path, 'checksum': checksum}
+            return {'url': request.url, 'path': path, 'checksum': checksum, 'status': 'uptodate'}
 
         path = self.file_path(request, info=info)
         dfd = defer.maybeDeferred(self.store.stat_file, path, info)
@@ -510,7 +509,7 @@ class FilesPipeline(MediaPipeline):
             )
             raise FileException(str(exc))
 
-        return {'url': request.url, 'path': path, 'checksum': checksum}
+        return {'url': request.url, 'path': path, 'checksum': checksum, 'status': status}
 
     def inc_stats(self, spider, status):
         spider.crawler.stats.inc_value('file_count', spider=spider)

scrapy/responsetypes.py

@@ -58,9 +58,9 @@ class ResponseTypes:
 
     def from_content_disposition(self, content_disposition):
         try:
-            filename = to_unicode(content_disposition,
-                encoding='latin-1', errors='replace').split(';')[1].split('=')[1]
-            filename = filename.strip('"\'')
+            filename = to_unicode(
+                content_disposition, encoding='latin-1', errors='replace'
+            ).split(';')[1].split('=')[1].strip('"\'')
             return self.from_filename(filename)
         except IndexError:
             return Response

scrapy/robotstxt.py

@@ -17,10 +17,12 @@ def decode_robotstxt(robotstxt_body, spider, to_native_str_type=False):
     except UnicodeDecodeError:
         # If we found garbage or robots.txt in an encoding other than UTF-8, disregard it.
         # Switch to 'allow all' state.
-        logger.warning("Failure while parsing robots.txt. "
-                       "File either contains garbage or is in an encoding other than UTF-8, treating it as an empty file.",
-                       exc_info=sys.exc_info(),
-                       extra={'spider': spider})
+        logger.warning(
+            "Failure while parsing robots.txt. File either contains garbage or "
+            "is in an encoding other than UTF-8, treating it as an empty file.",
+            exc_info=sys.exc_info(),
+            extra={'spider': spider},
+        )
         robotstxt_body = ''
     return robotstxt_body
 

scrapy/selector/unified.py

@@ -65,9 +65,9 @@ class Selector(_ParselSelector, object_ref):
     selectorlist_cls = SelectorList
 
     def __init__(self, response=None, text=None, type=None, root=None, **kwargs):
-        if not(response is None or text is None):
-           raise ValueError('%s.__init__() received both response and text'
-                            % self.__class__.__name__)
+        if response is not None and text is not None:
+            raise ValueError('%s.__init__() received both response and text'
+                             % self.__class__.__name__)
 
         st = _st(response, type or self._default_type)
 

scrapy/shell.py

@@ -13,7 +13,7 @@ from w3lib.url import any_to_uri
 from scrapy.crawler import Crawler
 from scrapy.exceptions import IgnoreRequest
 from scrapy.http import Request, Response
-from scrapy.item import BaseItem
+from scrapy.item import _BaseItem
 from scrapy.settings import Settings
 from scrapy.spiders import Spider
 from scrapy.utils.console import start_python_console
@@ -26,8 +26,7 @@ from scrapy.utils.console import DEFAULT_PYTHON_SHELLS
 
 class Shell:
 
-    relevant_classes = (Crawler, Spider, Request, Response, BaseItem,
-                        Settings)
+    relevant_classes = (Crawler, Spider, Request, Response, _BaseItem, Settings)
 
     def __init__(self, crawler, update_vars=None, code=None):
         self.crawler = crawler
@@ -146,14 +145,13 @@ class Shell:
         b.append("Useful shortcuts:")
         if self.inthread:
             b.append("  fetch(url[, redirect=True]) "
-                     "Fetch URL and update local objects "
-                     "(by default, redirects are followed)")
+                     "Fetch URL and update local objects (by default, redirects are followed)")
             b.append("  fetch(req)                  "
                      "Fetch a scrapy.Request and update local objects ")
         b.append("  shelp()           Shell help (print this help)")
         b.append("  view(response)    View response in a browser")
 
-        return "\n".join("[s] %s" % l for l in b)
+        return "\n".join("[s] %s" % line for line in b)
 
     def _is_relevant(self, value):
         return isinstance(value, self.relevant_classes)

scrapy/signals.py

@@ -17,6 +17,7 @@ request_reached_downloader = object()
 request_left_downloader = object()
 response_received = object()
 response_downloaded = object()
+bytes_received = object()
 item_scraped = object()
 item_dropped = object()
 item_error = object()

scrapy/spiders/crawl.py

@@ -54,8 +54,12 @@ class Rule:
         self.process_request = _get_method(self.process_request, spider)
         self.process_request_argcount = len(get_func_args(self.process_request))
         if self.process_request_argcount == 1:
-            msg = 'Rule.process_request should accept two arguments (request, response), accepting only one is deprecated'
-            warnings.warn(msg, category=ScrapyDeprecationWarning, stacklevel=2)
+            warnings.warn(
+                "Rule.process_request should accept two arguments "
+                "(request, response), accepting only one is deprecated",
+                category=ScrapyDeprecationWarning,
+                stacklevel=2,
+            )
 
     def _process_request(self, request, response):
         """

scrapy/spiders/feed.py

@@ -52,7 +52,7 @@ class XMLFeedSpider(Spider):
         """This method is called for the nodes matching the provided tag name
         (itertag). Receives the response and an Selector for each node.
         Overriding this method is mandatory. Otherwise, you spider won't work.
-        This method must return either a BaseItem, a Request, or a list
+        This method must return either an item, a request, or a list
         containing any of them.
         """
 

scrapy/spiders/sitemap.py

@@ -96,5 +96,4 @@ def iterloc(it, alt=False):
 
         # Also consider alternate URLs (xhtml:link rel="alternate")
         if alt and 'alternate' in d:
-            for l in d['alternate']:
-                yield l
+            yield from d['alternate']

scrapy/squeues.py

@@ -81,12 +81,11 @@ def _scrapy_non_serialization_queue(queue_class):
 
 def _pickle_serialize(obj):
     try:
-        return pickle.dumps(obj, protocol=2)
-    # Python <= 3.4 raises pickle.PicklingError here while
-    # 3.5 <= Python < 3.6 raises AttributeError and
-    # Python >= 3.6 raises TypeError
+        return pickle.dumps(obj, protocol=4)
+    # Both pickle.PicklingError and AttributeError can be raised by pickle.dump(s)
+    # TypeError is raised from parsel.Selector
     except (pickle.PicklingError, AttributeError, TypeError) as e:
-        raise ValueError(str(e))
+        raise ValueError(str(e)) from e
 
 
 PickleFifoDiskQueueNonRequest = _serializable_queue(

scrapy/utils/console.py

@@ -28,6 +28,7 @@ def _embed_ipython_shell(namespace={}, banner=''):
 def _embed_bpython_shell(namespace={}, banner=''):
     """Start a bpython shell"""
     import bpython
+
     @wraps(_embed_bpython_shell)
     def wrapper(namespace=namespace, banner=''):
         bpython.embed(locals_=namespace, banner=banner)
@@ -37,6 +38,7 @@ def _embed_bpython_shell(namespace={}, banner=''):
 def _embed_ptpython_shell(namespace={}, banner=''):
     """Start a ptpython shell"""
     import ptpython.repl
+
     @wraps(_embed_ptpython_shell)
     def wrapper(namespace=namespace, banner=''):
         print(banner)

scrapy/utils/defer.py

@@ -88,8 +88,11 @@ def process_chain_both(callbacks, errbacks, input, *a, **kw):
     """Return a Deferred built by chaining the given callbacks and errbacks"""
     d = defer.Deferred()
     for cb, eb in zip(callbacks, errbacks):
-        d.addCallbacks(cb, eb, callbackArgs=a, callbackKeywords=kw,
-            errbackArgs=a, errbackKeywords=kw)
+        d.addCallbacks(
+            callback=cb, errback=eb,
+            callbackArgs=a, callbackKeywords=kw,
+            errbackArgs=a, errbackKeywords=kw,
+        )
     if isinstance(input, failure.Failure):
         d.errback(input)
     else:

scrapy/utils/log.py

@@ -37,7 +37,7 @@ class TopLevelFormatter(logging.Filter):
         self.loggers = loggers or []
 
     def filter(self, record):
-        if any(record.name.startswith(l + '.') for l in self.loggers):
+        if any(record.name.startswith(logger + '.') for logger in self.loggers):
             record.name = record.name.split('.', 1)[0]
         return True
 
@@ -142,10 +142,12 @@ def _get_handler(settings):
 def log_scrapy_info(settings):
     logger.info("Scrapy %(version)s started (bot: %(bot)s)",
                 {'version': scrapy.__version__, 'bot': settings['BOT_NAME']})
-    logger.info("Versions: %(versions)s",
-                {'versions': ", ".join("%s %s" % (name, version)
-                    for name, version in scrapy_components_versions()
-                    if name != "Scrapy")})
+    versions = [
+        "%s %s" % (name, version)
+        for name, version in scrapy_components_versions()
+        if name != "Scrapy"
+    ]
+    logger.info("Versions: %(versions)s", {'versions': ", ".join(versions)})
     from twisted.internet import reactor
     logger.debug("Using reactor: %s.%s", reactor.__module__, reactor.__class__.__name__)
 

scrapy/utils/misc.py

@@ -14,10 +14,10 @@ from w3lib.html import replace_entities
 
 from scrapy.utils.datatypes import LocalWeakReferencedCache
 from scrapy.utils.python import flatten, to_unicode
-from scrapy.item import BaseItem
+from scrapy.item import _BaseItem
 
 
-_ITERABLE_SINGLE_VALUES = dict, BaseItem, str, bytes
+_ITERABLE_SINGLE_VALUES = dict, _BaseItem, str, bytes
 
 
 def arg_to_iter(arg):
@@ -137,17 +137,26 @@ def create_instance(objcls, settings, crawler, *args, **kwargs):
     ``*args`` and ``**kwargs`` are forwarded to the constructors.
 
     Raises ``ValueError`` if both ``settings`` and ``crawler`` are ``None``.
+
+    Raises ``TypeError`` if the resulting instance is ``None`` (e.g. if an
+    extension has not been implemented correctly).
     """
     if settings is None:
         if crawler is None:
             raise ValueError("Specify at least one of settings and crawler.")
         settings = crawler.settings
     if crawler and hasattr(objcls, 'from_crawler'):
-        return objcls.from_crawler(crawler, *args, **kwargs)
+        instance = objcls.from_crawler(crawler, *args, **kwargs)
+        method_name = 'from_crawler'
     elif hasattr(objcls, 'from_settings'):
-        return objcls.from_settings(settings, *args, **kwargs)
+        instance = objcls.from_settings(settings, *args, **kwargs)
+        method_name = 'from_settings'
     else:
-        return objcls(*args, **kwargs)
+        instance = objcls(*args, **kwargs)
+        method_name = '__new__'
+    if instance is None:
+        raise TypeError("%s.%s returned None" % (objcls.__qualname__, method_name))
+    return instance
 
 
 @contextmanager

scrapy/utils/python.py

@@ -152,6 +152,7 @@ def memoizemethod_noargs(method):
     weak reference to its object
     """
     cache = weakref.WeakKeyDictionary()
+
     @wraps(method)
     def new_method(self, *args, **kwargs):
         if self not in cache:

scrapy/utils/response.py

@@ -19,8 +19,7 @@ def get_base_url(response):
     """Return the base url of the given response, joined with the response url"""
     if response not in _baseurl_cache:
         text = response.text[0:4096]
-        _baseurl_cache[response] = html.get_base_url(text, response.url,
-            response.encoding)
+        _baseurl_cache[response] = html.get_base_url(text, response.url, response.encoding)
     return _baseurl_cache[response]
 
 
@@ -31,8 +30,8 @@ def get_meta_refresh(response, ignore_tags=('script', 'noscript')):
     """Parse the http-equiv refrsh parameter from the given response"""
     if response not in _metaref_cache:
         text = response.text[0:4096]
-        _metaref_cache[response] = html.get_meta_refresh(text, response.url,
-            response.encoding, ignore_tags=ignore_tags)
+        _metaref_cache[response] = html.get_meta_refresh(
+            text, response.url, response.encoding, ignore_tags=ignore_tags)
     return _metaref_cache[response]
 
 

scrapy/utils/serialize.py

@@ -5,7 +5,7 @@ import decimal
 from twisted.internet import defer
 
 from scrapy.http import Request, Response
-from scrapy.item import BaseItem
+from scrapy.item import _BaseItem
 
 
 class ScrapyJSONEncoder(json.JSONEncoder):
@@ -26,7 +26,7 @@ class ScrapyJSONEncoder(json.JSONEncoder):
             return str(o)
         elif isinstance(o, defer.Deferred):
             return str(o)
-        elif isinstance(o, BaseItem):
+        elif isinstance(o, _BaseItem):
             return dict(o)
         elif isinstance(o, Request):
             return "<%s %s %s>" % (type(o).__name__, o.method, o.url)

scrapy/utils/signal.py

@@ -28,8 +28,7 @@ def send_catch_log(signal=Any, sender=Anonymous, *arguments, **named):
     responses = []
     for receiver in liveReceivers(getAllReceivers(sender, signal)):
         try:
-            response = robustApply(receiver, signal=signal, sender=sender,
-                *arguments, **named)
+            response = robustApply(receiver, signal=signal, sender=sender, *arguments, **named)
             if isinstance(response, Deferred):
                 logger.error("Cannot return deferreds from signal handler: %(receiver)s",
                              {'receiver': receiver}, extra={'spider': spider})
@@ -63,8 +62,7 @@ def send_catch_log_deferred(signal=Any, sender=Anonymous, *arguments, **named):
     spider = named.get('spider', None)
     dfds = []
     for receiver in liveReceivers(getAllReceivers(sender, signal)):
-        d = maybeDeferred_coro(robustApply, receiver, signal=signal, sender=sender,
-                *arguments, **named)
+        d = maybeDeferred_coro(robustApply, receiver, signal=signal, sender=sender, *arguments, **named)
         d.addErrback(logerror, receiver)
         d.addBoth(lambda result: (receiver, result))
         dfds.append(d)

scrapy/utils/url.py

@@ -27,8 +27,7 @@ def url_is_from_any_domain(url, domains):
 
 def url_is_from_spider(url, spider):
     """Return True if the url belongs to the given spider"""
-    return url_is_from_any_domain(url,
-        [spider.name] + list(getattr(spider, 'allowed_domains', [])))
+    return url_is_from_any_domain(url, [spider.name] + list(getattr(spider, 'allowed_domains', [])))
 
 
 def url_has_any_extension(url, extensions):

tests/pipelines.py

@@ -6,7 +6,7 @@ Some pipelines used for testing
 class ZeroDivisionErrorPipeline:
 
     def open_spider(self, spider):
-        a = 1 / 0
+        1 / 0
 
     def process_item(self, item, spider):
         return item

tests/test_command_parse.py

@@ -142,8 +142,8 @@ ITEM_PIPELINES = {'%s.pipelines.MyPipeline': 1}
     @defer.inlineCallbacks
     def test_request_without_meta(self):
         _, _, stderr = yield self.execute(['--spider', self.spider_name,
-                                          '-c', 'parse_request_without_meta',
-                                          '--nolinks',
+                                           '-c', 'parse_request_without_meta',
+                                           '--nolinks',
                                            self.url('/html')])
         self.assertIn("DEBUG: It Works!", _textmode(stderr))
 

tests/test_command_shell.py

@@ -56,7 +56,9 @@ class ShellTest(ProcessTest, SiteTest, unittest.TestCase):
 
     @defer.inlineCallbacks
     def test_redirect_not_follow_302(self):
-        _, out, _ = yield self.execute(['--no-redirect', self.url('/redirect-no-meta-refresh'), '-c', 'response.status'])
+        _, out, _ = yield self.execute(
+            ['--no-redirect', self.url('/redirect-no-meta-refresh'), '-c', 'response.status']
+        )
         assert out.strip().endswith(b'302')
 
     @defer.inlineCallbacks
@@ -101,15 +103,13 @@ class ShellTest(ProcessTest, SiteTest, unittest.TestCase):
     @defer.inlineCallbacks
     def test_local_nofile(self):
         filepath = 'file:///tests/sample_data/test_site/nothinghere.html'
-        errcode, out, err = yield self.execute([filepath, '-c', 'item'],
-                                       check_code=False)
+        errcode, out, err = yield self.execute([filepath, '-c', 'item'], check_code=False)
         self.assertEqual(errcode, 1, out or err)
         self.assertIn(b'No such file or directory', err)
 
     @defer.inlineCallbacks
     def test_dns_failures(self):
         url = 'www.somedomainthatdoesntexi.st'
-        errcode, out, err = yield self.execute([url, '-c', 'item'],
-                                       check_code=False)
+        errcode, out, err = yield self.execute([url, '-c', 'item'], check_code=False)
         self.assertEqual(errcode, 1, out or err)
         self.assertIn(b'DNS lookup failed', err)

tests/test_command_version.py

@@ -23,8 +23,10 @@ class VersionTest(ProcessTest, unittest.TestCase):
     def test_verbose_output(self):
         encoding = getattr(sys.stdout, 'encoding') or 'utf-8'
         _, out, _ = yield self.execute(['-v'])
-        headers = [l.partition(":")[0].strip()
-                   for l in out.strip().decode(encoding).splitlines()]
+        headers = [
+            line.partition(":")[0].strip()
+            for line in out.strip().decode(encoding).splitlines()
+        ]
         self.assertEqual(headers, ['Scrapy', 'lxml', 'libxml2',
                                    'cssselect', 'parsel', 'w3lib',
                                    'Twisted', 'Python', 'pyOpenSSL',

tests/test_contracts.py

@@ -232,7 +232,8 @@ class ContractsManagerTest(unittest.TestCase):
         # extract contracts correctly
         contracts = self.conman.extract_contracts(spider.returns_request)
         self.assertEqual(len(contracts), 2)
-        self.assertEqual(frozenset(type(x) for x in contracts),
+        self.assertEqual(
+            frozenset(type(x) for x in contracts),
             frozenset([UrlContract, ReturnsContract]))
 
         # returns request for valid method

tests/test_crawl.py

@@ -104,44 +104,44 @@ class CrawlTestCase(TestCase):
     @defer.inlineCallbacks
     def test_retry_503(self):
         crawler = self.runner.create_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl(self.mockserver.url("/status?n=503"), mockserver=self.mockserver)
-        self._assert_retried(l)
+        self._assert_retried(log)
 
     @defer.inlineCallbacks
     def test_retry_conn_failed(self):
         crawler = self.runner.create_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl("http://localhost:65432/status?n=503", mockserver=self.mockserver)
-        self._assert_retried(l)
+        self._assert_retried(log)
 
     @defer.inlineCallbacks
     def test_retry_dns_error(self):
         crawler = self.runner.create_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             # try to fetch the homepage of a non-existent domain
             yield crawler.crawl("http://dns.resolution.invalid./", mockserver=self.mockserver)
-        self._assert_retried(l)
+        self._assert_retried(log)
 
     @defer.inlineCallbacks
     def test_start_requests_bug_before_yield(self):
-        with LogCapture('scrapy', level=logging.ERROR) as l:
+        with LogCapture('scrapy', level=logging.ERROR) as log:
             crawler = self.runner.create_crawler(BrokenStartRequestsSpider)
             yield crawler.crawl(fail_before_yield=1, mockserver=self.mockserver)
 
-        self.assertEqual(len(l.records), 1)
-        record = l.records[0]
+        self.assertEqual(len(log.records), 1)
+        record = log.records[0]
         self.assertIsNotNone(record.exc_info)
         self.assertIs(record.exc_info[0], ZeroDivisionError)
 
     @defer.inlineCallbacks
     def test_start_requests_bug_yielding(self):
-        with LogCapture('scrapy', level=logging.ERROR) as l:
+        with LogCapture('scrapy', level=logging.ERROR) as log:
             crawler = self.runner.create_crawler(BrokenStartRequestsSpider)
             yield crawler.crawl(fail_yielding=1, mockserver=self.mockserver)
 
-        self.assertEqual(len(l.records), 1)
-        record = l.records[0]
+        self.assertEqual(len(log.records), 1)
+        record = log.records[0]
         self.assertIsNotNone(record.exc_info)
         self.assertIs(record.exc_info[0], ZeroDivisionError)
 
@@ -187,25 +187,25 @@ foo body
 with multiples lines
 '''})
         crawler = self.runner.create_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl(self.mockserver.url("/raw?{0}".format(query)), mockserver=self.mockserver)
-        self.assertEqual(str(l).count("Got response 200"), 1)
+        self.assertEqual(str(log).count("Got response 200"), 1)
 
     @defer.inlineCallbacks
     def test_retry_conn_lost(self):
         # connection lost after receiving data
         crawler = self.runner.create_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl(self.mockserver.url("/drop?abort=0"), mockserver=self.mockserver)
-        self._assert_retried(l)
+        self._assert_retried(log)
 
     @defer.inlineCallbacks
     def test_retry_conn_aborted(self):
         # connection lost before receiving data
         crawler = self.runner.create_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl(self.mockserver.url("/drop?abort=1"), mockserver=self.mockserver)
-        self._assert_retried(l)
+        self._assert_retried(log)
 
     def _assert_retried(self, log):
         self.assertEqual(str(log).count("Retrying"), 2)

tests/test_crawler.py

@@ -87,7 +87,7 @@ class CrawlerLoggingTestCase(unittest.TestCase):
         class MySpider(scrapy.Spider):
             name = 'spider'
 
-        crawler = Crawler(MySpider, {})
+        Crawler(MySpider, {})
         assert get_scrapy_root_handler() is None
 
     def test_spider_custom_settings_log_level(self):
@@ -240,13 +240,13 @@ class CrawlerRunnerHasSpider(unittest.TestCase):
 
     def test_crawler_runner_asyncio_enabled_true(self):
         if self.reactor_pytest == 'asyncio':
-            runner = CrawlerRunner(settings={
+            CrawlerRunner(settings={
                 "TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor",
             })
         else:
             msg = r"The installed reactor \(.*?\) does not match the requested one \(.*?\)"
             with self.assertRaisesRegex(Exception, msg):
-                runner = CrawlerRunner(settings={
+                CrawlerRunner(settings={
                     "TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor",
                 })
 
@@ -305,8 +305,10 @@ class CrawlerProcessSubprocess(ScriptRunnerMixin, unittest.TestCase):
     def test_ipv6_default_name_resolver(self):
         log = self.run_script('default_name_resolver.py')
         self.assertIn('Spider closed (finished)', log)
-        self.assertIn("twisted.internet.error.DNSLookupError: DNS lookup failed: no results for hostname lookup: ::1.", log)
         self.assertIn("'downloader/exception_type_count/twisted.internet.error.DNSLookupError': 1,", log)
+        self.assertIn(
+            "twisted.internet.error.DNSLookupError: DNS lookup failed: no results for hostname lookup: ::1.",
+            log)
 
     def test_ipv6_alternative_name_resolver(self):
         log = self.run_script('alternative_name_resolver.py')

tests/test_dependencies.py

@@ -6,7 +6,7 @@ class ScrapyUtilsTest(unittest.TestCase):
     def test_required_openssl_version(self):
         try:
             module = import_module('OpenSSL')
-        except ImportError as ex:
+        except ImportError:
             raise unittest.SkipTest("OpenSSL is not available")
 
         if hasattr(module, '__version__'):

tests/test_downloader_handlers.py

@@ -493,7 +493,10 @@ class Http11TestCase(HttpTestCase):
 class Https11TestCase(Http11TestCase):
     scheme = 'https'
 
-    tls_log_message = 'SSL connection certificate: issuer "/C=IE/O=Scrapy/CN=localhost", subject "/C=IE/O=Scrapy/CN=localhost"'
+    tls_log_message = (
+        'SSL connection certificate: issuer "/C=IE/O=Scrapy/CN=localhost", '
+        'subject "/C=IE/O=Scrapy/CN=localhost"'
+    )
 
     @defer.inlineCallbacks
     def test_tls_logging(self):
@@ -542,7 +545,10 @@ class Https11InvalidDNSPattern(Https11TestCase):
             from service_identity.exceptions import CertificateError  # noqa: F401
         except ImportError:
             raise unittest.SkipTest("cryptography lib is too old")
-        self.tls_log_message = 'SSL connection certificate: issuer "/C=IE/O=Scrapy/CN=127.0.0.1", subject "/C=IE/O=Scrapy/CN=127.0.0.1"'
+        self.tls_log_message = (
+            'SSL connection certificate: issuer "/C=IE/O=Scrapy/CN=127.0.0.1", '
+            'subject "/C=IE/O=Scrapy/CN=127.0.0.1"'
+        )
         super(Https11InvalidDNSPattern, self).setUp()
 
 
@@ -730,6 +736,9 @@ class Http11ProxyTestCase(HttpProxyTestCase):
 
 class HttpDownloadHandlerMock:
 
+    def __init__(self, *args, **kwargs):
+        pass
+
     def download_request(self, request, spider):
         return request
 
@@ -853,8 +862,7 @@ class S3TestCase(unittest.TestCase):
     def test_request_signing4(self):
         # fetches the access control policy sub-resource for the 'johnsmith' bucket.
         date = 'Tue, 27 Mar 2007 19:44:46 +0000'
-        req = Request('s3://johnsmith/?acl',
-            method='GET', headers={'Date': date})
+        req = Request('s3://johnsmith/?acl', method='GET', headers={'Date': date})
         with self._mocked_date(date):
             httpreq = self.download_request(req, self.spider)
         self.assertEqual(httpreq.headers['Authorization'],
@@ -879,8 +887,9 @@ class S3TestCase(unittest.TestCase):
         with self._mocked_date(date):
             httpreq = self.download_request(req, self.spider)
         # botocore does not override Date with x-amz-date
-        self.assertEqual(httpreq.headers['Authorization'],
-                b'AWS 0PN5J17HBGZHT7JJ3X82:k3nL7gH3+PadhTEVn5Ip83xlYzk=')
+        self.assertEqual(
+            httpreq.headers['Authorization'],
+            b'AWS 0PN5J17HBGZHT7JJ3X82:k3nL7gH3+PadhTEVn5Ip83xlYzk=')
 
     def test_request_signing6(self):
         # uploads an object to a CNAME style virtual hosted bucket with metadata.

tests/test_downloadermiddleware_cookies.py

@@ -63,7 +63,7 @@ class CookiesMiddlewareTest(TestCase):
         mw = CookiesMiddleware.from_crawler(crawler)
         with LogCapture('scrapy.downloadermiddlewares.cookies',
                         propagate=False,
-                        level=logging.DEBUG) as l:
+                        level=logging.DEBUG) as log:
             req = Request('http://scrapytest.org/')
             res = Response('http://scrapytest.org/',
                            headers={'Set-Cookie': 'C1=value1; path=/'})
@@ -71,7 +71,7 @@ class CookiesMiddlewareTest(TestCase):
             req2 = Request('http://scrapytest.org/sub1/')
             mw.process_request(req2, crawler.spider)
 
-            l.check(
+            log.check(
                 ('scrapy.downloadermiddlewares.cookies',
                  'DEBUG',
                  'Received cookies from: <200 http://scrapytest.org/>\n'
@@ -87,7 +87,7 @@ class CookiesMiddlewareTest(TestCase):
         mw = CookiesMiddleware.from_crawler(crawler)
         with LogCapture('scrapy.downloadermiddlewares.cookies',
                         propagate=False,
-                        level=logging.DEBUG) as l:
+                        level=logging.DEBUG) as log:
             req = Request('http://scrapytest.org/')
             res = Response('http://scrapytest.org/',
                            headers={'Set-Cookie': 'C1=value1; path=/'})
@@ -95,7 +95,7 @@ class CookiesMiddlewareTest(TestCase):
             req2 = Request('http://scrapytest.org/sub1/')
             mw.process_request(req2, crawler.spider)
 
-            l.check()
+            log.check()
 
     def test_do_not_break_on_non_utf8_header(self):
         req = Request('http://scrapytest.org/')

tests/test_downloadermiddleware_httpcompression.py

@@ -124,7 +124,8 @@ class HttpCompressionTest(TestCase):
             'Content-Encoding': 'gzip',
         }
         f = BytesIO()
-        plainbody = b"""<html><head><title>Some page</title><meta http-equiv="Content-Type" content="text/html; charset=gb2312">"""
+        plainbody = (b'<html><head><title>Some page</title>'
+                     b'<meta http-equiv="Content-Type" content="text/html; charset=gb2312">')
         zf = GzipFile(fileobj=f, mode='wb')
         zf.write(plainbody)
         zf.close()
@@ -142,7 +143,8 @@ class HttpCompressionTest(TestCase):
             'Content-Encoding': 'gzip',
         }
         f = BytesIO()
-        plainbody = b"""<html><head><title>Some page</title><meta http-equiv="Content-Type" content="text/html; charset=gb2312">"""
+        plainbody = (b'<html><head><title>Some page</title>'
+                     b'<meta http-equiv="Content-Type" content="text/html; charset=gb2312">')
         zf = GzipFile(fileobj=f, mode='wb')
         zf.write(plainbody)
         zf.close()
@@ -158,7 +160,8 @@ class HttpCompressionTest(TestCase):
         headers = {
             'Content-Encoding': 'identity',
         }
-        plainbody = b"""<html><head><title>Some page</title><meta http-equiv="Content-Type" content="text/html; charset=gb2312">"""
+        plainbody = (b'<html><head><title>Some page</title>'
+                     b'<meta http-equiv="Content-Type" content="text/html; charset=gb2312">')
         respcls = responsetypes.from_args(url="http://www.example.com/index", headers=headers, body=plainbody)
         response = respcls("http://www.example.com/index", headers=headers, body=plainbody)
         request = Request("http://www.example.com/index")

tests/test_downloadermiddleware_httpproxy.py

@@ -43,8 +43,11 @@ class TestHttpProxyMiddleware(TestCase):
         os.environ.pop('file_proxy', None)
         mw = HttpProxyMiddleware()
 
-        for url, proxy in [('http://e.com', http_proxy),
-                ('https://e.com', https_proxy), ('file://tmp/a', None)]:
+        for url, proxy in [
+            ('http://e.com', http_proxy),
+            ('https://e.com', https_proxy),
+            ('file://tmp/a', None),
+        ]:
             req = Request(url)
             assert mw.process_request(req, spider) is None
             self.assertEqual(req.url, url)

tests/test_downloadermiddleware_redirect.py

@@ -70,7 +70,7 @@ class RedirectMiddlewareTest(unittest.TestCase):
         url = 'http://www.example.com/302'
         url2 = 'http://www.example.com/redirected2'
         req = Request(url, method='POST', body='test',
-            headers={'Content-Type': 'text/plain', 'Content-length': '4'})
+                      headers={'Content-Type': 'text/plain', 'Content-length': '4'})
         rsp = Response(url, headers={'Location': url2}, status=302)
 
         req2 = self.mw.process_response(req, rsp, self.spider)
@@ -149,7 +149,10 @@ class RedirectMiddlewareTest(unittest.TestCase):
         self.assertEqual(req2.url, 'http://scrapytest.org/redirected')
         self.assertEqual(req2.meta['redirect_urls'], ['http://scrapytest.org/first'])
         self.assertEqual(req3.url, 'http://scrapytest.org/redirected2')
-        self.assertEqual(req3.meta['redirect_urls'], ['http://scrapytest.org/first', 'http://scrapytest.org/redirected'])
+        self.assertEqual(
+            req3.meta['redirect_urls'],
+            ['http://scrapytest.org/first', 'http://scrapytest.org/redirected']
+        )
 
     def test_redirect_reasons(self):
         req1 = Request('http://scrapytest.org/first')
@@ -279,7 +282,10 @@ class MetaRefreshMiddlewareTest(unittest.TestCase):
         self.assertEqual(req2.url, 'http://scrapytest.org/redirected')
         self.assertEqual(req2.meta['redirect_urls'], ['http://scrapytest.org/first'])
         self.assertEqual(req3.url, 'http://scrapytest.org/redirected2')
-        self.assertEqual(req3.meta['redirect_urls'], ['http://scrapytest.org/first', 'http://scrapytest.org/redirected'])
+        self.assertEqual(
+            req3.meta['redirect_urls'],
+            ['http://scrapytest.org/first', 'http://scrapytest.org/redirected']
+        )
 
     def test_redirect_reasons(self):
         req1 = Request('http://scrapytest.org/first')

tests/test_downloadermiddleware_retry.py

@@ -81,9 +81,17 @@ class RetryTest(unittest.TestCase):
         assert self.crawler.stats.get_value('retry/count') == 2
 
     def test_twistederrors(self):
-        exceptions = [defer.TimeoutError, TCPTimedOutError, TimeoutError,
-                DNSLookupError, ConnectionRefusedError, ConnectionDone,
-                ConnectError, ConnectionLost, ResponseFailed]
+        exceptions = [
+            ConnectError,
+            ConnectionDone,
+            ConnectionLost,
+            ConnectionRefusedError,
+            defer.TimeoutError,
+            DNSLookupError,
+            ResponseFailed,
+            TCPTimedOutError,
+            TimeoutError,
+        ]
 
         for exc in exceptions:
             req = Request('http://www.scrapytest.org/%s' % exc.__name__)

tests/test_dupefilters.py

@@ -160,7 +160,7 @@ class RFPDupeFilterTest(unittest.TestCase):
             shutil.rmtree(path)
 
     def test_log(self):
-        with LogCapture() as l:
+        with LogCapture() as log:
             settings = {'DUPEFILTER_DEBUG': False,
                         'DUPEFILTER_CLASS': __name__ + '.FromCrawlerRFPDupeFilter'}
             crawler = get_crawler(SimpleSpider, settings_dict=settings)
@@ -177,15 +177,19 @@ class RFPDupeFilterTest(unittest.TestCase):
             dupefilter.log(r2, spider)
 
             assert crawler.stats.get_value('dupefilter/filtered') == 2
-            l.check_present(('scrapy.dupefilters', 'DEBUG',
-                ('Filtered duplicate request: <GET http://scrapytest.org/index.html>'
-                ' - no more duplicates will be shown'
-                ' (see DUPEFILTER_DEBUG to show all duplicates)')))
+            log.check_present(
+                (
+                    'scrapy.dupefilters',
+                    'DEBUG',
+                    'Filtered duplicate request: <GET http://scrapytest.org/index.html> - no more'
+                    ' duplicates will be shown (see DUPEFILTER_DEBUG to show all duplicates)'
+                )
+            )
 
             dupefilter.close('finished')
 
     def test_log_debug(self):
-        with LogCapture() as l:
+        with LogCapture() as log:
             settings = {'DUPEFILTER_DEBUG': True,
                         'DUPEFILTER_CLASS': __name__ + '.FromCrawlerRFPDupeFilter'}
             crawler = get_crawler(SimpleSpider, settings_dict=settings)
@@ -203,11 +207,20 @@ class RFPDupeFilterTest(unittest.TestCase):
             dupefilter.log(r2, spider)
 
             assert crawler.stats.get_value('dupefilter/filtered') == 2
-            l.check_present(('scrapy.dupefilters', 'DEBUG',
-                ('Filtered duplicate request: <GET http://scrapytest.org/index.html>'
-                ' (referer: None)')))
-            l.check_present(('scrapy.dupefilters', 'DEBUG',
-                ('Filtered duplicate request: <GET http://scrapytest.org/index.html>'
-                ' (referer: http://scrapytest.org/INDEX.html)')))
+            log.check_present(
+                (
+                    'scrapy.dupefilters',
+                    'DEBUG',
+                    'Filtered duplicate request: <GET http://scrapytest.org/index.html> (referer: None)'
+                )
+            )
+            log.check_present(
+                (
+                    'scrapy.dupefilters',
+                    'DEBUG',
+                    'Filtered duplicate request: <GET http://scrapytest.org/index.html>'
+                    ' (referer: http://scrapytest.org/INDEX.html)'
+                )
+            )
 
             dupefilter.close('finished')

tests/test_engine.py

@@ -13,23 +13,25 @@ module with the ``runserver`` argument::
 import os
 import re
 import sys
+from collections import defaultdict
 from urllib.parse import urlparse
 
 from pytest import mark
 from twisted.internet import reactor, defer
-from twisted.web import server, static, util
 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.utils.test import get_crawler
-from pydispatch import dispatcher
-from tests import tests_datadir
-from scrapy.spiders import Spider
+from scrapy.http import Request
 from scrapy.item import Item, Field
 from scrapy.linkextractors import LinkExtractor
-from scrapy.http import Request
+from scrapy.spiders import Spider
 from scrapy.utils.signal import disconnect_all
+from scrapy.utils.test import get_crawler
+
+from tests import tests_datadir, get_testdata
 
 
 class TestItem(Item):
@@ -94,6 +96,8 @@ 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)]
+    r.putChild(b"numbers", static.Data(b"".join(numbers), "text/plain"))
 
     port = reactor.listenTCP(0, server.Site(r), interface="127.0.0.1")
     if debug:
@@ -113,15 +117,20 @@ class CrawlerRun:
         self.reqreached = []
         self.itemerror = []
         self.itemresp = []
-        self.signals_catched = {}
+        self.bytes = defaultdict(lambda: list())
+        self.signals_caught = {}
         self.spider_class = spider_class
 
     def run(self):
         self.port = start_test_site()
         self.portno = self.port.getHost().port
 
-        start_urls = [self.geturl("/"), self.geturl("/redirect"),
-                      self.geturl("/redirect")]  # a duplicate
+        start_urls = [
+            self.geturl("/"),
+            self.geturl("/redirect"),
+            self.geturl("/redirect"),  # duplicate
+            self.geturl("/numbers"),
+        ]
 
         for name, signal in vars(signals).items():
             if not name.startswith('_'):
@@ -130,6 +139,7 @@ class CrawlerRun:
         self.crawler = get_crawler(self.spider_class)
         self.crawler.signals.connect(self.item_scraped, signals.item_scraped)
         self.crawler.signals.connect(self.item_error, signals.item_error)
+        self.crawler.signals.connect(self.bytes_received, signals.bytes_received)
         self.crawler.signals.connect(self.request_scheduled, signals.request_scheduled)
         self.crawler.signals.connect(self.request_dropped, signals.request_dropped)
         self.crawler.signals.connect(self.request_reached, signals.request_reached_downloader)
@@ -161,6 +171,9 @@ class CrawlerRun:
     def item_scraped(self, item, spider, response):
         self.itemresp.append((item, response))
 
+    def bytes_received(self, data, request, spider):
+        self.bytes[request].append(data)
+
     def request_scheduled(self, request, spider):
         self.reqplug.append((request, spider))
 
@@ -178,7 +191,7 @@ class CrawlerRun:
         signalargs = kwargs.copy()
         sig = signalargs.pop('signal')
         signalargs.pop('sender', None)
-        self.signals_catched[sig] = signalargs
+        self.signals_caught[sig] = signalargs
 
 
 class EngineTest(unittest.TestCase):
@@ -189,16 +202,17 @@ class EngineTest(unittest.TestCase):
             self.run = CrawlerRun(spider)
             yield self.run.run()
             self._assert_visited_urls()
-            self._assert_scheduled_requests(urls_to_visit=8)
+            self._assert_scheduled_requests(urls_to_visit=9)
             self._assert_downloaded_responses()
             self._assert_scraped_items()
-            self._assert_signals_catched()
+            self._assert_signals_caught()
+            self._assert_bytes_received()
 
     @defer.inlineCallbacks
     def test_crawler_dupefilter(self):
         self.run = CrawlerRun(TestDupeFilterSpider)
         yield self.run.run()
-        self._assert_scheduled_requests(urls_to_visit=7)
+        self._assert_scheduled_requests(urls_to_visit=8)
         self._assert_dropped_requests()
 
     @defer.inlineCallbacks
@@ -242,8 +256,8 @@ class EngineTest(unittest.TestCase):
     def _assert_visited_urls(self):
         must_be_visited = ["/", "/redirect", "/redirected",
                            "/item1.html", "/item2.html", "/item999.html"]
-        urls_visited = set([rp[0].url for rp in self.run.respplug])
-        urls_expected = set([self.run.geturl(p) for p in must_be_visited])
+        urls_visited = {rp[0].url for rp in self.run.respplug}
+        urls_expected = {self.run.geturl(p) for p in must_be_visited}
         assert urls_expected <= urls_visited, "URLs not visited: %s" % list(urls_expected - urls_visited)
 
     def _assert_scheduled_requests(self, urls_to_visit=None):
@@ -251,8 +265,8 @@ class EngineTest(unittest.TestCase):
 
         paths_expected = ['/item999.html', '/item2.html', '/item1.html']
 
-        urls_requested = set([rq[0].url for rq in self.run.reqplug])
-        urls_expected = set([self.run.geturl(p) for p in paths_expected])
+        urls_requested = {rq[0].url for rq in self.run.reqplug}
+        urls_expected = {self.run.geturl(p) for p in paths_expected}
         assert urls_expected <= urls_requested
         scheduled_requests_count = len(self.run.reqplug)
         dropped_requests_count = len(self.run.reqdropped)
@@ -267,8 +281,8 @@ class EngineTest(unittest.TestCase):
 
     def _assert_downloaded_responses(self):
         # response tests
-        self.assertEqual(8, len(self.run.respplug))
-        self.assertEqual(8, len(self.run.reqreached))
+        self.assertEqual(9, len(self.run.respplug))
+        self.assertEqual(9, len(self.run.reqreached))
 
         for response, _ in self.run.respplug:
             if self.run.getpath(response.url) == '/item999.html':
@@ -301,19 +315,61 @@ class EngineTest(unittest.TestCase):
                 self.assertEqual('Item 2 name', item['name'])
                 self.assertEqual('200', item['price'])
 
-    def _assert_signals_catched(self):
-        assert signals.engine_started in self.run.signals_catched
-        assert signals.engine_stopped in self.run.signals_catched
-        assert signals.spider_opened in self.run.signals_catched
-        assert signals.spider_idle in self.run.signals_catched
-        assert signals.spider_closed in self.run.signals_catched
+    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)
+            if self.run.getpath(request.url) == "/":
+                self.assertEqual(joined_data, get_testdata("test_site", "index.html"))
+            elif self.run.getpath(request.url) == "/item1.html":
+                self.assertEqual(joined_data, get_testdata("test_site", "item1.html"))
+            elif self.run.getpath(request.url) == "/item2.html":
+                self.assertEqual(joined_data, get_testdata("test_site", "item2.html"))
+            elif self.run.getpath(request.url) == "/redirected":
+                self.assertEqual(joined_data, b"Redirected here")
+            elif self.run.getpath(request.url) == '/redirect':
+                self.assertEqual(
+                    joined_data,
+                    b"\n<html>\n"
+                    b"    <head>\n"
+                    b"        <meta http-equiv=\"refresh\" content=\"0;URL=/redirected\">\n"
+                    b"    </head>\n"
+                    b"    <body bgcolor=\"#FFFFFF\" text=\"#000000\">\n"
+                    b"    <a href=\"/redirected\">click here</a>\n"
+                    b"    </body>\n"
+                    b"</html>\n"
+                )
+            elif self.run.getpath(request.url) == "/tem999.html":
+                self.assertEqual(
+                    joined_data,
+                    b"\n<html>\n"
+                    b"  <head><title>404 - No Such Resource</title></head>\n"
+                    b"  <body>\n"
+                    b"    <h1>No Such Resource</h1>\n"
+                    b"    <p>File not found.</p>\n"
+                    b"  </body>\n"
+                    b"</html>\n"
+                )
+            elif self.run.getpath(request.url) == "/numbers":
+                # 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)]
+                self.assertEqual(joined_data, b"".join(numbers))
+
+    def _assert_signals_caught(self):
+        assert signals.engine_started in self.run.signals_caught
+        assert signals.engine_stopped in self.run.signals_caught
+        assert signals.spider_opened in self.run.signals_caught
+        assert signals.spider_idle in self.run.signals_caught
+        assert signals.spider_closed in self.run.signals_caught
 
         self.assertEqual({'spider': self.run.spider},
-                         self.run.signals_catched[signals.spider_opened])
+                         self.run.signals_caught[signals.spider_opened])
         self.assertEqual({'spider': self.run.spider},
-                         self.run.signals_catched[signals.spider_idle])
+                         self.run.signals_caught[signals.spider_idle])
         self.assertEqual({'spider': self.run.spider, 'reason': 'finished'},
-                         self.run.signals_catched[signals.spider_closed])
+                         self.run.signals_caught[signals.spider_closed])
 
     @defer.inlineCallbacks
     def test_close_downloader(self):

tests/test_exporters.py

@@ -111,7 +111,10 @@ class PythonItemExporterTest(BaseItemExporterTest):
         ie = self._get_exporter()
         exported = ie.export_item(i3)
         self.assertEqual(type(exported), dict)
-        self.assertEqual(exported, {'age': {'age': {'age': '22', 'name': u'Joseph'}, 'name': u'Maria'}, 'name': 'Jesus'})
+        self.assertEqual(
+            exported,
+            {'age': {'age': {'age': '22', 'name': u'Joseph'}, 'name': u'Maria'}, 'name': 'Jesus'}
+        )
         self.assertEqual(type(exported['age']), dict)
         self.assertEqual(type(exported['age']['age']), dict)
 
@@ -121,7 +124,10 @@ class PythonItemExporterTest(BaseItemExporterTest):
         i3 = TestItem(name=u'Jesus', age=[i2])
         ie = self._get_exporter()
         exported = ie.export_item(i3)
-        self.assertEqual(exported, {'age': [{'age': [{'age': '22', 'name': u'Joseph'}], 'name': u'Maria'}], 'name': 'Jesus'})
+        self.assertEqual(
+            exported,
+            {'age': [{'age': [{'age': '22', 'name': u'Joseph'}], 'name': u'Maria'}], 'name': 'Jesus'}
+        )
         self.assertEqual(type(exported['age'][0]), dict)
         self.assertEqual(type(exported['age'][0]['age'][0]), dict)
 
@@ -131,7 +137,10 @@ class PythonItemExporterTest(BaseItemExporterTest):
         i3 = TestItem(name=u'Jesus', age=[i2])
         ie = self._get_exporter()
         exported = ie.export_item(i3)
-        self.assertEqual(exported, {'age': [{'age': [{'age': '22', 'name': u'Joseph'}], 'name': u'Maria'}], 'name': 'Jesus'})
+        self.assertEqual(
+            exported,
+            {'age': [{'age': [{'age': '22', 'name': u'Joseph'}], 'name': u'Maria'}], 'name': 'Jesus'}
+        )
         self.assertEqual(type(exported['age'][0]), dict)
         self.assertEqual(type(exported['age'][0]['age'][0]), dict)
 
@@ -328,13 +337,19 @@ class XmlItemExporterTest(BaseItemExporterTest):
         self.assertXmlEquivalent(fp.getvalue(), expected_value)
 
     def _check_output(self):
-        expected_value = b'<?xml version="1.0" encoding="utf-8"?>\n<items><item><age>22</age><name>John\xc2\xa3</name></item></items>'
+        expected_value = (
+            b'<?xml version="1.0" encoding="utf-8"?>\n'
+            b'<items><item><age>22</age><name>John\xc2\xa3</name></item></items>'
+        )
         self.assertXmlEquivalent(self.output.getvalue(), expected_value)
 
     def test_multivalued_fields(self):
         self.assertExportResult(
             TestItem(name=[u'John\xa3', u'Doe']),
-            b'<?xml version="1.0" encoding="utf-8"?>\n<items><item><name><value>John\xc2\xa3</value><value>Doe</value></name></item></items>'
+            (
+                b'<?xml version="1.0" encoding="utf-8"?>\n'
+                b'<items><item><name><value>John\xc2\xa3</value><value>Doe</value></name></item></items>'
+            )
         )
 
     def test_nested_item(self):

tests/test_extension_telnet.py

@@ -11,8 +11,6 @@ class TelnetExtensionTest(unittest.TestCase):
     def _get_console_and_portal(self, settings=None):
         crawler = get_crawler(settings_dict=settings)
         console = TelnetConsole(crawler)
-        username = console.username
-        password = console.password
 
         # This function has some side effects we don't need for this test
         console._get_telnet_vars = lambda: {}

tests/test_feedexport.py

@@ -715,13 +715,15 @@ class FeedExportTest(unittest.TestCase):
     @defer.inlineCallbacks
     def test_export_encoding(self):
         items = [dict({'foo': u'Test\xd6'})]
-        header = ['foo']
 
         formats = {
-            'json': u'[{"foo": "Test\\u00d6"}]'.encode('utf-8'),
-            'jsonlines': u'{"foo": "Test\\u00d6"}\n'.encode('utf-8'),
-            'xml': u'<?xml version="1.0" encoding="utf-8"?>\n<items><item><foo>Test\xd6</foo></item></items>'.encode('utf-8'),
-            'csv': u'foo\r\nTest\xd6\r\n'.encode('utf-8'),
+            'json': '[{"foo": "Test\\u00d6"}]'.encode('utf-8'),
+            'jsonlines': '{"foo": "Test\\u00d6"}\n'.encode('utf-8'),
+            'xml': (
+                '<?xml version="1.0" encoding="utf-8"?>\n'
+                '<items><item><foo>Test\xd6</foo></item></items>'
+            ).encode('utf-8'),
+            'csv': 'foo\r\nTest\xd6\r\n'.encode('utf-8'),
         }
 
         for fmt, expected in formats.items():
@@ -735,10 +737,13 @@ class FeedExportTest(unittest.TestCase):
             self.assertEqual(expected, data[fmt])
 
         formats = {
-            'json': u'[{"foo": "Test\xd6"}]'.encode('latin-1'),
-            'jsonlines': u'{"foo": "Test\xd6"}\n'.encode('latin-1'),
-            'xml': u'<?xml version="1.0" encoding="latin-1"?>\n<items><item><foo>Test\xd6</foo></item></items>'.encode('latin-1'),
-            'csv': u'foo\r\nTest\xd6\r\n'.encode('latin-1'),
+            'json': '[{"foo": "Test\xd6"}]'.encode('latin-1'),
+            'jsonlines': '{"foo": "Test\xd6"}\n'.encode('latin-1'),
+            'xml': (
+                '<?xml version="1.0" encoding="latin-1"?>\n'
+                '<items><item><foo>Test\xd6</foo></item></items>'
+            ).encode('latin-1'),
+            'csv': 'foo\r\nTest\xd6\r\n'.encode('latin-1'),
         }
 
         for fmt, expected in formats.items():
@@ -757,9 +762,12 @@ class FeedExportTest(unittest.TestCase):
         items = [dict({'foo': u'FOO', 'bar': u'BAR'})]
 
         formats = {
-            'json': u'[\n{"bar": "BAR"}\n]'.encode('utf-8'),
-            'xml': u'<?xml version="1.0" encoding="latin-1"?>\n<items>\n  <item>\n    <foo>FOO</foo>\n  </item>\n</items>'.encode('latin-1'),
-            'csv': u'bar,foo\r\nBAR,FOO\r\n'.encode('utf-8'),
+            'json': '[\n{"bar": "BAR"}\n]'.encode('utf-8'),
+            'xml': (
+                '<?xml version="1.0" encoding="latin-1"?>\n'
+                '<items>\n  <item>\n    <foo>FOO</foo>\n  </item>\n</items>'
+            ).encode('latin-1'),
+            'csv': 'bar,foo\r\nBAR,FOO\r\n'.encode('utf-8'),
         }
 
         settings = {

tests/test_http_request.py

@@ -415,8 +415,7 @@ class FormRequestTest(RequestTest):
         # using multiples values for a single key
         data = {'price': u'\xa3 100', 'colours': ['red', 'blue', 'green']}
         r3 = self.request_class("http://www.example.com", formdata=data)
-        self.assertQueryEqual(r3.body,
-            b'colours=red&colours=blue&colours=green&price=%C2%A3+100')
+        self.assertQueryEqual(r3.body, b'colours=red&colours=blue&colours=green&price=%C2%A3+100')
 
     def test_from_response_post(self):
         response = _buildresponse(
@@ -426,8 +425,7 @@ class FormRequestTest(RequestTest):
             <input type="hidden" name="test2" value="xxx">
             </form>""",
             url="http://www.example.com/this/list.html")
-        req = self.request_class.from_response(response,
-                formdata={'one': ['two', 'three'], 'six': 'seven'})
+        req = self.request_class.from_response(response, formdata={'one': ['two', 'three'], 'six': 'seven'})
 
         self.assertEqual(req.method, 'POST')
         self.assertEqual(req.headers[b'Content-type'], b'application/x-www-form-urlencoded')
@@ -446,8 +444,7 @@ class FormRequestTest(RequestTest):
             <input type="hidden" name="test2" value="xxx \xc2\xb5">
             </form>""",
             url="http://www.example.com/this/list.html")
-        req = self.request_class.from_response(response,
-                formdata={'one': ['two', 'three'], 'six': 'seven'})
+        req = self.request_class.from_response(response, formdata={'one': ['two', 'three'], 'six': 'seven'})
 
         self.assertEqual(req.method, 'POST')
         self.assertEqual(req.headers[b'Content-type'], b'application/x-www-form-urlencoded')
@@ -468,8 +465,7 @@ class FormRequestTest(RequestTest):
             url="http://www.example.com/this/list.html",
             encoding='latin1',
         )
-        req = self.request_class.from_response(response,
-                formdata={'one': ['two', 'three'], 'six': 'seven'})
+        req = self.request_class.from_response(response, formdata={'one': ['two', 'three'], 'six': 'seven'})
 
         self.assertEqual(req.method, 'POST')
         self.assertEqual(req.headers[b'Content-type'], b'application/x-www-form-urlencoded')
@@ -488,8 +484,7 @@ class FormRequestTest(RequestTest):
             <input type="hidden" name="test2" value="xxx µ">
             </form>""",
             url="http://www.example.com/this/list.html")
-        req = self.request_class.from_response(response,
-                formdata={'one': ['two', 'three'], 'six': 'seven'})
+        req = self.request_class.from_response(response, formdata={'one': ['two', 'three'], 'six': 'seven'})
 
         self.assertEqual(req.method, 'POST')
         self.assertEqual(req.headers[b'Content-type'], b'application/x-www-form-urlencoded')
@@ -549,14 +544,13 @@ class FormRequestTest(RequestTest):
             <input type="hidden" name="test2" value="xxx">
             </form>""",
             url="http://www.example.com/this/list.html")
-        r1 = self.request_class.from_response(response,
-                formdata={'one': ['two', 'three'], 'six': 'seven'})
+        r1 = self.request_class.from_response(response, formdata={'one': ['two', 'three'], 'six': 'seven'})
         self.assertEqual(r1.method, 'GET')
         self.assertEqual(urlparse(r1.url).hostname, "www.example.com")
         self.assertEqual(urlparse(r1.url).path, "/this/get.php")
         fs = _qs(r1)
-        self.assertEqual(set(fs[b'test']), set([b'val1', b'val2']))
-        self.assertEqual(set(fs[b'one']), set([b'two', b'three']))
+        self.assertEqual(set(fs[b'test']), {b'val1', b'val2'})
+        self.assertEqual(set(fs[b'one']), {b'two', b'three'})
         self.assertEqual(fs[b'test2'], [b'xxx'])
         self.assertEqual(fs[b'six'], [b'seven'])
 
@@ -1053,7 +1047,7 @@ class FormRequestTest(RequestTest):
             </form>''')
         req = self.request_class.from_response(res)
         fs = _qs(req)
-        self.assertEqual(set(fs), set([b'h2', b'i2', b'i1', b'i3', b'h1', b'i5', b'i4']))
+        self.assertEqual(set(fs), {b'h2', b'i2', b'i1', b'i3', b'h1', b'i5', b'i4'})
 
     def test_from_response_xpath(self):
         response = _buildresponse(
@@ -1264,7 +1258,10 @@ class XmlRpcRequestTest(RequestTest):
 class JsonRequestTest(RequestTest):
     request_class = JsonRequest
     default_method = 'GET'
-    default_headers = {b'Content-Type': [b'application/json'], b'Accept': [b'application/json, text/javascript, */*; q=0.01']}
+    default_headers = {
+        b'Content-Type': [b'application/json'],
+        b'Accept': [b'application/json, text/javascript, */*; q=0.01'],
+    }
 
     def setUp(self):
         warnings.simplefilter("always")

tests/test_http_response.py

@@ -1,7 +1,9 @@
 import unittest
+from warnings import catch_warnings
 
 from w3lib.encoding import resolve_encoding
 
+from scrapy.exceptions import ScrapyDeprecationWarning
 from scrapy.http import (Request, Response, TextResponse, HtmlResponse,
                          XmlResponse, Headers)
 from scrapy.selector import Selector
@@ -24,7 +26,11 @@ class BaseResponseTest(unittest.TestCase):
         self.assertTrue(isinstance(self.response_class('http://example.com/', body=b''), self.response_class))
         self.assertTrue(isinstance(self.response_class('http://example.com/', body=b'body'), self.response_class))
         # test presence of all optional parameters
-        self.assertTrue(isinstance(self.response_class('http://example.com/', body=b'', headers={}, status=200), self.response_class))
+        self.assertTrue(
+            isinstance(
+                self.response_class('http://example.com/', body=b'', headers={}, status=200), self.response_class
+            )
+        )
 
         r = self.response_class("http://www.example.com")
         assert isinstance(r.url, str)
@@ -322,13 +328,16 @@ class TextResponseTest(BaseResponseTest):
         self.assertEqual(resp.url, to_unicode(b'http://www.example.com/price/\xc2\xa3'))
         resp = self.response_class(url=u"http://www.example.com/price/\xa3", encoding='latin-1')
         self.assertEqual(resp.url, 'http://www.example.com/price/\xa3')
-        resp = self.response_class(u"http://www.example.com/price/\xa3", headers={"Content-type": ["text/html; charset=utf-8"]})
+        resp = self.response_class(u"http://www.example.com/price/\xa3",
+                                   headers={"Content-type": ["text/html; charset=utf-8"]})
         self.assertEqual(resp.url, to_unicode(b'http://www.example.com/price/\xc2\xa3'))
-        resp = self.response_class(u"http://www.example.com/price/\xa3", headers={"Content-type": ["text/html; charset=iso-8859-1"]})
+        resp = self.response_class(u"http://www.example.com/price/\xa3",
+                                   headers={"Content-type": ["text/html; charset=iso-8859-1"]})
         self.assertEqual(resp.url, 'http://www.example.com/price/\xa3')
 
     def test_unicode_body(self):
-        unicode_string = u'\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u0442\u0435\u043a\u0441\u0442'
+        unicode_string = ('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0447\u0435\u0441\u043a\u0438\u0439 '
+                          '\u0442\u0435\u043a\u0441\u0442')
         self.assertRaises(TypeError, self.response_class, 'http://www.example.com', body=u'unicode body')
 
         original_string = unicode_string.encode('cp1251')
@@ -343,13 +352,18 @@ class TextResponseTest(BaseResponseTest):
         self.assertEqual(r1.text, unicode_string)
 
     def test_encoding(self):
-        r1 = self.response_class("http://www.example.com", headers={"Content-type": ["text/html; charset=utf-8"]}, body=b"\xc2\xa3")
+        r1 = self.response_class("http://www.example.com", body=b"\xc2\xa3",
+                                 headers={"Content-type": ["text/html; charset=utf-8"]})
         r2 = self.response_class("http://www.example.com", encoding='utf-8', body=u"\xa3")
-        r3 = self.response_class("http://www.example.com", headers={"Content-type": ["text/html; charset=iso-8859-1"]}, body=b"\xa3")
+        r3 = self.response_class("http://www.example.com", body=b"\xa3",
+                                 headers={"Content-type": ["text/html; charset=iso-8859-1"]})
         r4 = self.response_class("http://www.example.com", body=b"\xa2\xa3")
-        r5 = self.response_class("http://www.example.com", headers={"Content-type": ["text/html; charset=None"]}, body=b"\xc2\xa3")
-        r6 = self.response_class("http://www.example.com", headers={"Content-type": ["text/html; charset=gb2312"]}, body=b"\xa8D")
-        r7 = self.response_class("http://www.example.com", headers={"Content-type": ["text/html; charset=gbk"]}, body=b"\xa8D")
+        r5 = self.response_class("http://www.example.com", body=b"\xc2\xa3",
+                                 headers={"Content-type": ["text/html; charset=None"]})
+        r6 = self.response_class("http://www.example.com", body=b"\xa8D",
+                                 headers={"Content-type": ["text/html; charset=gb2312"]})
+        r7 = self.response_class("http://www.example.com", body=b"\xa8D",
+                                 headers={"Content-type": ["text/html; charset=gbk"]})
 
         self.assertEqual(r1._headers_encoding(), "utf-8")
         self.assertEqual(r2._headers_encoding(), None)
@@ -484,8 +498,10 @@ class TextResponseTest(BaseResponseTest):
             response.xpath("normalize-space(//p[@class=\"content\"])").getall(),
         )
         self.assertEqual(
-            response.xpath("//title[count(following::p[@class=$pclass])=$pcount]/text()",
-                pclass="content", pcount=1).getall(),
+            response.xpath(
+                "//title[count(following::p[@class=$pclass])=$pcount]/text()",
+                pclass="content", pcount=1,
+            ).getall(),
             response.xpath("//title[count(following::p[@class=\"content\"])=1]/text()").getall(),
         )
 
@@ -565,12 +581,14 @@ class TextResponseTest(BaseResponseTest):
             'http://example.com',
             body=b'''<html><body><a href=" foo\n">click me</a></body></html>'''
         )
-        self._assert_followed_url(resp.css('a')[0],
-                                 'http://example.com/foo',
-                                  response=resp)
-        self._assert_followed_url(resp.css('a::attr(href)')[0],
-                                 'http://example.com/foo',
-                                  response=resp)
+        self._assert_followed_url(
+            resp.css('a')[0],
+            'http://example.com/foo',
+            response=resp)
+        self._assert_followed_url(
+            resp.css('a::attr(href)')[0],
+            'http://example.com/foo',
+            response=resp)
 
     def test_follow_encoding(self):
         resp1 = self.response_class(
@@ -660,6 +678,13 @@ class TextResponseTest(BaseResponseTest):
         with self.assertRaises(ValueError):
             response.follow_all(css='a[href*="example.com"]', xpath='//a[contains(@href, "example.com")]')
 
+    def test_body_as_unicode_deprecation_warning(self):
+        with catch_warnings(record=True) as warnings:
+            r1 = self.response_class("http://www.example.com", body=u'Hello', encoding='utf-8')
+            self.assertEqual(r1.body_as_unicode(), u'Hello')
+            self.assertEqual(len(warnings), 1)
+            self.assertEqual(warnings[0].category, ScrapyDeprecationWarning)
+
 
 class HtmlResponseTest(TextResponseTest):
 
@@ -684,7 +709,8 @@ class HtmlResponseTest(TextResponseTest):
         body = b"""<html><head><title>Some page</title><meta http-equiv="Content-Type" content="text/html; charset=utf-8">
         </head><body>Price: \xa3100</body></html>'
         """
-        r3 = self.response_class("http://www.example.com", headers={"Content-type": ["text/html; charset=iso-8859-1"]}, body=body)
+        r3 = self.response_class("http://www.example.com", body=body,
+                                 headers={"Content-type": ["text/html; charset=iso-8859-1"]})
         self._assert_response_values(r3, 'iso-8859-1', body)
 
         # make sure replace() preserves the encoding of the original response

tests/test_item.py

@@ -4,7 +4,7 @@ from unittest import mock
 from warnings import catch_warnings
 
 from scrapy.exceptions import ScrapyDeprecationWarning
-from scrapy.item import ABCMeta, DictItem, Field, Item, ItemMeta
+from scrapy.item import ABCMeta, _BaseItem, BaseItem, DictItem, Field, Item, ItemMeta
 
 
 PY36_PLUS = (sys.version_info.major >= 3) and (sys.version_info.minor >= 6)
@@ -131,12 +131,12 @@ class ItemTest(unittest.TestCase):
         self.assertSortedEqual(list(item.values()), [u'New'])
 
     def test_metaclass_inheritance(self):
-        class BaseItem(Item):
+        class ParentItem(Item):
             name = Field()
             keys = Field()
             values = Field()
 
-        class TestItem(BaseItem):
+        class TestItem(ParentItem):
             keys = Field()
 
         i = TestItem()
@@ -162,8 +162,7 @@ class ItemTest(unittest.TestCase):
         item = D(save='X', load='Y')
         self.assertEqual(item['save'], 'X')
         self.assertEqual(item['load'], 'Y')
-        self.assertEqual(D.fields, {'load': {'default': 'A'},
-            'save': {'default': 'A'}})
+        self.assertEqual(D.fields, {'load': {'default': 'A'}, 'save': {'default': 'A'}})
 
         # D class inverted
         class E(C, B):
@@ -171,8 +170,7 @@ class ItemTest(unittest.TestCase):
 
         self.assertEqual(E(save='X')['save'], 'X')
         self.assertEqual(E(load='X')['load'], 'X')
-        self.assertEqual(E.fields, {'load': {'default': 'C'},
-            'save': {'default': 'C'}})
+        self.assertEqual(E.fields, {'load': {'default': 'C'}, 'save': {'default': 'C'}})
 
     def test_metaclass_multiple_inheritance_diamond(self):
         class A(Item):
@@ -193,8 +191,9 @@ class ItemTest(unittest.TestCase):
 
         self.assertEqual(D(save='X')['save'], 'X')
         self.assertEqual(D(load='X')['load'], 'X')
-        self.assertEqual(D.fields, {'save': {'default': 'C'},
-            'load': {'default': 'D'}, 'update': {'default': 'D'}})
+        self.assertEqual(
+            D.fields,
+            {'save': {'default': 'C'}, 'load': {'default': 'D'}, 'update': {'default': 'D'}})
 
         # D class inverted
         class E(C, B):
@@ -202,8 +201,9 @@ class ItemTest(unittest.TestCase):
 
         self.assertEqual(E(save='X')['save'], 'X')
         self.assertEqual(E(load='X')['load'], 'X')
-        self.assertEqual(E.fields, {'save': {'default': 'C'},
-            'load': {'default': 'E'}, 'update': {'default': 'C'}})
+        self.assertEqual(
+            E.fields,
+            {'save': {'default': 'C'}, 'load': {'default': 'E'}, 'update': {'default': 'C'}})
 
     def test_metaclass_multiple_inheritance_without_metaclass(self):
         class A(Item):
@@ -223,8 +223,7 @@ class ItemTest(unittest.TestCase):
 
         self.assertRaises(KeyError, D, not_allowed='value')
         self.assertEqual(D(save='X')['save'], 'X')
-        self.assertEqual(D.fields, {'save': {'default': 'A'},
-            'load': {'default': 'A'}})
+        self.assertEqual(D.fields, {'save': {'default': 'A'}, 'load': {'default': 'A'}})
 
         # D class inverted
         class E(C, B):
@@ -232,8 +231,7 @@ class ItemTest(unittest.TestCase):
 
         self.assertRaises(KeyError, E, not_allowed='value')
         self.assertEqual(E(save='X')['save'], 'X')
-        self.assertEqual(E.fields, {'save': {'default': 'A'},
-            'load': {'default': 'A'}})
+        self.assertEqual(E.fields, {'save': {'default': 'A'}, 'load': {'default': 'A'}})
 
     def test_to_dict(self):
         class TestItem(Item):
@@ -264,12 +262,12 @@ class ItemTest(unittest.TestCase):
         """Make sure the DictItem deprecation warning is not issued for
         Item"""
         with catch_warnings(record=True) as warnings:
-            item = Item()
+            Item()
             self.assertEqual(len(warnings), 0)
 
             class SubclassedItem(Item):
                 pass
-            subclassed_item = SubclassedItem()
+            SubclassedItem()
             self.assertEqual(len(warnings), 0)
 
 
@@ -321,16 +319,88 @@ class DictItemTest(unittest.TestCase):
 
     def test_deprecation_warning(self):
         with catch_warnings(record=True) as warnings:
-            dict_item = DictItem()
+            DictItem()
             self.assertEqual(len(warnings), 1)
             self.assertEqual(warnings[0].category, ScrapyDeprecationWarning)
         with catch_warnings(record=True) as warnings:
             class SubclassedDictItem(DictItem):
                 pass
-            subclassed_dict_item = SubclassedDictItem()
+            SubclassedDictItem()
             self.assertEqual(len(warnings), 1)
             self.assertEqual(warnings[0].category, ScrapyDeprecationWarning)
 
 
+class BaseItemTest(unittest.TestCase):
+
+    def test_isinstance_check(self):
+
+        class SubclassedBaseItem(BaseItem):
+            pass
+
+        class SubclassedItem(Item):
+            pass
+
+        self.assertTrue(isinstance(BaseItem(), BaseItem))
+        self.assertTrue(isinstance(SubclassedBaseItem(), BaseItem))
+        self.assertTrue(isinstance(Item(), BaseItem))
+        self.assertTrue(isinstance(SubclassedItem(), BaseItem))
+
+        # make sure internal checks using private _BaseItem class succeed
+        self.assertTrue(isinstance(BaseItem(), _BaseItem))
+        self.assertTrue(isinstance(SubclassedBaseItem(), _BaseItem))
+        self.assertTrue(isinstance(Item(), _BaseItem))
+        self.assertTrue(isinstance(SubclassedItem(), _BaseItem))
+
+    def test_deprecation_warning(self):
+        """
+        Make sure deprecation warnings are logged whenever BaseItem is used,
+        either instantiated or in an isinstance check
+        """
+        with catch_warnings(record=True) as warnings:
+            BaseItem()
+            self.assertEqual(len(warnings), 1)
+            self.assertEqual(warnings[0].category, ScrapyDeprecationWarning)
+
+        with catch_warnings(record=True) as warnings:
+
+            class SubclassedBaseItem(BaseItem):
+                pass
+
+            SubclassedBaseItem()
+            self.assertEqual(len(warnings), 1)
+            self.assertEqual(warnings[0].category, ScrapyDeprecationWarning)
+
+        with catch_warnings(record=True) as warnings:
+            self.assertFalse(isinstance("foo", BaseItem))
+            self.assertEqual(len(warnings), 1)
+            self.assertEqual(warnings[0].category, ScrapyDeprecationWarning)
+
+        with catch_warnings(record=True) as warnings:
+            self.assertTrue(isinstance(BaseItem(), BaseItem))
+            self.assertEqual(len(warnings), 1)
+            self.assertEqual(warnings[0].category, ScrapyDeprecationWarning)
+
+
+class ItemNoDeprecationWarningTest(unittest.TestCase):
+    def test_no_deprecation_warning(self):
+        """
+        Make sure deprecation warnings are NOT logged whenever BaseItem subclasses are used.
+        """
+        class SubclassedItem(Item):
+            pass
+
+        with catch_warnings(record=True) as warnings:
+            Item()
+            SubclassedItem()
+            _BaseItem()
+            self.assertFalse(isinstance("foo", _BaseItem))
+            self.assertFalse(isinstance("foo", Item))
+            self.assertFalse(isinstance("foo", SubclassedItem))
+            self.assertTrue(isinstance(_BaseItem(), _BaseItem))
+            self.assertTrue(isinstance(Item(), Item))
+            self.assertTrue(isinstance(SubclassedItem(), SubclassedItem))
+            self.assertEqual(len(warnings), 0)
+
+
 if __name__ == "__main__":
     unittest.main()

tests/test_linkextractors.py

@@ -1,3 +1,4 @@
+import pickle
 import re
 import unittest
 from warnings import catch_warnings
@@ -171,9 +172,9 @@ class Base:
             self.assertEqual(lx.matches(url1), False)
             self.assertEqual(lx.matches(url2), True)
 
-            lx = self.extractor_cls(allow=('blah1',), deny=('blah2',),
-                                   allow_domains=('blah1.com',),
-                                   deny_domains=('blah2.com',))
+            lx = self.extractor_cls(allow=['blah1'], deny=['blah2'],
+                                    allow_domains=['blah1.com'],
+                                    deny_domains=['blah2.com'])
             self.assertEqual(lx.matches('http://blah1.com/blah1'), True)
             self.assertEqual(lx.matches('http://blah1.com/blah2'), False)
             self.assertEqual(lx.matches('http://blah2.com/blah1'), False)
@@ -279,8 +280,8 @@ class Base:
         def test_process_value(self):
             """Test restrict_xpaths with encodings"""
             html = b"""
-            <a href="javascript:goToPage('../other/page.html','photo','width=600,height=540,scrollbars'); return false">Link text</a>
-            <a href="/about.html">About us</a>
+<a href="javascript:goToPage('../other/page.html','photo','width=600,height=540,scrollbars'); return false">Text</a>
+<a href="/about.html">About us</a>
             """
             response = HtmlResponse("http://example.org/somepage/index.html", body=html, encoding='windows-1252')
 
@@ -291,7 +292,7 @@ class Base:
 
             lx = self.extractor_cls(process_value=process_value)
             self.assertEqual(lx.extract_links(response),
-                             [Link(url='http://example.org/other/page.html', text='Link text')])
+                             [Link(url='http://example.org/other/page.html', text='Text')])
 
         def test_base_url_with_restrict_xpaths(self):
             html = b"""<html><head><title>Page title<title><base href="http://otherdomain.com/base/" />
@@ -332,7 +333,10 @@ class Base:
             self.assertEqual(lx.extract_links(self.response), [])
 
         def test_tags(self):
-            html = b"""<html><area href="sample1.html"></area><a href="sample2.html">sample 2</a><img src="sample2.jpg"/></html>"""
+            html = (
+                b'<html><area href="sample1.html"></area>'
+                b'<a href="sample2.html">sample 2</a><img src="sample2.jpg"/></html>'
+            )
             response = HtmlResponse("http://example.com/index.html", body=html)
 
             lx = self.extractor_cls(tags=None)
@@ -418,8 +422,10 @@ class Base:
                 [
                     Link(url='http://example.com/about.html', text=u'About us', fragment='', nofollow=False),
                     Link(url='http://example.com/follow.html', text=u'Follow this link', fragment='', nofollow=False),
-                    Link(url='http://example.com/nofollow.html', text=u'Dont follow this one', fragment='', nofollow=True),
-                    Link(url='http://example.com/nofollow2.html', text=u'Choose to follow or not', fragment='', nofollow=False),
+                    Link(url='http://example.com/nofollow.html', text=u'Dont follow this one',
+                         fragment='', nofollow=True),
+                    Link(url='http://example.com/nofollow2.html', text=u'Choose to follow or not',
+                         fragment='', nofollow=False),
                     Link(url='http://google.com/something', text=u'External link not to follow', nofollow=True),
                 ]
             )
@@ -432,8 +438,10 @@ class Base:
                 [
                     Link(url='http://example.com/about.html', text=u'About us', fragment='', nofollow=False),
                     Link(url='http://example.com/follow.html', text=u'Follow this link', fragment='', nofollow=False),
-                    Link(url='http://example.com/nofollow.html', text=u'Dont follow this one', fragment='', nofollow=True),
-                    Link(url='http://example.com/nofollow2.html', text=u'Choose to follow or not', fragment='', nofollow=False),
+                    Link(url='http://example.com/nofollow.html', text=u'Dont follow this one',
+                         fragment='', nofollow=True),
+                    Link(url='http://example.com/nofollow2.html', text=u'Choose to follow or not',
+                         fragment='', nofollow=False),
                     Link(url='http://google.com/something', text=u'External link not to follow', nofollow=True),
                 ]
             )
@@ -462,6 +470,10 @@ class Base:
                 Link(url='ftp://www.external.com/', text=u'An Item', fragment='', nofollow=False),
             ])
 
+        def test_pickle_extractor(self):
+            lx = self.extractor_cls()
+            self.assertIsInstance(pickle.loads(pickle.dumps(lx)), self.extractor_cls)
+
 
 class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase):
     extractor_cls = LxmlLinkExtractor

tests/test_loader.py

@@ -601,7 +601,7 @@ class NoInputReprocessingItemLoader(BaseNoInputReprocessingLoader):
 
 class NoInputReprocessingFromItemTest(unittest.TestCase):
     """
-    Loaders initialized from loaded items must not reprocess fields (BaseItem instances)
+    Loaders initialized from loaded items must not reprocess fields (Item instances)
     """
     def test_avoid_reprocessing_with_initial_values_single(self):
         il = NoInputReprocessingItemLoader(item=NoInputReprocessingItem(title='foo'))

tests/test_logformatter.py

@@ -34,15 +34,15 @@ class LogFormatterTestCase(unittest.TestCase):
         res = Response("http://www.example.com")
         logkws = self.formatter.crawled(req, res, self.spider)
         logline = logkws['msg'] % logkws['args']
-        self.assertEqual(logline,
-            "Crawled (200) <GET http://www.example.com> (referer: None)")
+        self.assertEqual(logline, "Crawled (200) <GET http://www.example.com> (referer: None)")
 
     def test_crawled_without_referer(self):
         req = Request("http://www.example.com", headers={'referer': 'http://example.com'})
         res = Response("http://www.example.com", flags=['cached'])
         logkws = self.formatter.crawled(req, res, self.spider)
         logline = logkws['msg'] % logkws['args']
-        self.assertEqual(logline,
+        self.assertEqual(
+            logline,
             "Crawled (200) <GET http://www.example.com> (referer: http://example.com) ['cached']")
 
     def test_flags_in_request(self):
@@ -50,8 +50,9 @@ class LogFormatterTestCase(unittest.TestCase):
         res = Response("http://www.example.com")
         logkws = self.formatter.crawled(req, res, self.spider)
         logline = logkws['msg'] % logkws['args']
-        self.assertEqual(logline,
-        "Crawled (200) <GET http://www.example.com> ['test', 'flag'] (referer: None)")
+        self.assertEqual(
+            logline,
+            "Crawled (200) <GET http://www.example.com> ['test', 'flag'] (referer: None)")
 
     def test_dropped(self):
         item = {}
@@ -140,7 +141,8 @@ class LogformatterSubclassTest(LogFormatterTestCase):
         res = Response("http://www.example.com")
         logkws = self.formatter.crawled(req, res, self.spider)
         logline = logkws['msg'] % logkws['args']
-        self.assertEqual(logline,
+        self.assertEqual(
+            logline,
             "Crawled (200) <GET http://www.example.com> (referer: None) []")
 
     def test_crawled_without_referer(self):
@@ -148,7 +150,8 @@ class LogformatterSubclassTest(LogFormatterTestCase):
         res = Response("http://www.example.com")
         logkws = self.formatter.crawled(req, res, self.spider)
         logline = logkws['msg'] % logkws['args']
-        self.assertEqual(logline,
+        self.assertEqual(
+            logline,
             "Crawled (200) <GET http://www.example.com> (referer: http://example.com) ['cached']")
 
     def test_flags_in_request(self):
@@ -156,7 +159,9 @@ class LogformatterSubclassTest(LogFormatterTestCase):
         res = Response("http://www.example.com")
         logkws = self.formatter.crawled(req, res, self.spider)
         logline = logkws['msg'] % logkws['args']
-        self.assertEqual(logline, "Crawled (200) <GET http://www.example.com> (referer: None) ['test', 'flag']")
+        self.assertEqual(
+            logline,
+            "Crawled (200) <GET http://www.example.com> (referer: None) ['test', 'flag']")
 
 
 class SkipMessagesLogFormatter(LogFormatter):

tests/test_mail.py

@@ -49,7 +49,7 @@ class MailSenderTest(unittest.TestCase):
 
         mailsender = MailSender(debug=True)
         mailsender.send(to=['test@scrapy.org'], subject='subject', body='body',
-                       attachs=attachs, _callback=self._catch_mail_sent)
+                        attachs=attachs, _callback=self._catch_mail_sent)
 
         assert self.catched_msg
         self.assertEqual(self.catched_msg['to'], ['test@scrapy.org'])

tests/test_middleware.py

@@ -69,11 +69,14 @@ class MiddlewareManagerTest(unittest.TestCase):
 
     def test_methods(self):
         mwman = TestMiddlewareManager(M1(), M2(), M3())
-        self.assertEqual([x.__self__.__class__ for x in mwman.methods['open_spider']],
+        self.assertEqual(
+            [x.__self__.__class__ for x in mwman.methods['open_spider']],
             [M1, M2])
-        self.assertEqual([x.__self__.__class__ for x in mwman.methods['close_spider']],
+        self.assertEqual(
+            [x.__self__.__class__ for x in mwman.methods['close_spider']],
             [M2, M1])
-        self.assertEqual([x.__self__.__class__ for x in mwman.methods['process']],
+        self.assertEqual(
+            [x.__self__.__class__ for x in mwman.methods['process']],
             [M1, M3])
 
     def test_enabled(self):

tests/test_pipeline_crawl.py

@@ -51,10 +51,10 @@ class FileDownloadCrawlTestCase(TestCase):
     store_setting_key = 'FILES_STORE'
     media_key = 'files'
     media_urls_key = 'file_urls'
-    expected_checksums = set([
+    expected_checksums = {
         '5547178b89448faf0015a13f904c936e',
         'c2281c83670e31d8aaab7cb642b824db',
-        'ed3f6538dc15d4d9179dae57319edc5f'])
+        'ed3f6538dc15d4d9179dae57319edc5f'}
 
     def setUp(self):
         self.mockserver = MockServer()
@@ -91,6 +91,11 @@ class FileDownloadCrawlTestCase(TestCase):
         file_dl_success = 'File (downloaded): Downloaded file from'
         self.assertEqual(logs.count(file_dl_success), 3)
 
+        # check that the images/files status is `downloaded`
+        for item in items:
+            for i in item[self.media_key]:
+                self.assertEqual(i['status'], 'downloaded')
+
         # check that the images/files checksums are what we know they should be
         if self.expected_checksums is not None:
             checksums = set(
@@ -131,7 +136,8 @@ class FileDownloadCrawlTestCase(TestCase):
     def test_download_media(self):
         crawler = self._create_crawler(MediaDownloadSpider)
         with LogCapture() as log:
-            yield crawler.crawl(self.mockserver.url("/files/images/"),
+            yield crawler.crawl(
+                self.mockserver.url("/files/images/"),
                 media_key=self.media_key,
                 media_urls_key=self.media_urls_key)
         self._assert_files_downloaded(self.items, str(log))
@@ -140,7 +146,8 @@ class FileDownloadCrawlTestCase(TestCase):
     def test_download_media_wrong_urls(self):
         crawler = self._create_crawler(BrokenLinksMediaDownloadSpider)
         with LogCapture() as log:
-            yield crawler.crawl(self.mockserver.url("/files/images/"),
+            yield crawler.crawl(
+                self.mockserver.url("/files/images/"),
                 media_key=self.media_key,
                 media_urls_key=self.media_urls_key)
         self._assert_files_download_failure(crawler, self.items, 404, str(log))
@@ -149,7 +156,8 @@ class FileDownloadCrawlTestCase(TestCase):
     def test_download_media_redirected_default_failure(self):
         crawler = self._create_crawler(RedirectedMediaDownloadSpider)
         with LogCapture() as log:
-            yield crawler.crawl(self.mockserver.url("/files/images/"),
+            yield crawler.crawl(
+                self.mockserver.url("/files/images/"),
                 media_key=self.media_key,
                 media_urls_key=self.media_urls_key,
                 mockserver=self.mockserver)
@@ -163,7 +171,8 @@ class FileDownloadCrawlTestCase(TestCase):
 
         crawler = self._create_crawler(RedirectedMediaDownloadSpider)
         with LogCapture() as log:
-            yield crawler.crawl(self.mockserver.url("/files/images/"),
+            yield crawler.crawl(
+                self.mockserver.url("/files/images/"),
                 media_key=self.media_key,
                 media_urls_key=self.media_urls_key,
                 mockserver=self.mockserver)

tests/test_pipeline_files.py

@@ -38,27 +38,36 @@ class FilesPipelineTestCase(unittest.TestCase):
 
     def test_file_path(self):
         file_path = self.pipeline.file_path
-        self.assertEqual(file_path(Request("https://dev.mydeco.com/mydeco.pdf")),
-                         'full/c9b564df929f4bc635bdd19fde4f3d4847c757c5.pdf')
-        self.assertEqual(file_path(Request("http://www.maddiebrown.co.uk///catalogue-items//image_54642_12175_95307.txt")),
-                         'full/4ce274dd83db0368bafd7e406f382ae088e39219.txt')
-        self.assertEqual(file_path(Request("https://dev.mydeco.com/two/dirs/with%20spaces%2Bsigns.doc")),
-                         'full/94ccc495a17b9ac5d40e3eabf3afcb8c2c9b9e1a.doc')
-        self.assertEqual(file_path(Request("http://www.dfsonline.co.uk/get_prod_image.php?img=status_0907_mdm.jpg")),
-                         'full/4507be485f38b0da8a0be9eb2e1dfab8a19223f2.jpg')
-        self.assertEqual(file_path(Request("http://www.dorma.co.uk/images/product_details/2532/")),
-                         'full/97ee6f8a46cbbb418ea91502fd24176865cf39b2')
-        self.assertEqual(file_path(Request("http://www.dorma.co.uk/images/product_details/2532")),
-                         'full/244e0dd7d96a3b7b01f54eded250c9e272577aa1')
-        self.assertEqual(file_path(Request("http://www.dorma.co.uk/images/product_details/2532"),
-                                   response=Response("http://www.dorma.co.uk/images/product_details/2532"),
-                                   info=object()),
-                         'full/244e0dd7d96a3b7b01f54eded250c9e272577aa1')
-        self.assertEqual(file_path(Request("http://www.dfsonline.co.uk/get_prod_image.php?img=status_0907_mdm.jpg.bohaha")),
-                         'full/76c00cef2ef669ae65052661f68d451162829507')
-        self.assertEqual(file_path(Request("data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAR0AAACxCAMAAADOHZloAAACClBMVEX/\
+        self.assertEqual(
+            file_path(Request("https://dev.mydeco.com/mydeco.pdf")),
+            'full/c9b564df929f4bc635bdd19fde4f3d4847c757c5.pdf')
+        self.assertEqual(
+            file_path(Request("http://www.maddiebrown.co.uk///catalogue-items//image_54642_12175_95307.txt")),
+            'full/4ce274dd83db0368bafd7e406f382ae088e39219.txt')
+        self.assertEqual(
+            file_path(Request("https://dev.mydeco.com/two/dirs/with%20spaces%2Bsigns.doc")),
+            'full/94ccc495a17b9ac5d40e3eabf3afcb8c2c9b9e1a.doc')
+        self.assertEqual(
+            file_path(Request("http://www.dfsonline.co.uk/get_prod_image.php?img=status_0907_mdm.jpg")),
+            'full/4507be485f38b0da8a0be9eb2e1dfab8a19223f2.jpg')
+        self.assertEqual(
+            file_path(Request("http://www.dorma.co.uk/images/product_details/2532/")),
+            'full/97ee6f8a46cbbb418ea91502fd24176865cf39b2')
+        self.assertEqual(
+            file_path(Request("http://www.dorma.co.uk/images/product_details/2532")),
+            'full/244e0dd7d96a3b7b01f54eded250c9e272577aa1')
+        self.assertEqual(
+            file_path(Request("http://www.dorma.co.uk/images/product_details/2532"),
+                      response=Response("http://www.dorma.co.uk/images/product_details/2532"),
+                      info=object()),
+            'full/244e0dd7d96a3b7b01f54eded250c9e272577aa1')
+        self.assertEqual(
+            file_path(Request("http://www.dfsonline.co.uk/get_prod_image.php?img=status_0907_mdm.jpg.bohaha")),
+            'full/76c00cef2ef669ae65052661f68d451162829507')
+        self.assertEqual(
+            file_path(Request("data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAR0AAACxCAMAAADOHZloAAACClBMVEX/\
                                     //+F0tzCwMK76ZKQ21AMqr7oAAC96JvD5aWM2kvZ78J0N7fmAAC46Y4Ap7y")),
-                         'full/178059cbeba2e34120a67f2dc1afc3ecc09b61cb.png')
+            'full/178059cbeba2e34120a67f2dc1afc3ecc09b61cb.png')
 
     def test_fs_store(self):
         assert isinstance(self.pipeline.store, FSFilesStore)
@@ -84,6 +93,7 @@ class FilesPipelineTestCase(unittest.TestCase):
 
         result = yield self.pipeline.process_item(item, None)
         self.assertEqual(result['files'][0]['checksum'], 'abc')
+        self.assertEqual(result['files'][0]['status'], 'uptodate')
 
         for p in patchers:
             p.stop()
@@ -105,6 +115,29 @@ class FilesPipelineTestCase(unittest.TestCase):
 
         result = yield self.pipeline.process_item(item, None)
         self.assertNotEqual(result['files'][0]['checksum'], 'abc')
+        self.assertEqual(result['files'][0]['status'], 'downloaded')
+
+        for p in patchers:
+            p.stop()
+
+    @defer.inlineCallbacks
+    def test_file_cached(self):
+        item_url = "http://example.com/file3.pdf"
+        item = _create_item_with_files(item_url)
+        patchers = [
+            mock.patch.object(FilesPipeline, 'inc_stats', return_value=True),
+            mock.patch.object(FSFilesStore, 'stat_file', return_value={
+                'checksum': 'abc',
+                'last_modified': time.time() - (self.pipeline.expires * 60 * 60 * 24 * 2)}),
+            mock.patch.object(FilesPipeline, 'get_media_requests',
+                              return_value=[_prepare_request_object(item_url, flags=['cached'])])
+        ]
+        for p in patchers:
+            p.start()
+
+        result = yield self.pipeline.process_item(item, None)
+        self.assertNotEqual(result['files'][0]['checksum'], 'abc')
+        self.assertEqual(result['files'][0]['status'], 'cached')
 
         for p in patchers:
             p.stop()
@@ -403,10 +436,10 @@ def _create_item_with_files(*files):
     return item
 
 
-def _prepare_request_object(item_url):
+def _prepare_request_object(item_url, flags=None):
     return Request(
         item_url,
-        meta={'response': Response(item_url, status=200, body=b'data')})
+        meta={'response': Response(item_url, status=200, body=b'data', flags=flags)})
 
 
 if __name__ == "__main__":

tests/test_pipeline_images.py

@@ -15,10 +15,10 @@ from scrapy.utils.python import to_bytes
 skip = False
 try:
     from PIL import Image
-except ImportError as e:
+except ImportError:
     skip = 'Missing Python Imaging Library, install https://pypi.python.org/pypi/Pillow'
 else:
-    encoders = set(('jpeg_encoder', 'jpeg_decoder'))
+    encoders = {'jpeg_encoder', 'jpeg_decoder'}
     if not encoders.issubset(set(Image.core.__dict__)):
         skip = 'Missing JPEG encoders'
 
@@ -41,22 +41,29 @@ class ImagesPipelineTestCase(unittest.TestCase):
 
     def test_file_path(self):
         file_path = self.pipeline.file_path
-        self.assertEqual(file_path(Request("https://dev.mydeco.com/mydeco.gif")),
-                         'full/3fd165099d8e71b8a48b2683946e64dbfad8b52d.jpg')
-        self.assertEqual(file_path(Request("http://www.maddiebrown.co.uk///catalogue-items//image_54642_12175_95307.jpg")),
-                         'full/0ffcd85d563bca45e2f90becd0ca737bc58a00b2.jpg')
-        self.assertEqual(file_path(Request("https://dev.mydeco.com/two/dirs/with%20spaces%2Bsigns.gif")),
-                         'full/b250e3a74fff2e4703e310048a5b13eba79379d2.jpg')
-        self.assertEqual(file_path(Request("http://www.dfsonline.co.uk/get_prod_image.php?img=status_0907_mdm.jpg")),
-                         'full/4507be485f38b0da8a0be9eb2e1dfab8a19223f2.jpg')
-        self.assertEqual(file_path(Request("http://www.dorma.co.uk/images/product_details/2532/")),
-                         'full/97ee6f8a46cbbb418ea91502fd24176865cf39b2.jpg')
-        self.assertEqual(file_path(Request("http://www.dorma.co.uk/images/product_details/2532")),
-                         'full/244e0dd7d96a3b7b01f54eded250c9e272577aa1.jpg')
-        self.assertEqual(file_path(Request("http://www.dorma.co.uk/images/product_details/2532"),
-                                   response=Response("http://www.dorma.co.uk/images/product_details/2532"),
-                                   info=object()),
-                         'full/244e0dd7d96a3b7b01f54eded250c9e272577aa1.jpg')
+        self.assertEqual(
+            file_path(Request("https://dev.mydeco.com/mydeco.gif")),
+            'full/3fd165099d8e71b8a48b2683946e64dbfad8b52d.jpg')
+        self.assertEqual(
+            file_path(Request("http://www.maddiebrown.co.uk///catalogue-items//image_54642_12175_95307.jpg")),
+            'full/0ffcd85d563bca45e2f90becd0ca737bc58a00b2.jpg')
+        self.assertEqual(
+            file_path(Request("https://dev.mydeco.com/two/dirs/with%20spaces%2Bsigns.gif")),
+            'full/b250e3a74fff2e4703e310048a5b13eba79379d2.jpg')
+        self.assertEqual(
+            file_path(Request("http://www.dfsonline.co.uk/get_prod_image.php?img=status_0907_mdm.jpg")),
+            'full/4507be485f38b0da8a0be9eb2e1dfab8a19223f2.jpg')
+        self.assertEqual(
+            file_path(Request("http://www.dorma.co.uk/images/product_details/2532/")),
+            'full/97ee6f8a46cbbb418ea91502fd24176865cf39b2.jpg')
+        self.assertEqual(
+            file_path(Request("http://www.dorma.co.uk/images/product_details/2532")),
+            'full/244e0dd7d96a3b7b01f54eded250c9e272577aa1.jpg')
+        self.assertEqual(
+            file_path(Request("http://www.dorma.co.uk/images/product_details/2532"),
+                      response=Response("http://www.dorma.co.uk/images/product_details/2532"),
+                      info=object()),
+            'full/244e0dd7d96a3b7b01f54eded250c9e272577aa1.jpg')
 
     def test_thumbnail_name(self):
         thumb_path = self.pipeline.thumb_path

tests/test_pipeline_media.py

@@ -63,21 +63,21 @@ class BaseMediaPipelineTestCase(unittest.TestCase):
         fail = Failure(Exception())
         results = [(True, 1), (False, fail)]
 
-        with LogCapture() as l:
+        with LogCapture() as log:
             new_item = self.pipe.item_completed(results, item, self.info)
 
         assert new_item is item
-        assert len(l.records) == 1
-        record = l.records[0]
+        assert len(log.records) == 1
+        record = log.records[0]
         assert record.levelname == 'ERROR'
         self.assertTupleEqual(record.exc_info, failure_to_exc_info(fail))
 
         # disable failure logging and check again
         self.pipe.LOG_FAILED_RESULTS = False
-        with LogCapture() as l:
+        with LogCapture() as log:
             new_item = self.pipe.item_completed(results, item, self.info)
         assert new_item is item
-        assert len(l.records) == 0
+        assert len(log.records) == 0
 
     @inlineCallbacks
     def test_default_process_item(self):
@@ -214,9 +214,9 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase):
         item = dict(requests=req)
         new_item = yield self.pipe.process_item(item, self.spider)
         self.assertEqual(new_item['results'], [(True, rsp)])
-        self.assertEqual(self.pipe._mockcalled,
-                ['get_media_requests', 'media_to_download',
-                    'media_downloaded', 'request_callback', 'item_completed'])
+        self.assertEqual(
+            self.pipe._mockcalled,
+            ['get_media_requests', 'media_to_download', 'media_downloaded', 'request_callback', 'item_completed'])
 
     @inlineCallbacks
     def test_result_failure(self):
@@ -227,9 +227,9 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase):
         item = dict(requests=req)
         new_item = yield self.pipe.process_item(item, self.spider)
         self.assertEqual(new_item['results'], [(False, fail)])
-        self.assertEqual(self.pipe._mockcalled,
-                ['get_media_requests', 'media_to_download',
-                    'media_failed', 'request_errback', 'item_completed'])
+        self.assertEqual(
+            self.pipe._mockcalled,
+            ['get_media_requests', 'media_to_download', 'media_failed', 'request_errback', 'item_completed'])
 
     @inlineCallbacks
     def test_mix_of_success_and_failure(self):

tests/test_proxy_connect.py

@@ -4,6 +4,7 @@ import re
 import sys
 from subprocess import Popen, PIPE
 from urllib.parse import urlsplit, urlunsplit
+from unittest import skipIf
 
 import pytest
 from testfixtures import LogCapture
@@ -56,6 +57,8 @@ def _wrong_credentials(proxy_url):
     return urlunsplit(bad_auth_proxy)
 
 
+@skipIf(sys.version_info < (3, 5, 4),
+        "requires mitmproxy < 3.0.0, which these tests do not support")
 class ProxyConnectTestCase(TestCase):
 
     def setUp(self):
@@ -76,35 +79,35 @@ class ProxyConnectTestCase(TestCase):
     @defer.inlineCallbacks
     def test_https_connect_tunnel(self):
         crawler = get_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl(self.mockserver.url("/status?n=200", is_secure=True))
-        self._assert_got_response_code(200, l)
+        self._assert_got_response_code(200, log)
 
-    @pytest.mark.xfail(reason='Python 3.6+ fails this earlier', condition=sys.version_info.minor >= 6)
+    @pytest.mark.xfail(reason='Python 3.6+ fails this earlier', condition=sys.version_info >= (3, 6))
     @defer.inlineCallbacks
     def test_https_connect_tunnel_error(self):
         crawler = get_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl("https://localhost:99999/status?n=200")
-        self._assert_got_tunnel_error(l)
+        self._assert_got_tunnel_error(log)
 
     @defer.inlineCallbacks
     def test_https_tunnel_auth_error(self):
         os.environ['https_proxy'] = _wrong_credentials(os.environ['https_proxy'])
         crawler = get_crawler(SimpleSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl(self.mockserver.url("/status?n=200", is_secure=True))
         # The proxy returns a 407 error code but it does not reach the client;
         # he just sees a TunnelError.
-        self._assert_got_tunnel_error(l)
+        self._assert_got_tunnel_error(log)
 
     @defer.inlineCallbacks
     def test_https_tunnel_without_leak_proxy_authorization_header(self):
         request = Request(self.mockserver.url("/echo", is_secure=True))
         crawler = get_crawler(SingleRequestSpider)
-        with LogCapture() as l:
+        with LogCapture() as log:
             yield crawler.crawl(seed=request)
-        self._assert_got_response_code(200, l)
+        self._assert_got_response_code(200, log)
         echo = json.loads(crawler.spider.meta['responses'][0].text)
         self.assertTrue('Proxy-Authorization' not in echo['headers'])
 

tests/test_request_cb_kwargs.py

@@ -158,6 +158,12 @@ class CallbackKeywordArgumentsTestCase(TestCase):
                 if key in line.getMessage():
                     exceptions[key] = line
         self.assertEqual(exceptions['takes_less'].exc_info[0], TypeError)
-        self.assertEqual(str(exceptions['takes_less'].exc_info[1]), "parse_takes_less() got an unexpected keyword argument 'number'")
+        self.assertEqual(
+            str(exceptions['takes_less'].exc_info[1]),
+            "parse_takes_less() got an unexpected keyword argument 'number'"
+        )
         self.assertEqual(exceptions['takes_more'].exc_info[0], TypeError)
-        self.assertEqual(str(exceptions['takes_more'].exc_info[1]), "parse_takes_more() missing 1 required positional argument: 'other'")
+        self.assertEqual(
+            str(exceptions['takes_more'].exc_info[1]),
+            "parse_takes_more() missing 1 required positional argument: 'other'"
+        )

tests/test_responsetypes.py

@@ -63,8 +63,9 @@ class ResponseTypesTest(unittest.TestCase):
     def test_from_headers(self):
         mappings = [
             ({'Content-Type': ['text/html; charset=utf-8']}, HtmlResponse),
-            ({'Content-Type': ['application/octet-stream'], 'Content-Disposition': ['attachment; filename=data.txt']}, TextResponse),
             ({'Content-Type': ['text/html; charset=utf-8'], 'Content-Encoding': ['gzip']}, Response),
+            ({'Content-Type': ['application/octet-stream'],
+              'Content-Disposition': ['attachment; filename=data.txt']}, TextResponse),
         ]
         for source, cls in mappings:
             source = Headers(source)
@@ -76,8 +77,10 @@ class ResponseTypesTest(unittest.TestCase):
         mappings = [
             ({'url': 'http://www.example.com/data.csv'}, TextResponse),
             # headers takes precedence over url
-            ({'headers': Headers({'Content-Type': ['text/html; charset=utf-8']}), 'url': 'http://www.example.com/item/'}, HtmlResponse),
-            ({'headers': Headers({'Content-Disposition': ['attachment; filename="data.xml.gz"']}), 'url': 'http://www.example.com/page/'}, Response),
+            ({'headers': Headers({'Content-Type': ['text/html; charset=utf-8']}),
+              'url': 'http://www.example.com/item/'}, HtmlResponse),
+            ({'headers': Headers({'Content-Disposition': ['attachment; filename="data.xml.gz"']}),
+              'url': 'http://www.example.com/page/'}, Response),
 
 
         ]

tests/test_selector.py

@@ -19,18 +19,26 @@ class SelectorTestCase(unittest.TestCase):
         for x in xl:
             assert isinstance(x, Selector)
 
-        self.assertEqual(sel.xpath('//input').getall(),
-                         [x.get() for x in sel.xpath('//input')])
-
-        self.assertEqual([x.get() for x in sel.xpath("//input[@name='a']/@name")],
-                         [u'a'])
-        self.assertEqual([x.get() for x in sel.xpath("number(concat(//input[@name='a']/@value, //input[@name='b']/@value))")],
-                         [u'12.0'])
-
-        self.assertEqual(sel.xpath("concat('xpath', 'rules')").getall(),
-                         [u'xpathrules'])
-        self.assertEqual([x.get() for x in sel.xpath("concat(//input[@name='a']/@value, //input[@name='b']/@value)")],
-                         [u'12'])
+        self.assertEqual(
+            sel.xpath('//input').getall(),
+            [x.get() for x in sel.xpath('//input')]
+        )
+        self.assertEqual(
+            [x.get() for x in sel.xpath("//input[@name='a']/@name")],
+            [u'a']
+        )
+        self.assertEqual(
+            [x.get() for x in sel.xpath("number(concat(//input[@name='a']/@value, //input[@name='b']/@value))")],
+            [u'12.0']
+        )
+        self.assertEqual(
+            sel.xpath("concat('xpath', 'rules')").getall(),
+            [u'xpathrules']
+        )
+        self.assertEqual(
+            [x.get() for x in sel.xpath("concat(//input[@name='a']/@value, //input[@name='b']/@value)")],
+            [u'12']
+        )
 
     def test_root_base_url(self):
         body = b'<html><form action="/path"><input name="a" /></form></html>'

tests/test_settings/__init__.py

@@ -314,13 +314,17 @@ class BaseSettingsTest(unittest.TestCase):
                           'TEST_BASE': BaseSettings({1: 1, 2: 2}, 'project'),
                           'TEST': BaseSettings({1: 10, 3: 30}, 'default'),
                           'HASNOBASE': BaseSettings({3: 3000}, 'default')})
-        self.assertDictEqual(s.copy_to_dict(),
-                            {'HASNOBASE': {3: 3000},
-                             'TEST': {1: 10, 3: 30},
-                             'TEST_BASE': {1: 1, 2: 2},
-                             'TEST_BOOLEAN': False,
-                             'TEST_LIST': [1, 2],
-                             'TEST_STRING': 'a string'})
+        self.assertDictEqual(
+            s.copy_to_dict(),
+            {
+                'HASNOBASE': {3: 3000},
+                'TEST': {1: 10, 3: 30},
+                'TEST_BASE': {1: 1, 2: 2},
+                'TEST_LIST': [1, 2],
+                'TEST_BOOLEAN': False,
+                'TEST_STRING': 'a string',
+            }
+        )
 
     def test_freeze(self):
         self.settings.freeze()

tests/test_spider.py

@@ -120,7 +120,9 @@ class XMLFeedSpiderTest(SpiderTest):
         body = b"""<?xml version="1.0" encoding="UTF-8"?>
         <urlset xmlns:x="http://www.google.com/schemas/sitemap/0.84"
                 xmlns:y="http://www.example.com/schemas/extras/1.0">
-        <url><x:loc>http://www.example.com/Special-Offers.html</loc><y:updated>2009-08-16</updated><other value="bar" y:custom="fuu"/></url>
+        <url><x:loc>http://www.example.com/Special-Offers.html</loc><y:updated>2009-08-16</updated>
+            <other value="bar" y:custom="fuu"/>
+        </url>
         <url><loc>http://www.example.com/</loc><y:updated>2009-08-16</updated><other value="foo"/></url>
         </urlset>"""
         response = XmlResponse(url='http://example.com/sitemap.xml', body=body)

tests/test_spiderloader/__init__.py

@@ -40,25 +40,32 @@ class SpiderLoaderTest(unittest.TestCase):
         verifyObject(ISpiderLoader, self.spider_loader)
 
     def test_list(self):
-        self.assertEqual(set(self.spider_loader.list()),
-            set(['spider1', 'spider2', 'spider3', 'spider4']))
+        self.assertEqual(
+            set(self.spider_loader.list()),
+            {'spider1', 'spider2', 'spider3', 'spider4'})
 
     def test_load(self):
         spider1 = self.spider_loader.load("spider1")
         self.assertEqual(spider1.__name__, 'Spider1')
 
     def test_find_by_request(self):
-        self.assertEqual(self.spider_loader.find_by_request(Request('http://scrapy1.org/test')),
+        self.assertEqual(
+            self.spider_loader.find_by_request(Request('http://scrapy1.org/test')),
             ['spider1'])
-        self.assertEqual(self.spider_loader.find_by_request(Request('http://scrapy2.org/test')),
+        self.assertEqual(
+            self.spider_loader.find_by_request(Request('http://scrapy2.org/test')),
             ['spider2'])
-        self.assertEqual(set(self.spider_loader.find_by_request(Request('http://scrapy3.org/test'))),
-            set(['spider1', 'spider2']))
-        self.assertEqual(self.spider_loader.find_by_request(Request('http://scrapy999.org/test')),
+        self.assertEqual(
+            set(self.spider_loader.find_by_request(Request('http://scrapy3.org/test'))),
+            {'spider1', 'spider2'})
+        self.assertEqual(
+            self.spider_loader.find_by_request(Request('http://scrapy999.org/test')),
             [])
-        self.assertEqual(self.spider_loader.find_by_request(Request('http://spider3.com')),
+        self.assertEqual(
+            self.spider_loader.find_by_request(Request('http://spider3.com')),
             [])
-        self.assertEqual(self.spider_loader.find_by_request(Request('http://spider3.com/onlythis')),
+        self.assertEqual(
+            self.spider_loader.find_by_request(Request('http://spider3.com/onlythis')),
             ['spider3'])
 
     def test_load_spider_module(self):
@@ -137,9 +144,14 @@ class DuplicateSpiderNameLoaderTest(unittest.TestCase):
             msg = str(w[0].message)
             self.assertIn("several spiders with the same name", msg)
             self.assertIn("'spider3'", msg)
+            self.assertTrue(msg.count("'spider3'") == 2)
+
+            self.assertNotIn("'spider1'", msg)
+            self.assertNotIn("'spider2'", msg)
+            self.assertNotIn("'spider4'", msg)
 
             spiders = set(spider_loader.list())
-            self.assertEqual(spiders, set(['spider1', 'spider2', 'spider3', 'spider4']))
+            self.assertEqual(spiders, {'spider1', 'spider2', 'spider3', 'spider4'})
 
     def test_multiple_dupename_warning(self):
         # copy 2 spider modules so as to have duplicate spider name
@@ -156,7 +168,13 @@ class DuplicateSpiderNameLoaderTest(unittest.TestCase):
             msg = str(w[0].message)
             self.assertIn("several spiders with the same name", msg)
             self.assertIn("'spider1'", msg)
+            self.assertTrue(msg.count("'spider1'") == 2)
+
             self.assertIn("'spider2'", msg)
+            self.assertTrue(msg.count("'spider2'") == 2)
+
+            self.assertNotIn("'spider3'", msg)
+            self.assertNotIn("'spider4'", msg)
 
             spiders = set(spider_loader.list())
-            self.assertEqual(spiders, set(['spider1', 'spider2', 'spider3', 'spider4']))
+            self.assertEqual(spiders, {'spider1', 'spider2', 'spider3', 'spider4'})

tests/test_spidermiddleware_httperror.py

@@ -21,10 +21,10 @@ class _HttpErrorSpider(MockServerSpider):
     def __init__(self, *args, **kwargs):
         super(_HttpErrorSpider, self).__init__(*args, **kwargs)
         self.start_urls = [
-           self.mockserver.url("/status?n=200"),
-           self.mockserver.url("/status?n=404"),
-           self.mockserver.url("/status?n=402"),
-           self.mockserver.url("/status?n=500"),
+            self.mockserver.url("/status?n=200"),
+            self.mockserver.url("/status?n=404"),
+            self.mockserver.url("/status?n=402"),
+            self.mockserver.url("/status?n=500"),
         ]
         self.failed = set()
         self.skipped = set()
@@ -68,29 +68,23 @@ class TestHttpErrorMiddleware(TestCase):
         self.res200, self.res404 = _responses(self.req, [200, 404])
 
     def test_process_spider_input(self):
-        self.assertEqual(None,
-                self.mw.process_spider_input(self.res200, self.spider))
-        self.assertRaises(HttpError,
-                self.mw.process_spider_input, self.res404, self.spider)
+        self.assertIsNone(self.mw.process_spider_input(self.res200, self.spider))
+        self.assertRaises(HttpError, self.mw.process_spider_input, self.res404, self.spider)
 
     def test_process_spider_exception(self):
-        self.assertEqual([],
-                self.mw.process_spider_exception(self.res404,
-                        HttpError(self.res404), self.spider))
-        self.assertEqual(None,
-                self.mw.process_spider_exception(self.res404,
-                        Exception(), self.spider))
+        self.assertEqual(
+            [],
+            self.mw.process_spider_exception(self.res404, HttpError(self.res404), self.spider))
+        self.assertIsNone(self.mw.process_spider_exception(self.res404, Exception(), self.spider))
 
     def test_handle_httpstatus_list(self):
         res = self.res404.copy()
         res.request = Request('http://scrapytest.org',
                               meta={'handle_httpstatus_list': [404]})
-        self.assertEqual(None,
-            self.mw.process_spider_input(res, self.spider))
+        self.assertIsNone(self.mw.process_spider_input(res, self.spider))
 
         self.spider.handle_httpstatus_list = [404]
-        self.assertEqual(None,
-            self.mw.process_spider_input(self.res404, self.spider))
+        self.assertIsNone(self.mw.process_spider_input(self.res404, self.spider))
 
 
 class TestHttpErrorMiddlewareSettings(TestCase):
@@ -103,12 +97,9 @@ class TestHttpErrorMiddlewareSettings(TestCase):
         self.res200, self.res404, self.res402 = _responses(self.req, [200, 404, 402])
 
     def test_process_spider_input(self):
-        self.assertEqual(None,
-                self.mw.process_spider_input(self.res200, self.spider))
-        self.assertRaises(HttpError,
-                self.mw.process_spider_input, self.res404, self.spider)
-        self.assertEqual(None,
-                self.mw.process_spider_input(self.res402, self.spider))
+        self.assertIsNone(self.mw.process_spider_input(self.res200, self.spider))
+        self.assertRaises(HttpError, self.mw.process_spider_input, self.res404, self.spider)
+        self.assertIsNone(self.mw.process_spider_input(self.res402, self.spider))
 
     def test_meta_overrides_settings(self):
         request = Request('http://scrapytest.org', meta={'handle_httpstatus_list': [404]})
@@ -117,17 +108,13 @@ class TestHttpErrorMiddlewareSettings(TestCase):
         res402 = self.res402.copy()
         res402.request = request
 
-        self.assertEqual(None,
-            self.mw.process_spider_input(res404, self.spider))
-        self.assertRaises(HttpError,
-                self.mw.process_spider_input, res402, self.spider)
+        self.assertIsNone(self.mw.process_spider_input(res404, self.spider))
+        self.assertRaises(HttpError, self.mw.process_spider_input, res402, self.spider)
 
     def test_spider_override_settings(self):
         self.spider.handle_httpstatus_list = [404]
-        self.assertEqual(None,
-            self.mw.process_spider_input(self.res404, self.spider))
-        self.assertRaises(HttpError,
-                self.mw.process_spider_input, self.res402, self.spider)
+        self.assertIsNone(self.mw.process_spider_input(self.res404, self.spider))
+        self.assertRaises(HttpError, self.mw.process_spider_input, self.res402, self.spider)
 
 
 class TestHttpErrorMiddlewareHandleAll(TestCase):
@@ -139,10 +126,8 @@ class TestHttpErrorMiddlewareHandleAll(TestCase):
         self.res200, self.res404, self.res402 = _responses(self.req, [200, 404, 402])
 
     def test_process_spider_input(self):
-        self.assertEqual(None,
-                self.mw.process_spider_input(self.res200, self.spider))
-        self.assertEqual(None,
-                self.mw.process_spider_input(self.res404, self.spider))
+        self.assertIsNone(self.mw.process_spider_input(self.res200, self.spider))
+        self.assertIsNone(self.mw.process_spider_input(self.res404, self.spider))
 
     def test_meta_overrides_settings(self):
         request = Request('http://scrapytest.org', meta={'handle_httpstatus_list': [404]})
@@ -151,10 +136,8 @@ class TestHttpErrorMiddlewareHandleAll(TestCase):
         res402 = self.res402.copy()
         res402.request = request
 
-        self.assertEqual(None,
-            self.mw.process_spider_input(res404, self.spider))
-        self.assertRaises(HttpError,
-                self.mw.process_spider_input, res402, self.spider)
+        self.assertIsNone(self.mw.process_spider_input(res404, self.spider))
+        self.assertRaises(HttpError, self.mw.process_spider_input, res402, self.spider)
 
 
 class TestHttpErrorMiddlewareIntegrational(TrialTestCase):

tests/test_spidermiddleware_offsite.py

@@ -22,20 +22,24 @@ class TestOffsiteMiddleware(TestCase):
     def test_process_spider_output(self):
         res = Response('http://scrapytest.org')
 
-        onsite_reqs = [Request('http://scrapytest.org/1'),
-                       Request('http://scrapy.org/1'),
-                       Request('http://sub.scrapy.org/1'),
-                       Request('http://offsite.tld/letmepass', dont_filter=True),
-                       Request('http://scrapy.test.org/'),
-                       Request('http://scrapy.test.org:8000/')]
-        offsite_reqs = [Request('http://scrapy2.org'),
-                       Request('http://offsite.tld/'),
-                       Request('http://offsite.tld/scrapytest.org'),
-                       Request('http://offsite.tld/rogue.scrapytest.org'),
-                       Request('http://rogue.scrapytest.org.haha.com'),
-                       Request('http://roguescrapytest.org'),
-                       Request('http://test.org/'),
-                       Request('http://notscrapy.test.org/')]
+        onsite_reqs = [
+            Request('http://scrapytest.org/1'),
+            Request('http://scrapy.org/1'),
+            Request('http://sub.scrapy.org/1'),
+            Request('http://offsite.tld/letmepass', dont_filter=True),
+            Request('http://scrapy.test.org/'),
+            Request('http://scrapy.test.org:8000/'),
+        ]
+        offsite_reqs = [
+            Request('http://scrapy2.org'),
+            Request('http://offsite.tld/'),
+            Request('http://offsite.tld/scrapytest.org'),
+            Request('http://offsite.tld/rogue.scrapytest.org'),
+            Request('http://rogue.scrapytest.org.haha.com'),
+            Request('http://roguescrapytest.org'),
+            Request('http://test.org/'),
+            Request('http://notscrapy.test.org/'),
+        ]
         reqs = onsite_reqs + offsite_reqs
 
         out = list(self.mw.process_spider_output(res, reqs, self.spider))

tests/test_spidermiddleware_output_chain.py

@@ -385,9 +385,15 @@ class TestSpiderMiddleware(TestCase):
         log4 = yield self.crawl_log(GeneratorOutputChainSpider)
         self.assertIn("'item_scraped_count': 2", str(log4))
         self.assertIn("GeneratorRecoverMiddleware.process_spider_exception: LookupError caught", str(log4))
-        self.assertIn("GeneratorDoNothingAfterFailureMiddleware.process_spider_exception: LookupError caught", str(log4))
-        self.assertNotIn("GeneratorFailMiddleware.process_spider_exception: LookupError caught", str(log4))
-        self.assertNotIn("GeneratorDoNothingAfterRecoveryMiddleware.process_spider_exception: LookupError caught", str(log4))
+        self.assertIn(
+            "GeneratorDoNothingAfterFailureMiddleware.process_spider_exception: LookupError caught",
+            str(log4))
+        self.assertNotIn(
+            "GeneratorFailMiddleware.process_spider_exception: LookupError caught",
+            str(log4))
+        self.assertNotIn(
+            "GeneratorDoNothingAfterRecoveryMiddleware.process_spider_exception: LookupError caught",
+            str(log4))
         item_from_callback = {'processed': [
             'parse-first-item',
             'GeneratorFailMiddleware.process_spider_output',
@@ -414,9 +420,13 @@ class TestSpiderMiddleware(TestCase):
         log5 = yield self.crawl_log(NotGeneratorOutputChainSpider)
         self.assertIn("'item_scraped_count': 1", str(log5))
         self.assertIn("GeneratorRecoverMiddleware.process_spider_exception: ReferenceError caught", str(log5))
-        self.assertIn("GeneratorDoNothingAfterFailureMiddleware.process_spider_exception: ReferenceError caught", str(log5))
+        self.assertIn(
+            "GeneratorDoNothingAfterFailureMiddleware.process_spider_exception: ReferenceError caught",
+            str(log5))
         self.assertNotIn("GeneratorFailMiddleware.process_spider_exception: ReferenceError caught", str(log5))
-        self.assertNotIn("GeneratorDoNothingAfterRecoveryMiddleware.process_spider_exception: ReferenceError caught", str(log5))
+        self.assertNotIn(
+            "GeneratorDoNothingAfterRecoveryMiddleware.process_spider_exception: ReferenceError caught",
+            str(log5))
         item_recovered = {'processed': [
             'NotGeneratorRecoverMiddleware.process_spider_exception',
             'NotGeneratorDoNothingAfterRecoveryMiddleware.process_spider_output']}

tests/test_spidermiddleware_referer.py

@@ -119,7 +119,11 @@ class MixinSameOrigin:
         ('https://example.com:443/page.html', 'https://example.com/not-page.html', b'https://example.com/page.html'),
         ('http://example.com:80/page.html', 'http://example.com/not-page.html', b'http://example.com/page.html'),
         ('http://example.com/page.html', 'http://example.com:80/not-page.html', b'http://example.com/page.html'),
-        ('http://example.com:8888/page.html', 'http://example.com:8888/not-page.html', b'http://example.com:8888/page.html'),
+        (
+            'http://example.com:8888/page.html',
+            'http://example.com:8888/not-page.html',
+            b'http://example.com:8888/page.html',
+        ),
 
         # Different host: do NOT send referrer
         ('https://example.com/page.html', 'https://not.example.com/otherpage.html', None),
@@ -139,8 +143,12 @@ class MixinSameOrigin:
         ('ftps://example.com/urls.zip', 'https://example.com/not-page.html', None),
 
         # test for user/password stripping
-        ('https://user:password@example.com/page.html', 'https://example.com/not-page.html', b'https://example.com/page.html'),
         ('https://user:password@example.com/page.html', 'http://example.com/not-page.html', None),
+        (
+            'https://user:password@example.com/page.html',
+            'https://example.com/not-page.html',
+            b'https://example.com/page.html',
+        ),
     ]
 
 
@@ -184,7 +192,11 @@ class MixinOriginWhenCrossOrigin:
         ('https://example.com:443/page.html', 'https://example.com/not-page.html', b'https://example.com/page.html'),
         ('http://example.com:80/page.html', 'http://example.com/not-page.html', b'http://example.com/page.html'),
         ('http://example.com/page.html', 'http://example.com:80/not-page.html', b'http://example.com/page.html'),
-        ('http://example.com:8888/page.html', 'http://example.com:8888/not-page.html', b'http://example.com:8888/page.html'),
+        (
+            'http://example.com:8888/page.html',
+            'http://example.com:8888/not-page.html',
+            b'http://example.com:8888/page.html',
+        ),
 
         # Different host: send origin as referrer
         ('https://example2.com/page.html', 'https://scrapy.org/otherpage.html', b'https://example2.com/'),
@@ -205,9 +217,17 @@ class MixinOriginWhenCrossOrigin:
         ('ftps://example4.com/urls.zip', 'https://example4.com/not-page.html', b'ftps://example4.com/'),
 
         # test for user/password stripping
-        ('https://user:password@example5.com/page.html', 'https://example5.com/not-page.html', b'https://example5.com/page.html'),
+        (
+            'https://user:password@example5.com/page.html',
+            'https://example5.com/not-page.html',
+            b'https://example5.com/page.html',
+        ),
         # TLS to non-TLS downgrade: send origin
-        ('https://user:password@example5.com/page.html', 'http://example5.com/not-page.html', b'https://example5.com/'),
+        (
+            'https://user:password@example5.com/page.html',
+            'http://example5.com/not-page.html',
+            b'https://example5.com/',
+        ),
     ]
 
 
@@ -219,7 +239,11 @@ class MixinStrictOriginWhenCrossOrigin:
         ('https://example.com:443/page.html', 'https://example.com/not-page.html', b'https://example.com/page.html'),
         ('http://example.com:80/page.html', 'http://example.com/not-page.html', b'http://example.com/page.html'),
         ('http://example.com/page.html', 'http://example.com:80/not-page.html', b'http://example.com/page.html'),
-        ('http://example.com:8888/page.html', 'http://example.com:8888/not-page.html', b'http://example.com:8888/page.html'),
+        (
+            'http://example.com:8888/page.html',
+            'http://example.com:8888/not-page.html',
+            b'http://example.com:8888/page.html',
+        ),
 
         # Different host: send origin as referrer
         ('https://example2.com/page.html', 'https://scrapy.org/otherpage.html', b'https://example2.com/'),
@@ -248,7 +272,11 @@ class MixinStrictOriginWhenCrossOrigin:
         ('ftps://example4.com/urls.zip', 'https://example4.com/not-page.html', b'ftps://example4.com/'),
 
         # test for user/password stripping
-        ('https://user:password@example5.com/page.html', 'https://example5.com/not-page.html', b'https://example5.com/page.html'),
+        (
+            'https://user:password@example5.com/page.html',
+            'https://example5.com/not-page.html',
+            b'https://example5.com/page.html',
+        ),
 
         # TLS to non-TLS downgrade: send nothing
         ('https://user:password@example5.com/page.html', 'http://example5.com/not-page.html', None),
@@ -281,8 +309,16 @@ class MixinUnsafeUrl:
         ('ftp://example3.com/urls.zip', 'https://scrapy.org/', b'ftp://example3.com/urls.zip'),
 
         # test for user/password stripping
-        ('http://user:password@example4.com/page.html', 'https://not.example4.com/', b'http://example4.com/page.html'),
-        ('https://user:password@example4.com/page.html', 'http://scrapy.org/', b'https://example4.com/page.html'),
+        (
+            'http://user:password@example4.com/page.html',
+            'https://not.example4.com/',
+            b'http://example4.com/page.html',
+        ),
+        (
+            'https://user:password@example4.com/page.html',
+            'http://scrapy.org/',
+            b'https://example4.com/page.html',
+        ),
     ]
 
 
@@ -459,7 +495,6 @@ class TestRequestMetaSettingFallback(TestCase):
         target = 'http://www.example.com'
 
         for settings, response_headers, request_meta, policy_class, check_warning in self.params[3:]:
-            spider = Spider('foo')
             mw = RefererMiddleware(Settings(settings))
 
             response = Response(origin, headers=response_headers)
@@ -511,7 +546,7 @@ class TestSettingsPolicyByName(TestCase):
     def test_invalid_name(self):
         settings = Settings({'REFERRER_POLICY': 'some-custom-unknown-policy'})
         with self.assertRaises(RuntimeError):
-            mw = RefererMiddleware(settings)
+            RefererMiddleware(settings)
 
 
 class TestPolicyHeaderPredecence001(MixinUnsafeUrl, TestRefererMiddleware):

tests/test_squeues.py

@@ -1,4 +1,5 @@
 import pickle
+import sys
 
 from queuelib.tests import test_queue as t
 from scrapy.squeues import (
@@ -28,31 +29,13 @@ class TestLoader(ItemLoader):
 
 def nonserializable_object_test(self):
     q = self.queue()
-    try:
-        pickle.dumps(lambda x: x)
-    except Exception:
-        # Trigger Twisted bug #7989
-        import twisted.persisted.styles  # NOQA
-        self.assertRaises(ValueError, q.push, lambda x: x)
-    else:
-        # Use a different unpickleable object
-        class A:
-            pass
-
-        a = A()
-        a.__reduce__ = a.__reduce_ex__ = None
-        self.assertRaises(ValueError, q.push, a)
+    self.assertRaises(ValueError, q.push, lambda x: x)
     # Selectors should fail (lxml.html.HtmlElement objects can't be pickled)
     sel = Selector(text='<html><body><p>some text</p></body></html>')
     self.assertRaises(ValueError, q.push, sel)
 
 
-class MarshalFifoDiskQueueTest(t.FifoDiskQueueTest):
-
-    chunksize = 100000
-
-    def queue(self):
-        return MarshalFifoDiskQueue(self.qpath, chunksize=self.chunksize)
+class FifoDiskQueueTestMixin:
 
     def test_serialize(self):
         q = self.queue()
@@ -66,6 +49,13 @@ class MarshalFifoDiskQueueTest(t.FifoDiskQueueTest):
     test_nonserializable_object = nonserializable_object_test
 
 
+class MarshalFifoDiskQueueTest(t.FifoDiskQueueTest, FifoDiskQueueTestMixin):
+    chunksize = 100000
+
+    def queue(self):
+        return MarshalFifoDiskQueue(self.qpath, chunksize=self.chunksize)
+
+
 class ChunkSize1MarshalFifoDiskQueueTest(MarshalFifoDiskQueueTest):
     chunksize = 1
 
@@ -82,7 +72,7 @@ class ChunkSize4MarshalFifoDiskQueueTest(MarshalFifoDiskQueueTest):
     chunksize = 4
 
 
-class PickleFifoDiskQueueTest(MarshalFifoDiskQueueTest):
+class PickleFifoDiskQueueTest(t.FifoDiskQueueTest, FifoDiskQueueTestMixin):
 
     chunksize = 100000
 
@@ -99,12 +89,12 @@ class PickleFifoDiskQueueTest(MarshalFifoDiskQueueTest):
 
     def test_serialize_loader(self):
         q = self.queue()
-        l = TestLoader()
-        q.push(l)
-        l2 = q.pop()
-        assert isinstance(l2, TestLoader)
-        assert l2.default_item_class is TestItem
-        self.assertEqual(l2.name_out('x'), 'xx')
+        loader = TestLoader()
+        q.push(loader)
+        loader2 = q.pop()
+        assert isinstance(loader2, TestLoader)
+        assert loader2.default_item_class is TestItem
+        self.assertEqual(loader2.name_out('x'), 'xx')
 
     def test_serialize_request_recursive(self):
         q = self.queue()
@@ -116,6 +106,21 @@ class PickleFifoDiskQueueTest(MarshalFifoDiskQueueTest):
         self.assertEqual(r.url, r2.url)
         assert r2.meta['request'] is r2
 
+    def test_non_pickable_object(self):
+        q = self.queue()
+        try:
+            q.push(lambda x: x)
+        except ValueError as exc:
+            if hasattr(sys, "pypy_version_info"):
+                self.assertIsInstance(exc.__context__, pickle.PicklingError)
+            else:
+                self.assertIsInstance(exc.__context__, AttributeError)
+        sel = Selector(text='<html><body><p>some text</p></body></html>')
+        try:
+            q.push(sel)
+        except ValueError as exc:
+            self.assertIsInstance(exc.__context__, TypeError)
+
 
 class ChunkSize1PickleFifoDiskQueueTest(PickleFifoDiskQueueTest):
     chunksize = 1
@@ -133,10 +138,7 @@ class ChunkSize4PickleFifoDiskQueueTest(PickleFifoDiskQueueTest):
     chunksize = 4
 
 
-class MarshalLifoDiskQueueTest(t.LifoDiskQueueTest):
-
-    def queue(self):
-        return MarshalLifoDiskQueue(self.qpath)
+class LifoDiskQueueTestMixin:
 
     def test_serialize(self):
         q = self.queue()
@@ -150,7 +152,13 @@ class MarshalLifoDiskQueueTest(t.LifoDiskQueueTest):
     test_nonserializable_object = nonserializable_object_test
 
 
-class PickleLifoDiskQueueTest(MarshalLifoDiskQueueTest):
+class MarshalLifoDiskQueueTest(t.LifoDiskQueueTest, LifoDiskQueueTestMixin):
+
+    def queue(self):
+        return MarshalLifoDiskQueue(self.qpath)
+
+
+class PickleLifoDiskQueueTest(t.LifoDiskQueueTest, LifoDiskQueueTestMixin):
 
     def queue(self):
         return PickleLifoDiskQueue(self.qpath)
@@ -165,12 +173,12 @@ class PickleLifoDiskQueueTest(MarshalLifoDiskQueueTest):
 
     def test_serialize_loader(self):
         q = self.queue()
-        l = TestLoader()
-        q.push(l)
-        l2 = q.pop()
-        assert isinstance(l2, TestLoader)
-        assert l2.default_item_class is TestItem
-        self.assertEqual(l2.name_out('x'), 'xx')
+        loader = TestLoader()
+        q.push(loader)
+        loader2 = q.pop()
+        assert isinstance(loader2, TestLoader)
+        assert loader2.default_item_class is TestItem
+        self.assertEqual(loader2.name_out('x'), 'xx')
 
     def test_serialize_request_recursive(self):
         q = self.queue()

tests/test_utils_conf.py

@@ -93,7 +93,8 @@ class BuildComponentListTest(unittest.TestCase):
 class UtilsConfTestCase(unittest.TestCase):
 
     def test_arglist_to_dict(self):
-        self.assertEqual(arglist_to_dict(['arg1=val1', 'arg2=val2']),
+        self.assertEqual(
+            arglist_to_dict(['arg1=val1', 'arg2=val2']),
             {'arg1': 'val1', 'arg2': 'val2'})
 
 

tests/test_utils_datatypes.py

@@ -217,7 +217,7 @@ class SequenceExcludeTest(unittest.TestCase):
 
     def test_set(self):
         """Anything that is not in the supplied sequence will evaluate as 'in' the container."""
-        seq = set([-3, "test", 1.1])
+        seq = {-3, "test", 1.1}
         d = SequenceExclude(seq)
         self.assertIn(0, d)
         self.assertIn("foo", d)

tests/test_utils_defer.py

@@ -64,7 +64,7 @@ class DeferUtilsTest(unittest.TestCase):
         gotexc = False
         try:
             yield process_chain([cb1, cb_fail, cb3], 'res', 'v1', 'v2')
-        except TypeError as e:
+        except TypeError:
             gotexc = True
         self.assertTrue(gotexc)
 
@@ -104,7 +104,7 @@ class IterErrbackTest(unittest.TestCase):
         def iterbad():
             for x in range(10):
                 if x == 5:
-                    a = 1 / 0
+                    1 / 0
                 yield x
 
         errors = []