Merge pull request scrapy#6406 from wRAR/more-flake8

Add some flake8 plugins

.flake8

@@ -1,8 +1,63 @@
 [flake8]
 
 max-line-length = 119
-ignore = E203, E501, E701, E704, W503
+ignore =
+    # black disagrees with flake8 about these
+    E203, E501, E701, E704, W503
 
+    # Assigning to `os.environ` doesn't clear the environment.
+    B003
+    # Do not use mutable data structures for argument defaults.
+    B006
+    # Loop control variable not used within the loop body.
+    B007
+    # Do not perform function calls in argument defaults.
+    B008
+    # return/continue/break inside finally blocks cause exceptions to be
+    # silenced.
+    B012
+    # Star-arg unpacking after a keyword argument is strongly discouraged
+    B026
+    # No explicit stacklevel argument found.
+    B028
+
+    # docstring does contain unindexed parameters
+    P102
+    # other string does contain unindexed parameters
+    P103
+
+    # Missing docstring in public module
+    D100
+    # Missing docstring in public class
+    D101
+    # Missing docstring in public method
+    D102
+    # Missing docstring in public function
+    D103
+    # Missing docstring in public package
+    D104
+    # Missing docstring in magic method
+    D105
+    # Missing docstring in public nested class
+    D106
+    # Missing docstring in __init__
+    D107
+    # One-line docstring should fit on one line with quotes
+    D200
+    # No blank lines allowed after function docstring
+    D202
+    # 1 blank line required between summary line and description
+    D205
+    # Multi-line docstring closing quotes should be on a separate line
+    D209
+    # First line should end with a period
+    D400
+    # First line should be in imperative mood; try rephrasing
+    D401
+    # First line should not be the function's "signature"
+    D402
+    # First word of the first line should be properly capitalized
+    D403
 exclude =
     docs/conf.py
 

.pre-commit-config.yaml

@@ -8,6 +8,12 @@ repos:
   rev: 7.0.0
   hooks:
   - id: flake8
+    additional_dependencies:
+    - flake8-bugbear
+    - flake8-comprehensions
+    - flake8-debugger
+    - flake8-docstrings
+    - flake8-string-format
 - repo: https://github.com/psf/black.git
   rev: 24.2.0
   hooks:

scrapy/extensions/debug.py

@@ -74,4 +74,4 @@ def __init__(self) -> None:
 
     def _enter_debugger(self, signum: int, frame: Optional[FrameType]) -> None:
         assert frame
-        Pdb().set_trace(frame.f_back)
+        Pdb().set_trace(frame.f_back)  # noqa: T100

scrapy/extensions/feedexport.py

@@ -104,7 +104,7 @@ def __init__(self, feed_options: Optional[Dict[str, Any]]) -> None:
                 for item_class in feed_options.get("item_classes") or ()
             )
         else:
-            self.item_classes = tuple()
+            self.item_classes = ()
 
     def accepts(self, item: Any) -> bool:
         """

scrapy/pipelines/media.py

@@ -234,7 +234,7 @@ def _cache_result_and_execute_waiters(
             # Exception Chaining (https://www.python.org/dev/peps/pep-3134/).
             context = getattr(result.value, "__context__", None)
             if isinstance(context, StopIteration):
-                setattr(result.value, "__context__", None)
+                result.value.__context__ = None
 
         info.downloading.remove(fp)
         info.downloaded[fp] = result  # cache result

scrapy/utils/console.py

@@ -10,10 +10,10 @@ def _embed_ipython_shell(
 ) -> EmbedFuncT:
     """Start an IPython Shell"""
     try:
-        from IPython.terminal.embed import InteractiveShellEmbed
+        from IPython.terminal.embed import InteractiveShellEmbed  # noqa: T100
         from IPython.terminal.ipapp import load_default_config
     except ImportError:
-        from IPython.frontend.terminal.embed import (  # type: ignore[no-redef]
+        from IPython.frontend.terminal.embed import (  # type: ignore[no-redef]  # noqa: T100
             InteractiveShellEmbed,
         )
         from IPython.frontend.terminal.ipapp import (  # type: ignore[no-redef]

scrapy/utils/defer.py

@@ -407,7 +407,7 @@ def maybeDeferred_coro(
     """Copy of defer.maybeDeferred that also converts coroutines to Deferreds."""
     try:
         result = f(*args, **kw)
-    except:  # noqa: E722
+    except:  # noqa: E722,B001
         return defer.fail(failure.Failure(captureVars=Deferred.debug))
 
     if isinstance(result, Deferred):

scrapy/utils/python.py

@@ -269,7 +269,7 @@ def get_spec(func: Callable[..., Any]) -> Tuple[List[str], Dict[str, Any]]:
 
     if inspect.isfunction(func) or inspect.ismethod(func):
         spec = inspect.getfullargspec(func)
-    elif hasattr(func, "__call__"):
+    elif hasattr(func, "__call__"):  # noqa: B004
         spec = inspect.getfullargspec(func.__call__)
     else:
         raise TypeError(f"{type(func)} is not callable")

scrapy/utils/signal.py

@@ -100,7 +100,10 @@ def logerror(failure: Failure, recv: Any) -> Failure:
         d.addErrback(logerror, receiver)
         # TODO https://pylint.readthedocs.io/en/latest/user_guide/messages/warning/cell-var-from-loop.html
         d.addBoth(
-            lambda result: (receiver, result)  # pylint: disable=cell-var-from-loop
+            lambda result: (
+                receiver,  # pylint: disable=cell-var-from-loop  # noqa: B023
+                result,
+            )
         )
         dfds.append(d)
     d = DeferredList(dfds)

tests/test_cmdline/__init__.py

@@ -20,7 +20,7 @@ def setUp(self):
         self.env["SCRAPY_SETTINGS_MODULE"] = "tests.test_cmdline.settings"
 
     def _execute(self, *new_args, **kwargs):
-        encoding = getattr(sys.stdout, "encoding") or "utf-8"
+        encoding = sys.stdout.encoding or "utf-8"
         args = (sys.executable, "-m", "scrapy.cmdline") + new_args
         proc = Popen(args, stdout=PIPE, stderr=PIPE, env=self.env, **kwargs)
         comm = proc.communicate()[0].strip()

tests/test_command_version.py

@@ -12,7 +12,7 @@ class VersionTest(ProcessTest, unittest.TestCase):
 
     @defer.inlineCallbacks
     def test_output(self):
-        encoding = getattr(sys.stdout, "encoding") or "utf-8"
+        encoding = sys.stdout.encoding or "utf-8"
         _, out, _ = yield self.execute([])
         self.assertEqual(
             out.strip().decode(encoding),
@@ -21,7 +21,7 @@ def test_output(self):
 
     @defer.inlineCallbacks
     def test_verbose_output(self):
-        encoding = getattr(sys.stdout, "encoding") or "utf-8"
+        encoding = sys.stdout.encoding or "utf-8"
         _, out, _ = yield self.execute(["-v"])
         headers = [
             line.partition(":")[0].strip()

tests/test_commands.py

@@ -101,7 +101,7 @@ def proc(self, *new_args, **popen_kwargs):
         def kill_proc():
             p.kill()
             p.communicate()
-            assert False, "Command took too much time to complete"
+            raise AssertionError("Command took too much time to complete")
 
         timer = Timer(15, kill_proc)
         try:
@@ -200,7 +200,7 @@ def get_permissions(path: Path) -> str:
 
     path_obj = Path(path)
 
-    renamings = renamings or tuple()
+    renamings = renamings or ()
     permissions_dict = {
         ".": get_permissions(path_obj),
     }

tests/test_downloader_handlers.py

@@ -892,7 +892,7 @@ def test_extra_kw(self):
         except Exception as e:
             self.assertIsInstance(e, (TypeError, NotConfigured))
         else:
-            assert False
+            raise AssertionError()
 
     def test_request_signing1(self):
         # gets an object from the johnsmith bucket.

tests/test_dupefilters.py

@@ -146,7 +146,7 @@ def fingerprint(self, request):
         case_insensitive_dupefilter.close("finished")
 
     def test_seenreq_newlines(self):
-        """Checks against adding duplicate \r to
+        r"""Checks against adding duplicate \r to
         line endings on Windows platforms."""
 
         r1 = Request("http://scrapytest.org/1")

tests/test_engine.py

@@ -459,7 +459,7 @@ def test_short_timeout(self):
         def kill_proc():
             p.kill()
             p.communicate()
-            assert False, "Command took too much time to complete"
+            raise AssertionError("Command took too much time to complete")
 
         timer = Timer(15, kill_proc)
         try:

tests/test_feedexport.py

@@ -1356,7 +1356,7 @@ def test_export_feed_export_fields(self):
 
     @defer.inlineCallbacks
     def test_export_encoding(self):
-        items = [dict({"foo": "Test\xd6"})]
+        items = [{"foo": "Test\xd6"}]
 
         formats = {
             "json": b'[{"foo": "Test\\u00d6"}]',
@@ -1401,7 +1401,7 @@ def test_export_encoding(self):
 
     @defer.inlineCallbacks
     def test_export_multiple_configs(self):
-        items = [dict({"foo": "FOO", "bar": "BAR"})]
+        items = [{"foo": "FOO", "bar": "BAR"}]
 
         formats = {
             "json": b'[\n{"bar": "BAR"}\n]',
@@ -2513,8 +2513,8 @@ def test_export_no_items_store_empty(self):
     @defer.inlineCallbacks
     def test_export_multiple_configs(self):
         items = [
-            dict({"foo": "FOO", "bar": "BAR"}),
-            dict({"foo": "FOO1", "bar": "BAR1"}),
+            {"foo": "FOO", "bar": "BAR"},
+            {"foo": "FOO1", "bar": "BAR1"},
         ]
 
         formats = {
@@ -2574,7 +2574,7 @@ def test_export_multiple_configs(self):
 
     @defer.inlineCallbacks
     def test_batch_item_count_feeds_setting(self):
-        items = [dict({"foo": "FOO"}), dict({"foo": "FOO1"})]
+        items = [{"foo": "FOO"}, {"foo": "FOO1"}]
         formats = {
             "json": [
                 b'[{"foo": "FOO"}]',

tests/test_linkextractors.py

@@ -186,7 +186,7 @@ def test_extraction_using_single_values(self):
             )
 
         def test_nofollow(self):
-            '''Test the extractor's behaviour for links with rel="nofollow"'''
+            """Test the extractor's behaviour for links with rel='nofollow'"""
 
             html = b"""<html><head><title>Page title<title>
             <body>

tests/test_loader.py

@@ -156,7 +156,7 @@ def test_get_output_value_singlevalue(self):
         self.assertEqual(il.get_output_value("name"), ["foo"])
         loaded_item = il.load_item()
         self.assertIsInstance(loaded_item, self.item_class)
-        self.assertEqual(ItemAdapter(loaded_item).asdict(), dict({"name": ["foo"]}))
+        self.assertEqual(ItemAdapter(loaded_item).asdict(), {"name": ["foo"]})
 
     def test_get_output_value_list(self):
         """Getting output value must not remove value from item"""
@@ -165,9 +165,7 @@ def test_get_output_value_list(self):
         self.assertEqual(il.get_output_value("name"), ["foo", "bar"])
         loaded_item = il.load_item()
         self.assertIsInstance(loaded_item, self.item_class)
-        self.assertEqual(
-            ItemAdapter(loaded_item).asdict(), dict({"name": ["foo", "bar"]})
-        )
+        self.assertEqual(ItemAdapter(loaded_item).asdict(), {"name": ["foo", "bar"]})
 
     def test_values_single(self):
         """Values from initial item must be added to loader._values"""

tests/test_loader_deprecated.py

@@ -526,7 +526,7 @@ def test_get_output_value_singlevalue(self):
         self.assertEqual(il.get_output_value("name"), ["foo"])
         loaded_item = il.load_item()
         self.assertIsInstance(loaded_item, self.item_class)
-        self.assertEqual(loaded_item, dict({"name": ["foo"]}))
+        self.assertEqual(loaded_item, {"name": ["foo"]})
 
     def test_get_output_value_list(self):
         """Getting output value must not remove value from item"""
@@ -535,7 +535,7 @@ def test_get_output_value_list(self):
         self.assertEqual(il.get_output_value("name"), ["foo", "bar"])
         loaded_item = il.load_item()
         self.assertIsInstance(loaded_item, self.item_class)
-        self.assertEqual(loaded_item, dict({"name": ["foo", "bar"]}))
+        self.assertEqual(loaded_item, {"name": ["foo", "bar"]})
 
     def test_values_single(self):
         """Values from initial item must be added to loader._values"""

tests/test_request_dict.py

@@ -147,7 +147,7 @@ def parse(self, response):
 
         spider = MySpider()
         r = Request("http://www.example.com", callback=spider.parse)
-        setattr(spider, "parse", None)
+        spider.parse = None
         self.assertRaises(ValueError, r.to_dict, spider=spider)
 
     def test_callback_not_available(self):

tests/test_scheduler.py

@@ -284,7 +284,7 @@ def test_logic(self):
             downloader.decrement(slot)
 
         self.assertTrue(
-            _is_scheduling_fair(list(s for u, s in _URLS_WITH_SLOTS), dequeued_slots)
+            _is_scheduling_fair([s for u, s in _URLS_WITH_SLOTS], dequeued_slots)
         )
         self.assertEqual(sum(len(s.active) for s in downloader.slots.values()), 0)