Scrapy, a fast high-level web crawling & scraping framework for Python.
Add flake8-raise rules to ruff.
Andrey Rakhmatulline7595837a60b
diff --git a/pyproject.toml b/pyproject.tomlindex 9a4a91a7e..131684724 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -246,6 +246,8 @@ extend-select = ["Q",# flake8-return"RET",+ # flake8-raise+ "RSE",# flake8-bandit"S",# flake8-slotsdiff --git a/scrapy/commands/crawl.py b/scrapy/commands/crawl.pyindex 0d71ab6c6..86d4cc41c 100644--- a/scrapy/commands/crawl.py+++ b/scrapy/commands/crawl.py@@ -22,7 +22,7 @@ class Command(BaseRunSpiderCommand):def run(self, args: list[str], opts: argparse.Namespace) -> None:if len(args) < 1:- raise UsageError()+ raise UsageErrorif len(args) > 1:raise UsageError("running 'scrapy crawl' with more than one spider is not supported"diff --git a/scrapy/commands/edit.py b/scrapy/commands/edit.pyindex 0e046cece..d153a5271 100644--- a/scrapy/commands/edit.py+++ b/scrapy/commands/edit.py@@ -28,7 +28,7 @@ class Command(ScrapyCommand):def run(self, args: list[str], opts: argparse.Namespace) -> None:if len(args) != 1:- raise UsageError()+ raise UsageErroreditor = self.settings["EDITOR"]assert self.crawler_processdiff --git a/scrapy/commands/fetch.py b/scrapy/commands/fetch.pyindex 05e5e53e9..8a8d04ff6 100644--- a/scrapy/commands/fetch.py+++ b/scrapy/commands/fetch.py@@ -68,7 +68,7 @@ class Command(ScrapyCommand):def run(self, args: list[str], opts: Namespace) -> None:if len(args) != 1 or not is_url(args[0]):- raise UsageError()+ raise UsageErrorrequest = Request(args[0],callback=self._print_response,diff --git a/scrapy/commands/genspider.py b/scrapy/commands/genspider.pyindex 38f917c7e..d7dc104c2 100644--- a/scrapy/commands/genspider.py+++ b/scrapy/commands/genspider.py@@ -101,7 +101,7 @@ class Command(ScrapyCommand):print(template_file.read_text(encoding="utf-8"))returnif len(args) != 2:- raise UsageError()+ raise UsageErrorname, url = args[0:2]url = verify_url_scheme(url)diff --git a/scrapy/commands/parse.py b/scrapy/commands/parse.pyindex 62d094411..cc5c1350b 100644--- a/scrapy/commands/parse.py+++ b/scrapy/commands/parse.py@@ -399,7 +399,7 @@ class Command(BaseRunSpiderCommand):def run(self, args: list[str], opts: argparse.Namespace) -> None:# parse argumentsif not len(args) == 1 or not is_url(args[0]):- raise UsageError()+ raise UsageErrorurl = args[0]# prepare spiderclsdiff --git a/scrapy/commands/runspider.py b/scrapy/commands/runspider.pyindex 55211f8d7..bf8e41020 100644--- a/scrapy/commands/runspider.py+++ b/scrapy/commands/runspider.py@@ -43,7 +43,7 @@ class Command(BaseRunSpiderCommand):def run(self, args: list[str], opts: argparse.Namespace) -> None:if len(args) != 1:- raise UsageError()+ raise UsageErrorfilename = Path(args[0])if not filename.exists():raise UsageError(f"File not found: {filename}\n")diff --git a/scrapy/commands/startproject.py b/scrapy/commands/startproject.pyindex 6da877610..5cb73f0d2 100644--- a/scrapy/commands/startproject.py+++ b/scrapy/commands/startproject.py@@ -92,7 +92,7 @@ class Command(ScrapyCommand):def run(self, args: list[str], opts: argparse.Namespace) -> None:if len(args) not in (1, 2):- raise UsageError()+ raise UsageErrorproject_name = args[0]diff --git a/scrapy/core/scheduler.py b/scrapy/core/scheduler.pyindex f09d1903c..823677175 100644--- a/scrapy/core/scheduler.py+++ b/scrapy/core/scheduler.py@@ -98,7 +98,7 @@ class BaseScheduler(metaclass=BaseSchedulerMeta):"""``True`` if the scheduler has enqueued requests, ``False`` otherwise"""- raise NotImplementedError()+ raise NotImplementedError@abstractmethoddef enqueue_request(self, request: Request) -> bool:@@ -112,7 +112,7 @@ class BaseScheduler(metaclass=BaseSchedulerMeta):For reference, the default Scrapy scheduler returns ``False`` when therequest is rejected by the dupefilter."""- raise NotImplementedError()+ raise NotImplementedError@abstractmethoddef next_request(self) -> Request | None:@@ -124,7 +124,7 @@ class BaseScheduler(metaclass=BaseSchedulerMeta):to the downloader in the current reactor cycle. The engine will continuecalling ``next_request`` until ``has_pending_requests`` is ``False``."""- raise NotImplementedError()+ raise NotImplementedErrorclass Scheduler(BaseScheduler):diff --git a/scrapy/pipelines/media.py b/scrapy/pipelines/media.pyindex 691a1cbf2..b16f1cb84 100644--- a/scrapy/pipelines/media.py+++ b/scrapy/pipelines/media.py@@ -293,12 +293,12 @@ class MediaPipeline(ABC):self, request: Request, info: SpiderInfo, *, item: Any = None) -> Deferred[FileInfo | None]:"""Check request before starting download"""- raise NotImplementedError()+ raise NotImplementedError@abstractmethoddef get_media_requests(self, item: Any, info: SpiderInfo) -> list[Request]:"""Returns the media requests to download"""- raise NotImplementedError()+ raise NotImplementedError@abstractmethoddef media_downloaded(@@ -310,14 +310,14 @@ class MediaPipeline(ABC):item: Any = None,) -> FileInfo:"""Handler for success downloads"""- raise NotImplementedError()+ raise NotImplementedError@abstractmethoddef media_failed(self, failure: Failure, request: Request, info: SpiderInfo) -> NoReturn:"""Handler for failed downloads"""- raise NotImplementedError()+ raise NotImplementedErrordef item_completed(self, results: list[FileInfoOrError], item: Any, info: SpiderInfo@@ -345,4 +345,4 @@ class MediaPipeline(ABC):item: Any = None,) -> str:"""Returns the path where downloaded media should be stored"""- raise NotImplementedError()+ raise NotImplementedErrordiff --git a/scrapy/resolver.py b/scrapy/resolver.pyindex 0e8260736..f5f00ab0f 100644--- a/scrapy/resolver.py+++ b/scrapy/resolver.py@@ -76,7 +76,7 @@ class HostResolution:self.name: str = namedef cancel(self) -> None:- raise NotImplementedError()+ raise NotImplementedError@provider(IResolutionReceiver)diff --git a/scrapy/spidermiddlewares/referer.py b/scrapy/spidermiddlewares/referer.pyindex 720217c97..93b7fcf17 100644--- a/scrapy/spidermiddlewares/referer.py+++ b/scrapy/spidermiddlewares/referer.py@@ -51,7 +51,7 @@ class ReferrerPolicy:name: strdef referrer(self, response_url: str, request_url: str) -> str | None:- raise NotImplementedError()+ raise NotImplementedErrordef stripped_referrer(self, url: str) -> str | None:if urlparse(url).scheme not in self.NOREFERRER_SCHEMES:diff --git a/tests/test_addons.py b/tests/test_addons.pyindex 775f629b3..17949997c 100644--- a/tests/test_addons.py+++ b/tests/test_addons.py@@ -64,7 +64,7 @@ class AddonManagerTest(unittest.TestCase):def test_notconfigured(self):class NotConfiguredAddon:def update_settings(self, settings):- raise NotConfigured()+ raise NotConfiguredsettings_dict = {"ADDONS": {NotConfiguredAddon: 0},diff --git a/tests/test_downloader_handlers.py b/tests/test_downloader_handlers.pyindex 6a7597e9f..3fcba4ef2 100644--- a/tests/test_downloader_handlers.py+++ b/tests/test_downloader_handlers.py@@ -894,7 +894,7 @@ class S3TestCase(unittest.TestCase):except Exception as e:self.assertIsInstance(e, (TypeError, NotConfigured))else:- raise AssertionError()+ raise AssertionErrordef test_request_signing1(self):# gets an object from the johnsmith bucket.diff --git a/tests/test_downloadermiddleware.py b/tests/test_downloadermiddleware.pyindex 8987a76fb..e650b4936 100644--- a/tests/test_downloadermiddleware.py+++ b/tests/test_downloadermiddleware.py@@ -178,7 +178,7 @@ class ProcessExceptionInvalidOutput(ManagerTestCase):class InvalidProcessExceptionMiddleware:def process_request(self, request, spider):- raise Exception()+ raise Exceptiondef process_exception(self, request, exception, spider):return 1diff --git a/tests/test_downloadermiddleware_httpcompression.py b/tests/test_downloadermiddleware_httpcompression.pyindex 934af6590..78d0dd99d 100644--- a/tests/test_downloadermiddleware_httpcompression.py+++ b/tests/test_downloadermiddleware_httpcompression.py@@ -59,7 +59,7 @@ class HttpCompressionTest(TestCase):def _getresponse(self, coding):if coding not in FORMAT:- raise ValueError()+ raise ValueErrorsamplefile, contentencoding = FORMAT[coding]diff --git a/tests/test_spidermiddleware.py b/tests/test_spidermiddleware.pyindex 1aca0fe54..af3b7543d 100644--- a/tests/test_spidermiddleware.py+++ b/tests/test_spidermiddleware.py@@ -78,7 +78,7 @@ class ProcessSpiderExceptionInvalidOutput(SpiderMiddlewareTestCase):class RaiseExceptionProcessSpiderOutputMiddleware:def process_spider_output(self, response, result, spider):- raise Exception()+ raise Exceptionself.mwman._add_middleware(InvalidProcessSpiderOutputExceptionMiddleware())self.mwman._add_middleware(RaiseExceptionProcessSpiderOutputMiddleware())diff --git a/tests/test_spidermiddleware_output_chain.py b/tests/test_spidermiddleware_output_chain.pyindex 670c41f2b..4c19d167f 100644--- a/tests/test_spidermiddleware_output_chain.py+++ b/tests/test_spidermiddleware_output_chain.py@@ -43,7 +43,7 @@ class RecoverySpider(Spider):yield {"test": 1}self.logger.info("DONT_FAIL: %s", response.meta.get("dont_fail"))if not response.meta.get("dont_fail"):- raise TabError()+ raise TabErrorclass RecoveryAsyncGenSpider(RecoverySpider):@@ -59,7 +59,7 @@ class RecoveryAsyncGenSpider(RecoverySpider):class FailProcessSpiderInputMiddleware:def process_spider_input(self, response, spider):spider.logger.info("Middleware: will raise IndexError")- raise IndexError()+ raise IndexErrorclass ProcessSpiderInputSpiderWithoutErrback(Spider):@@ -109,14 +109,14 @@ class GeneratorCallbackSpider(Spider):def parse(self, response):yield {"test": 1}yield {"test": 2}- raise ImportError()+ raise ImportErrorclass AsyncGeneratorCallbackSpider(GeneratorCallbackSpider):async def parse(self, response):yield {"test": 1}yield {"test": 2}- raise ImportError()+ raise ImportError# ================================================================================@@ -176,7 +176,7 @@ class GeneratorFailMiddleware:for r in result:r["processed"].append(f"{self.__class__.__name__}.process_spider_output")yield r- raise LookupError()+ raise LookupErrordef process_spider_exception(self, response, exception, spider):method = f"{self.__class__.__name__}.process_spider_exception"@@ -246,7 +246,7 @@ class NotGeneratorFailMiddleware:for r in result:r["processed"].append(f"{self.__class__.__name__}.process_spider_output")out.append(r)- raise ReferenceError()+ raise ReferenceErrorreturn outdef process_spider_exception(self, response, exception, spider):diff --git a/tests/test_squeues_request.py b/tests/test_squeues_request.pyindex 499ca46b8..02ea8027f 100644--- a/tests/test_squeues_request.py+++ b/tests/test_squeues_request.py@@ -41,7 +41,7 @@ class BaseQueueTestCase(unittest.TestCase):class RequestQueueTestMixin:def queue(self):- raise NotImplementedError()+ raise NotImplementedErrordef test_one_element_with_peek(self):if not hasattr(queuelib.queue.FifoMemoryQueue, "peek"):diff --git a/tests/test_utils_misc/test_return_with_argument_inside_generator.py b/tests/test_utils_misc/test_return_with_argument_inside_generator.pyindex 484757035..c7774751e 100644--- a/tests/test_utils_misc/test_return_with_argument_inside_generator.py+++ b/tests/test_utils_misc/test_return_with_argument_inside_generator.py@@ -10,7 +10,7 @@ from scrapy.utils.misc import (def _indentation_error(*args, **kwargs):- raise IndentationError()+ raise IndentationErrordef top_level_return_something():