diff --git a/scrapy/crawler.py b/scrapy/crawler.py index e768bca12..65174d846 100644 --- a/scrapy/crawler.py +++ b/scrapy/crawler.py @@ -31,7 +31,12 @@ from scrapy.utils.log import ( ) from scrapy.utils.misc import create_instance, load_object from scrapy.utils.ossignal import install_shutdown_handlers, signal_names -from scrapy.utils.reactor import install_reactor, verify_installed_reactor +from scrapy.utils.reactor import ( + install_reactor, + is_asyncio_reactor_installed, + verify_installed_asyncio_event_loop, + verify_installed_reactor, +) logger = logging.getLogger(__name__) @@ -78,17 +83,20 @@ class Crawler: crawler=self, ) - reactor_class = self.settings.get("TWISTED_REACTOR") + reactor_class = self.settings["TWISTED_REACTOR"] + event_loop = self.settings["ASYNCIO_EVENT_LOOP"] if init_reactor: # this needs to be done after the spider settings are merged, # but before something imports twisted.internet.reactor if reactor_class: - install_reactor(reactor_class, self.settings["ASYNCIO_EVENT_LOOP"]) + install_reactor(reactor_class, event_loop) else: from twisted.internet import reactor # noqa: F401 log_reactor_info() if reactor_class: verify_installed_reactor(reactor_class) + if is_asyncio_reactor_installed() and event_loop: + verify_installed_asyncio_event_loop(event_loop) self.extensions = ExtensionManager.from_crawler(self) diff --git a/scrapy/utils/reactor.py b/scrapy/utils/reactor.py index bc543b230..652733ce8 100644 --- a/scrapy/utils/reactor.py +++ b/scrapy/utils/reactor.py @@ -90,6 +90,24 @@ def verify_installed_reactor(reactor_path): raise Exception(msg) +def verify_installed_asyncio_event_loop(loop_path): + from twisted.internet import reactor + loop_class = load_object(loop_path) + if isinstance(reactor._asyncioEventloop, loop_class): + return + installed = ( + f"{reactor._asyncioEventloop.__class__.__module__}" + f".{reactor._asyncioEventloop.__class__.__qualname__}" + ) + specified = f"{loop_class.__module__}.{loop_class.__qualname__}" + raise Exception( + "Scrapy found an asyncio Twisted reactor already " + f"installed, and its event loop class ({installed}) does " + "not match the one specified in the ASYNCIO_EVENT_LOOP " + f"setting ({specified})" + ) + + def is_asyncio_reactor_installed(): from twisted.internet import reactor return isinstance(reactor, asyncioreactor.AsyncioSelectorReactor) diff --git a/tests/CrawlerProcess/asyncio_enabled_reactor_different_loop.py b/tests/CrawlerProcess/asyncio_enabled_reactor_different_loop.py new file mode 100644 index 000000000..ea8242f67 --- /dev/null +++ b/tests/CrawlerProcess/asyncio_enabled_reactor_different_loop.py @@ -0,0 +1,25 @@ +import asyncio +import sys + +from twisted.internet import asyncioreactor +if sys.version_info >= (3, 8) and sys.platform == "win32": + asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy()) +asyncioreactor.install(asyncio.get_event_loop()) + +import scrapy # noqa: E402 +from scrapy.crawler import CrawlerProcess # noqa: E402 + + +class NoRequestsSpider(scrapy.Spider): + name = 'no_request' + + def start_requests(self): + return [] + + +process = CrawlerProcess(settings={ + "TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor", + "ASYNCIO_EVENT_LOOP": "uvloop.Loop", +}) +process.crawl(NoRequestsSpider) +process.start() diff --git a/tests/CrawlerProcess/asyncio_enabled_reactor_same_loop.py b/tests/CrawlerProcess/asyncio_enabled_reactor_same_loop.py new file mode 100644 index 000000000..d24bf3031 --- /dev/null +++ b/tests/CrawlerProcess/asyncio_enabled_reactor_same_loop.py @@ -0,0 +1,28 @@ +import asyncio +import sys + +from uvloop import Loop + +from twisted.internet import asyncioreactor +if sys.version_info >= (3, 8) and sys.platform == "win32": + asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy()) +asyncio.set_event_loop(Loop()) +asyncioreactor.install(asyncio.get_event_loop()) + +import scrapy # noqa: E402 +from scrapy.crawler import CrawlerProcess # noqa: E402 + + +class NoRequestsSpider(scrapy.Spider): + name = 'no_request' + + def start_requests(self): + return [] + + +process = CrawlerProcess(settings={ + "TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor", + "ASYNCIO_EVENT_LOOP": "uvloop.Loop", +}) +process.crawl(NoRequestsSpider) +process.start() diff --git a/tests/test_crawler.py b/tests/test_crawler.py index cf15ba9b9..c61d461f7 100644 --- a/tests/test_crawler.py +++ b/tests/test_crawler.py @@ -454,6 +454,29 @@ class CrawlerProcessSubprocess(ScriptRunnerMixin, unittest.TestCase): self.assertIn("Using asyncio event loop: uvloop.Loop", log) self.assertIn("async pipeline opened!", log) + @mark.skipif(sys.implementation.name == 'pypy', reason='uvloop does not support pypy properly') + @mark.skipif(platform.system() == 'Windows', reason='uvloop does not support Windows') + @mark.skipif(twisted_version == Version('twisted', 21, 2, 0), reason='https://twistedmatrix.com/trac/ticket/10106') + def test_asyncio_enabled_reactor_same_loop(self): + log = self.run_script("asyncio_enabled_reactor_same_loop.py") + self.assertIn("Spider closed (finished)", log) + self.assertIn("Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor", log) + self.assertIn("Using asyncio event loop: uvloop.Loop", log) + + @mark.skipif(sys.implementation.name == 'pypy', reason='uvloop does not support pypy properly') + @mark.skipif(platform.system() == 'Windows', reason='uvloop does not support Windows') + @mark.skipif(twisted_version == Version('twisted', 21, 2, 0), reason='https://twistedmatrix.com/trac/ticket/10106') + def test_asyncio_enabled_reactor_different_loop(self): + log = self.run_script("asyncio_enabled_reactor_different_loop.py") + self.assertNotIn("Spider closed (finished)", log) + self.assertIn( + ( + "does not match the one specified in the ASYNCIO_EVENT_LOOP " + "setting (uvloop.Loop)" + ), + log, + ) + def test_default_loop_asyncio_deferred_signal(self): log = self.run_script("asyncio_deferred_signal.py") self.assertIn("Spider closed (finished)", log)