From b81938684b55fca29e48faa766f2b6f6e3ab5d6a Mon Sep 17 00:00:00 2001 From: Andrey Oskin Date: Fri, 31 Dec 2021 21:49:18 +1100 Subject: [PATCH 1/3] Docs: correct process repetition start step (#5356) The process repeats from step 3, the scheduler feeds request to the engine. Steps 1 and 2 are not parts of the loop as their incarnations steps 7 and 8 are parts of the loop. --- docs/topics/architecture.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/topics/architecture.rst b/docs/topics/architecture.rst index 71d027c86..0c3a7ed88 100644 --- a/docs/topics/architecture.rst +++ b/docs/topics/architecture.rst @@ -67,7 +67,7 @@ this: the :ref:`Scheduler ` and asks for possible next Requests to crawl. -9. The process repeats (from step 1) until there are no more requests from the +9. The process repeats (from step 3) until there are no more requests from the :ref:`Scheduler `. Components From e4bdd1cb958b7d89b86ea66f0af1cec2d91a6d44 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pawe=C5=82=20Miech?= Date: Fri, 31 Dec 2021 11:57:12 +0100 Subject: [PATCH 2/3] downloader.webclient: make reactor import local (#5357) --- scrapy/core/downloader/webclient.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scrapy/core/downloader/webclient.py b/scrapy/core/downloader/webclient.py index 915cb5fe3..06cb96489 100644 --- a/scrapy/core/downloader/webclient.py +++ b/scrapy/core/downloader/webclient.py @@ -3,7 +3,7 @@ from time import time from urllib.parse import urlparse, urlunparse, urldefrag from twisted.web.http import HTTPClient -from twisted.internet import defer, reactor +from twisted.internet import defer from twisted.internet.protocol import ClientFactory from scrapy.http import Headers @@ -170,6 +170,7 @@ class ScrapyHTTPClientFactory(ClientFactory): p.followRedirect = self.followRedirect p.afterFoundGet = self.afterFoundGet if self.timeout: + from twisted.internet import reactor timeoutCall = reactor.callLater(self.timeout, p.timeout) self.deferred.addBoth(self._cancelTimeout, timeoutCall) return p From 57dc58123b98e2026025cc87bdee474bf0656dcb Mon Sep 17 00:00:00 2001 From: Andrey Rahmatullin Date: Fri, 31 Dec 2021 17:15:08 +0500 Subject: [PATCH 3/3] Remove the experimental note about asyncio (#5332) --- docs/topics/asyncio.rst | 5 ----- 1 file changed, 5 deletions(-) diff --git a/docs/topics/asyncio.rst b/docs/topics/asyncio.rst index 28241ae24..402352721 100644 --- a/docs/topics/asyncio.rst +++ b/docs/topics/asyncio.rst @@ -10,11 +10,6 @@ Scrapy has partial support for :mod:`asyncio`. After you :ref:`install the asyncio reactor `, you may use :mod:`asyncio` and :mod:`asyncio`-powered libraries in any :doc:`coroutine `. -.. warning:: :mod:`asyncio` support in Scrapy is experimental, and not yet - recommended for production environments. Future Scrapy versions - may introduce related changes without a deprecation period or - warning. - .. _install-asyncio: Installing the asyncio reactor