diff --git a/scrapy/core/downloader/handlers/http11.py b/scrapy/core/downloader/handlers/http11.py index 6b8a18f1a..f07f0780e 100644 --- a/scrapy/core/downloader/handlers/http11.py +++ b/scrapy/core/downloader/handlers/http11.py @@ -3,7 +3,6 @@ import ipaddress import logging import re -import warnings from contextlib import suppress from io import BytesIO from time import time @@ -22,7 +21,7 @@ from zope.interface import implementer from scrapy import signals from scrapy.core.downloader.contextfactory import load_context_factory_from_settings from scrapy.core.downloader.webclient import _parse -from scrapy.exceptions import ScrapyDeprecationWarning, StopDownload +from scrapy.exceptions import StopDownload from scrapy.http import Headers from scrapy.responsetypes import responsetypes from scrapy.utils.python import to_bytes, to_unicode @@ -279,17 +278,7 @@ class ScrapyAgent: proxyScheme, proxyNetloc, proxyHost, proxyPort, proxyParams = _parse(proxy) scheme = _parse(request.url)[0] proxyHost = to_unicode(proxyHost) - omitConnectTunnel = b'noconnect' in proxyParams - if omitConnectTunnel: - warnings.warn( - "Using HTTPS proxies in the noconnect mode is deprecated. " - "If you use Zyte Smart Proxy Manager, it doesn't require " - "this mode anymore, so you should update scrapy-crawlera " - "to scrapy-zyte-smartproxy and remove '?noconnect' " - "from the Zyte Smart Proxy Manager URL.", - ScrapyDeprecationWarning, - ) - if scheme == b'https' and not omitConnectTunnel: + if scheme == b'https': proxyAuth = request.headers.get(b'Proxy-Authorization', None) proxyConf = (proxyHost, proxyPort, proxyAuth) return self._TunnelingAgent( @@ -302,8 +291,6 @@ class ScrapyAgent: ) else: proxyScheme = proxyScheme or b'http' - proxyHost = to_bytes(proxyHost, encoding='ascii') - proxyPort = to_bytes(str(proxyPort), encoding='ascii') proxyURI = urlunparse((proxyScheme, proxyNetloc, proxyParams, '', '', '')) return self._ProxyAgent( reactor=reactor, diff --git a/scrapy/core/downloader/handlers/http2.py b/scrapy/core/downloader/handlers/http2.py index 7bb88a193..3f1b36e92 100644 --- a/scrapy/core/downloader/handlers/http2.py +++ b/scrapy/core/downloader/handlers/http2.py @@ -1,4 +1,3 @@ -import warnings from time import time from typing import Optional, Type, TypeVar from urllib.parse import urldefrag @@ -69,19 +68,8 @@ class ScrapyH2Agent: if proxy: _, _, proxy_host, proxy_port, proxy_params = _parse(proxy) scheme = _parse(request.url)[0] - proxy_host = proxy_host.decode() - omit_connect_tunnel = b'noconnect' in proxy_params - if omit_connect_tunnel: - warnings.warn( - "Using HTTPS proxies in the noconnect mode is not " - "supported by the downloader handler. If you use Zyte " - "Smart Proxy Manager, it doesn't require this mode " - "anymore, so you should update scrapy-crawlera to " - "scrapy-zyte-smartproxy and remove '?noconnect' from the " - "Zyte Smart Proxy Manager URL." - ) - if scheme == b'https' and not omit_connect_tunnel: + if scheme == b'https': # ToDo raise NotImplementedError('Tunneling via CONNECT method using HTTP/2.0 is not yet supported') return self._ProxyAgent( diff --git a/tests/test_downloader_handlers.py b/tests/test_downloader_handlers.py index 883960084..c69bd3da1 100644 --- a/tests/test_downloader_handlers.py +++ b/tests/test_downloader_handlers.py @@ -24,7 +24,7 @@ from scrapy.core.downloader.handlers.http import HTTPDownloadHandler from scrapy.core.downloader.handlers.http10 import HTTP10DownloadHandler from scrapy.core.downloader.handlers.http11 import HTTP11DownloadHandler from scrapy.core.downloader.handlers.s3 import S3DownloadHandler -from scrapy.exceptions import NotConfigured, ScrapyDeprecationWarning +from scrapy.exceptions import NotConfigured from scrapy.http import Headers, HtmlResponse, Request from scrapy.http.response.text import TextResponse from scrapy.responsetypes import responsetypes @@ -757,18 +757,6 @@ class HttpProxyTestCase(unittest.TestCase): request = Request('http://example.com', meta={'proxy': http_proxy}) return self.download_request(request, Spider('foo')).addCallback(_test) - def test_download_with_proxy_https_noconnect(self): - def _test(response): - self.assertEqual(response.status, 200) - self.assertEqual(response.url, request.url) - self.assertEqual(response.body, b'https://example.com') - - http_proxy = f'{self.getURL("")}?noconnect' - request = Request('https://example.com', meta={'proxy': http_proxy}) - with self.assertWarnsRegex(ScrapyDeprecationWarning, - r'Using HTTPS proxies in the noconnect mode is deprecated'): - return self.download_request(request, Spider('foo')).addCallback(_test) - def test_download_without_proxy(self): def _test(response): self.assertEqual(response.status, 200) diff --git a/tests/test_downloader_handlers_http2.py b/tests/test_downloader_handlers_http2.py index 3a9db3ee5..079267535 100644 --- a/tests/test_downloader_handlers_http2.py +++ b/tests/test_downloader_handlers_http2.py @@ -242,21 +242,6 @@ class Https2ProxyTestCase(Http11ProxyTestCase): def getURL(self, path): return f"{self.scheme}://{self.host}:{self.portno}/{path}" - def test_download_with_proxy_https_noconnect(self): - def _test(response): - self.assertEqual(response.status, 200) - self.assertEqual(response.url, request.url) - self.assertEqual(response.body, b'/') - - http_proxy = f"{self.getURL('')}?noconnect" - request = Request('https://example.com', meta={'proxy': http_proxy}) - with self.assertWarnsRegex( - Warning, - r'Using HTTPS proxies in the noconnect mode is not supported by the ' - r'downloader handler.' - ): - return self.download_request(request, Spider('foo')).addCallback(_test) - @defer.inlineCallbacks def test_download_with_proxy_https_timeout(self): with self.assertRaises(NotImplementedError):