diff --git a/Doc/howto/urllib2.rst b/Doc/howto/urllib2.rst index 24a4156..cea5403 100644 --- a/Doc/howto/urllib2.rst +++ b/Doc/howto/urllib2.rst @@ -538,6 +538,15 @@ setting up a `Basic Authentication`_ handler: :: through a proxy. However, this can be enabled by extending urllib.request as shown in the recipe [#]_. +.. note:: + + If the environment variable ``REQUEST_METHOD`` is set, which usually + indicates your script is running in a CGI environment, the environment + variable ``HTTP_PROXY`` will be ignored. This is because that variable can + be injected by a client using the "Proxy:" HTTP header. If you need to use + an HTTP proxy in a CGI environment, either use ``ProxyHandler`` explicitly, + or make sure the variable name is in lowercase (``http_proxy``). + Sockets and Layers ================== diff --git a/Doc/library/urllib.request.rst b/Doc/library/urllib.request.rst index 6c1bfb8..42c599f 100644 --- a/Doc/library/urllib.request.rst +++ b/Doc/library/urllib.request.rst @@ -173,6 +173,14 @@ The :mod:`urllib.request` module defines the following functions: If both lowercase and uppercase environment variables exist (and disagree), lowercase is preferred. + Note that if the environment variable ``REQUEST_METHOD`` is set, which + usually indicates your script is running in a CGI environment, the + environment variable ``HTTP_PROXY`` (uppercase) will be ignored. This is + because that variable can be injected by a client using the "Proxy:" HTTP + header. If you need to use an HTTP proxy in a CGI environment, either use + ``ProxyHandler`` explicitly, or make sure the variable name is in lowercase + (``http_proxy``) + The following classes are provided: @@ -280,6 +288,14 @@ The following classes are provided: list of hostname suffixes, optionally with ``:port`` appended, for example ``cern.ch,ncsa.uiuc.edu,some.host:8080``. + Note that if the environment variable ``REQUEST_METHOD`` is set, which + usually indicates your script is running in a CGI environment, the + environment variable ``HTTP_PROXY`` (uppercase) will be ignored. This is + because that variable can be injected by a client using the "Proxy:" HTTP + header. If you need to use an HTTP proxy in a CGI environment, either use + ``ProxyHandler`` explicitly, or make sure the variable name is in lowercase + (``http_proxy``). + .. class:: HTTPPasswordMgr() diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py index 5d05f8d..c26c52a 100644 --- a/Lib/test/test_urllib.py +++ b/Lib/test/test_urllib.py @@ -232,6 +232,18 @@ class ProxyTests(unittest.TestCase): self.assertTrue(urllib.request.proxy_bypass_environment('anotherdomain.com:8888')) self.assertTrue(urllib.request.proxy_bypass_environment('newdomain.com:1234')) + def test_proxy_cgi_ignore(self): + try: + self.env.set('HTTP_PROXY', 'http://somewhere:3128') + proxies = urllib.request.getproxies_environment() + self.assertEqual('http://somewhere:3128', proxies['http']) + self.env.set('REQUEST_METHOD', 'GET') + proxies = urllib.request.getproxies_environment() + self.assertNotIn('http', proxies) + finally: + self.env.unset('REQUEST_METHOD') + self.env.unset('HTTP_PROXY') + def test_proxy_bypass_environment_host_match(self): bypass = urllib.request.proxy_bypass_environment self.env.set('NO_PROXY', diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py index 1731fe3..c157dac 100644 --- a/Lib/urllib/request.py +++ b/Lib/urllib/request.py @@ -2412,6 +2412,11 @@ def getproxies_environment(): name = name.lower() if value and name[-6:] == '_proxy': proxies[name[:-6]] = value + # If we are running as CGI script, forget HTTP_PROXY (uppercase) as it + # may be set from the web server by a "Proxy:" header from the client + # If lowercase, it will still be used thanks to the next block + if 'REQUEST_METHOD' in os.environ: + proxies.pop('http', None) for name, value in os.environ.items(): if name[-6:] == '_proxy': name = name.lower()