Fixed Issue1424152 in Py3k: urllib2 fails with HTTPS over Proxy.

orsenthil · orsenthil · commit 97f0c6be463b · 2009-07-25T04:24:38.000Z
diff --git a/Doc/library/http.client.rst b/Doc/library/http.client.rst
@@ -386,6 +386,12 @@ HTTPConnection Objects
 
    .. versionadded:: 2.7
 
+.. method:: HTTPConnection.set_tunnel(host, port=None)
+
+   Set the host and the port for HTTP Connect Tunnelling. Normally used when it
+   is required to a HTTPS Connection through a proxy server.
+
+   .. versionadded:: 3.1
 
 .. method:: HTTPConnection.connect()
 
diff --git a/Lib/http/client.py b/Lib/http/client.py
@@ -644,11 +644,17 @@ def __init__(self, host, port=None, strict=None,
         self.__response = None
         self.__state = _CS_IDLE
         self._method = None
+        self._tunnel_host = None
+        self._tunnel_port = None
 
         self._set_hostport(host, port)
         if strict is not None:
             self.strict = strict
 
+    def set_tunnel(self, host, port=None):
+        self._tunnel_host = host
+        self._tunnel_port = port
+
     def _set_hostport(self, host, port):
         if port is None:
             i = host.rfind(':')
@@ -669,10 +675,29 @@ def _set_hostport(self, host, port):
     def set_debuglevel(self, level):
         self.debuglevel = level
 
+    def _tunnel(self):
+        self._set_hostport(self._tunnel_host, self._tunnel_port)
+        connect_str = "CONNECT %s:%d HTTP/1.0\r\n\r\n" %(self.host, self.port)
+        connect_bytes = connect_str.encode("ascii")
+        self.send(connect_bytes)
+        response = self.response_class(self.sock, strict = self.strict,
+                                       method= self._method)
+        (version, code, message) = response._read_status()
+        if code != 200:
+            self.close()
+            raise socket.error("Tunnel connection failed: %d %s" % (code,
+                                                                    message.strip()))
+        while True:
+            line = response.fp.readline()
+            if line == b'\r\n':
+                break
+
     def connect(self):
         """Connect to the host and port specified in __init__."""
         self.sock = socket.create_connection((self.host,self.port),
                                              self.timeout)
+        if self._tunnel_host:
+            self._tunnel()
 
     def close(self):
         """Close the connection to the HTTP server."""
@@ -1008,6 +1033,11 @@ def connect(self):
 
             sock = socket.create_connection((self.host, self.port),
                                             self.timeout)
+
+            if self._tunnel_host:
+                self.sock = sock
+                self._tunnel()
+
             self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file)
 
 
diff --git a/Lib/test/test_urllib2.py b/Lib/test/test_urllib2.py
@@ -947,6 +947,23 @@ def test_proxy(self):
         self.assertEqual([(handlers[0], "http_open")],
                          [tup[0:2] for tup in o.calls])
 
+    def test_proxy_https(self):
+        o = OpenerDirector()
+        ph = urllib.request.ProxyHandler(dict(https="proxy.example.com:3128"))
+        o.add_handler(ph)
+        meth_spec = [
+            [("https_open", "return response")]
+        ]
+        handlers = add_ordered_mock_handlers(o, meth_spec)
+
+        req = Request("https://www.example.com/")
+        self.assertEqual(req.get_host(), "www.example.com")
+        r = o.open(req)
+        self.assertEqual(req.get_host(), "proxy.example.com:3128")
+        self.assertEqual([(handlers[0], "https_open")],
+                         [tup[0:2] for tup in o.calls])
+
+
     def test_basic_auth(self, quote_char='"'):
         opener = OpenerDirector()
         password_manager = MockPasswordManager()
diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py
@@ -163,6 +163,7 @@ def __init__(self, url, data=None, headers={},
         self.full_url = unwrap(url)
         self.data = data
         self.headers = {}
+        self._tunnel_host = None
         for key, value in headers.items():
             self.add_header(key, value)
         self.unredirected_hdrs = {}
@@ -218,8 +219,12 @@ def get_origin_req_host(self):
     # End deprecated methods
 
     def set_proxy(self, host, type):
-        self.host, self.type = host, type
-        self.selector = self.full_url
+        if self.type == 'https' and not self._tunnel_host:
+            self._tunnel_host = self.host
+        else:
+            self.type= type
+            self.selector = self.full_url
+        self.host = host
 
     def has_proxy(self):
         return self.selector == self.full_url
@@ -659,7 +664,7 @@ def proxy_open(self, req, proxy, type):
             req.add_header('Proxy-authorization', 'Basic ' + creds)
         hostport = unquote(hostport)
         req.set_proxy(hostport, proxy_type)
-        if orig_type == proxy_type:
+        if orig_type == proxy_type or orig_type == 'https':
             # let other handlers take care of it
             return None
         else:
@@ -1041,6 +1046,10 @@ def do_open(self, http_class, req):
         # request.
         headers["Connection"] = "close"
         headers = dict((name.title(), val) for name, val in headers.items())
+
+        if req._tunnel_host:
+            h.set_tunnel(req._tunnel_host)
+
         try:
             h.request(req.get_method(), req.selector, req.data, headers)
             r = h.getresponse()  # an HTTPResponse instance
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -60,6 +60,9 @@ C-API
 Library
 -------
 
+- Issue #1424152: Fix for httplib, urllib2 to support SSL while working through
+  proxy. Original patch by Christopher Li, changes made by Senthil Kumaran
+
 - Add importlib.abc.ExecutionLoader to represent the PEP 302 protocol for
   loaders that allow for modules to be executed. Both importlib.abc.PyLoader
   and PyPycLoader inherit from this class and provide implementations in
