cookie handling WIP -.-

1 files changed, 146 insertions, 0 deletions

diff --git a/module/network/CookieRedirectHandler.py b/module/network/CookieRedirectHandler.py
new file mode 100644
index 000000000..3eeb3e711
--- /dev/null
+++ b/module/network/CookieRedirectHandler.py
@@ -0,0 +1,146 @@
+# -*- coding: utf-8 -*-
+
+"""
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 3 of the License,
+    or (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+    See the GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+    @author: mkaay, RaNaN
+"""
+
+from urllib2 import BaseHandler
+from urllib import addinfourl
+from urllib2 import Request
+from urlparse import urlparse, urlunparse, urljoin
+from CookieJar import CookieJar
+
+class CookieRedirectHandler(BaseHandler):
+    # maximum number of redirections to any single URL
+    # this is needed because of the state that cookies introduce
+    max_repeats = 4
+    # maximum total number of redirections (regardless of URL) before
+    # assuming we're in a loop
+    max_redirections = 10
+    
+    def __init__(self, cookiejar=None, follow=True):
+        if cookiejar is None:
+            cookiejar = CookieJar()
+        self.cookiejar = cookiejar
+        self.follow = follow
+
+    def http_request(self, request):
+        print "add", self.cookiejar
+        self.cookiejar.add_cookie_header(request)
+        return request
+
+    def http_response(self, request, response):
+        print "get", self.cookiejar
+        self.cookiejar.extract_cookies(response, request)
+        return response
+
+    def redirect_request(self, req, fp, code, msg, headers, newurl):
+        """Return a Request or None in response to a redirect.
+
+        This is called by the http_error_30x methods when a
+        redirection response is received.  If a redirection should
+        take place, return a new Request to allow http_error_30x to
+        perform the redirect.  Otherwise, raise HTTPError if no-one
+        else should try to handle this url.  Return None if you can't
+        but another Handler might.
+        """
+        m = req.get_method()
+        if (code in (301, 302, 303, 307) and m in ("GET", "HEAD")
+            or code in (301, 302, 303) and m == "POST"):
+            # Strictly (according to RFC 2616), 301 or 302 in response
+            # to a POST MUST NOT cause a redirection without confirmation
+            # from the user (of urllib2, in this case).  In practice,
+            # essentially all clients do redirect in this case, so we
+            # do the same.
+            # be conciliant with URIs containing a space
+            newurl = newurl.replace(' ', '%20')
+            newheaders = dict((k,v) for k,v in req.headers.items()
+                              if k.lower() not in ("content-length", "content-type")
+                             )
+            req = Request(newurl,
+                           headers=newheaders,
+                           origin_req_host=req.get_origin_req_host(),
+                           unverifiable=True)
+            self.cookiejar.add_cookie_header(req)
+            print req.headers
+            return req
+        else:
+            raise HTTPError(req.get_full_url(), code, msg, headers, fp)
+
+    # Implementation note: To avoid the server sending us into an
+    # infinite loop, the request object needs to track what URLs we
+    # have already seen.  Do this by adding a handler-specific
+    # attribute to the Request object.
+    def http_error_302(self, req, fp, code, msg, headers):
+        resp = addinfourl(fp, headers, req.get_full_url())
+        resp.code = code
+        resp.msg = msg
+        self.cookiejar.extract_cookies(resp, req)
+        
+        if not self.follow:
+            return resp
+        
+        # Some servers (incorrectly) return multiple Location headers
+        # (so probably same goes for URI).  Use first header.
+        if 'location' in headers:
+            newurl = headers.getheaders('location')[0]
+        elif 'uri' in headers:
+            newurl = headers.getheaders('uri')[0]
+        else:
+            return
+
+        # fix a possible malformed URL
+        urlparts = urlparse(newurl)
+        if not urlparts.path:
+            urlparts = list(urlparts)
+            urlparts[2] = "/"
+        newurl = urlunparse(urlparts)
+
+        newurl = urljoin(req.get_full_url(), newurl)
+
+        # XXX Probably want to forget about the state of the current
+        # request, although that might interact poorly with other
+        # handlers that also use handler-specific request attributes
+        new = self.redirect_request(req, fp, code, msg, headers, newurl)
+        if new is None:
+            return
+
+        # loop detection
+        # .redirect_dict has a key url if url was previously visited.
+        if hasattr(req, 'redirect_dict'):
+            visited = new.redirect_dict = req.redirect_dict
+            if (visited.get(newurl, 0) >= self.max_repeats or
+                len(visited) >= self.max_redirections):
+                raise HTTPError(req.get_full_url(), code,
+                                self.inf_msg + msg, headers, fp)
+        else:
+            visited = new.redirect_dict = req.redirect_dict = {}
+        visited[newurl] = visited.get(newurl, 0) + 1
+
+        # Don't close the fp until we are sure that we won't use it
+        # with HTTPError.
+        fp.read()
+        fp.close()
+        return self.parent.open(new, timeout=req.timeout)
+
+    http_error_301 = http_error_303 = http_error_307 = http_error_302
+
+    inf_msg = "The HTTP server returned a redirect error that would " \
+              "lead to an infinite loop.\n" \
+              "The last 30x error message was:\n"
+
+    https_request = http_request
+    https_response = http_response