SF Patch 549151: urllib2 POSTs on redirect

(contributed by John J Lee)

Doc/lib/liburllib.tex

@@ -254,12 +254,18 @@ actually retrieve a resource at an \file{https:} URL.
 
 \begin{classdesc}{FancyURLopener}{...}
 \class{FancyURLopener} subclasses \class{URLopener} providing default
-handling for the following HTTP response codes: 301, 302 or 401.  For
-301 and 302 response codes, the \mailheader{Location} header is used to
-fetch the actual URL.  For 401 response codes (authentication
-required), basic HTTP authentication is performed.  For 301 and 302 response
-codes, recursion is bounded by the value of the \var{maxtries} attribute,
-which defaults 10.
+handling for the following HTTP response codes: 301, 302, 303 and 401.
+For 301, 302 and 303 response codes, the \mailheader{Location} header
+is used to fetch the actual URL.  For 401 response codes
+(authentication required), basic HTTP authentication is performed.
+For 301, 302 and 303 response codes, recursion is bounded by the value
+of the \var{maxtries} attribute, which defaults 10.
+
+\note{According to the letter of \rfc{2616}, 301 and 302 responses to
+  POST requests must not be automatically redirected without
+  confirmation by the user.  In reality, browsers do allow automatic
+  redirection of these responses, changing the POST to a GET, and
+  \module{urllib} reproduces this behaviour.}
 
 The parameters to the constructor are the same as those for
 \class{URLopener}.

Doc/lib/liburllib2.tex

@@ -217,6 +217,12 @@ by all handlers except HTTP handlers --- and there it should be an
 request to be \code{POST} rather than \code{GET}. 
 \end{methoddesc}
 
+\begin{methoddesc}[Request]{get_method}{}
+Return a string indicating the HTTP request method.  This is only
+meaningful for HTTP requests, and currently always takes one of the
+values ("GET", "POST").
+\end{methoddesc}
+
 \begin{methoddesc}[Request]{has_data}{}
 Return whether the instance has a non-\code{None} data.
 \end{methoddesc}
@@ -394,25 +400,49 @@ Arguments, return values and exceptions raised should be the same as
 for \method{http_error_default()}.
 \end{methoddesc}
 
-
 \subsection{HTTPRedirectHandler Objects \label{http-redirect-handler}}
 
-\note{303 redirection is not supported by this version of 
-\module{urllib2}.}
+\note{Some HTTP redirections require action from this module's client
+  code.  If this is the case, \exception{HTTPError} is raised.  See
+  \rfc{2616} for details of the precise meanings of the various
+  redirection codes.}
+
+\begin{methoddesc}[HTTPRedirectHandler]{redirect_request}{req,
+                                                  fp, code, msg, hdrs}
+Return a \class{Request} or \code{None} in response to a redirect.
+This is called by the default implementations of the
+\code{http_error_30x()} methods when a redirection is received from
+the server.  If a redirection should take place, return a new
+\class{Request} to allow \code{http_error_30x()} to perform the
+redirect.  Otherwise, raise \exception{HTTPError} if no other
+\class{Handler} should try to handle this URL, or return \code{None}
+if you can't but another \class{Handler} might.
+
+\note{The default implementation of this method does not strictly
+ follow \rfc{2616}: it allows automatic 302 redirection of POST
+ requests, because essentially all HTTP clients do this.}
+
+\end{methoddesc}
+
 
 \begin{methoddesc}[HTTPRedirectHandler]{http_error_301}{req,
                                                   fp, code, msg, hdrs}
 Redirect to the \code{Location:} URL.  This method is called by
 the parent \class{OpenerDirector} when getting an HTTP
-permanent-redirect response.
+`moved permanently' response.
 \end{methoddesc}
 
 \begin{methoddesc}[HTTPRedirectHandler]{http_error_302}{req,
                                                   fp, code, msg, hdrs}
 The same as \method{http_error_301()}, but called for the
-temporary-redirect response.
+`found' response.
 \end{methoddesc}
 
+\begin{methoddesc}[HTTPRedirectHandler]{http_error_303}{req,
+                                                  fp, code, msg, hdrs}
+The same as \method{http_error_301()}, but called for the
+`see other' redirect response.
+\end{methoddesc}
 
 \subsection{ProxyHandler Objects \label{proxy-handler}}
 

Lib/urllib.py

@@ -586,6 +586,10 @@ def http_error_301(self, url, fp, errcode, errmsg, headers, data=None):
         """Error 301 -- also relocated (permanently)."""
         return self.http_error_302(url, fp, errcode, errmsg, headers, data)
 
+    def http_error_303(self, url, fp, errcode, errmsg, headers, data=None):
+        """Error 303 -- also relocated (essentially identical to 302)."""
+        return self.http_error_302(url, fp, errcode, errmsg, headers, data)
+
     def http_error_401(self, url, fp, errcode, errmsg, headers, data=None):
         """Error 401 -- authentication required.
         See this URL for a description of the basic authentication scheme:

Lib/urllib2.py

@@ -11,8 +11,8 @@
 Handlers needed to open the requested URL.  For example, the
 HTTPHandler performs HTTP GET and POST requests and deals with
 non-error returns.  The HTTPRedirectHandler automatically deals with
-HTTP 301 & 302 redirect errors, and the HTTPDigestAuthHandler deals
-with digest authentication.
+HTTP 301, 302, 303 and 307 redirect errors, and the HTTPDigestAuthHandler
+deals with digest authentication.
 
 urlopen(url, data=None) -- basic usage is that same as original
 urllib.  pass the url and optionally data to post to an HTTP URL, and
@@ -207,6 +207,12 @@ def __getattr__(self, attr):
                 return getattr(self, attr)
         raise AttributeError, attr
 
+    def get_method(self):
+        if self.has_data():
+            return "POST"
+        else:
+            return "GET"
+
     def add_data(self, data):
         self.data = data
 
@@ -402,6 +408,26 @@ def http_error_default(self, req, fp, code, msg, hdrs):
         raise HTTPError(req.get_full_url(), code, msg, hdrs, fp)
 
 class HTTPRedirectHandler(BaseHandler):
+    def redirect_request(self, req, fp, code, msg, headers):
+        """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.
+
+        """
+        if (code in (301, 302, 303, 307) and req.method() in ("GET", "HEAD") or
+            code in (302, 303) and req.method() == "POST"):
+            # Strictly (according to RFC 2616), 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.
+            return Request(newurl, headers=req.headers)
+        else:
+            raise HTTPError(req.get_full_url(), code, msg, hdrs, 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
@@ -418,7 +444,11 @@ def http_error_302(self, req, fp, code, msg, headers):
         # 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 = Request(newurl, req.get_data(), req.headers)
+        new = self.redirect_request(req, fp, code, msg, headers)
+        if new is None:
+            return
+
+        # loop detection
         new.error_302_dict = {}
         if hasattr(req, 'error_302_dict'):
             if len(req.error_302_dict)>10 or \
@@ -435,7 +465,7 @@ def http_error_302(self, req, fp, code, msg, headers):
 
         return self.parent.open(new)
 
-    http_error_301 = http_error_302
+    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" \