How can I prevent gae from scrambling gzipped xml feeds?

Question

I have a script in GAE that requests an XML feed from a partner, which is usually 40 MB, but only 5 MB gzipped. GAE automatically unpacks this content and throws an error that the answer is too large:

The HTTP response was too large: 46677241. Limit: 33554432.

A script is a setting for self-compressing the response itself. How can I stop the GAE from getting in the way and breaking down?

Here is the response header from my partner:

HTTP/1.0 200 OK
Expires: Wed, 27 Jun 2012 05:42:07 GMT
Cache-Control: max-age=10368000
Content-Type: application/x-gzip
Accept-Ranges: bytes
Last-Modified: Wed, 22 Feb 2012 11:06:09 GMT
Content-Length: 5263323
Date: Tue, 28 Feb 2012 05:42:07 GMT
Server: lighttpd
X-Cache: MISS from static01
X-Cache-Lookup: MISS from static01:80
Via: 1.0 static01:80 (squid)

Answer 1

, XML, , HTTP- (.. GRE URL Fetch) gzipping. , " ".

, gzipped-, Accept-Encoding: gzip URL.