filtering_proxy.py

#!/usr/bin/env python
"""
Quick and dirty filtering HTTP proxy using only Python stdlib

Change REMOTE_HOST below and adjust the regexp to suit your needs
"""

from BaseHTTPServer import BaseHTTPRequestHandler, HTTPServer
from urllib import urlopen, basejoin
import re

class FilteringProxy(BaseHTTPRequestHandler):
    """
    Template to easily allow filtering HTTP responses
    """
    
    def do_GET(self):
        remote = urlopen(basejoin("http://REMOTE_HOST/", self.path))

        self.send_response(remote.code, 'OK')
        for k, v in remote.info().items():
            self.send_header(k, v)
        self.end_headers()
        
        content = remote.read()
        content = re.sub(
            r'<meta http-equiv="Content-Type" content="text/html; charset=windows-1252">',
            "",
            content
        )

        self.wfile.write(content)

    @staticmethod
    def serve_forever():
        s = HTTPServer(('', 8080), FilteringProxy).serve_forever()

if __name__ == "__main__":
    FilteringProxy.serve_forever()