Python Google Server

[fuzzyman at gmail.com]

I've hacked together a 'GoogleCacheServer'. It is based on
SimpleHTTPServer. Run the following script (hopefully google groups
won't mangle the indentation) and set your browser proxy settings to
'localhost:8000'. It will let you browse the internet using google's
cache. Obviously you'll miss images, javascript, css files, etc.

See the world as google sees it !

(This is actually an 'inventive' short term measure to get round a
restrictive internet policy at work :-) I'll probably put it in the
Python Cookbook as it's quite fun (so if line lengths or indentation is
mangled here, try there). Tested on Windows XP, with Python 2.3 and IE.



# Copyright Michael Foord, 2004 & 2005.
# Released subject to the BSD License
# Please see http://www.voidspace.org.uk/documents/BSD-LICENSE.txt

# For information about bugfixes, updates and support, please join the
Pythonutils mailing list.
# http://voidspace.org.uk/mailman/listinfo/pythonutils_voidspace.org.uk
# Comments, suggestions and bug reports welcome.
# Scripts maintained at http://www.voidspace.org.uk/python/index.shtml
# E-mail fuzzyman at voidspace.org.uk

import google
import BaseHTTPServer
import shutil
from StringIO import StringIO
import urlparse

__version__ = '0.1.0'


"""
This is a simple implementation of a server that fetches web pages
from the google cache.

It lets you explore the internet from your browser, using the google
cache.

Run this script and then set your browser proxy settings to
localhost:8000

Needs google.py (and a google license key).
See http://pygoogle.sourceforge.net/
and http://www.google.com/apis/
"""

cached_types = ['txt', 'html', 'htm', 'shtml', 'shtm', 'cgi', 'pl',
'py']
google.setLicense(google.getLicense())
googlemarker = '''<i>Google is not affiliated with the authors of this
page nor responsible for its
content.</i></font></center></td></tr></table></td></tr></table>\n<hr>\n'''
markerlen = len(googlemarker)

class googleCacheHandler(BaseHTTPServer.BaseHTTPRequestHandler):
    server_version = "googleCache/" + __version__
    cached_types = cached_types
    googlemarker = googlemarker
    markerlen = markerlen

    def do_GET(self):
        f = self.send_head()
        if f:
            self.copyfile(f, self.wfile)
            f.close()

    def send_head(self):
        """Common code for GET and HEAD commands.

        This sends the response code and MIME headers.

        Return value is either a file object (which has to be copied
        to the outputfile by the caller unless the command was HEAD,
        and must be closed by the caller under all circumstances), or
        None, in which case the caller has nothing further to do.

        """
        print self.path
        url = urlparse.urlparse(self.path)[2]
        dotloc = url.find('.') + 1
        if dotloc and url[dotloc:] not in self.cached_types:
            return None     # not a cached type - don't even try

        thepage = google.doGetCachedPage(self.path)
        headerpos = thepage.find(self.googlemarker)
        if headerpos != -1: # remove the google header
            pos = self.markerlen + headerpos
            thepage = thepage[pos:]

        f = StringIO(thepage)

        self.send_response(200)
        self.send_header("Content-type", 'text/html')
        self.send_header("Content-Length", str(len(thepage)))
        self.end_headers()
        return f

    def copyfile(self, source, outputfile):
        shutil.copyfileobj(source, outputfile)


def test(HandlerClass = googleCacheHandler,
         ServerClass = BaseHTTPServer.HTTPServer):
    BaseHTTPServer.test(HandlerClass, ServerClass)


if __name__ == '__main__':
    test()