С рандомной страницы баша выдирает и выводит посты с рейтингом больше 10 000

bash_parser.py

# -*- coding: utf-8 -*-
'''
Created on 28.09.2012

Created by pokidovea([email protected])
'''

import lxml.html
import urllib2
from StringIO import StringIO
import gzip

request = urllib2.Request('http://bash.im/random')
request.add_header('Accept-encoding', 'gzip')
request.add_header('Cache-Control', 'no-cache')
request.add_header('Pragma', 'no-cache')
request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; rv:18.0) Gecko/20100101 Firefox/18.0')
response = urllib2.urlopen(request)
if response.info().get('Content-Encoding') == 'gzip':
    buf = StringIO(response.read())
    f = gzip.GzipFile(fileobj=buf)
    data = f.read()

doc = lxml.html.document_fromstring(data)
for quote in doc.cssselect('.quote'):
    if len(quote.cssselect('.rating')) > 0 and \
        quote.cssselect('.rating')[0].text.isdigit() and \
            int(quote.cssselect('.rating')[0].text) > 10000:

        text_iterator = quote.cssselect('div.text')[0].itertext()
        try:
            while 1:
                print text_iterator.next().encode('CP1252').decode('cp1251')
        except StopIteration:
            print u'\n++++++++++++++\n'