#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""

This script accepts Domain, Search String and Google Locale arguments, then returns
which Search String results page for the Google Locale the Domain appears on.

Usage example:
rankcheck {domain} {searchstring} {locale}

Output example:
rankcheck rassware.de 'BMW 325e' de
The domain 'rassware.de' is listed in position 2 (page 1) for the search 'BMW 325e' on google.de
 
"""
 
__author__    = "Christian Raßmann (info@rassware.de)"
__version__   = "$Revision: 1.0"
__date__      = "$Date: 2009-09-02 22:44:24"
 
import sys, re, urllib2
 
# check if all arguments were specified and whether help was requested:
if len(sys.argv) < 4:
    if len(sys.argv) == 1:
        print "usage: rankcheck {finddomain} {keyphrase} {topleveldomain}";
        print "`rankcheck --help' for more information."
        sys.exit()
    elif sys.argv[1] == '--help':
        print "usage: rankcheck {finddomain} {keyphrase} {topleveldomain}"
        print "Check the Search String page ranking of a Domain on a specific Google Locale"
        print "\nExample: rankcheck rassware.de 'BMW 325e' de"
        print "\nReport bugs to <info@rassware>."
        sys.exit()
    else:
        print "usage: rankcheck DOMAIN SEARCHSTRING LOCALE";
        print "`rankcheck --help' for more information."
        sys.exit()

# some initial setup:
useragent = 'Mozilla/4.0 (compatible; MSIE 6.0)'
finddomain = sys.argv[1]
keyphrase = sys.argv[2]
keyphrase_urlcode = sys.argv[2].replace(' ','+')
topleveldomain = sys.argv[3]

urlstr = 'http://www.google.' + topleveldomain + '/search?hl=' + topleveldomain + '&q=' + keyphrase_urlcode
html = ''
for i in range(0, 10):
    requesturl = urlstr + '&start=' + str(i * 10)
    #print requesturl
    url=urllib2.Request(requesturl)
    url.add_header('User-Agent',useragent)
    html = html + urllib2.urlopen(url).read()
result = 0
counter = 0
url=unicode(r'(<h3 class=r><a href=")((https?):((//))+[\w\d:#@%/;$()~_?\+-=\\\.&]*).([^)]*)')
for google_result in re.finditer(url, html):
    #print google_result.group()
    this_url = google_result.group()
    this_url = this_url[21:]
    google_url_regex = re.compile("((https?):((//))+([\w\d:#@%/;$()~_?\+-=\\\.&])*" + finddomain + "+([\w\d:#@%/;$()~_?\+-=\\\.&])*)")
    google_url_regex_result = google_url_regex.match(this_url)
    if google_url_regex_result:
        #result = re.search("'\d+'", google_result.group())
        #result = int(result.group().replace('\'',''))
        result = counter
        break
    counter += 1

# show results
if result == 0:
    print "The domain '" + finddomain + "' wasn't listed in the first 10 pages for the search '" + keyphrase + "' on google." + topleveldomain
else:
    print "The domain '" + finddomain + "' is listed in position " + str(result) + " (page " + str((result / 10) + 1) + ") for the search '" + keyphrase + "' on google." + topleveldomain