gstats.py

import re
import json
import urllib

RE_FIRST_PARENTHESIS = re.compile('^([^\{]*){([^}]*)}(.*)$')

def parse_parenthesis(string):
    """
    >>> parse_parenthesis('aaa {bbb,ccc} ddd')
    ['aaa bbb ddd', 'aaa ccc ddd']
    >>> parse_parenthesis('aaa {bbb,ccc} {ddd,eee}')
    ['aaa bbb ddd', 'aaa bbb eee', 'aaa ccc ddd', 'aaa ccc eee']
    >>> parse_parenthesis('no parenthesis')
    ['no parenthesis']
    """
    match = RE_FIRST_PARENTHESIS.match(string)
    if match:
        (sa, sb, sc) = match.groups()
        return [parsed
                for w in sb.split(',')
                for parsed in parse_parenthesis(sa + w + sc)]
    else:
        return [string]

def get_result_count(searchfor):
    query = urllib.urlencode({'q': searchfor})
    url = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&%s' % query
    search_response = urllib.urlopen(url)
    search_results = search_response.read()
    results = json.loads(search_results)
    return results['responseData']['cursor']['estimatedResultCount']

def main(patterns):
    parsed_patterns = [
        '"%s"' % parsed for p in patterns for parsed in parse_parenthesis(p)]
    result_count_list = [
        get_result_count(parsed) for parsed in parsed_patterns]
    count_width = max([len(cont) for cont in result_count_list])

    for (count, parsed) in zip(result_count_list, parsed_patterns):
        print count.rjust(count_width), parsed

if __name__ == '__main__':
    import sys
    main(sys.argv[1:])

usage

$ python gstats.py 'search{, on, in} the web'
25600000 "search the web"
   22600 "search on the web"
    4270 "search in the web"