#
# This is a quick and dirty script to pull the most likely url and description
# for a list of terms.  Here's how you use it:
#
# python term2url.py < {a txt file with a list of terms} > {a tab delimited file of results}
#
# You'll must install the simpljson module to use it 
#
import urllib
import urllib2
import simplejson
import sys

# Read the terms we want to convert into URL from info redirected from the command line
terms = sys.stdin.readlines()

for term in terms:

   # Define the query to pass to Google Search API
   query = urllib.urlencode({'q' : term.rstrip("\n")})
   url = "http://ajax.googleapis.com/ajax/services/search/web?v=1.0&%s" % (query)

   # Fetch the results and convert to JSON format
   search_results = urllib2.urlopen(url)
   json = simplejson.loads(search_results.read())

   # Process the results by pulling the first record, which has the best match
   results = json['responseData']['results']
   for r in results[:1]:
      url = r['url']
      desc = r['content'].encode('ascii', 'replace')

   # Print the results to stdout.  Use redirect to capture the output
   print "%s\t%s\t%s" % (term.rstrip("\n"), url, desc)