thisisengland.py

#!/usr/bin/env python

"""
A quick-and-dirty method for grabbing tweets from Twitter retrospectively, using the Search API.

Searches for mentions of "thisisengland" in this instance...
"""

import urllib
import anyjson
import sys

def main():
    url = 'http://search.twitter.com/search.json'
    q = '?q=thisisengland&page=1&rpp=100'
    results = []
    while q:
        sys.stdout.write(str(q))
        request = url + q
        response = urllib.urlopen(request)
        d = response.read()
        response.close()
        o = anyjson.deserialize(d)
        sys.stdout.write(d)
        if o.has_key('results'):
            results.extend(o['results'])
        q = o.get('next_page', None)
        sys.stdout.flush()
    # print results
    return results
        
if __name__ == "__main__":
    results = main()
    output = open('thisisengland.json', 'w')
    output.write(anyjson.serialize(results))
    output.close()