Save tweets containing certain keywords from the twitter Straming API to MongoDB

save_tweets.py

import tweetstream
from pymongo import MongoClient

# look for these words:
WORDS = ['word1', 'word2']

TWITTER_USER = ""
TWITTER_PASS = ""

MONGO_DB = 'tweetstream'
MONGO_COLLECTION = 'tweets'


if __name__ == '__main__':
    connection = MongoClient()
    db = connection[MONGO_DB]
    collection = db[MONGO_COLLECTION]
    collection.ensure_index('id', unique=True)
    try:
        with tweetstream.FilterStream(TWITTER_USER, TWITTER_PASS, track=WORDS) as stream:
            for tweet in stream:
                print "From: %s (%d)\n%s" % (
                      tweet["user"]["screen_name"], stream.count, tweet['text'])
                collection.update({'id': tweet['id']}, tweet, upsert=True)
    except tweetstream.ConnectionError, e:
        print "Disconnected from twitter. Reason:", e.reason