Filtering Tweets By Location

Question

I'm trying to modify this script to only save the JSONs of tweets that have a location attached to them and am running into an issue with Python where checking that something isn't null doesn't seem to work. Has Key isn't working correctly, because they all have the key, most of them are just 'null'. Is not None isn't working because Python thinks null and None are different and checking it as text to not be "null" also didn't work. Does anyone have a clever idea on how to solve this?

from tweepy.streaming import StreamListener
from tweepy import OAuthHandler
from tweepy import Stream
import pymongo
import tweepy
import json


#Variables that contains the user credentials to access Twitter API 
access_key = '' #redacted for privacy and such
access_secret = ''
consumer_key = ''
consumer_secret = ''

#Runs auth to Twitter API
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_key, access_secret)
api = tweepy.API(auth)


#This is a basic listener that will print incoming data to stdout
class StdOutListener(StreamListener):

    def on_data(self, data):
        print data
        return True

    def on_error(self, status):
        print status


#Customizes the stream and saves text and lang to databases 
class CustomStreamListener(tweepy.StreamListener):
    def __init__(self, api):
        self.api = api
        super(tweepy.StreamListener, self).__init__()
        self.db = pymongo.MongoClient('localhost', 27017).crime



    def on_data(self, data):
        jd = json.loads(data)
        if jd.has_key('coordinates') :
            self.db.tweets.insert( { 'text' : jd['text'], 'coordinates' : jd['coordinates'], 'lang' : jd['lang'] } )




    def on_error(self, status_code):
        return True # Don't kill the stream

    def on_timeout(self):
        return True # Don't kill the stream

#Calls on StreamListerner and provides specifications of tracking
l = tweepy.streaming.Stream(auth, CustomStreamListener(api))
l.filter(track=['guns'])

Answer 1

You could try something like checking the length of the string:

if len( jd['coordinates'] ) > 1:
    self.db.tweets.insert( { 'text' : jd['text'], 'coordinates' : jd['coordinates'], 'lang' : jd['lang'] } )