uFynMBNj

1import twitter,json,csv
2
3CONSUMER_KEY = 'PZBQNWFthc0kExKvCascYvwFr' #my consumer key
4CONSUMER_SECRET = 'E4IwsQdZPMF1MYCWbTcJLcbFy9mXmD3CI0zNtTd39CWim2XjHP' #my consumer secret 
5OAUTH_TOKEN = '1365237002-6XENowGxqc0I0epaBjROPu9kBfFSlHW1BNYtDhV' #my oauth token 
6OAUTH_TOKEN_SECRET = 'uN0ocsmOt9Mo0DBUhOlOF5DddvQ8DIiQpAkz1safCmEPr' #my token secret 
7
8auth = twitter.oauth.OAuth(OAUTH_TOKEN, OAUTH_TOKEN_SECRET,
9                           CONSUMER_KEY, CONSUMER_SECRET)
10
11twitter_api = twitter.Twitter(auth=auth)
12
13# setup a file to write to
14csvfile = open('XXX9.csv', 'w')
15csvwriter = csv.writer(csvfile, delimiter='|')
16
17#  heres a function that takes out characters that can break
18#  our import into Excel and replaces them with spaces
19#  it also does the unicode bit
20def getVal(val):
21    clean = ""
22    if val:
23        val = val.replace('|', ' ')
24        val = val.replace('\n', ' ')
25        val = val.replace('\r', ' ')
26        clean = val.encode('utf-8')
27    return clean
28
29retweet_indicator = "RT".encode('utf-8', 'ignore').decode('utf-8')
30
31q = "giletsjaunes" # Comma-separated list of terms can go here
32print 'Filtering the public timeline for track="%s"' % (q,)
33
34twitter_stream = twitter.TwitterStream(auth=twitter_api.auth)
35
36stream = twitter_stream.statuses.filter(track=q)
37
38for tweet in stream:
39
40    if tweet['truncated']:
41        tweet_text = tweet['extended_tweet']['full_text']
42### that's the bit that I changed:
43    if 'retweeted_status' in tweet: #checking whether the tweet is a retweet
44        if 'extended_tweet' in tweet['retweeted_status']:
45            user_text = tweet['retweeted_status']['user']
46            [x.encode('utf-8') for x in user_text]
47            retweet_text = tweet['retweeted_status']['extended_tweet']['full_text']
48            [x.encode('utf-8') for x in retweet_text]
49            # tweet_text =  "RT ".join(tweet['retweeted_status']['user'], tweet['retweeted_status']['text']))
50            tweet_text = "RT " + tweet['retweeted_status']['user']['screen_name'] + tweet['retweeted_status']['extended_tweet']['full_text']
51
52        else:
53            tweet_text = tweet['text']
54    else:
55        tweet_text = tweet['text']
56    # write the values to file
57    csvwriter.writerow([
58        tweet['created_at'],
59        getVal(tweet['user']['screen_name']),
60        getVal(tweet_text),
61        getVal(tweet['user']['location']),
62        getVal(tweet['source']),
63        tweet['user']['statuses_count'],
64        tweet['user']['followers_count'],
65        tweet['user']['friends_count'],
66        tweet['user']['created_at'],
67        ])
68
69    # print something to the screen, mostly so we can see what is going on...
70    print tweet['user']['screen_name'].encode('utf-8'), tweet['text'].encode('utf-8')
71    # if 'retweeted_status' in tweet:
72    #     if 'extended_tweet' in tweet['retweeted_status']:
73    #
74    #     # print json.dumps(tweet) + "||||||||||||||"
75    #         print tweet['retweeted_status']['extended_tweet']['full_text']