Skip to content

Instantly share code, notes, and snippets.

@revox

revox/tweetatron_tags_style.py

Last active December 3, 2020 14:22
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save revox/11c6160b2a5fc9af3463687af713bd11 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save revox/11c6160b2a5fc9af3463687af713bd11 to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. revox revised this gist Nov 17, 2020. 1 changed file with 1 addition and 1 deletion.
    2 changes: 1 addition & 1 deletion tweetatron_tags_style.py
    View file
    Original file line number Diff line number Diff line change
    @@ -57,7 +57,7 @@ def clean(val):

    geo_coordinates = ""
    if tweet['coordinates']:
    geo_coordinates = tweet['coordinates']['coordinates'][1] + ',' + weet['coordinates']['coordinates'][0]
    geo_coordinates = tweet['coordinates']['coordinates'][1] + ',' + tweet['coordinates']['coordinates'][0]

    csvwriter.writerow([tweet['id_str'],
    tweet['created_at'],
  2. revox created this gist Nov 17, 2020.
    82 changes: 82 additions & 0 deletions tweetatron_tags_style.py
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,82 @@
    import twitter, json, csv

    # == OAuth Authentication ==
    CONSUMER_KEY = ''
    CONSUMER_SECRET = ''
    OAUTH_TOKEN = ''
    OAUTH_TOKEN_SECRET = ''

    auth = twitter.oauth.OAuth(OAUTH_TOKEN,
    OAUTH_TOKEN_SECRET,
    CONSUMER_KEY,
    CONSUMER_SECRET)
    twitter_api = twitter.Twitter(auth=auth, retry=True)

    csvfile = open('brexit.csv', 'w')
    csvwriter = csv.writer(csvfile,delimiter ='|')

    q = "#brexit"

    # clean up our data so we can write unicode to CSV
    def clean(val):
    clean = ""
    if val:
    val = val.replace('|', ' ')
    val = val.replace('\n', ' ')
    val = val.replace('\r', ' ')
    clean = val
    return clean

    print ('Filtering the public timeline for keyword="%s"' % (q))
    twitter_stream = twitter.TwitterStream(auth=twitter_api.auth)
    stream = twitter_stream.statuses.filter(track=q)


    for tweet in stream:
    # print (json.dumps(tweet, indent=1)) # for debugging purposes

    if tweet['truncated']:
    tweet_text = tweet['extended_tweet']['full_text']
    else:
    tweet_text = tweet['text']

    if 'retweeted_status' in tweet:
    rt_prefix = 'RT @' + tweet['retweeted_status']['user']['screen_name'] + ': '
    if tweet['retweeted_status']['truncated']:
    tweet_text = tweet['retweeted_status']['extended_tweet']['full_text']
    else:
    tweet_text = tweet['retweeted_status']['text']
    tweet_text = rt_prefix + tweet_text
    if ('quoted_status' in tweet):
    quote_suffix = tweet['quoted_status_permalink']['url']
    tweet_text = tweet_text + ' ' + quote_suffix

    if ('quoted_status' in tweet) and ('retweeted_status' not in tweet) :
    quote_suffix = tweet['quoted_status_permalink']['url']
    tweet_text = tweet_text + ' ' + quote_suffix

    geo_coordinates = ""
    if tweet['coordinates']:
    geo_coordinates = tweet['coordinates']['coordinates'][1] + ',' + weet['coordinates']['coordinates'][0]

    csvwriter.writerow([tweet['id_str'],
    tweet['created_at'],
    clean(tweet['user']['screen_name']),
    clean(tweet_text),
    tweet['user']['created_at'],
    geo_coordinates,
    tweet['user']['lang'],
    tweet['in_reply_to_user_id_str'],
    tweet['in_reply_to_screen_name'],
    tweet['user']['id_str'],
    tweet['in_reply_to_status_id_str'],
    clean(tweet['source']),
    tweet['user']['profile_image_url_https'],
    tweet['user']['followers_count'],
    tweet['user']['friends_count'],
    tweet['user']['statuses_count'],
    clean(tweet['user']['location']),
    tweet['entities']]
    )

    print('text: ', tweet_text) # just so we can see it runnning