mining_infoatac.py

import tweepy
from tweepy import OAuthHandler
import re
 
consumer_key = 'CONSUMER_KEY'
consumer_secret = 'CONSUMER_SECRET'
access_token = 'ACCESS_TOKEN'
access_secret = 'ACCESS_SECRET'
 
auth = OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_secret)
 
api = tweepy.API(auth)
regexp = re.compile(r'guast[a|e|i|o]')

def findWholeWord(r,w):
    if r.search(w) is not None:
        return True
    else:
        return False

username = 'infoatac'
tweet_cursor = tweepy.Cursor(api.user_timeline,id=username)
tweet_nr = 1000
items = tweet_cursor.items(tweet_nr)
tweets = open('tweet.txt',"w")
matches = open('matches.txt',"w")
match_counter = 0
counter = 0
with open('tweet.txt','w') as tweets:
    with open('matches.txt','w') as matches:
        for item in items:
            tweets.write("%s - %s\n" % (item.created_at, item.text))
            counter = counter + 1
            if findWholeWord(regexp,item.text):
                matches.write("%s) %s - %s\n" % (match_counter, item.created_at, item.text))
                match_counter = match_counter+1

matches.close()
tweets.close()
print(match_counter/counter)