Adriano10 Adriano10 - 1 month ago 15
Python Question

Filter tweets before saving into csv

The below part of code fetches all tweets for a specific user and stores them into a csv file. I want to filter the tweets before storing them and store only those that contain the term "car". How can i do it?

import tweepy #https://github.com/tweepy/tweepy
import csv

#Twitter API credentials
consumer_key = ""
consumer_secret = ""
access_key = ""
access_secret = ""


def get_all_tweets(screen_name):
#Twitter only allows access to a users most recent 3240 tweets with this method

#authorize twitter, initialize tweepy
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_key, access_secret)
api = tweepy.API(auth)



#initialize a list to hold all the tweepy Tweets
alltweets = []

#make initial request for most recent tweets (200 is the maximum allowed count)
new_tweets = api.user_timeline(screen_name = screen_name,count=200)

#save most recent tweets
alltweets.extend(new_tweets)

#save the id of the oldest tweet less one
oldest = alltweets[-1].id - 1

#keep grabbing tweets until there are no tweets left to grab
while len(new_tweets) > 0:
print "getting tweets before %s" % (oldest)

#all subsiquent requests use the max_id param to prevent duplicates
new_tweets = api.user_timeline(screen_name = screen_name,count=200,max_id=oldest)

#save most recent tweets


alltweets.extend(new_tweets)

#update the id of the oldest tweet less one
oldest = alltweets[-1].id - 1

print "...%s tweets downloaded so far" % (len(alltweets))

#transform the tweepy tweets into a 2D array that will populate the csv
outtweets = [[tweet.id_str, tweet.created_at, tweet.text.encode("utf-8")]for tweet in alltweets]

#write the csv
with open('%s_tweets.csv' % screen_name, 'wb') as f:
writer = csv.writer(f)
writer.writerow(["id","created_at","text"])
writer.writerows(outtweets)

pass


if __name__ == '__main__':
#pass in the username of the account you want to download
get_all_tweets("owo_batista")

Answer

I would add an if-statement to the end of your outtweets list comprehension:

outtweets = [[tweet.id_str, tweet.created_at, tweet.text.encode("utf-8")]for tweet in alltweets if 'car' in tweet.text.encode("utf-8")]