-
-
Save lamthuyvo/44e682f39021c18d28bdd8133b934782 to your computer and use it in GitHub Desktop.
A script to download all of a user's tweets into a csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# encoding: utf-8 | |
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 | you can comment out data you don't need | |
outtweets = [[tweet.id_str, | |
tweet.created_at, | |
tweet.favorite_count, | |
tweet.retweet_count, | |
tweet.retweeted, | |
tweet.source.encode("utf-8"), | |
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", | |
"favorites", | |
"retweets", | |
"retweeted", | |
"source", | |
"text"]) | |
writer.writerows(outtweets) | |
pass | |
if __name__ == '__main__': | |
#pass in the username of the account you want to download | |
get_all_tweets("potus") |
The code works great! Thank you but the tweeps are cut short.
How I can I modify the code by inserting tweet_mode="extended"?
It didnt work for me. Is this a running code?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thank you for this code, it is really worked.
I have a question, How can i get all tweets since this code shows approximately 3000 tweets only, and it seems that the code support multi-languages by using (Utf-8) but in the CSV file it does not support any language except English, So how can I fix this?
Thank you,