ada/multipub
Archived
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

small progress.

Browse source
This commit is contained in:
Alex Huddleston 2019-02-13 17:33:56 -06:00
parent 3c635464d8
commit de2be0b7af
1 changed files with 20 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
tweet_downloader.py
View file

@ -4,7 +4,7 @@
# Some legacy code I wrote for a project in college. It's ugly and messy. I'll clean it up and repurpose it later. # Some legacy code I wrote for a project in college. It's ugly and messy. I'll clean it up and repurpose it later.
import tweepy #https://github.com/tweepy/tweepy import tweepy #https://github.com/tweepy/tweepy
import csv import json
from time import sleep from time import sleep
@ -23,13 +23,14 @@ def get_all_tweets(screen_name):
api = tweepy.API(auth) api = tweepy.API(auth)
#initialize a list to hold all the tweepy Tweets #initialize a list to hold all the tweepy Tweets
alltweets = [] recent_tweets = []
#make initial request for most recent tweets (200 is the maximum allowed count) #make initial request for most recent tweets (200 is the maximum allowed count)
new_tweets = api.user_timeline(screen_name = screen_name,count=200,tweet_mode = 'extended') new_tweets = api.user_timeline(screen_name = screen_name,count=10,tweet_mode = 'extended')
#save most recent tweets #save most recent tweets
alltweets.extend(new_tweets) recent_tweets.extend(new_tweets)
'''
#save the id of the oldest tweet less one #save the id of the oldest tweet less one
oldest = alltweets[-1].id - 1 oldest = alltweets[-1].id - 1
@ -49,9 +50,10 @@ def get_all_tweets(screen_name):
print("...%s tweets downloaded so far" % (len(alltweets))) print("...%s tweets downloaded so far" % (len(alltweets)))
'''
#transform the tweepy tweets into a 2D array that will populate the csv #transform the tweepy tweets into a 2D array that will populate the csv
outtweets = [] outtweets = []
for tweet in alltweets: for tweet in recent_tweets:
try: try:
if tweet.retweeted or ('RT @' in tweet.text): if tweet.retweeted or ('RT @' in tweet.text):
outtweets.append([tweet.id_str, tweet.created_at, "True", tweet.retweeted_status.text.encode("utf-8"), tweet.entities.get('hashtags'), tweet.entities.get('user_mentions')]) outtweets.append([tweet.id_str, tweet.created_at, "True", tweet.retweeted_status.text.encode("utf-8"), tweet.entities.get('hashtags'), tweet.entities.get('user_mentions')])
@ -61,6 +63,10 @@ def get_all_tweets(screen_name):
except: except:
outtweets.append([tweet.id_str, tweet.created_at, ('RT @' in tweet.text), tweet.text.encode("utf-8"), tweet.entities.get('hashtags'), tweet.entities.get('user_mentions')]) outtweets.append([tweet.id_str, tweet.created_at, ('RT @' in tweet.text), tweet.text.encode("utf-8"), tweet.entities.get('hashtags'), tweet.entities.get('user_mentions')])
for t in outtweets:
print(t[3])
'''
#write the csv #write the csv
with open('%s_tweets.csv' % screen_name, 'w') as f: with open('%s_tweets.csv' % screen_name, 'w') as f:
writer = csv.writer(f) writer = csv.writer(f)
@ -68,7 +74,14 @@ def get_all_tweets(screen_name):
writer.writerows(outtweets) writer.writerows(outtweets)
pass pass
'''
if __name__ == '__main__':
with open('users.txt', 'r') as f:
for l in f:
get_all_tweets(l.rstrip())
'''
if __name__ == '__main__': if __name__ == '__main__':
#pass in the username of the account you want to download #pass in the username of the account you want to download
@ -79,3 +92,5 @@ if __name__ == '__main__':
counter = counter + 1 counter = counter + 1
if (counter % 5) == 0: if (counter % 5) == 0:
sleep(15*60) sleep(15*60)
'''