proof of concept for tweet downloading.

.gitignore

@@ -1 +1,4 @@
 .pyenv/*
+keys*
+users*
+*_tweets*

tweet_downloader.py

@@ -0,0 +1,81 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+# 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 csv
+from time import sleep
+
+
+def get_all_tweets(screen_name):
+    #Twitter only allows access to a users most recent 3240 tweets with this method
+    with open('keys.txt', 'r') as f:
+        #Twitter API credential
+        consumer_key = f.readline().rstrip()
+        consumer_secret = f.readline().rstrip()
+        access_key = f.readline().rstrip()
+        access_secret = f.readline().rstrip()
+
+    #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,tweet_mode = 'extended')
+
+    #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 and len(alltweets) < 3000:
+        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 = []
+    for tweet in alltweets:
+        try: 
+            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')])
+        except:
+            try: 
+                outtweets.append([tweet.id_str, tweet.created_at, ('RT @' in tweet.full_text), tweet.full_text.encode("utf-8"), tweet.entities.get('hashtags'), tweet.entities.get('user_mentions')])
+            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')])
+
+    #write the csv	
+    with open('%s_tweets.csv' % screen_name, 'w') as f:
+        writer = csv.writer(f)
+        writer.writerow(["id","created_at","retweet","text","hashtags","user_mentions"])
+        writer.writerows(outtweets)
+
+    pass
+
+
+if __name__ == '__main__':
+    #pass in the username of the account you want to download
+    counter = 0
+    with open("users.txt", "r") as f:
+        for line in f:
+            get_all_tweets(line.rstrip())
+            counter = counter + 1
+            if (counter % 5) == 0:
+                sleep(15*60)