todatasudata · February 19, 2017 23:17 · Feb 19, 2017 · Feb 19, 2017 · Feb 19, 2017 · Nov 1, 2013
diff --git a/tweet_dumper.py b/tweet_dumper.py
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# forked from https://gist.github.com/yanofsky/5436496
+# forked from https://gist.github.com/yanofsky/5436496 and ported to Python3
 import tweepy #https://github.com/tweepy/tweepy
 import csv
 

diff --git a/tweet_dumper.py b/tweet_dumper.py
@@ -1,14 +1,13 @@
-#!/usr/bin/env python
-# encoding: utf-8
-
+#!/usr/bin/env python3
+# forked from https://gist.github.com/yanofsky/5436496
 import tweepy #https://github.com/tweepy/tweepy
 import csv
 
 #Twitter API credentials
-consumer_key = ""
-consumer_secret = ""
-access_key = ""
-access_secret = ""
+consumer_key = ''
+consumer_secret = ''
+access_key = ''
+access_secret = ''
 
 
 def get_all_tweets(screen_name):
@@ -33,7 +32,7 @@ def get_all_tweets(screen_name):
 
 	#keep grabbing tweets until there are no tweets left to grab
 	while len(new_tweets) > 0:
-		print "getting tweets before %s" % (oldest)
+		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)
@@ -44,20 +43,21 @@ def get_all_tweets(screen_name):
 		#update the id of the oldest tweet less one
 		oldest = alltweets[-1].id - 1
 
-		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	
-	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)
-
+	outtweets = [[tweet.id_str, tweet.created_at, tweet.text] for tweet in alltweets]
+	#write the csv
+	try:
+		with open('%s_tweets.csv' % screen_name, 'a') as f:
+			writer = csv.writer(f)
+			writer.writerow(["id","created_at","text"])
+			writer.writerows(outtweets)
+	except TypeError:
+		pass
 	pass
 
 
 if __name__ == '__main__':
 	#pass in the username of the account you want to download
-	get_all_tweets("J_tsar")
+	get_all_tweets("neuro_skeptic")
diff --git a/tweet_dumper.py b/tweet_dumper.py
@@ -33,7 +33,7 @@ def get_all_tweets(screen_name):
 
 	#keep grabbing tweets until there are no tweets left to grab
 	while len(new_tweets) > 0:
-		print "getting tweets gefore %s" % (oldest)
+		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)

diff --git a/tweet_dumper.py b/tweet_dumper.py
@@ -12,6 +12,7 @@
 
 
 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)

diff --git a/tweet_dumper.py b/tweet_dumper.py
@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # encoding: utf-8
 
-import tweepy
+import tweepy #https://github.com/tweepy/tweepy
 import csv
 
 #Twitter API credentials

diff --git a/tweet_dumper.py b/tweet_dumper.py
@@ -0,0 +1,62 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+import tweepy
+import csv
+
+#Twitter API credentials
+consumer_key = ""
+consumer_secret = ""
+access_key = ""
+access_secret = ""
+
+
+def get_all_tweets(screen_name):
+
+	#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 gefore %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("J_tsar")