Last active
February 21, 2019 15:03
-
-
Save pytholabsbot1/517ecdd84421de9f973ea6470bafd2a6 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
import sys | |
import jsonpickle | |
import os | |
searchQuery = 'brexit' # this is what we're searching for | |
maxTweets = 1000 # Some arbitrary large number | |
tweetsPerQry = 100 # this is the max the API permits | |
fName = 'tweets.txt' # We'll store the tweets in a text file. | |
# If results from a specific ID onwards are reqd, set since_id to that ID. | |
# else default to no lower limit, go as far back as API allows | |
sinceId = None | |
places = [] | |
time = [] | |
tweets = [] | |
# If results only below a specific ID are, set max_id to that ID. | |
# else default to no upper limit, start from the most recent tweet matching the search query. | |
max_id = -1 | |
tweetCount = 0 | |
print("Downloading max {0} tweets".format(maxTweets)) | |
with open(fName, 'w') as f: | |
while tweetCount < maxTweets: | |
try: | |
if (max_id <= 0): | |
if (not sinceId): | |
new_tweets = api.search(q=searchQuery, count=tweetsPerQry) | |
else: | |
new_tweets = api.search(q=searchQuery, count=tweetsPerQry, | |
since_id=sinceId) | |
else: | |
if (not sinceId): | |
new_tweets = api.search(q=searchQuery, count=tweetsPerQry, | |
max_id=str(max_id - 1)) | |
else: | |
new_tweets = api.search(q=searchQuery, count=tweetsPerQry, | |
max_id=str(max_id - 1), | |
since_id=sinceId) | |
if not new_tweets: | |
print("No more tweets found") | |
break | |
for tweet in new_tweets: | |
#add data to lists | |
#1. creted at | |
time.append((tweet.created_at.month,tweet.created_at.year)) | |
#location of user | |
places.append(tweet.user.location) | |
#text of tweet | |
tweets.append(tweet.text) | |
f.write(jsonpickle.encode(tweet.text, unpicklable=False) +'\n') | |
tweetCount += len(new_tweets) | |
print("Downloaded {0} tweets".format(tweetCount)) | |
max_id = new_tweets[-1].id | |
except tweepy.TweepError as e: | |
# Just exit if any error | |
print("some error : " + str(e)) | |
break | |
print ("Downloaded {0} tweets, Saved to {1}".format(tweetCount, fName)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment