Last active
October 15, 2018 01:30
-
-
Save palewire/4666689 to your computer and use it in GitHub Desktop.
A quick Python script for archiving a user's tweets via the Twitter API. Only goes back as far as Twitter allows. Doesn't include RTs by default.
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
import re | |
import os | |
import csv | |
import codecs | |
import twitter | |
import cStringIO | |
from pprint import pprint | |
from dateutil.parser import parse as dateparse | |
class UnicodeWriter: | |
""" | |
A CSV writer which will write rows to CSV file "f", | |
which is encoded in the given encoding. | |
""" | |
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds): | |
# Redirect output to a queue | |
self.queue = cStringIO.StringIO() | |
self.writer = csv.writer(self.queue, dialect=dialect, **kwds) | |
self.stream = f | |
self.encoder = codecs.getincrementalencoder(encoding)() | |
def writerow(self, row): | |
self.writer.writerow([s.encode("utf-8") for s in row]) | |
# Fetch UTF-8 output from the queue ... | |
data = self.queue.getvalue() | |
data = data.decode("utf-8") | |
# ... and reencode it into the target encoding | |
data = self.encoder.encode(data) | |
# write to the target stream | |
self.stream.write(data) | |
# empty queue | |
self.queue.truncate(0) | |
def writerows(self, rows): | |
for row in rows: | |
self.writerow(row) | |
class TwitterClient(object): | |
""" | |
A minimal Twitter client. | |
""" | |
def __init__(self, username): | |
self.username = username | |
self.api = twitter.Api( | |
consumer_key='your', | |
consumer_secret='shiz', | |
access_token_key='goes', | |
access_token_secret='here' | |
) | |
def __getattr__(self): | |
return TwitterClient(self.username) | |
def __repr__(self): | |
return "<TwitterClient: %s>" % self.username | |
def pull(self): | |
outfile = UnicodeWriter(open("%s.csv" % self.username, "w")) | |
keep_going = True | |
max_id = None | |
page = 1 | |
big_total = 0 | |
while keep_going: | |
tweet_list = list(self.api.GetUserTimeline(self.username, max_id=max_id)) | |
big_total += len(tweet_list) | |
print "Fetched page %s, Found %s tweets, Total up to %s" % (page, len(tweet_list), big_total) | |
if len(tweet_list) == 0: | |
print "No more tweets" | |
keep_going = False | |
break | |
max_id = tweet_list[-1].id | |
page += 1 | |
tweet_list.pop(0) | |
[outfile.writerow(map(unicode, [t.id, dateparse(t.created_at), t.text])) | |
for t in tweet_list] | |
if __name__ == '__main__': | |
client = TwitterClient("palewire") | |
client.pull() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment