get_twitter_followings.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import json
import oauth2 # <- pip install oauth2
import time

# Oauth request helper. Mostly copy-pasta from Twitter's docs.
def oauth_req(url, http_method="GET"):
    consumer = oauth2.Consumer(key='YOUR TWITTER API KEY', secret='YOUR TWITTER API SECRET')
    client = oauth2.Client(consumer)
    resp, content = client.request( url, method=http_method)
    return content

twitter_user_ids = ['List', 'Of', 'Peoples', 'IDS']

for i, twid in enumerate(twitter_user_ids):
    # I like status updates, okay?
    print "Working on %d (%d of %d)" % (twid, i+1, len(twitter_user_ids))
    # I've written enough scrapers in my life to know that things will break randomly and
    # for a thousand reasons. Just catch them, tell me what happened, and move on.
    try:
        # Twitter limits the values returned to 5,000. I didn't write pagination code because I'm lazy.
        response = oauth_req("https://api.twitter.com/1.1/friends/ids.json?user_id=%d" % twid)
        obj = json.loads(response)
        # File writing in fear. If I accidentally close the program, I don't want to be left high and dry.
        with open('twitter_ids.txt', 'a') as fo:
            # More status updates.
            print "Found %d users" % len(obj['ids'])
            print ""
            for following_id in obj['ids']:
                # Save both the user and who followed them
                fo.write("%d,%d\n" % (following_id, twid))
    except Exception as e:
        # ¯\_(ツ)_/¯
        print "Failure: " + e.message
    # Twitter rates limits you to 15 requests in 15 minutes. Just sleep for a minute after each.
    time.sleep(60)