delete old tweets from archive

deleteoldtweets.py

#!/bin/python3
# Largely copied from http://www.mathewinkson.com/2015/03/delete-old-tweets-selectively-using-python-and-tweepy
# However, Mathew's script cannot delete tweets older than something like a year (these tweets are not available from the twitter API)
# This script is a complement on first use, to delete old tweets. It uses your twitter archive to find tweets' ids to delete
# How to use it :
#     - download and extract your twitter archive (tweet.js will contain all your tweets with dates and ids)
#     - put this script in the extracted directory
#     - complete the secrets to access twitter's API on your behalf and, possibly, modify days_to_keep
#     - delete the few junk characters at the beginning of tweet.js, until the first '['   (it crashed my json parser)
#     - review the script !!!! It has not been thoroughly tested, it may have some unexpected behaviors...
#     - run this script
#     - forget this script, you can now use Mathew's script for your future deletions
#
#  License : Unlicense http://unlicense.org/

import tweepy

import json
from datetime import datetime, timedelta, timezone
from dateutil.parser import parse
import os
from os import path

consumer_key = 'cwpc33VDHfGm0L7CP0p4xtZU7'
consumer_secret = 'Q7izFcO3OT6AvcDElZQZThezmLIWIBQIlXwUB0jmjhcs582F66'
access_token = '81061781-7NNtWyz11k2d3OiaeLFzMGVQZQmuiM07Ap1IoFaa2'
access_token_secret = 'tgW3i6G09qnPcMo2sUWHtU8eXIgFlm7TEVtMiRiyiB9gQ'
days_to_keep = 7

auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth)



cutoff_date = datetime.now(timezone.utc) - timedelta(days=days_to_keep)

print(cutoff_date)

data_dir = path.join(os.getcwd(), 'data')

tweets = []


with open(path.join(data_dir, "tweet.js"), 'r', encoding='UTF-8') as fp:
    js_file = fp.read()
    contents = json.loads(js_file)
    tweets.extend(contents)

for tweet in tweets:
    t = tweet['tweet']
    d = parse(t['created_at'])
    if d < cutoff_date:
        try:
            api.destroy_status(t['id_str'])
            print(t['created_at'] + " " + t['id_str'])
        except tweepy.TweepError as e:
            print("failed to delete " + t['id_str'])
            print (e.api_code)
            print (e.reason)
            pass

You need to run sudo pip3 install python-dateutil :)