Delete (very) old tweets obtained from a twitter archive

deloldtweets.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
import os
from os import path

consumer_key = ''
consumer_secret = ''
access_token = ''
access_token_secret = ''
days_to_keep = 365

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', 'js', 'tweets')

tweets = []

for filename in os.listdir(data_dir):
    with open(path.join(data_dir, filename), 'r', encoding='UTF-8') as fp:
        js_file = fp.read()
        contents = json.loads(js_file[js_file.find('\n') + 1:])
        tweets.extend(contents)

for tweet in tweets:
    d = datetime.strptime(tweet['created_at'], "%Y-%m-%d %H:%M:%S %z")
    if d < cutoff_date:
        try:
            api.destroy_status(tweet['id_str'])
            print(tweet['created_at'] + " " + tweet['id_str'])
        except:
            print("failed to delete " + tweet['id_str'])
            pass

What would be the required changes to have the script delete everything before a set date based on the current year (and only the year) ? Eg. keep only the current and previous year, delete everything older.

I'm running into an issue with converting the .js file into json, I think, and I'm getting errors regarding the json part of the code. I will keep looking into this issue, but wondered if you had any ideas on what the issue may be.

line 52, in
contents = json.loads(js_file[js_file.find('\n') + 1:])
File "C:\Python3.7\lib\json_init_.py", line 348, in loads
return _default_decoder.decode(s)
File "C:\Python3.7\lib\json\decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Python3.7\lib\json\decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 2 column 1 (char 1)

Hi,

Thanks for the awesome work.
I stumbled upon many small bugs (among other things related to datetime and json parsing), so I forked the script to a new gist that works.
If anyone is interested : https://gist.github.com/marrakchino/d6bd3438cd87ab419888edbc4dc1f0f5.

Best

This works for me:

https://gist.github.com/bluebossa63/e1dbdad9c0bc4fd625e072bfe304cf42

#!/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 = ''
consumer_secret = ''
access_token = ''
access_token_secret = ''
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