Created
November 14, 2022 06:50
-
-
Save salty-horse/a30f478c90d5ea54e029bd2c5aa900b3 to your computer and use it in GitHub Desktop.
Extract Twitter display names from the Wayback Machine
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
#!/usr/bin/env python | |
# gem install --user-install wayback_machine_downloader | |
# wayback_machine_downloader -c 20 -s http://twitter.com/haszombiesinit | |
# find . -type f -iname '*html' | xargs grep '<title[^>]*>' | sort | ./extract_display_names.py | |
# | |
# Filter 'Tweets with replies by' manually' | |
import fileinput | |
import html | |
import os | |
import re | |
RE_TITLE = re.compile('<title[^>]*>') | |
ON_TWITTER = [ | |
' on Twitter:', | |
' auf Twitter', | |
' sa Twitter', | |
' sur Twitter ', | |
' op Twitter', | |
' Twitter ನಲ್ಲಿ', | |
' على تويتر', | |
' ٹوئٹر پر', | |
' på Twitter', | |
' Twitterissä', | |
' Twitterren', | |
' di Twitter', | |
' na Twitterze', | |
' na Twitteri', | |
' บนทวิตเตอร์', | |
' Twitter वर', | |
' a Twitteren', | |
' su Twitter', | |
'さんのツイート', | |
' en Twitter', | |
' Twitter'da', | |
' в Твиттере', | |
' 的 Twitter', | |
' בטוויטר', | |
' ar Twitter', | |
' pe Twitter', | |
' na Twitteru', | |
' на Твитеру', | |
' a Twitter', | |
] | |
known_names = {} | |
files_to_delete = [] | |
for line in fileinput.input(): | |
fname, line = line.split(':', 1) | |
date = fname.split('/')[4] | |
name = None | |
if '(@hasz' in line: | |
name = RE_TITLE.split(line.split('(@hasz', 1)[0])[1].strip() | |
else: | |
for on_twitter in ON_TWITTER: | |
if on_twitter in line: | |
name = RE_TITLE.split(line.split(on_twitter)[0])[1].strip() | |
if 'on Twitter:' in name: | |
print(repr(name[:100])) | |
break | |
if not name: | |
print('Unknown', date, line) | |
pass | |
if name: | |
if not (known_date := known_names.get(name)) or date < known_date: | |
known_names[name] = date | |
else: | |
files_to_delete.append(fname) | |
for (name, date) in sorted(known_names.items(), key=lambda x:x[1]): | |
print(f'{date[0:4]}-{date[4:6]}-{date[6:8]}\t{html.unescape(name)}') | |
# As files are downloaded, this deletes duplicate files | |
# for fname in files_to_delete: | |
# os.unlink(fname) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment