import zipfile
import json
import os
import shutil
import re
from datetime import datetime
def parse_twitter_js(content):
"""Fjerner JavaScript variabel-tildelingen og returnerer ren JSON."""
start_idx = content.find('[')
if start_idx == -1:
start_idx = content.find('{')
if start_idx == -1:
return []
try:
cleaned_content = re.sub(r'^\/\*.*?\*\/', '', content, flags=re.DOTALL).strip()
start_match = re.search(r'[\[\{]', cleaned_content)
if not start_match:
return []
return json.loads(cleaned_content[start_match.start():])
except json.JSONDecodeError as e:
print(f"Fejl ved JSON-parsing: {e}")
return []
def main():
zip_path = 'twitter.zip'
if not os.path.exists(zip_path):
print("Fejl: Fandt ikke twitter.zip i samme mappe.")
return
if not os.path.exists('avatar.png'):
print("Fejl: Fandt ikke avatar.png i samme mappe. Brug venligst et billede med dette navn.")
return
print("Analyserer twitter.zip...")
media_dir = 'media'
if not os.path.exists(media_dir):
os.makedirs(media_dir)
profile_data = {}
tweets_data = []
with zipfile.ZipFile(zip_path, 'r') as z:
file_list = z.namelist()
profile_file = next((f for f in file_list if f.endswith('data/profile.js')), None)
account_file = next((f for f in file_list if f.endswith('data/account.js')), None)
followers_file = next((f for f in file_list if f.endswith('data/follower.js')), None)
following_file = next((f for f in file_list if f.endswith('data/following.js')), None)
profile_data['name'] = 'Andreas Andersen'
profile_data['bio'] = ''
if profile_file:
prof_json = parse_twitter_js(z.read(profile_file).decode('utf-8'))
if prof_json and len(prof_json) > 0:
p = prof_json[0].get('profile', {})
profile_data['bio'] = p.get('description', {}).get('bio', '')
if account_file:
acc_json = parse_twitter_js(z.read(account_file).decode('utf-8'))
if acc_json and len(acc_json) > 0:
acc = acc_json[0].get('account', {})
profile_data['handle'] = '@' + acc.get('username', 'ukendt')
profile_data['created'] = acc.get('createdAt', '')
profile_data['followersCount'] = len(parse_twitter_js(z.read(followers_file).decode('utf-8'))) if followers_file else 0
profile_data['followingCount'] = len(parse_twitter_js(z.read(following_file).decode('utf-8'))) if following_file else 0
# Opdateret søgning: Find ALLE tweet-filer (f.eks. tweets.js, tweets-part1.js, tweets-part2.js)
tweet_files = [f for f in file_list if re.match(r'^data/tweets?(?:-part\d+)?\.js$', f)]
if tweet_files:
print(f"Fandt {len(tweet_files)} fil(er) med tweets. Udtrækker og behandler...")
for tweets_file in tweet_files:
print(f"- Læser {tweets_file}...")
raw_tweets = parse_twitter_js(z.read(tweets_file).decode('utf-8'))
for item in raw_tweets:
t = item.get('tweet', item)
is_reply = t.get('in_reply_to_status_id') is not None or t.get('in_reply_to_user_id') is not None
text = t.get('full_text', '')
has_links = 'http' in text
if 'entities' in t:
if 'media' in t['entities']:
for m_ent in t['entities']['media']:
tco_media = m_ent.get('url', '')
if tco_media:
text = text.replace(tco_media, '').strip()
if 'urls' in t['entities']:
for u_ent in t['entities']['urls']:
tco_url = u_ent.get('url', '')
expanded_url = u_ent.get('expanded_url', '')
display_url = u_ent.get('display_url', expanded_url)
if tco_url and expanded_url:
html_link = f'{display_url}'
text = text.replace(tco_url, html_link)
tags = [tag['text'].lower() for tag in t.get('entities', {}).get('hashtags', [])]
media_files = []
if 'extended_entities' in t and 'media' in t['extended_entities']:
for m in t['extended_entities']['media']:
media_url = m.get('media_url', '')
if media_url:
filename = media_url.split('/')[-1]
tweet_id = t.get('id_str', '')
zip_media_path = f"data/tweets_media/{tweet_id}-{filename}"
try:
with z.open(zip_media_path) as source, open(os.path.join(media_dir, filename), 'wb') as target:
shutil.copyfileobj(source, target)
media_files.append(f"{media_dir}/{filename}")
except:
pass
try:
date_obj = datetime.strptime(t.get('created_at'), '%a %b %d %H:%M:%S +0000 %Y')
except ValueError:
date_obj = datetime.now()
tweets_data.append({
'id': t.get('id_str', ''),
'text': text,
'date': date_obj.strftime('%d. %b %Y, %H:%M'),
'year': date_obj.strftime('%Y'),
'timestamp': date_obj.timestamp(),
'is_reply': is_reply,
'has_links': has_links,
'tags': tags,
'media': media_files,
'likes': int(t.get('favorite_count', 0)),
'retweets': int(t.get('retweet_count', 0))
})
profile_data['totalPosts'] = sum(1 for t in tweets_data if not t['is_reply'])
profile_data['totalReplies'] = sum(1 for t in tweets_data if t['is_reply'])
print("Genererer HTML...")
generate_html(profile_data, tweets_data)
print("Færdig! Åbn index.html i din browser.")
def generate_html(profile, tweets):
html_content = f"""
Twitter/X Arkiv
"""
with open('index.html', 'w', encoding='utf-8') as f:
f.write(html_content)
if __name__ == "__main__":
main()