diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..ccfd90c --- /dev/null +++ b/.gitignore @@ -0,0 +1,196 @@ +# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore + +# Environment variables and secrets +.env +.env.local +.env.*.local +cookies.json + +# Data and posts tracking +posts.json + +# Temporary video processing files +temp/ +*.mp4 +*.webm +*.mov +*.mpeg + +# Python cache +__pycache__/ +*.py[cod] +*$py.class +*.so + +# Logs +logs +*.log +npm-debug.log* +yarn-debug.log* +yarn-error.log* +lerna-debug.log* +.pnpm-debug.log* + +# Caches + +.cache + +# Diagnostic reports (https://nodejs.org/api/report.html) + +report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json + +# Runtime data + +pids +_.pid +_.seed +*.pid.lock + +# Directory for instrumented libs generated by jscoverage/JSCover + +lib-cov + +# Coverage directory used by tools like istanbul + +coverage +*.lcov + +# nyc test coverage + +.nyc_output + +# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files) + +.grunt + +# Bower dependency directory (https://bower.io/) + +bower_components + +# node-waf configuration + +.lock-wscript + +# Compiled binary addons (https://nodejs.org/api/addons.html) + +build/Release + +# Dependency directories + +node_modules/ +jspm_packages/ + +# Snowpack dependency directory (https://snowpack.dev/) + +web_modules/ + +# TypeScript cache + +*.tsbuildinfo + +# Optional npm cache directory + +.npm + +# Optional eslint cache + +.eslintcache + +# Optional stylelint cache + +.stylelintcache + +# Microbundle cache + +.rpt2_cache/ +.rts2_cache_cjs/ +.rts2_cache_es/ +.rts2_cache_umd/ + +# Optional REPL history + +.node_repl_history + +# Output of 'npm pack' + +*.tgz + +# Yarn Integrity file + +.yarn-integrity + +# dotenv environment variable files + +.env +.env.development.local +.env.test.local +.env.production.local +.env.local + +# parcel-bundler cache (https://parceljs.org/) + +.parcel-cache + +# Next.js build output + +.next +out + +# Nuxt.js build / generate output + +.nuxt +dist + +# Gatsby files + +# Comment in the public line in if your project uses Gatsby and not Next.js + +# https://nextjs.org/blog/next-9-1#public-directory-support + +# public + +# vuepress build output + +.vuepress/dist + +# vuepress v2.x temp and cache directory + +.temp + +# Docusaurus cache and generated files + +.docusaurus + +# Serverless directories + +.serverless/ + +# FuseBox cache + +.fusebox/ + +# DynamoDB Local files + +.dynamodb/ + +# TernJS port file + +.tern-port + +# Stores VSCode versions used for testing VSCode extensions + +.vscode-test + +# yarn v2 + +.yarn/cache +.yarn/unplugged +.yarn/build-state.yml +.yarn/install-state.gz +.pnp.* + +# IntelliJ based IDEs +.idea + +# Finder (MacOS) folder config +.DS_Store diff --git a/bun.lockb b/bun.lockb new file mode 100644 index 0000000..86913f5 Binary files /dev/null and b/bun.lockb differ diff --git a/cookies.json b/cookies.json new file mode 100644 index 0000000..9f45335 --- /dev/null +++ b/cookies.json @@ -0,0 +1,4 @@ +{ + "ct0": "", + "auth_token": "" +} diff --git a/example.env b/example.env new file mode 100644 index 0000000..02aff33 --- /dev/null +++ b/example.env @@ -0,0 +1,10 @@ +# Bluesky Credentials +# Use an app password from https://bsky.app/settings/app-passwords +BSKY_USERNAME=example.bsky.social +BSKY_PASSWORD= + +# Twitter User to Monitor +TWITTER_USER=exampleuser + +# Check interval in milliseconds (60000 = 1 minute) +CHECK_INTERVAL=60000 diff --git a/get_tweets.py b/get_tweets.py new file mode 100644 index 0000000..16f8e97 --- /dev/null +++ b/get_tweets.py @@ -0,0 +1,89 @@ +import sys +import json +import asyncio +from twikit import Client + +async def get_user_tweets(username, count=10): + client = Client('en-US') + + try: + client.load_cookies('cookies.json') + except: + print(json.dumps({"error": "Not logged in. Run login script first."})) + return + + try: + user = await client.get_user_by_screen_name(username) + user_id = user.id + + tweets_data = [] + tweets = await client.get_user_tweets(user_id, 'Tweets', count=count) + + for tweet in tweets: + if tweet.text.startswith('RT @'): + continue + + # Get full text - twikit truncates long tweets at 280 chars + # Full text is available on the tweet object under different attributes + full_text = None + + # Try note_tweet first (X Premium long posts are stored as "note tweets") + if hasattr(tweet, 'note_tweet') and tweet.note_tweet: + note = tweet.note_tweet + if hasattr(note, 'text'): + full_text = note.text + elif isinstance(note, dict): + full_text = note.get('text') or note.get('note_tweet_results', {}).get('result', {}).get('text') + + # Fall back to full_text attribute if available + if not full_text and hasattr(tweet, 'full_text') and tweet.full_text: + full_text = tweet.full_text + + # Fall back to regular text + if not full_text: + full_text = tweet.text + + # Strip trailing ellipsis if still truncated (shouldn't happen but just in case) + if full_text.endswith('…'): + full_text = full_text[:-1] + + media = [] + if tweet.media: + for m in tweet.media: + media_url = None + media_type = m.type + + if hasattr(m, 'media_url'): + media_url = m.media_url + + if media_type == 'video' and hasattr(m, 'streams') and m.streams: + best_stream = max(m.streams, key=lambda s: s.bitrate if hasattr(s, 'bitrate') and s.bitrate else 0) + if hasattr(best_stream, 'url'): + media_url = best_stream.url + + if media_url: + media.append({ + 'type': media_type, + 'url': media_url + }) + + tweets_data.append({ + 'id': tweet.id, + 'text': full_text, + 'media': media, + 'created_at': tweet.created_at + }) + + print(json.dumps(tweets_data)) + except Exception as e: + print(json.dumps({"error": str(e)})) + +if __name__ == '__main__': + username = sys.argv[1] if len(sys.argv) > 1 else None + count = int(sys.argv[2]) if len(sys.argv) > 2 else 10 + + if not username: + print(json.dumps({"error": "Username required"})) + sys.exit(1) + + asyncio.run(get_user_tweets(username, count))