Video Watcher

Fetch transcripts from YouTube and Bilibili videos to enable summarization, QA, and content extraction.

Supported Platforms

• ✅ YouTube (youtube.com, youtu.be)
• ✅ Bilibili (bilibili.com, b23.tv)

Usage

Get Transcript (Auto-detect Platform)

python3 {baseDir}/scripts/get_transcript.py "VIDEO_URL"

Specify Language

python3 {baseDir}/scripts/get_transcript.py "VIDEO_URL" --lang zh-CN

Examples

YouTube Video

python3 {baseDir}/scripts/get_transcript.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ"

Bilibili Video

python3 {baseDir}/scripts/get_transcript.py "https://www.bilibili.com/video/BV1xx411c7mD"

With Custom Language

# Get English subtitles for a Bilibili video
python3 {baseDir}/scripts/get_transcript.py "https://bilibili.com/video/..." --lang en

# Get Chinese subtitles for a YouTube video
python3 {baseDir}/scripts/get_transcript.py "https://youtube.com/watch?v=..." --lang zh-CN

Default Languages

Common Language Codes

• en - English
• zh-CN - Simplified Chinese (简体中文)
• zh-TW - Traditional Chinese (繁體中文)
• ja - Japanese
• ko - Korean
• es - Spanish
• fr - French
• de - German

Notes

• Requires yt-dlp to be installed and available in PATH
• Works with videos that have closed captions (CC) or auto-generated subtitles
• Automatically detects platform from URL
• If no subtitles available, the script will fail with an error message
• yt-dlp natively supports both YouTube and Bilibili