Extracts and saves YouTube video subtitles or transcripts to local text files using command-line tools or automated browser interaction.
This skill provides a robust, two-tiered workflow for acquiring YouTube transcripts, ensuring reliable results even when standard methods fail. It prioritizing high-speed extraction using yt-dlp with integrated browser cookie support to bypass common access restrictions. If command-line tools are unavailable, the skill automatically switches to a sophisticated browser automation fallback that navigates the YouTube interface, expands descriptions, and uses DOM injection to scrape the transcript panel. It is an essential tool for researchers, developers, and content creators who need to convert video content into searchable, timestamped text data for analysis or archiving.
주요 기능
01Intelligent UI navigation to locate and expand hidden transcript panels
02925 GitHub stars
03Support for authenticated sessions via browser cookies to bypass sign-in walls
04Automatic file naming and formatting including timestamps and multi-language support
05Efficient transcript scraping via JavaScript DOM evaluation for faster processing
06Dual-mode extraction using CLI tools (yt-dlp) or automated browser fallbacks
사용 사례
01Converting educational videos or lectures into searchable text for study and research
02Gathering large datasets of video transcripts for LLM training or sentiment analysis
03Creating local archives of video content for offline reference and accessibility compliance