YouTube to Markdown

Multiple videos: Process one video at a time, sequentially. Do not run parallel extractions. Do not create your own scripts.

Step 0: Check if extracted before

python3 ./check_existing.py "<YOUTUBE_URL>" "<output_directory>"

If any *_valid: false: Show the issues to user and proceed.

Output JSON contains video_id. Set BASE_NAME = youtube_{video_id} for all subsequent steps.

Step 1: Choose output

AskUserQuestion:

• question: "What do you want to extract from the video?"
• header: "Output"
• multiSelect: false
• options: A. "Summary only" - Tight summary of video content B. "Transcript only" - Cleaned, formatted full transcript C. "Comments only" - Curated comments D. "Summary + Comments" - Summary with cross-analyzed comment insights E. "Full (Recommended)" - All: summary, transcript, comments

Step 2: Execute modules

Based on user's choice, read and follow each module instruction in ./modules/{file}. "|" marks possibility to run concurrently.

• A: transcript_extract.md → transcript_summarize.md
• B: transcript_extract.md → transcript_polish.md
• C: comment_extract.md
• D: transcript_extract.md → (transcript_summarize.md | comment_extract.md) → comment_summarize.md
• E: transcript_extract.md → (transcript_summarize.md | transcript_polish.md | comment_extract.md) → comment_summarize.md

Step 3: Finalize

python3 finalize.py [flag] "${BASE_NAME}" "<output_directory>"

Flags: A=--summary-only, B=--transcript-only, C=--comments-only, D=--summary-comments, E=(none)

Use --debug to keep intermediate files.