internals

How MarkItDown's YouTube Converter Works: From URL to Structured Markdown

April 11, 2026 microsoft/markitdown ↗

MarkItDown's YouTube converter extracts video metadata, descriptions, and optional transcripts from YouTube HTML pages and converts them into clean Markdown using BeautifulSoup and the youtube-transcript-api library.

The microsoft/markitdown repository includes a specialized DocumentConverter that transforms YouTube video pages into structured Markdown documents suitable for LLM processing. This converter handles URL validation, metadata extraction from both HTML tags and JavaScript variables, and optional transcript retrieval through a multi-phase pipeline.

URL Detection and Acceptance Logic

The conversion process begins with the accepts()

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:

curl -s "https://instagit.com/install.md"

Add to your MCP client configuration:

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}

Ask your agent:

"Use Instagit MCP to understand how microsoft/markitdown works."

Works with

Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →