Html2md

소개

Html2md is an MCP server that intelligently converts HTML webpages into clean, size-reduced Markdown. It achieves significant content compression (typically 90-95%) by preserving vital elements like tables, images, and links, while discarding unnecessary clutter such as scripts and navigation. This makes it an excellent solution for feeding focused, relevant web data to AI models. The tool's robust browser mode, powered by Playwright, allows it to effectively extract content from dynamic, JavaScript-heavy sites and securely access authenticated pages using user browser profiles, ensuring comprehensive and accurate data capture.

주요 기능

• Preserves essential content like tables, images, and links while removing clutter.
• Browser mode with Playwright handles JavaScript-heavy sites and authenticated pages.
• Supports optional caching for faster repeated conversions.
• Converts HTML from URLs to clean Markdown, reducing size by 90-95%.
• Efficiently processes large pages with stream processing and configurable size limits.
• 1 GitHub stars

사용 사례

• Converting public articles or documentation to a simplified Markdown format for AI processing.
• Extracting content from dynamic, JavaScript-rendered Single Page Applications (SPAs).
• Accessing and transforming information from password-protected or authenticated web dashboards.