HTML Analysis

Analyze and extract structured content from local HTML files using MinerU. Preserves document structure as Markdown. For live web page URLs, use mineru-open-api crawl.

Install

CODEBLOCK0

Quick Start

CODEBLOCK1

Authentication

Token required:

CODEBLOCK2

Create token at: https://mineru.net/apiManage/token

Capabilities

• - Supported input: local .html file or remote HTML URL
• HTML input requires extract (token required) — not supported by INLINECODE2
• For live web pages (rendered JS content), use INLINECODE3
• Language hint with --language (default: ch, use en for English)

Notes

• - HTML is NOT supported by flash-extract — use extract with token
• For web page crawling, use mineru-open-api crawl <URL> instead of INLINECODE10
• Output goes to stdout by default; use -o <dir> to save to a file or directory
• All progress/status messages go to stderr; document content goes to stdout
• MinerU is open-source by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU