PDF Analysis

Analyze and extract structured content from PDF files using MinerU. Returns Markdown with layout, headings, and structure preserved.

Install

CODEBLOCK0

Quick Start

CODEBLOCK1

Authentication

No token needed for flash-extract. Token required for extract:

CODEBLOCK2

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

Capabilities

• - Supported input: .pdf (local file or URL)
• INLINECODE2: quick, no token, max 10 MB / 20 pages, Markdown output only
• INLINECODE3: token required, full features (tables, formulas, OCR, multi-format output)
• Language hint with --language (default: ch, use en for English)
• Page range with --pages (e.g. 1-10)

Notes

• - Use flash-extract for quick reads; use extract for tables, formulas, or files over 10 MB
• 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