Ocr Pro

Convert and extract content from .pdf / images (.png/.jpg/.jpeg/.jp2/.webp/.gif/.bmp) using MinerU (mineru-open-api).

Install

npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Quick Start

# Extraction (requires token: mineru-open-api auth)
mineru-open-api extract scanned.pdf -o ./out/

# From URL
mineru-open-api extract https://example.com/scanned.pdf -o ./out/

# Specify language
mineru-open-api extract scanned.pdf --language en -o ./out/

Authentication

Token required for extract and crawl:

mineru-open-api auth            # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable

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

Capabilities

• Supports local files and URLs
• Requires token (mineru-open-api auth or MINERU_TOKEN env)
• Supported input: .pdf / images (.png/.jpg/.jpeg/.jp2/.webp/.gif/.bmp)
• Language hint with --language (default: ch, use en for English)
• Page range with --pages (where applicable)

Notes

• OCR is only available via extract with token. Use --ocr flag. For complex layouts use --model vlm.
• Output goes to stdout by default; use -o <dir> to save to file
• Binary formats (docx) require -o flag (cannot stream to stdout)
• All progress/status messages go to stderr
• MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU