MinerU PDF Parser

Parse PDF documents into Markdown with LaTeX formula preservation, table extraction, and image handling.

Setup

Get API token from https://mineru.net/user-center/api-token (free: 2000 pages/day, 200MB max):

export MINERU_TOKEN="your-token-here"

Commands

Single File

python3 scripts/mineru_v2.py --file ./document.pdf --output ./output/

Batch Directory with Resume

python3 scripts/mineru_v2.py \
  --dir ./pdfs/ \
  --output ./output/ \
  --workers 10 \
  --resume

Direct to Obsidian

python3 scripts/mineru_v2.py \
  --dir ./pdfs/ \
  --output "~/Library/Mobile Documents/com~apple~CloudDocs/Obsidian/VaultName/" \
  --resume

CLI Options

--dir PATH        Input directory of PDFs
--file PATH       Single PDF file  
--output PATH     Output directory (default: ./output/)
--workers N       Concurrent workers (default: 5, max: 15)
--resume          Skip already processed files
--timeout SEC     Per-file timeout (default: 600)

Script Selection

Output

output/
├── document-name/
│   ├── document-name.md    # Main Markdown
│   ├── images/             # Extracted images
│   └── content.json        # Metadata

Supported Documents

• Academic papers (LaTeX formulas)
• Exam papers (考研, 高考)
• Financial reports (tables)
• Textbooks (formulas + diagrams)
• Scanned PDFs (enable OCR)

Performance

Error Handling

• 3x auto-retry with exponential backoff
• Use --resume to skip completed files
• Check logs for failed files

API Reference

For detailed API documentation, see references/api_reference.md.