paddleocr-doc-parsing

Extract structured Markdown and JSON from PDFs and document images.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/wjlmrzd/OpenClaw-Wren --skill paddleocr-doc-parsing-wjlmrzd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paddleocr-doc-parsing
Source: https://github.com/wjlmrzd/OpenClaw-Wren/tree/main/skills/paddleocr-doc-parsing
Command: npx skills add https://github.com/wjlmrzd/OpenClaw-Wren --skill paddleocr-doc-parsing-wjlmrzd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, Pillow, pypdfium2, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Converts complex PDFs and document images into complete, structured Markdown/JSON with layout-aware extraction so users no longer need to manually reconstruct tables, formulas, multi-column text, figures, stamps, or reading order from scans and print documents.

Core Features & Use Cases

  • Table extraction: Recover table structure and cell contents for invoices, financial reports, and spreadsheets.
  • Formula recognition: Detect and output mathematical formulas as LaTeX for academic papers and technical documents.
  • Layout analysis & reading order: Restore multi-column layouts, headers/footers, page numbers, and correct reading order for magazines, newspapers, and brochures.
  • Figures, charts, seals: Identify figures, charts, and stamps and include associated metadata and image references.
  • Use Case: Parse a scanned annual report to extract all text, tables, and formulas into Markdown and export raw provider JSON for downstream data pipelines.

Quick Start

Run the vl_caller.py script after configuring PADDLEOCR_DOC_PARSING_API_URL and PADDLEOCR_ACCESS_TOKEN and provide a file URL or local file path to receive the full structured JSON and markdown output.

Frequently Asked Questions about paddleocr-doc-parsing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract tables and formulas from a PDF into Markdown?

You can extract tables and formulas from a PDF into Markdown by using layout-aware document parsing to recover table structures and output mathematical formulas as LaTeX for academic papers and financial reports.

How does layout analysis restore reading order for multi-column scanned documents?

Layout analysis restores reading order for multi-column scanned documents by detecting headers, footers, and page numbers, ensuring that magazines and brochures are converted into structured Markdown and JSON correctly.

Do I need a PaddleOCR API endpoint to parse scanned invoices?

Yes, you need a configured PaddleOCR document parsing API endpoint and access token to parse scanned invoices, as the Skill returns the provider's full JSON including markdown text and pruned results.

What is the best way to convert scanned annual reports into structured JSON?

The best way to convert scanned annual reports into structured JSON is using layout-aware document parsing, which identifies text, tables, figures, and seals to export raw provider JSON for downstream data pipelines.

Can I process local PDF files and document images for formula recognition?

Yes, you can process local PDF files and document images for formula recognition by providing a local file path or file URL to the parsing script to receive full structured JSON and Markdown output.

What types of documents are supported for layout-aware parsing?

Layout-aware parsing supports multi-column layouts, scanned documents, invoices, financial reports, and academic papers with formulas, extracting all contents into structured Markdown and JSON formats.