paddleocr-doc-parsing

Extract structured Markdown/JSON from PDFs and document images using PaddleOCR.

4|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/hwj123hwj/custom-skills --skill paddleocr-doc-parsing-hwj123hwj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paddleocr-doc-parsing
Source: https://github.com/hwj123hwj/custom-skills/tree/main/skills/paddleocr-doc-parsing
Command: npx skills add https://github.com/hwj123hwj/custom-skills --skill paddleocr-doc-parsing-hwj123hwj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires uv, paddleocr, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of manually extracting structured information from PDFs and document images, such as tables, formulas, and layouts, which can be time-consuming and error-prone.

Core Features & Use Cases

  • Structured Data Extraction: Extract tables, formulas, figures, and other structured data from PDFs and images with high precision.
  • Layout Analysis: Analyze the layout of documents to understand the structure and content.
  • Use Case: For example, you can use this Skill to extract tables from financial reports or formulas from academic papers, and convert them into a structured format like Markdown or JSON.

Quick Start

Use the paddleocr-doc-parsing skill to extract tables and formulas from the attached PDF 'financial_report.pdf'.

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 structured data like tables and formulas from a PDF?

Extracting structured data from a PDF involves using layout analysis and text recognition to identify tables and formulas, converting them into structured Markdown or JSON formats. This Skill utilizes PaddleOCR to automate that precise document parsing process.

Can I convert PDF tables and formulas into Markdown or JSON formats?

Yes, you can convert PDF tables and formulas into Markdown or JSON formats. This Skill uses PaddleOCR layout analysis to extract structured data from PDFs and document images, outputting the recognized content directly into these structured formats.

Do I need Python and uv to perform document parsing with PaddleOCR?

Yes, you need Python 3.9 or higher and the uv package installer to perform document parsing with PaddleOCR. Additionally, an active internet connection is required to utilize the text recognition and layout analysis features.

What is the best way to analyze document layouts and extract text from images?

The best way to analyze document layouts and extract text from images is using an advanced layout analysis engine like PaddleOCR. It identifies structural elements such as tables and formulas, converting the extracted content into structured Markdown or JSON.

Does this PDF parsing approach work for extracting financial tables and academic formulas?

Yes, this PDF parsing approach works for extracting financial tables and academic formulas. It applies layout analysis to identify specific structural elements in documents and images, accurately extracting them into structured Markdown or JSON formats.

Why does document layout analysis require an internet connection?

Document layout analysis requires an internet connection to fetch the necessary PaddleOCR models and dependencies for text recognition. Without internet access, the tool cannot initialize the environment or perform the structured data extraction from PDFs.