pdf

Extract text, tables, and metadata from PDF documents.

Updated Dec 26, 2025

Search Tags:#pdf #document-processing #text-extraction #table-extraction #pdf-automation #form-processing

Ready to run

npx skills add https://github.com/yutaoshao/agent-skills --skill pdf-yutaoshao

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/yutaoshao/agent-skills/tree/main/glm-skills/document-skills/pdf
Command: npx skills add https://github.com/yutaoshao/agent-skills --skill pdf-yutaoshao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdf2image, Pillow, and includes scripts (resource) components.

What problem does it solve?

PDFs are ubiquitous in business workflows, but extracting text, tables, and form data, and performing batch edits remain error-prone and time-consuming.

Core Features & Use Cases

Text extraction from PDFs
Table data extraction and export (CSV/JSON)
PDF creation, merging, splitting, and form handling

Quick Start

Process a sample PDF to extract text, tables, and metadata, and save results to a structured format.

Frequently Asked Questions about pdf

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

FAQPage Schema

How do I extract text and tables from PDF documents in bulk?▼

Python libraries like pypdf enable PDF text extraction, table extraction, and metadata parsing for batch document processing. Extracted table data exports to CSV or JSON formats for archiving and downstream analysis.

What is the best way to digitize PDF forms and handle invoice data extraction?▼

Automating PDF processing with Python handles form digitization and invoice data extraction across large document sets. This converts unstructured PDF forms into actionable data with robust error handling and input validation.

Can I use pypdf and Pillow to merge, split, and compose new PDF files?▼

pypdf supports PDF creation, merging, splitting, and form handling, while Pillow and pdf2image manage image-based operations and page rendering. Together they enable robust PDF composition and editing workflows with input validation.

Does this PDF automation approach work for batch processing large sets of invoices?▼

This PDF automation approach supports batch document processing for large sets of invoices and forms. Robust error handling and input validation ensure reliable text extraction and archiving across high-volume workflows.

Why does PDF table extraction sometimes fail and require image rendering?▼

PDF table extraction fails when documents contain scanned images instead of selectable text. Rendering pages with pdf2image and applying Pillow for image-based operations processes visually embedded tables for reliable data export.