pdf

Extract text, tables, and metadata from PDFs using Python libraries.

Updated Mar 19, 2026

Search Tags:#pdf #python #document-processing #data-extraction #text-extraction #form-filling #pdf-processing

Ready to run

npx skills add https://github.com/gaos6e/MyOpenclaw --skill pdf-gaos6e

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/gaos6e/MyOpenclaw/tree/main/skills/pdf
Command: npx skills add https://github.com/gaos6e/MyOpenclaw --skill pdf-gaos6e

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow.

What problem does it solve?

PDF documents are ubiquitous and manual processing (text extraction, table capture, merging, and form handling) is time-consuming and error-prone; this skill provides a practical, code-backed workflow to automate those tasks.

Core Features & Use Cases

Read and extract text and metadata from PDFs, including OCR for scanned pages
Merge, split, and watermark or annotate PDFs
Extract images and tables, and convert content to structured formats
Use with forms to fill or annotate fields across multiple documents

Quick Start

Ask me to extract text and tables from a sample PDF and export them as CSV or JSON.

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 a PDF and export them as structured data?▼

You can extract text and tables from a PDF using pdfplumber and pypdf to parse document content, then export the extracted data into structured formats like CSV or JSON for analysis.

Can I perform OCR on scanned PDF pages to extract text?▼

Yes, you can perform OCR on scanned PDFs by converting pages to images with pdf2image and Pillow, then applying text extraction techniques to capture text from the scanned document images.

What is the best way to merge, split, or watermark PDF documents in Python?▼

The best way to merge, split, or watermark PDF documents is using pypdf to manipulate page structures, allowing you to combine files, separate specific pages, and apply annotations across diverse documents programmatically.

How do I fill or annotate PDF form fields across multiple documents?▼

You can fill or annotate PDF form fields across multiple documents by using pypdf to programmatically identify interactive form fields and input data, automating the form-filling process for batch document processing.

Does pdfplumber support extracting images from PDFs alongside text?▼

Yes, pdfplumber alongside Pillow and pdf2image supports extracting images from PDFs, enabling you to pull embedded visual content while simultaneously parsing text and table data from the document pages.

Why does text extraction fail on scanned PDFs without OCR?▼

Text extraction fails on scanned PDFs without OCR because the content is embedded as image pixels rather than selectable text, requiring pdf2image and Pillow to convert pages for extraction.