How people use PyMuPDF
Explore how PyMuPDF turns complex PDF documents into structured data ready for AI and document workflows, discover the full potential of PyMuPDF.
LLM
Turn PDF content into structured data ready for AI workflows, perfect for RAG applications.
Layout
Preserve document structure while extracting text, tables, and images.
Beyond extraction
Key Capabilities
From low-level PDF manipulation to LLM-ready extraction.
Choose what your workflow needs.
Extract all Document Text
Find Out How
Extract Key-Value Pairs from a Page
Find Out How
Extract Text from within a Rectangle
Find Out How
Extract Text in Natural Reading Order
Find Out How
Extract Table Content from Documents
Find Out How
Mark Extracted Text
Find Out How
Extract Text with Color
Find Out How
Extract Images: Non-PDF Documents
Find Out How
Extract Images: PDF Documents
Find Out How
Extract vector graphics
Find Out How
Getting All Annotations from a Document
Find Out How
Extract Drawings
Find Out How
