pdf-extraction

Installation
SKILL.md

PDF Extraction

Tool Comparison

Tool Speed Layout Quality Tables Images Best For
PyMuPDF (fitz) Very fast Good Basic Yes Bulk text extraction
pdfplumber Slow Excellent Very good Yes Tables + coordinates
Docling Medium Excellent (layout model) Excellent Yes Structured docs, RAG
LlamaParse Slow (API) Excellent (LLM) Excellent Yes Complex layouts, forms
Marker Medium (GPU) Excellent Very good Yes PDF to markdown
pypdf Fast Poor No No Simple linear text only

PyMuPDF (fitz) — Fast Text + Metadata

import fitz  # PyMuPDF
Installs
4
GitHub Stars
37
First Seen
Jun 14, 2026
pdf-extraction — claude-dev-suite/claude-dev-suite