paper-image-extractor

Extract figures from academic papers using arXiv source packages or PDFs.

1.0k|117|Updated Feb 26, 2026

Search Tags:#python #arxiv #pdf-processing #image-extraction #research-tools #figure-extraction

Ready to run

npx skills add https://github.com/OpenLAIR/dr-claw --skill paper-image-extractor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: paper-image-extractor
Source: https://github.com/OpenLAIR/dr-claw/tree/main/skills/paper-image-extractor
Command: npx skills add https://github.com/OpenLAIR/dr-claw --skill paper-image-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, requests, and includes scripts (resource) components.

What problem does it solve?

Automates extraction of figures from research papers, prioritizing arXiv source packages to obtain original, high-quality images instead of relying on embedded PDF figures.

Core Features & Use Cases

Priority-based extraction: arXiv source package, then PDF figures, then embedded images
Flexible figure discovery across common directories (pics, figures, fig, images, img) with automatic copying to an output directory
Generates an index file detailing sources (arxiv-source, pdf-figure, pdf-extraction) for easy reuse in presentations or manuscripts

Quick Start

Run the tool on a paper's arXiv ID to collect all figures and generate an index in the output directory.

Frequently Asked Questions about paper-image-extractor

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

FAQPage Schema

How do I extract figures from an arXiv paper?▼

The tool finds and extracts figures from academic papers by prioritizing arXiv source packages to obtain original images instead of embedded PDF figures. It handles arXiv IDs or local PDFs with multiple fallbacks, outputting an images directory with an index.

Can I extract images from a local PDF if I do not have an arXiv ID?▼

Yes, figure extraction works on local PDFs without an arXiv ID. The tool applies multiple fallbacks, moving from arXiv source packages to PDF figures, and finally to embedded images, outputting an images directory with an index.

Do I need PyMuPDF and Python 3.8 to extract figures from research papers?▼

Yes, Python 3.8+ and PyMuPDF are required to extract figures from research papers. These dependencies enable PDF processing and image extraction when arXiv source packages are unavailable, producing an images directory with an index.

What is the best way to get high-quality images from arXiv source packages instead of embedded PDF figures?▼

Prioritizing arXiv source packages is the best way to get high-quality images. The tool searches common directories like figures and images within the source package to copy original files, generating an index for reuse in presentations.

What are the limitations of extracting figures from PDF when arXiv source packages are unavailable?▼

When arXiv source packages are unavailable, figure extraction falls back to PDF figures and embedded images using PyMuPDF. This may yield lower-quality images compared to original source files and depends on how figures are embedded in the PDF.