---
title: "pdf-image-text-extractor"
description: "Extract text from PDFs and images with format preservation and table detection"
canonical: https://agentpluginsdirectory.com/plugins/pdf-image-text-extractor
last-updated: 2026-09-15
---

# pdf-image-text-extractor
Extract text from PDFs and images with format preservation and table detection
- Slug: pdf-image-text-extractor
- Publisher: Redfox Data
- Repository: https://github.com/redfox-data/redfox-agent-plugins
- Manifest: plugins/pdf-image-text-extractor/plugin.json
- Version: 1.0.0
- License: MIT
- Category (editorial): other
- Skills: 1 (pdf-image-text-extractor)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-09-15
- Repository last pushed: 2026-09-15
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/pdf-image-text-extractor
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What pdf-image-text-extractor does, in the publisher's words

> Extract text from PDFs and images with format preservation and table detection

Powered by Redfox Data: this plugin works across Claude Code / OpenAI Codex / Cursor / Gemini CLI and any client conforming to the Agent Plugins or Agent Skills open standards.

OCR text extractor for PDFs and images with zero extra dependencies. Scanned PDFs are auto-rendered and processed by AI vision (no tesseract/rapidocr needed); tables extracted via pymupdf's built-in find_tables (no pdfplumber needed); supports batch directory processing.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/redfox-data/redfox-agent-plugins/HEAD/plugins/pdf-image-text-extractor/README.md

## Skills

- pdf-image-text-extractor: PDF & image OCR text extractor: extract text from PDFs and images with original format preserved. Scanned PDFs auto-rendered for AI vision recognition (no tesseract/rapidocr needed); tables structured via pymupdf find_tables (no pdfplumber needed); supports batch directory processing (PDF + images…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.