skills.rest
ahundt
ahundtCOMMUNITY
Explore all skills by this author →
Website𝕏@athundtGitHub

pdf-extractor

Extract text and structured data from PDF documents with OCR fallback.

12|2|Updated Jan 25, 2026
Search Tags:#ocr#document processing#data extraction#pdf#batch processing#extraction
One-click install
npx skills add https://github.com/ahundt/autorun --skill pdf-extractor-ahundt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-extractor
Source: https://github.com/ahundt/autorun/tree/main/plugins/pdf-extractor/skills/pdf-extractor
Command: npx skills add https://github.com/ahundt/autorun --skill pdf-extractor-ahundt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown, pdfplumber, pdfminer.six, PyPDF2, tqdm, docling, marker-pdf, pymupdf4llm, pdfbox, torch, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the extraction of text and structured data from PDF documents, handling various formats and even scanned documents, thereby reducing manual data entry and processing time.

Core Features & Use Cases

  • Multi-Backend Extraction: Utilizes multiple libraries (e.g., markitdown, pdfplumber, docling, marker) to ensure robust extraction across different PDF types.
  • Batch Processing: Efficiently extracts data from multiple PDF files in a directory.
  • OCR Support: Capable of extracting text from scanned PDFs using vision-based backends.
  • Use Case: Automatically convert a folder of scanned receipts into markdown files for easier searching and analysis.

Quick Start

Extract all text from the document named 'report.pdf' and save it as 'report.md'.

Frequently Asked Questions about pdf-extractor

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

FAQPage Schema
How do I extract text from scanned PDFs that standard tools cannot read?▼

To extract text from scanned PDFs, this tool utilizes vision-based OCR backends like docling and marker to recognize text in images, converting the document into searchable markdown or structured data.

Can I batch process multiple PDF files in a directory for text extraction?▼

Yes, you can batch process multiple PDF files in a directory for text extraction, efficiently converting an entire folder of documents into structured markdown files using its multi-backend approach.

What is the best way to extract structured data from complex PDF documents?▼

The best way to extract structured data from complex PDFs is using a multi-backend approach with automatic fallback across libraries like pdfplumber and PyPDF2, ensuring robust extraction across various digital document formats.

Does this PDF extraction method support converting documents directly to markdown?▼

Yes, this PDF extraction method supports converting documents directly to markdown, using backends like markitdown and pymupdf4llm to transform digital and scanned PDF content into structured markdown files.

Why does my PDF text extraction fail on certain digital documents?▼

PDF text extraction often fails due to complex formatting or scanned content, but this tool resolves it by automatically falling back to alternative processing backends like pdfminer.six or OCR when initial methods fail.

Related Skills

Explore More Software Engineering Skills→
StratioStratio
4

pdf-reader

Extract PDF content into structured Markdown with quick and deep modes.

Official
Advanced
PancrePal-xiaoyibaoPancrePal-xiaoyibao
6

pdf-reader

Extract text from local PDF files into structured Markdown format.

Official
Intermediate
rysweetrysweet
72

pdf

Extracts text and tables from PDFs, creates, merges, and handles OCR for scanned documents.

Community
Advanced
georgemarmelsteingeorgemarmelstein
12

converter-pdf

Convert judicial PDFs to cleaned TXT via OCR or pdfplumber.

Community
Intermediate