literature-pdf-ocr-library

Community

Build a traceable literature corpus from PDFs.

Authorxiaoyu-ops
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This tool helps researchers build a traceable, machine-readable literature corpus by discovering papers, downloading legally accessible PDFs, OCR'ing PDFs or page images into Markdown, and organizing results into a centralized knowledge base.

Core Features & Use Cases

  • Search across Open Access sources (arXiv, Semantic Scholar, OpenAlex, and Hugging Face daily papers) to locate relevant papers.
  • Download open-access PDFs and convert them to Markdown with PaddleOCR layout parsing (or fall back to pdfminer for text extraction).
  • Organize papers into a canonical library under .pipeline/literature/<corpus-name>/ with per-paper metadata, OCR manifests, and a consolidated library index for AI workloads.

Quick Start

Batch OCR a directory of PDFs into Markdown and generate a searchable literature library.

Dependency Matrix

Required Modules

requestspdfminer.six

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: literature-pdf-ocr-library
Download link: https://github.com/xiaoyu-ops/the_work_of_dedup/archive/main.zip#literature-pdf-ocr-library

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.