#66th of 7 in Data and scraping for AI
opendataloader-pdf
PDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 29.7k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Java
8,907 on 24 Mar 202629,695 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Java-based PDF parser with Python, Node.js and Java SDKs. The default local mode extracts text, tables, headings and images with bounding boxes and XY-Cut++ reading order. An optional hybrid mode runs a Docling-based backend server for OCR, complex tables, LaTeX formulas and chart descriptions. It can also auto-tag untagged PDFs into Tagged PDF; PDF/UA export is an enterprise add-on.
Who it is for: Engineers feeding PDFs into RAG pipelines or automating PDF tagging
Strengths
- Local mode is deterministic and runs without GPU; README lists 0.015 s/page
- JSON output includes bounding boxes for every element, useful for source citations
- Hybrid mode adds OCR (several engines), borderless tables, LaTeX formulas and picture descriptions
- Auto-tags untagged PDFs to Tagged PDF under Apache-2.0
Weaknesses
- Requires Java 11+ on the host in addition to Python or Node
- Each convert() call spawns a JVM, so calls must be batched
- PDF/UA-1/2 export and the accessibility studio are enterprise-only
- Hybrid mode needs a separate backend server; no Word, Excel or PowerPoint support
What it needs
- GPU optional
- Needs Java 11+, Python 3.10+ (Python SDK), Docling-based hybrid backend (optional)
- Models: SmolVLM 256M (picture description), EasyOCR, RapidOCR, Tesseract
- port 5002
Also in Data and scraping for AI
See all 7| Rank | Project | Score |
|---|---|---|
| 1 | Crawl4AIPython web crawler that converts pages to LLM-ready Markdown and JSON | 76 out of 100 |
| 2 | doclingPython library and CLI that converts PDFs, Office files and more into structured text | 73 out of 100 |
| 3 | FirecrawlWeb scraping and crawling API that returns LLM-ready markdown | 67 out of 100 |
| #4 | langextractPython library that extracts source-grounded structured data from text using LLMs | 59 out of 100 |
| #5 | paddleocrOCR and document parsing toolkit that outputs Markdown and JSON from PDFs and images | 55 out of 100 |