Deterministic local PDF parsing library for extracting layout, tables, and reading order into Markdown and JSON, with free auto-tagging to generate screen-reader-ready Tagged PDFs.
Project overview
Deterministic local PDF parsing library for extracting layout, tables, and reading order into Markdown and JSON, with free auto-tagging to generate screen-reader-ready Tagged PDFs.
Project type
RAG
Use cases
Documents & Office · Knowledge Q&A
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers and enterprise teams needing to extract complex PDF layouts into structured formats while preserving reading order and table integrity.
Teams requiring automated generation of screen-reader-ready Tagged PDFs to meet accessibility regulations at scale.
Key capabilities
Generates screen-reader-ready Tagged PDFs from untagged PDFs by applying structure tags for headings, paragraphs, lists, tables, and reading order.
Extracts exact layout details using native PDF structure tags when available, preserving author-intended headings, lists, tables, and reading order.
Provides functionality to verify PDF tag trees to ensure document structure integrity.
Limitations and risks
Repeated convert() calls may execute slowly because each call spawns a new JVM (Java Virtual Machine) process.
The tool is designed exclusively for PDF documents and cannot process Word, Excel, or PPT files.
Getting started
Ensure Java 11 or later is installed on the system before attempting to use the library.
Install or update the package by running 'pip install -U opendataloader-pdf' from the command line.
Evidence and sources
README: sdk: Python, Node.js, Java
README: import opendataloader_pdf
README: PDF structure lost during parsing — wrong reading order, broken tables, no element coordinates
README: solves: [PDF to structured data for RAG/LLM pipelines, accelerate PDF accessibility remediation — layout analysis + auto-tagging to Tagged PDF as foundation for PDF/UA (first open…