explosion/spacy-layout

📚 Process PDFs, Word documents and more with spaCy

51
/ 100
Established

This project helps convert your unstructured PDFs, Word documents, and other similar files into clean, structured data. It takes your documents as input and outputs organized text, including identified sections, headings, and tables. This tool is designed for anyone who needs to extract specific information from complex documents for further analysis or integration into AI-powered systems.

869 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to reliably extract text, identify document structure like headings, and pull data from tables within your PDFs and Word documents for things like data analysis or building AI applications.

Not ideal if you only need simple text extraction without any desire to understand the document's layout or extract tabular data.

document-processing information-extraction data-preparation content-analysis AI-pipeline-preparation
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

869

Forks

61

Language

Python

License

MIT

Last pushed

Mar 08, 2025

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/explosion/spacy-layout"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.