grobidOrg/grobid
A machine learning software for extracting information from scholarly documents
This tool helps researchers, librarians, and data scientists automatically extract detailed information from scholarly PDFs. You feed it research papers in PDF format, and it outputs structured data like titles, authors, abstracts, references, and even full-text sections, ready for analysis or database entry. This is ideal for anyone needing to process large volumes of academic literature to organize, search, or build knowledge bases.
4,703 stars. Actively maintained with 27 commits in the last 30 days.
Use this if you need to systematically pull out specific pieces of information, such as bibliographic data or structured full text, from a collection of scientific or technical PDF documents.
Not ideal if you only need a simple full-text extraction without detailed parsing or if your documents are not academic papers.
Stars
4,703
Forks
538
Language
Java
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
27
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/grobidOrg/grobid"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
lihanghang/NLP-Knowledge-Graph
自然语言处理、知识图谱、对话系统，大模型等技术研究与应用。
obss/jury
Comprehensive NLP Evaluation System
yzhangcs/parser
:rocket: State-of-the-art parsers for natural language.
alibaba/EasyNLP
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
polakowo/textai
Applications using state-of-the-art in NLP