hankcs/HanLP

Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

67
/ 100
Established

HanLP helps you analyze text in over 100 languages, breaking it down into individual words, identifying parts of speech, and recognizing entities like names or locations. This allows you to understand the structure and meaning of documents. It's used by researchers and businesses to process text data for tasks like information extraction or content analysis.

36,209 stars. Used by 1 other package. Available on PyPI.

Use this if you need to perform detailed linguistic analysis on text in multiple languages, such as identifying key terms or understanding sentence structure.

Not ideal if you only need very basic text operations or are looking for a simple keyword search tool.

text-analysis content-understanding linguistics information-extraction multilingual-data-processing
Maintenance 6 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

36,209

Forks

10,909

Language

Python

License

Apache-2.0

Last pushed

Nov 15, 2025

Commits (30d)

0

Dependencies

9

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/hankcs/HanLP"

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