# letiantian/TextRank4ZH

:deciduous_tree:从中文文本中自动提取关键词和摘要

Repository: https://github.com/letiantian/TextRank4ZH
Canonical: https://ross.abutalabs.com/products/textrank4zh
Language: Python
License: MIT
License Family: permissive
Topics: textrank, textrank-algorithm, keyword-extraction, pagerank, python
Last push: 2025-05-07T01:33:48+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 20, release rhythm 35, longevity 100
- inputs: {"age_days": 4293, "days_push": 484, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3393, forks 834 (observed 2026-08-28T04:07:59.145676+00:00)

## What it is
A Python implementation of the TextRank algorithm tailored for Chinese text, extracting keywords, key phrases, and extractive summaries using PageRank over word and sentence graphs. It depends on jieba for segmentation, numpy, and networkx.

## Use cases
- extract keywords from Chinese text
- generate summaries of Chinese articles
- find key phrases in Chinese documents
- rank important sentences in Chinese text
- implement TextRank for Chinese NLP
- summarize Chinese news articles

## When to choose
- you need keyword or extractive summarization for Chinese-language text
- you want a lightweight, pure-Python TextRank with jieba segmentation
- you need key phrase extraction that joins adjacent keywords

## When to avoid
- you need extractive summarization for non-Chinese languages
- you need abstractive or neural summarization quality
- you need actively maintained tooling with modern packaging

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, parser
- domain: -
- platform: python
- tags: textrank, keyword-extraction, text-summarization, pagerank, chinese-nlp, natural-language-processing, chinese-text

## Member repositories
- letiantian/TextRank4ZH (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:59.145676+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:38:59.863362+00:00, confidence not recorded.
  - readme: https://github.com/letiantian/TextRank4ZH (fetched 2026-08-28T04:07:59.145676+00:00, sha 4af0eef5afce)
- Data as of 2026-08-30T08:39:29.467469+00:00.