# DerwenAI/pytextrank

Python implementation of TextRank algorithms ("textgraphs") for phrase extraction

Repository: https://github.com/DerwenAI/pytextrank
Canonical: https://ross.abutalabs.com/products/pytextrank
Homepage: https://derwen.ai/docs/ptr/
Language: Python
License: MIT
License Family: permissive
Topics: textrank, summarization, natural-language-processing, nlp, machine-learning, graph-algorithms, spacy, spacy-extension, natural-language, textgraphs, python
Last push: 2026-06-24T03:52:57+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 89, release rhythm 8, longevity 100
- inputs: {"age_days": 3622, "days_push": 70, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2218, forks 334 (observed 2026-08-28T04:06:27.298874+00:00)

## What it is
PyTextRank is a Python implementation of TextRank and related textgraph algorithms (PositionRank, Biased TextRank, TopicRank) as a spaCy pipeline extension. It provides graph-based ranking for phrase extraction and low-cost extractive summarization of text documents.

## Use cases
- extract top-ranked key phrases from a document
- summarize long text documents extractively
- extract keywords from articles with python
- build a spacy pipeline for phrase extraction
- infer concepts from unstructured text into structured representations
- rank phrases in text using graph algorithms

## When to choose
- you already use spaCy and want a drop-in pipeline extension
- you need lightweight, dependency-free extractive summarization without training models
- you want graph-based keyword/phrase extraction with multiple algorithm variants

## When to avoid
- you need abstractive summarization or generative models
- you don't use spaCy and prefer standalone NLP tooling
- you need state-of-the-art transformer-based keyphrase extraction

## Facets
- artifact type: library
- maturity: active
- function: nlp, parser, machine-learning
- domain: machine-learning, data-science
- platform: python
- tags: textrank, spacy-extension, phrase-extraction, extractive-summarization, graph-algorithms, keyword-extraction, textgraphs, natural-language-processing

## Member repositories
- DerwenAI/pytextrank (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:27.298874+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 2026-08-30T02:45:53.490069+00:00, confidence not recorded.
  - readme: https://github.com/DerwenAI/pytextrank (fetched 2026-08-28T04:06:27.298874+00:00, sha 2c6284eefd80)
  - registry_pypi: https://pypi.org/pypi/pytextrank/json (fetched 2026-08-29T10:26:46.591419+00:00, sha df2ebf80ab4e)
- Data as of 2026-08-30T08:39:29.467469+00:00.