Contents

sumy 0.11.0

0

Module for automatic summarization of text documents and HTML pages.

Simple library and command line utility for extracting summary from HTML pages or plain texts. The package also contains simple evaluation framework for text summaries. Implemented summarization methods are described in the documentation.

Stars: 3514, Watchers: 3514, Forks: 529, Open Issues: 24

The miso-belica/sumy repo was created 11 years ago and the last code push was 4 months ago.
The project is very popular with an impressive 3514 github stars!

How to Install sumy

You can install sumy using pip

pip install sumy

or add it to a project with poetry

poetry add sumy

Package Details

Author
Mišo Belica
License
Apache License, Version 2.0
Homepage
https://github.com/miso-belica/sumy
PyPi:
https://pypi.org/project/sumy/
GitHub Repo:
https://github.com/miso-belica/sumy

Classifiers

  • Education
  • Internet
  • Scientific/Engineering/Information Analysis
  • Text Processing/Filters
  • Text Processing/Linguistic
  • Text Processing/Markup/HTML
No  sumy  pypi packages just yet.

Errors

A list of common sumy errors.

Code Examples

Here are some sumy code examples and snippets.

  • Sumy Code Examples

    Sumy uses nlp to summarize content on webpages and in text files. The below sumy code example fetches a wikipedia page and extacts a 10 sentence summary.

GitHub Issues

The sumy package has 24 open issues on GitHub

  • Would you be interested in adding more modern extractive summarization methods using things like BERT?
  • Becomes slow with huge text

See more issues on GitHub

Related Packages & Articles

textblob 0.18.0.post0

Simple, Pythonic text processing. Sentiment analysis, part-of-speech tagging, noun phrase parsing, and more.

numerizer 0.2.4

Python module for converting natural language numbers into ints and floats.

langua 1.0.12

Faster port of Language detection built by Shuyo in Python