Skip to main content

Module for automatic summarization of text documents and HTML pages.

Project description

https://api.travis-ci.org/miso-belica/sumy.png?branch=master

Here are some other summarizers:

Installation

Make sure you have Python 2.6+/3.2+ and pip (Windows, Linux) installed. Run simply (preferred way):

$ [sudo] pip install sumy

Or for the fresh version:

$ [sudo] pip install git+git://github.com/miso-belica/sumy.git

Or if you have to:

$ wget https://github.com/miso-belica/sumy/archive/master.zip # download the sources
$ unzip master.zip # extract the downloaded file
$ cd sumy-master/
$ [sudo] python setup.py install # install the package

Usage

Sumy contains command line utility for quick summarization of documents.

$ sumy lex-rank --length=10 --url=http://en.wikipedia.org/wiki/Automatic_summarization # what's summarization?
$ sumy luhn --language=czech --url=http://www.zdrojak.cz/clanky/automaticke-zabezpeceni/
$ sumy edmundson --language=czech --length=3% --url=http://cs.wikipedia.org/wiki/Bitva_u_Lipan
$ sumy --help # for more info

Various evaluation methods for some summarization method can be executed by commands below:

$ sumy_eval lex-rank reference_summary.txt --url=http://en.wikipedia.org/wiki/Automatic_summarization
$ sumy_eval lsa reference_summary.txt --language=czech --url=http://www.zdrojak.cz/clanky/automaticke-zabezpeceni/
$ sumy_eval edmundson reference_summary.txt --language=czech --url=http://cs.wikipedia.org/wiki/Bitva_u_Lipan
$ sumy_eval --help # for more info

Python API

Or you can use sumy like a library in your project.

# -*- coding: utf8 -*-

from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

from sumy.parsers.html import HtmlParser
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
from sumy.utils import get_stop_words


LANGUAGE = "czech"
SENTENCES_COUNT = 10


if __name__ == "__main__":
    url = "http://www.zsstritezuct.estranky.cz/clanky/predmety/cteni/jak-naucit-dite-spravne-cist.html"
    parser = HtmlParser.from_url(url, Tokenizer(LANGUAGE))
    # or for plain text files
    # parser = PlaintextParser.from_file("document.txt", Tokenizer(LANGUAGE))
    stemmer = Stemmer(LANGUAGE)

    summarizer = Summarizer(stemmer)
    summarizer.stop_words = get_stop_words(LANGUAGE)

    for sentence in summarizer(parser.document, SENTENCES_COUNT):
        print(sentence)

Tests

Run tests via

$ nosetests-2.6 && nosetests-3.2 && nosetests-2.7 && nosetests-3.3

Changelog

0.3.0 (2014-06-07)

  • Added possibility to specify format of input document for URL & stdin. Thanks to @Lucas-C.
  • Added possibility to specify custom file with stop-words in CLI. Thanks to @Lucas-C.
  • Added support for French language (added stopwords & stemmer). Thanks to @Lucas-C.
  • Function sumy.utils.get_stop_words raises LookupError instead of ValueError for unknown language.
  • Exception LookupError is raised for unknown language of stemmer instead of falling silently to null_stemmer.

0.2.1 (2014-01-23)

  • Fixed installation of my own readability fork. Added breadability to the dependencies instead of it #8. Thanks to @pratikpoddar.

0.2.0 (2014-01-18)

  • Removed dependency on SciPy #7. Use numpy.linalg.svd implementation. Thanks to Shantanu.

0.1.0 (2013-10-20)

  • First public release.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
sumy-0.3.0-py2.py3-none-any.whl (42.1 kB) Copy SHA256 hash SHA256 Wheel 2.7 Jun 7, 2014
sumy-0.3.0.zip (45.7 kB) Copy SHA256 hash SHA256 Source None Jun 7, 2014

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page