Versions

Description

Webstruct is a library for creating statistical `NER <http://en.wikipedia.org/wiki/Named-entity_recognition>`_ systems that work on HTML data, i.e. a library for building tools that extract named entities (addresses, organization names, open hours, etc) from webpages.

Repository

https://github.com/scrapinghub/webstruct

Project Slug

webstruct

Last Built

1 year, 10 months ago passed

Maintainers

Home Page

https://github.com/scrapinghub/webstruct

Badge

Tags

nlp, ner, natural-language-processing

Short URLs

webstruct.readthedocs.io
webstruct.rtfd.io

Default Version

latest

'latest' Version

master