DrDubWiki	Main Page | About | Help | FAQ | Special pages | Log in
	Category: Project Printable version | Disclaimers | Privacy policy

URL Classifier

From DrDubWiki

URL Classy: Guessing the class of URL from its tet

URL Classy is a library that assigns a top-level dmoz category based on the URL text. It is an implementation of URL-based classifiers.

In github: https://github.com/DrDub/urlclassy

See an example at: http://drdub.github.com/urlclassy/example

Links

• Similar services
  • http://www.cyberpatrol.com/research/sitereview.asp
  • http://www.uclassify.com/UrlApiDocumentation.aspx

• Using the page text
  • http://www.kindsight.net/en/categorizer-demo
  • http://www.programmableweb.com/api/url-classifier (discontinued)

• Research papers
  • http://infoscience.epfl.ch/record/136823/files/Topic_www_09.pdf
    • http://scholar.google.com/scholar?hl=en&lr=&cites=10066636259237732757&um=1&ie=UTF-8&sa=X&ei=NUySUNPyDpSg8gTH8YGABA&ved=0CEsQzgIwAw
  • http://wing.comp.nus.edu.sg/meurlin/nustrc8_05.pdf
    • http://scholar.google.com/scholar?hl=en&lr=&cites=6703768030271974033&um=1&ie=UTF-8&sa=X&ei=NUySUNPyDpSg8gTH8YGABA&ved=0CF0QzgIwBQ

• Tools
  • https://github.com/NaturalNode/natural
    • https://github.com/NaturalNode/apparatus
      • https://github.com/jcoglan/sylvester
  • Issue 847: 1gb memory limit

• Technology
  • http://en.wikipedia.org/wiki/Rolling_hash
  • https://github.com/lemire/rollinghashjava
  • http://code.google.com/p/smhasher/source/browse/trunk/MurmurHash3.cpp

View source | Discuss this page | Page history | What links here | Related changes Main Page | About DrDubWiki | Find: This page has been accessed 731 times. This page was last modified on 25 December 2012, at 07:30.