<?xml version="1.0" encoding="UTF-8" ?>
<rdf:RDF xmlns="http://usefulinc.com/ns/doap#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"><Project><name>webstemmer</name>
<shortdesc>A web crawler and HTML layout analyzer</shortdesc>
<description>Webstemmer is a web crawler and HTML layout analyzer. It extracts articles from
news sites as plain text and removes banners, ads and/or navigation links
automatically. You only need to give a URL of the top page of a site and it
works in an almost fully automatic way with little human intervention.</description>
<download-page>http://www.unixuser.org/~euske/python/webstemmer/webstemmer-0.6.1.tar.gz</download-page>
<homepage rdf:resource="http://www.unixuser.org/~euske/python/webstemmer/" />
<maintainer><foaf:Person><foaf:name>Yusuke Shinyama</foaf:name>
<foaf:mbox_sha1sum>7d040fdc296db36cee4ab11f12437142d8f2de85</foaf:mbox_sha1sum></foaf:Person></maintainer>
<release><Version><revision>0.6.1</revision></Version></release>
</Project></rdf:RDF>