def parser = new org.cyberneko.html.parsers.SAXParser()
parser.setFeature('http://xml.org/sax/features/namespaces', false)
def page = new XmlParser(parser).parse('http://groovy.codehaus.org/')
def data = page.depthFirst().A.'@href'.grep{ it != null && it.endsWith('.html') }
data.each { println it }