ウェブページのタイトルを取得

title_fetcher.groovy

@Grab(group='nekohtml', module='nekohtml', version='1.9.6')
import org.cyberneko.html.parsers.SAXParser

def title = { 
	def t = null
	new XmlSlurper(new SAXParser()).parse(it).'**'.findAll{
		if( it.name() == 'TITLE' ){ t = it.toString() }
	}
	t.trim()
}

def encode = { URL url->
	def encode = null

	def r = new BufferedReader(new InputStreamReader(url.openStream()) )
	while( true ){
		def line = r.readLine()
		if( line == null ){
			break
		}
		if( (line =~ /meta/ || line =~ /META/) && line =~ /charset/ ){
			//println line
			def pat = java.util.regex.Pattern.compile('charset=(.*)"')
			def m   = pat.matcher(line)
			if( m.find() ){
				encode = m.group(1)
			}
			break
		}
	}
	r.close()

	encode
}



def url = new URL(args[0])
def enc = encode(url)
if( enc==null ){ enc = 'UTF-8' }
def r = new BufferedReader(new InputStreamReader(url.openStream(),enc) )
println title( r )
r.close()