htm,html の拡張子をもったファイル全部列挙

chkTitle.groovy

//
// htm,html の拡張子をもったファイル全部列挙.
// さらに title 要素を調べる.
//


import java.util.regex.*


class Util {

	def fff = { it.isFile() && (it.name.endsWith('.htm') || it.name.endsWith('.html') ) } as FileFilter
	def ffd = { it.isDirectory() } as FileFilter


	def recur = { dir->

		dir.listFiles(fff).each{ htmllist.add(it) }

		dir.listFiles(ffd).each{
			recur( it )
		}
	}

	def htmllist
	def proc(){
		this.htmllist = []
		recur( new File('.') )
		this.htmllist
	}
}

new Util().proc().each{ file->

	def enc = 'UTF-8'

	def rlist=[]
	file.newReader(enc).each{

		def r = '<title>(.*)</title>'
		def p = Pattern.compile(r)
		def m = p.matcher(it)
		if( m.find() ){
			def t = m.group(1)
			println t
		}
	}
}

listhtml.groovy

//
// htm,html の拡張子をもったファイル全部列挙.
//


class Util {

	def fff = { it.isFile() && (it.name.endsWith('.htm') || it.name.endsWith('.html') ) } as FileFilter
	def ffd = { it.isDirectory() } as FileFilter


	def recur = { dir->

		dir.listFiles(fff).each{ println it }

		dir.listFiles(ffd).each{
			recur( it )
		}
	}

	def proc(){
		recur( new File('.') )
	}
}

new Util().proc()