dispatch+Lift+scala-ioでスクレイピング

WebScraping.scala

package com.github.tototoshi.example

import scala.xml.{ NodeSeq, Elem }

import dispatch._

import net.liftweb._
import common._
import util._

import scalax.io._

object Filename {
  def unapply(url: String): Option[String] = {
    url.split("/").reverse.toList.headOption
  }
}

object Main {

  def save(url: String): Unit = {
    val data = Resource.fromURL(url).byteArray
    println("downloading: %s ..." format url)
    url match {
      case Filename(file) => Resource.fromFile(new java.io.File("data", file)).write(data)
      case _ => sys.error("Oops!")
    }
  }

  def jpgFilter(filename: NodeSeq): Boolean = filename.text endsWith ".jpg"

  def main(args: Array[String]): Unit = {
    val h = new Http
    val req = url("http://satlog.blog119.fc2.com/blog-entry-2943.html") >\ "EUC-JP"
    val html: String = h(req as_str)

    val elem: NodeSeq = Html5.parse(html) openOr NodeSeq.Empty

    elem \\ "img" \\ "@src" filter jpgFilter foreach { img => save(img.text) }
  }
}