Scala language page pdf all download script

README.md

Scala公式ページの論文一覧のページのhtmlをパースして、自動でpdfのファイルっぽいものを全部ダウンロードするだけのものです

gistfile1.scala

object Main {
  
  def main(args : Array[String]){
    getURLList("http://www.scala-lang.org/node/143").map{ url =>
      try {
        save( url , url.split("/").last )
      } catch {
        case e: java.io.IOException =>
          System.err.println("Failed to save: " + url)
          e.printStackTrace()
      }
    }
  }
  
  def getURLList(url:String):List[String] = {
    val html = io.Source.fromURL(url,"UTF-8").mkString
    val reg = """(http://[\w\.\~\-\/\?\&\+\=\:\@\%\#]*?\.pdf)""".r
    reg.findAllIn(html).toList
  }

  def save(url:String,fileName:String){
    System.err.println("Downloading " + url)
    val in = new java.io.BufferedInputStream( new java.net.URL(url).openStream )
    val out = new java.io.PrintStream(fileName )
    val b = new Array[Byte](8192);  
    var i = 0
    while ( { i = in.read(b); i } >= 0) {
      out.write(b,0,i)
    }
    out.close
    in.close 
    System.err.println("Done")
  }

}