java 数据挖掘 URL 内容流

package com.url;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

/**
 *
 */
public class JavaUrl2 {
 
 public static boolean checkWebsite(String checkUrl) {
  try {
   URL url = new URL(checkUrl);
   HttpURLConnection httpsConn = (HttpURLConnection) url.openConnection();
   // 取得该连接的输入流，以读取响应内容
   InputStream ins = httpsConn.getInputStream();
   BufferedReader breader = new BufferedReader(new InputStreamReader(ins));
   String info = breader.readLine();
   long nowTime = new java.util.Date().getTime();
   while (info != null) {
    if (new java.util.Date().getTime() - nowTime > 10000)
     return false;// 达到10秒就认为超时
    info = breader.readLine();
    if(info!=null && info.indexOf("<a href=/"mp3")!=-1){
     info = info.substring(info.indexOf("<a href=/"mp3")+9,info.indexOf(".mp3/">")+4);
     System.out.print(checkUrl.substring(0,checkUrl.lastIndexOf("/")+1));
     System.out.println(info);
     return true;
    }
   }
  } catch (Exception e) {
   System.out.println("The error is:" + e.getMessage());
   e.printStackTrace();
   return false;
  }
  return false;
 }
 /**
  * create time：2009-8-5 下午02:33:45
  * @param args
  */
 public static void main(String[] args) {
  // TODO Auto-generated method stub
  String[] strArr = { 
    "http://www.baidu.com",
  };
  for(int i=0;i<strArr.length;i++){
    checkWebsite(strArr[i]);
  } 
 }

}