抓取百度一级页面

这个类是我工作之余写的一个小例子，供大家参考

 

 

import java.io.IOException;
import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;

public class SpiderBaidu {

 public void spiderBaiduBody() {
  URLConnection conn;
  try {
   conn = new URL(
     "http://www.baidu.com/s?lm=0&si=&rn=10&ie=gb2312&ct=0&wd=%B0%C2%D4%CB&pn=20&ver=0&cn=baidu01&cl=3")
     .openConnection();
   // conn.setRequestProperty("Cookie", partA.cookie);
   //setConnectTimeout设置链接服务器的最长时间
   conn.setConnectTimeout(1000);

   //从 URLConnection (或 URL) 对象中获得输入流 InputStream
   InputStream a = conn.getInputStream();

   int bt = 0;
   StringBuffer bs = new StringBuffer();
   while ((bt = a.read()) != -1) {
    bs.append((char) bt);
   }
   //将抓取到的内容字符编码转换为GBK的
   String recordStr = new String(bs.toString().getBytes("iso8859-1"),
     "gbk");
   System.out.println(recordStr);
   //去除网页文字的无关内容
   String splietBiaoTi = "<table border=/"0/" cellpadding=/"0/" cellspacing=/"0/">";
   //将其拆分为子字符串，然后以数组形式返回子字符串
   String strBiaoTiArr[] = recordStr.split(splietBiaoTi);
   for (int i = 0; i < strBiaoTiArr.length - 1; i++) {
    System.out
      .println("=========================================================================================");
    System.out.println(strBiaoTiArr[i]);
   }

  } catch (MalformedURLException e) {
   e.printStackTrace();
  } catch (IOException e) {
   e.printStackTrace();
  }

 }

 public static void main(String args[]) {
  SpiderBaidu sbd = new SpiderBaidu();
  sbd.spiderBaiduBody();
 }

}