java 取WEB资源的内容

canca canca
2008-05-13 08:06
1
0

作者:独钓寒江月

有时候需要取得网页内容,再分析处理。
会话管理、post方法等见代码注释。

<code>

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

public class GetHttp
{
    public String getValue(String url)
    {
        long stime = System.currentTimeMillis();
        String r = null;
      try{ 
         
          HttpURLConnection huc;
         
        InputStream  in;
        URL url1 = new URL(url);
        huc = (HttpURLConnection) url1.openConnection();

//      设置允许output
        if (!huc.getDoOutput())
        {
            huc.setDoOutput(true);
        }
//      设置为post/get方式
        huc.setRequestMethod("GET");
        /*
//      设置为cookie
        if(sessionId != null)
        {
            huc.setRequestProperty("Cookie", sessionId);
        }
        */
        //模拟浏览器
        huc.setRequestProperty("User-Agent","Mozilla/4.7 [en] (Win98; I)");
        //设置超时 3秒
        huc.setConnectTimeout(3000);
       
        /*
        ///////////////// 如果使用post方式,参数的传递
//        StringBuffer sb = new StringBuffer();
        sb.append("op=4117");
        sb.append("&i=17");
        sb.append("&o=0");
        sb.append("&l=110");
        sb.append("&t=WANGLUOGUIJI");
        sb.append("&u=4");
        sb.append("&d=1");
//        sb.append(pars);
//        sb.append("&spid=" + Const.FEE_SPID);
//        sb.append("&spv=" + Const.FEE_SP_VALIDATE);
       
//      post信息
//       OutputStream os = huc.getOutputStream();
//       os.write(sb.toString().getBytes("utf8"));
//       os.close();
       //huc.setDoOutput(false);
        */

       /////////////////////开始读 服务器的返回
       
       /*
//cookie       
        String cookieVal = huc.getHeaderField("Set-Cookie");
        if(cookieVal != null)
        {
            sessionId = cookieVal.substring(0, cookieVal.indexOf(";"));
        }
        */
      
        in = huc.getInputStream();
//        BufferedReader breader = new BufferedReader(new InputStreamReader(in , "utf8"));
        BufferedReader breader = new BufferedReader(new InputStreamReader(in , "gb2312"));
        String str=breader.readLine();
        while(str != null)
        {
          if(r != null)
              r += str;
          else
              r = str;
          str = breader.readLine();
        }
       
        //断开连接
        huc.disconnect();
       
        long etime = System.currentTimeMillis();
        System.out.println(".########################### web connect time : " + (etime-stime));
        return r;
      }
      catch(Exception e)
      {
          e.printStackTrace();
          return "";
      }
    }

    public static void main(String[] args ) throws Exception
    {
        String url = "http://www.baidu.com/";
        GetHttp gh = new GetHttp();
        String http = gh.getValue(url);
        gh = null;
       
        System.out.println(http);
    }

}


</code>

发表评论