Java实现web页面内容抓取

package demo;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;

/**
 * web页面内容抓取
 * @author sy
 *
 */
public class GrabWebHtml{
    
    public static void main(String[] args) {
        String url="http://www.baidu.com";
        System.out.println(getWebHtml(url));
    }
    
    public static String getWebHtml(String domain) {
        StringBuffer sb = new StringBuffer();
        InputStream is = null;
        InputStreamReader isr = null;
        BufferedReader in = null;
        try {
            java.net.URL url = new java.net.URL(domain);
            is = url.openStream();
            isr = new InputStreamReader(is,"utf-8");
            in = new BufferedReader(isr);
            String line;
            while ((line = in.readLine()) != null) {
                sb.append(line).append("
");
            }
            in.close();
            
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            try {
                if(in!=null){
                    in.close();
                    in=null;
                }
                if(isr!=null){
                    isr.close();
                    isr=null;
                }
                if(is!=null){
                    is.close();
                    is=null;
                }
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return sb.toString();
    }

}