获取网页的html文本

package com.huey.urldemo;

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

/**
 * 
 * @version 2013-08-05
 * @author huey2672
 *
 */
public class HtmlUtil {
	
	/**
	 * 获取指定网页的url的html文本
	 * @param urlStr	指定网页的url
	 * @return			html文本
	 */
	static public String getHtmlText(String urlStr) {
		
		URL url = null;
		URLConnection urlConn = null;
		InputStream ins = null;
		InputStreamReader insr = null;
		BufferedReader br = null;
		StringBuilder sb = new StringBuilder();
		
		try {
			// 创建URL实例
			url = new URL(urlStr);
			// 获取url连接
			urlConn = url.openConnection();
			// 获取输入流
			ins = urlConn.getInputStream();
			// 包装输入流，并指定为UTF-8编码
			insr = new InputStreamReader(ins, "UTF-8");
			br = new BufferedReader(insr);
			
			// 读取html文本内容
			String line = null;
			while ((line = br.readLine()) != null) {
				sb.append(line).append("\n");
			}
			
			// 关闭流
			br.close();
			insr.close();
		} catch (MalformedURLException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
		
		return sb.toString();	
	}
	
}