java之爬虫：爬取网页源代码

package com.dx.util;
import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;

public class CrawlerUtil {

/*
* 获取源代码
*/
public static String getHtmlSource(String url){

InputStream inputStream = null;
BufferedReader in = null;
StringBuilder htmlSource= new StringBuilder();

try {
//1.获取网址
URL u = new URL(url);
//2.打开连接
URLConnection conn = u.openConnection();
//3.获取输入流
inputStream = conn.getInputStream();
//4.将源代码写入内存(设置编码)
in = new BufferedReader(new InputStreamReader(inputStream,"utf-8"));
String str = "";
while((str = in.readLine()) != null){
htmlSource.append(str);
}
} catch (Exception e) {
e.printStackTrace();
}finally{
//关闭I/o
try {
if(in != null)in.close();
if(inputStream != null)inputStream.close();
} catch (IOException e) {
e.printStackTrace();
}

}
return htmlSource.toString();
}


public static void main(String[] args) {

String url = "http://v.baidu.com/";
System.out.println(getHtmlSource(url));
}
}