java中如何根据一个网址获得该网页的源代码？

package test

import java.io.BufferedReader

import java.io.InputStreamReader

import java.net.HttpURLConnection

import java.net.URL

public class HttpTest {

private String u

private String encoding

public static void main(String[] args) throws Exception {

HttpTest client = new HttpTest("http://www.baidu.com/", "UTF-8")

client.run()

}

public HttpTest(String u, String encoding) {

this.u = u

this.encoding = encoding

}

public void run() throws Exception {

URL url = new URL(u)// 根据链接（字符串格式），生成一个URL对象

HttpURLConnection urlConnection = (HttpURLConnection) url

.openConnection()// 打开URL

BufferedReader reader = new BufferedReader(new InputStreamReader(

urlConnection.getInputStream(), encoding))// 得到输入流，即获得了网页的内容

String line// 读取输入流的数据，并缺兄显示

while ((line = reader.readLine()) != null) {

System.out.println(line)

}

}

}

根据具体悔困问题类型，进行步骤拆解／原碧扮念因原理分析／内容拓展等。

具体步骤如下：／导致这种情况的原因主要是……

传入一个url，返回源代码； public static String getHTML(String url){// 获取指定唯哪URL的网页，返回网指漏码页内容的字符串，然后将此字符串搜世存到文件即可 try { URL newUrl = new URL(url)URLConnection connect = newUrl.openConnection()connect.setRequestProperty("User-Agent","Mozilla/4.0 (compatibleMSIE 5.0Windows NTDigExt)")DataInputStream dis = new DataInputStream(connect.getInputStream())BufferedReader in = new BufferedReader(new InputStreamReader(dis,"UTF-8"))String html = ""String readLine = nullwhile((readLine = in.readLine()) != null) { html = html + readLine} in.close()return html}catch (MalformedURLException me){ System.out.println("MalformedURLException" + me)}catch (IOException ioe){ System.out.println("ioeException" + ioe)} return null}

---