yxhxj2006

留言簿(7)

隨筆分類

文章分類

paypal (rss)

隨筆檔案

閱讀排行榜

評論排行榜

常用鏈接

統計

隨筆 - 228
文章 - 0
評論 - 53
引用 - 0

Java通過URL獲取網站Html源代碼

package com.wsw.j2se.url;

import java.io.ByteArrayOutputStream;

import java.io.InputStream;

import java.net.HttpURLConnection;

import java.net.URL;

/**

* 通過網站域名URL獲取該網站的源碼

* @author Administrator

*

*/

public class HtmlRequest {

/**

* @param args

* @throws MalformedURLException

*/

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

URL url = new URL("http://www.ifeng.com");

String urlsource = getURLSource(url);

System.out.println(urlsource);

}

/**

* 通過網站域名URL獲取該網站的源碼

* @param url

* @return String

* @throws Exception

*/

public static String getURLSource(URL url) throws Exception {

HttpURLConnection conn = (HttpURLConnection)url.openConnection();

conn.setRequestMethod("GET");

conn.setConnectTimeout(5 * 1000);

InputStream inStream = conn.getInputStream(); //通過輸入流獲取html二進制數據

byte[] data = readInputStream(inStream); //把二進制數據轉化為byte字節數據

String htmlSource = new String(data);

return htmlSource;

}

/**

* 把二進制流轉化為byte字節數組

* @param instream

* @return byte[]

* @throws Exception

*/

public static byte[] readInputStream(InputStream instream) throws Exception {

ByteArrayOutputStream outStream = new ByteArrayOutputStream();

byte[] buffer = new byte[1204];

int len = 0;

while ((len = instream.read(buffer)) != -1){

outStream.write(buffer,0,len);

}

instream.close();

return outStream.toByteArray();

}

posted on 2012-07-19 12:40 奮斗成就男人閱讀(4525) 評論(3) 編輯收藏

# re: Java通過URL獲取網站Html源代碼 [未登錄] 2013-09-25 14:58 Robot

# re: Java通過URL獲取網站Html源代碼為什么代碼出來的不全 2013-12-06 13:10 永

# re: Java通過URL獲取網站Html源代碼 2015-02-05 23:29 zuidaima