加载URL获得页面源代码

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;


import sun.net.www.protocol.http.HttpURLConnection;


/**
 * 通过加载给定的URL获得页面源文件
 * @author HaiCheng
 *
 */
public class UrlTest {
	public static void main(String[] args) throws IOException {
		String str="http://blog.csdn.net/caohaicheng"	;
		URL url=new URL(str);
		URLConnection con=url.openConnection();
		HttpURLConnection connection = (HttpURLConnection)con;//强转成URLConnection的子类   该子类是针对http的请求连接
		//设置请求头
			connection.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows; N; Windows NT 5.1; zh-CN) AppleWebKit/533.3 (KHTML, like Gecko) Qt/4.7.1 Safari/533.3");
			connection.setDoInput(true); 
			connection.setDoOutput(true); 
			connection.setInstanceFollowRedirects(false);
			connection.setRequestMethod("GET");
	    	connection.connect();
    	System.out.println( connection.getResponseCode());//HTTP响应码  200代表请求成功
		BufferedReader reader = null;
		InputStream is = null;   	 
		String currentLine = "";
		String content = "";
		is = connection.getInputStream();//URLConnection的方法 返回写入到此连接的输出流
			reader = new BufferedReader(new InputStreamReader(is , "UTF-8"));
			while((currentLine = reader.readLine())  != null)
			{
				if(currentLine.length()>0)
				{
					content = content + currentLine.trim();
				}
			}
		System.out.println(content);
		//将content内容放到EditPlus就是浏览器请求str得到的网页
	}	
}


你可能感兴趣的:(加载URL获得页面源代码)