根据网页地址获取页面内容

package test;

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;

public class Test01 {

public static String getPageSource(String pageUrl,String encoding) {
StringBuffer sb = new StringBuffer();
try {
//构建一URL对象
URL url = new URL(pageUrl);
//使用openStream得到一输入流并由此构造一个BufferedReader对象
BufferedReader in = new BufferedReader(new InputStreamReader(url
.openStream(), encoding));
String line;
//读取www资源
while ((line = in.readLine()) != null) {
sb.append(line);
sb.append("\n");
}
in.close();
} catch (Exception ex) {
System.err.println(ex);
}
return sb.toString();
}

public static void main(String[] args) throws Exception{
String htmls = getPageSource("http://sports.sohu.com/","GBK");
System.out.println(htmls);
}

}