本例子主要是获得网页中的代码:

package net;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.Collection;
import java.util.Iterator;
import java.util.LinkedList;

/**
 * 解析网页中的内容
 */
public class internetContent{
	public static Collection<String> getURLCollection(String address){
		Collection<String> collection = new LinkedList<String>();
		try{
			URL url = new URL(address);
			URLConnection conn = url.openConnection();
			conn.connect();
			InputStream in = conn.getInputStream();
			InputStreamReader input = new InputStreamReader(in, "UTF-8");
			BufferedReader buf = new BufferedReader(input);
			String nextLine = buf.readLine();

			while(nextLine != null){
				collection.add(nextLine);
				nextLine = buf.readLine();
			}
		}catch(Exception e){
			e.printStackTrace();
		}
		return collection;
	}

	public static void main(String[] args){
		String address = "http://www.baidu.com";
		Collection urlCollection = getURLCollection(address);
		Iterator iter = urlCollection.iterator();
		String buf = "";
		while(iter.hasNext()){
			buf += ((String) iter.next() + "\n");
		}
		System.out.println(buf);
	}
}

运行结果:

<!doctype html><html><head><meta http-equiv="Content-Type" content="text/html;charset=gb2312"><title>?????????????      </title><style>html{overflow-y:auto}body{font:12px arial;text-align:center;background:#fff}body,p,form,ul,li{margin:0;padding:0;list-style:none}body,form,#fm{position:relative}td{text-align:left}img{border:0}a{color:#00c}a:active{color:#f60}#u{padding:7px 10px 3px 0;text-align:right}#m{width:680px;margin:0 auto}#nv{font-size:16px;margin:0 0 4px;text-align:left;text-indent:117px}#nv a,#nv b,.btn,#lk{font-size:14px}#fm{padding-left:90px;text-align:left}#kw{width:404px;height:22px;padding:4px 7px;padding:6px 7px 2px\9;font:16px arial;background:url(http://www.baidu.com/img/i-1.0.0.png) no-repeat -304px 0;_background-attachment:fixed;border:1px solid #cdcdcd;border-color:#9a9a9a #cdcdcd #cdcdcd #9a9a9a;vertical-align:top}.btn{width:95px;height:32px;padding:0;padding-top:2px\9;border:0;background:#ddd url(http://www.baidu.com/img/i-1.0.0.png) no-repeat;cursor:pointer}.btn_h{background-position:-100px 0}#kw,.btn_wr{margin:0 5px 0 0}.btn_wr{width:97px;height:34px;display:inline-block;background:url(http://www.baidu.com/img/i-1.0.0.png) no-repeat -202px 0;_top:1px;*position:relative}#lk{margin:33px 0}#lk span{font:14px "????"}#lm{height:60px}#lh{margin:16px 0 5px;word-spacing:3px}#mCon{height:18px;line-height:18px;position:absolute;right:7px;top:8px;top:10px\9;cursor:pointer;padding:0 18px 0 0;background:url(http://www.baidu.com/img/bg-1.0.0.gif) no-repeat right -134px;background-position:right -136px\9}#mCon span{color:#00c;cursor:default;display:block}#mCon .hw{text-decoration:underline;cursor:pointer}#mMenu{width:56px;border:1px solid #9a99ff;list-style:none;position:absolute;right:7px;top:28px;display:none;background:#fff}#mMenu a{width:100%;height:100%;display:block;line-height:22px;text-indent:6px;text-decoration:none}#mMenu a:hover{background:#d9e1f6}#mMenu .ln{height:1px;background:#ccf;overflow:hidden;margin:2px;font-size:1px;line-height:1px}#cp,#cp a{color:#77c}#sh{display:none;behavior:url(#default#homepage)}#user{color:#00c;position:relative;display:inline-block;cursor:pointer}#user strong{text-decoration:underline}#user ul{width:67px;background:#fff;border:1px solid #9a99ff;position:absolute;right:0;top:18px;display:none}#user li{height:22px;border-bottom:1px solid #e6e6e6}#user li a{width:100%;height:17px;padding-top:5px;display:block;text-align:left;text-decoration:none;text-indent:10px}#user li a:hover{background:#d9e1f6}#user li.nl{border:none}</style></head>
<body><div ></script>
</html><!--9037e478e44a84b0-->


相关文章: