寻找可访问的随机网站（代码）

利用InetAddress.getAllByName(site)寻找随机网站。该方法，如果site可访问，则返回InetAddress[]，否则将抛出UnknownHostException。程序一个明显的问题是效率不高，在无用的链接上浪费时间过多，平均每找到一个花时间2－5秒；这是很恐怖的。

package corejava.chapter.network;

import java.net.InetAddress;
import java.net.UnknownHostException;
import java.util.Calendar;
import java.util.Random;
import java.util.Vector;

/**
 * 随机搜寻可以访问的网址
 */
public class LookforWWWSite {
	private static Random r = new Random();
	private static final int WANTSITESCOUNT = 10;
	/**
	 * 随机生成指定长度字符的2、3级域名
	 * 
	 * @param bits
	 * @return
	 */
	private static String getPrename (int bits) {
		char[] chars = new char[bits];
		for (int i = 0; i < bits; i++) {
			chars[i] = (char) (r.nextInt(26) + 97);	//a~z
		}
		return "www." + new String(chars);
	}

	/**
	 * 网址生成规则，3级别域名+ 2级域名 + 1级域名 
	 * 3级域名:www 2级域名：3-5位字符组合
	 * 
	 * @param args
	 */

	public static void main(String[] args) {
		Vector<String> sites = new Vector<String>();
		String[] name1 = { ".com", ".net", ".org", ".cn" };
		System.out.println("Start at "+ Calendar.getInstance().getTime());
		long start = Calendar.getInstance().getTimeInMillis();
		while (true) {
			String prename = getPrename(3 + r.nextInt(3));	// 3~5
			for (String n1 : name1) {
				try {
					String site = prename + n1;
					InetAddress.getAllByName(site);
					if (!sites.contains(site)) {
						sites.add(site);
						if (sites.size() >= WANTSITESCOUNT)	break;
					}
				} catch (UnknownHostException e) {
				}
			}
			if (sites.size() >= WANTSITESCOUNT)	break;
		}
		long end = Calendar.getInstance().getTimeInMillis();
		System.out.println("Take time in millis : "+ (end - start)); 
		for (String site : sites)
			System.out.println(site);
	}

}

输出结果：
Start at Wed Mar 19 14:56:18 CST 2008
Take time in millis : 41672
www.nag.com
www.nag.net
www.nag.org
www.rdlz.com
www.rdlz.cn
www.ctm.com
www.ctm.net
www.ctm.org
www.ctm.cn
www.pqqz.com