今天打算去淘宝买几个已备案域名，卖家发给我一个列表。想先查查收录，再看看域名过期时间。用curl+pcregrep完全能搞定，但是有个鸡肋就是不能控制多线程。所以用java来实现吧。

功能：查询百度收录、域名注册、过期、更新时间。

原理：get 百度搜索结果页和whois.chinaz.com查询页，然后正则一下。

import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.Scanner;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.TimeUnit;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class SiteBaidu {
 static String get(String url, String... _encoding) {
  String encoding = _encoding.length > 0 ? _encoding[0] : "UTF-8";
  String ret = "";
  try {
   URLConnection con = new URL(url).openConnection();
   con.addRequestProperty(
     "User-Agent",
     "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.71 Safari/537.36");
   InputStream in = con.getInputStream();
   byte[] buf = new byte[2048];
   int len = 0;
   ByteArrayOutputStream bo = new ByteArrayOutputStream();
   while ((len = in.read(buf)) > 0) {
    bo.write(buf, 0, len);
   }
   ret = new String(bo.toByteArray(), encoding);
   bo.close();
   in.close();
  } catch (IOException e) {
   e.printStackTrace();
  }
  return ret;
 }

 static Pattern baiduPattern = Pattern.compile("找到相关结果数(.*?)个");
 static Pattern updatePattern = Pattern.compile("更新时间：(.*?)<br/>");
 static Pattern createPattern = Pattern.compile("创建时间：(.*?)<br/>");
 static Pattern expPattern = Pattern.compile("过期时间：(.*?)<br/>");

 public static void main(String[] args) {
  try {
   int nThread = args.length > 0 ? Integer.parseInt(args[0]) : 10;
   ExecutorService ser = Executors.newFixedThreadPool(nThread);
   Scanner scan = new Scanner(System.in);
   System.out.println("域名\\t过期时间\\t注册时间\\t更新时间");
   while (scan.hasNextLine()) {
    String line = scan.nextLine().trim();
    if (line.length() > 0 && line.indexOf('.') > -1) {
     int index = -1;
     if ((index = line.indexOf("//")) > -1)
      line = line.substring(index + 2);
     if ((index = line.indexOf('/')) > -1)
      line = line.substring(0, index);
     final String site = line;
     ser.execute(new Runnable() {
      @Override
      public void run() {
       String ret = get("http://www.baidu.com/s?wd=site:"
         + site);
       Matcher m = baiduPattern.matcher(ret);
       String baiduSite = "0", update = "0", create = "0", exp = "0";
       if (m.find()) {
        baiduSite = m.group(1).replace(",", "");
       }

       ret = get("http://whois.chinaz.com/" + site);
       m = expPattern.matcher(ret);
       if (m.find())
        exp = m.group(1);
       m = createPattern.matcher(ret);
       if (m.find())
        create = m.group(1);
       m = updatePattern.matcher(ret);
       if (m.find())
        update = m.group(1);
       System.out.println(site + "\\t" + baiduSite + "\\t"
         + exp + "\\t" + create + "\\t" + update);
      }
     });
    }
   }
   scan.close();
   ser.shutdown();
   ser.awaitTermination(10, TimeUnit.DAYS);
   ser.shutdownNow();
  } catch (Exception e) {
   e.printStackTrace();
  }
 }
}