Java正则表达式获取因特网址和链接文字

Java正则表达式获取网址和链接文字
public class Test {


      public static void main(String[] args)
      {
         
         
          //String s="<p id=km>&nbsp;<a href=http://hi.baidu.com>空间</a>&nbsp;|&nbsp;<a ";
          String s="</p><p style=height:14px><a href=http://jingjia.baidu.com>企业推广</a> | <a href=http://top.baidu.com>搜索风云榜</a> | <a href=/home.html>关于百度</a> | <a href=http://ir.baidu.com>About Baidu</a></p><p id=b>&copy;2008 Baidu <a href=http://www.baidu.com/duty>使用百度前必读</a> <a href=http://www.miibeian.gov.cn target=_blank>京ICP证030173号</a> <a href=http://www.hd315.gov.cn/beian/view.asp?bianhao=010202001092500412><img src=http://gimg.baidu.com/img/gs.gif></a></p></center></body></html><!--543ff95f18f36b11-->";
       
           String regex="<a.*?/a>";       
          //String regex = "<a.*>(.*)</a>";
          Pattern pt=Pattern.compile(regex);
          Matcher mt=pt.matcher(s);
          while(mt.find())
          {
               System.out.println(mt.group());
               System.out.println();
               String s2=">.*?</a>";//标题部分
               String s3="href=.*?>";
               
                Pattern pt2=Pattern.compile(s2);
                Matcher mt2=pt2.matcher(mt.group());
                while(mt2.find())
                  {
                 System.out.println("标题："+mt2.group().replaceAll(">|</a>",""));
                }
               
                Pattern pt3=Pattern.compile(s3);
                Matcher mt3=pt3.matcher(mt.group());
                while(mt3.find())
                  {
                 System.out.println("网址："+mt3.group().replaceAll("href=|>",""));
                }             
          }
      }


}