*
     功能說明：分析字符串s，提取s里面的超鏈接和鏈接文字.并存入動態(tài)數(shù)組
     同時根據(jù)指定包含和不包含的字符串進行過濾相關(guān)鏈接。
     2008年3月30日
     
*/

import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.*;
public class RegTest
...{
    public static void main(String[] args)
    ...{

        //定義一個文章列表類。包含文章的網(wǎng)址和文章標(biāo)題
        class ArticleList
        ...{
            String URLs;
            String title;

            public ArticleList()...{}
            public ArticleList(String t,String u)
            ...{
                title=t;
                URLs=u;
            }
                   
            public String toString()
            ...{
                return ("標(biāo)題："+title+" 網(wǎng)址："+URLs+" ");
            }
        }
    
        ArrayList <ArticleList>  al=new ArrayList<ArticleList>();
        String s="</p><p style=height:14px><a href=http://jingjia.baidu.com>企業(yè)推廣</a> | <a href=http://top.baidu.com>搜索風(fēng)云榜</a> | <a href=/home.html>關(guān)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>使用百度前必讀</a> <a href=http://www.miibeian.gov.cn target=_blank>京ICP證030173號</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>";   
 
        Pattern pt=Pattern.compile(regex);
        //System.out.println(regex);
        Matcher mt=pt.matcher(s);
        String includeString=".*?baidu\.com.*?";//必須包含 字符串"baidu.com"
 
        while(mt.find())
        ...{
            if(mt.group().matches(includeString))
            ...{
                 //System.out.println(mt.group());
               
                 String s2=">.*?</a>";//標(biāo)題部分
                 String s3="href=.*?>";
                  
                  Pattern pt2=Pattern.compile(s2);
                  Matcher mt2=pt2.matcher(mt.group());
                  Pattern pt3=Pattern.compile(s3);
                  Matcher mt3=pt3.matcher(mt.group());
                  while(mt2.find()&&mt3.find())
                  ...{
                      //System.out.println("標(biāo)題："+mt2.group().replaceAll(">|</a>",""));
                      //System.out.println("網(wǎng)址："+mt3.group().replaceAll("href=|>",""));
                      String t=mt2.group().replaceAll(">|</a>","");
                      String u=mt3.group().replaceAll("href=|>","");
                      al.add(new ArticleList(t,u));
                  }
            }
           
        }//end while
       
        for(int i=0;i<al.size();i++)
        System.out.println(al.get(i));
        System.out.println("共有"+al.size()+"個結(jié)果");
    } 
}

文章出處：http://www.diybl.com/course/3_program/java/javajs/200843/108201.html