java读取html文件并抽取a href相关连接和链接标题

import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.*;
import java.io.*;
import java.nio.CharBuffer;
public class RegTest
{
    public static void main(String[] args)
    {
        //定义一个文章列表类。包含文章的网址和文章标题
        class ArticleList{
            String URLs;
            String title;
            public ArticleList(){}
            public ArticleList(String t,String u)
            {
                title=t;
                URLs=u;
                
            }
                   
            public String toString()
            {
                return ("标题："+title+" 网址："+URLs+" ");
               
            }
        }
        //----------start---读取HTML文件至buff--------------------------------------------------------