正则表达式 <A HREF>

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class RegexDemo {

    /**
     * @param args
     * @throws FileNotFoundException
     */
    public static void main(String[] args) throws Exception {
        // TODO Auto-generated method stub
        int count = 0;
        String fileName = "D:\\Users\\Administrator\\Desktop\\forRegex.txt";
        StringBuffer buffer = new StringBuffer(10240);
        FileReader fr = new FileReader(fileName);
        BufferedReader br = new BufferedReader(fr);
        while (br.ready()) {
            // System.out.println();
            buffer.append(br.readLine());
        }
        // 在HTML中取<a>到</a>
        // String regex =
//"(<a\\s+([^>h]|h(?!ref\\s))*href[\\s+]?=[\\s+]?('|\"))([^(\\s+|'|\")]*)([^>]*>)(.*?)</a>";
        // 在<a></a>中取href
        // String
        // regex="(?<=[\\s+]?href[\\s+]?=[\\s+]?('|\")?)[^(\"|')>]+?(?=\"|')";
        // 在<a></a>中同时取href与名称，使用group(4)与group(1)
        // String regex="((?<=[\\s+]?href[\\s+]?=[\\s+]?('|\")?)[^\"|'>]+?(?=\"|'))(.+?)?((?<=>)(.+?)?(?=</a>))";
        // 在<a></a>中取包含'登录'的链接
        //String regex = "((?<=[\\s+]?href[\\s+]?=[\\s+]?('|\")?)[^\"|'>]+?(?=\"|'))(.+?)?((?<=>).*登录.*(?=</a>))";
        //在html中同时取href与名称，使用group(3)与 group(5)
        String regex="<a\\s+([^>h]|h(?!ref\\s))*(?<=[\\s+]?href[\\s+]?=[\\s+]?('|\")?)([^\"|'>]+?(?=\"|'))(.+?)?((?<=>)(.+?)?(?=</a>))";
        Pattern p = Pattern.compile(regex);

        Matcher m = p.matcher(buffer.toString());

        System.out.println("INPUT: " + buffer);
        System.out.println("REGEX: " + regex + "\r\n");
        while (m.find()) {

            System.out.println(m.group(3) + ":" + m.group(5));
            //System.out.println(m.group(0) );
            count++;
        }
        if (count == 0) {
            System.out.println("NO MATCHES: ");
        }
        System.out.println("TOTAL:" + count);
    }

}

//BUG还是有的，花了一晚上时间