HTML资料的100%提取

package jing.reg;

/**
* 字符串匹配100%提取

*/
import java.util.*;
import java.io.*;
import java.net.URLConnection;
import java.net.URL;

public class Stringindexof {
    public Stringindexof() {
    }

    public static void main(String[] args) throws Exception {
        //读取网URL上的文件 运得时注意思url是不能正常打开
        URL url = new URL("http://www.08866.com/phrase_shortshow.asp?smallname=玉女心经&smallid=5&maxpage=200");
        URLConnection urlconn = url.openConnection();
        BufferedReader in = new BufferedReader(new InputStreamReader(urlconn.
                getInputStream(), "GB2312"));
        String subline = null;
        String lineall = null;
        while ((subline = in.readLine()) != null) {
            lineall = lineall + subline;
        }
        in.close();

        PrintWriter fileout = new PrintWriter(new FileOutputStream("玉女心经.txt"));
//提取title=" "格式的中的文字
        subline = lineall;
        int i = 0;
        while (true) {
            lineall = subline;
            int star = lineall.indexOf("title=");
            if (star < 0) {
                break;
            }
            int end = lineall.indexOf("class", star);
            if (end > star) {
                i = i + 1;
                //System.out.println(lineall.substring(star, end));
                fileout.println(lineall.substring(star, end));
                subline = lineall.substring(end + 5);
            } else {
                subline = lineall.substring(star + 6);
            }
        }
        fileout.close();
        System.out.println(i + "行数据");
    }
}