java爬虫--step1--简单网页获取

import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
//爬去电影天堂的最新电影
public class pp {

    public static void main(String[] args) throws IOException {
        // TODO Auto-generated method stub
        //读取网页源代码
        URL url = new URL("http://www.dytt8.net/");
        InputStream in = url.openStream();
        BufferedInputStream buff = new BufferedInputStream(in);
        byte[] bt = new byte[1024];
        int num;
        String html = "";
        while((num = buff.read(bt))!=-1) {
            String line = new String(bt,0,num,"gbk");
            html += line;
        }
        //System.out.println(html);
        //正则匹配得到需要的结果
        String regex = "<a href=\'/html/gndy/(.*?)\'>(.*?)</a><br/>";
        Pattern pattern = Pattern.compile(regex);
        Matcher matcher = pattern.matcher(html);
        while(matcher.find()){  
            System.out.println(matcher.groupCount());
            System.out.println(matcher.group(0));  
            System.out.println(matcher.group(1));
            System.out.println(matcher.group(2));  
        }  
    }
}