Java爬虫

时间：2014-05-29 05:08:30 阅读：381 评论：0 收藏：0 [点我收藏+]

1.昨天复习了Java基础(I/O流)和正则表达式

今天不讲Java中的 I/O

　主要用一个实例来爬取网站中的邮箱

代码如下:

 1 package com.miao.baba.pacong;
 2 
 3 import java.io.BufferedReader;
 4 import java.io.IOException;
 5 import java.io.InputStream;
 6 import java.io.InputStreamReader;
 7 import java.net.URL;
 8 import java.net.URLConnection;
 9 import java.util.regex.Matcher;
10 import java.util.regex.Pattern;
11 
12 public class Reptile {
13 
14     public static void main(String[] args) throws IOException {
15         String email = "[a-zA-Z0-9_]+@[a-zA-Z0-9]+(\\.[a-zA-Z0-9]+)+";
16         Pattern p = Pattern.compile(email);
17         URL url = new URL("http://acm.hrbust.edu.cn");
18 
19         URLConnection conn = url.openConnection();
20 
21         InputStream in = conn.getInputStream();
22         InputStreamReader isr = new InputStreamReader(in);
23         BufferedReader br = new BufferedReader(isr);
24 
25         String line = null;
26         while ((line = br.readLine()) != null) {
27             Matcher m = p.matcher(line);
28 
29             while (m.find()) {
30                 System.out.println(m.group());
31             }
32         }
33         br.close();
34     }
35 }