使用正则表达式进行某网页中的email邮箱抽取

Posted 2020-10-29 不怕天黑

 1 import java.io.BufferedReader;
 2 import java.io.FileNotFoundException;
 3 import java.io.FileReader;
 4 import java.io.IOException;
 5 import java.util.regex.Matcher;
 6 import java.util.regex.Pattern;
 7 
 8 
 9 public class EmailSpider {
10 
11     public static void main(String[] args) {
12         try {
13             BufferedReader br = new BufferedReader(new FileReader("D:\\share\\courseware\\1043633.html"));
14             String line = "";
15             while((line=br.readLine()) != null) {
16                 parse(line);
17             }
18         } catch (FileNotFoundException e) {
19             // TODO Auto-generated catch block
20             e.printStackTrace();
21         } catch (IOException e) {
22             // TODO Auto-generated catch block
23             e.printStackTrace();
24         }
25     }
26 
27     private static void parse(String line) {
28         Pattern p = Pattern.compile("[\\w[.-]][email protected][\\w[.-]]+\\.[\\w]+");
29         Matcher m = p.matcher(line);
30         while(m.find()) {
31             System.out.println(m.group());
32         }
33     }
34 
35 }