Java method of scraping email addresses on web pages

This article is an example of how Java can grab a mail address from a web page. Share with you for your reference. The specific implementation method is as follows:

import java.io.BufferedReader;  

import java.io.InputStreamReader;  

import java.net.URL;  

import java.util.regex.Matcher;  

import java.util.regex.Pattern;  

  

public class h1  

{  

   public static String   getWebCon(String domain)  

   {  

    System.out.println(" Start scraping email addresses ..("+domain+")");  

    StringBuffer sb=new StringBuffer();  

    try  

    {  

     java.net.URL url=new java.net.URL(domain);  

     BufferedReader in=new BufferedReader(new InputStreamReader(url.openStream()));  

     String line;  

     while((line=in.readLine())!=null)  

     {  

      parse(line);  

     }  

     in.close();  

    }  

    catch(Exception e)  

    {  

     sb.append(e.toString());  

     System.err.println(e);  

      

    }  

    return sb.toString();  

   }  

   public static void main(String[] args)  

   {  

    String s;  

    s=h1.getWebCon("http://post.baidu.com/f?kz=34942387"); //This is the web page to grab, you can try it yourself. < br / >
    //System.out.println(s);  

   }  

   private static void parse(String line)  

   {  

    Pattern p=Pattern.compile("[\w[.-]]+@[\w[.-]]+\.[\w]+");//Regular expression for mailboxes & NBSP; < br / >
    Matcher m=p.matcher(line);  

    while(m.find())  

    {  

     System.out.println(m.group());  

    }  

   }  

}

I hope this article has been helpful to your Java programming.