博客第一天！努力的开始！

package bs;

import java.io.BufferedReader;

import java.io.FileReader;

import java.io.IOException;

import java.io.InputStreamReader;

import java.net.URL;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

import org.junit.Test;

public class SpideDemo {

 public static void main(String[] args) {

        try {

   URL url=new URL("http://www.sina.com");

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

   

   String regex="\\w+@\\w+(\\.\\w+)+";

   String regex1="<a href=";

   Pattern p=Pattern.compile(regex);

   String line=null;

   while((line=br.readLine())!=null){

    

    Matcher m=p.matcher(line);

    Matcher m1=p.matcher(regex1);

    while(m1.find()){

     

    }

    while(m.find()){

     System.out.println(m.group());

    }

   }

  } catch (Exception e) {

   e.printStackTrace();

  }

       

 }

 @Test

 public void hello(){

  try {

   BufferedReader br=new BufferedReader(new FileReader("./net/mail.html"));

   String regex="^[a-z0-9]+([._\\-]*[a-z0-9])*@([a-z0-9]+[-a-z0-9]*[a-z0-9]+.){1,63}[a-z0-9]+$";

   Pattern p=Pattern.compile(regex);

   String str=null;

   while((str=br.readLine())!=null){

    Matcher m=p.matcher(str);

    while(m.find()){

     System.out.println(m.group());

    }

   }

  } catch (IOException e) {

   e.printStackTrace();

  }

 }

}