正则表达式之搜索引擎

 

正则表达式之搜索引擎

 

 

import java.io.BufferedReader;

import java.io.InputStream;

import java.io.InputStreamReader;

import java.net.URL;

import java.net.URLConnection;

import java.util.regex.*;

 

publicclass Test {

 

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

 

 URLConnectionurlConnection = url.openConnection();

 

 InputStream inn = urlConnection.getInputStream();

 BufferedReader in = new BufferedReader(

   new InputStreamReader(inn));

 

 StringBuffer str = new StringBuffer();

// 给一个暖冲区2048

 char[] arrayBytes = newchar[2048];

 int i = 0;

 while((i = in.read(arrayBytes,0,2048)) != -1) {

 String str1 = new String(arrayBytes,0,i);

 str.append(str1);

 }

 

 // 正则表达式载取

 Pattern pattern = Pattern.compile("<//s*a//s+href//s*=/".*/"//s*>.*<//s*///s*a//s*>");

 Matcher matcher = pattern.matcher(str);

 inti1 = 0;

 while(m.find()) {

// 输出控制台

 System.out.println("   " + (i1++) + " " + matcher.group());

 }

 System.out.println(i1);

 }

}