正则表达式--――网页爬虫

网页爬虫

importjava.net.*;
importjava.io.*;
importjava.util.regex.*;
classfindMail
{
	publicstaticvoidmain(String[]args)throwsException
	{
		//读取流关联文件
		//BufferedReaderbin=newBufferedReader(newFileReader("mail.txt"));
		//获取网页上的数据需要获取输入流来自网页端的URLConnection的getInputStream()来获取输入流
		URLurl=newURL("http://127.0.0.1:8080/myweb/mail.html");
		URLConnectionconn=url.openConnection();
		BufferedReaderbin=newBufferedReader(newInputStreamReader(conn.getInputStream()));

		Stringline=null;
		//定义邮箱格式正则规则
		Stringmailreg="\\w{2,13}@\\w{2,5}(\\.[a-z]+)+";
		//正则规则封装模式对象
		Patternp=Pattern.compile(mailreg);
		while((line=bin.readLine())!=null)
		{
			Matcherm=p.matcher(line);//将模式与字符串关联
			if(m.find())
			{
				System.out.println(m.group());
			}
			//System.out.println(line);
		}
	}
}