网页爬虫--从网页中获取邮箱地址

/*
网页爬虫(蜘蛛):
	获取指定文档或者网页中的邮件地址
	使用获取功能，Pattern   Matcher

*/
import java.net.*;
import java.io.*;
import java.util.regex.*;
class WebCrawler {
	public static void main(String[] args) throws Exception {
		//getMail_01();
		getMail_02();
	}
	//从指定网页中获取--------------------------------------------------------
	public static void getMail_02() throws Exception {
		//String path = "http://172.16.41.154:8080/myweb/demo.html";
		String path = "http://tieba.baidu.com/p/1664627884";
		URL url = new URL(path);
		URLConnection conn = url.openConnection();
		BufferedReader bufr = new BufferedReader(new InputStreamReader(conn.getInputStream()));
		PrintWriter pw = new PrintWriter(new FileWriter("mail.txt"), true);

		String line = null;
		String regex = "\\w+@\\w+(\\.[a-zA-Z]+)+";	//匹配邮箱地址
		Pattern p = Pattern.compile(regex);			//把正则封装成对象
		
		while((line=bufr.readLine()) != null) {
			//System.out.println(line);

			Matcher m = p.matcher(line);
			while(m.find()) {
				//System.out.println(m.group());
				//pw.println(m.group());				//把获取到的邮箱存到文件中
				pw.print(m.group()+ ";");				//把获取到的邮箱存到文件中
			}
		}
		pw.close();
		System.out.println(".....提取完毕");
	}

	//从本地文件中读获取--------------------------------------------------------
	public static void getMail_01() throws Exception {		
		BufferedReader bufr = new BufferedReader(new FileReader("unknown.txt"));
		PrintWriter pw = new PrintWriter(new FileWriter("mail.txt"), true);
		String line = null;
		String regex = "\\w+@\\w+(\\.[a-zA-Z]+)+";	//匹配邮箱地址
		Pattern p = Pattern.compile(regex);			//把正则封装成对象
		
		while((line=bufr.readLine()) != null) {
			//System.out.println(line);

			Matcher m = p.matcher(line);
			while(m.find()) {
				//System.out.println(m.group());
				pw.println(m.group());				//把获取到的邮箱存到文件中
			}
		}
		pw.close();
		System.out.println(".....提取完毕");
	}
}