网页爬虫小程序

一个简单的网页爬虫程序：

/**
 * 网页爬虫 ：
 *      得到网页上的邮箱地址  
 *      得到网页上的时间戳
 */
public class RegexDemo
{
    public static void main(String[] args) throws IOException
    {
        String url_1 = "http://blog.sina.com.cn/s/blog_515617e60101e151.html";
        String url_2 = "http://bbs.tianya.cn/post-934-163735-1.shtml";

        //邮箱地址
        String reg_1 = "\\w+@\\w+(\\.\\w+)+";

        //格式为这样的时间戳：2017-10-25 08:41:27
        String reg_2 = "(\\d+-){2}\\d+ (\\d+:){2}\\d+";

        webCrawler(url_1, reg_1);//得到网页上的邮箱地址
        webCrawler(url_2,reg_2); //得到网页上的时间戳
    }
    /**
     * 
     * @param str :网址
     * @param regex :正则表达式
     * @throws IOException
     */
    public static void webCrawler(String str,String regex) throws IOException
    {
        URL url = new URL(str);
        URLConnection conn = url.openConnection();
        BufferedReader br = new BufferedReader(new InputStreamReader(conn.getInputStream()));
        String line = null;
        Pattern pattern = Pattern.compile(regex);
        while((line = br.readLine()) != null)
        {
            Matcher matcher = pattern.matcher(line);
            while(matcher.find())
            {
                System.out.println(matcher.group());
            }
        }
        br.close();
    }
}