使用Java爬虫抓取网页中的email地址

package regex;
 
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
/**
 * 网络爬虫，抓取网页中的email地址
 */
public class WebCrawlersDemo {
    
    public static void main(String[] args) throws Exception {
        URL url = new URL("https://www.douban.com/group/topic/44274322/");
        // 打开连接
        URLConnection conn = url.openConnection();
        // 设置连接网络超时时间
        conn.setConnectTimeout(1000 * 10);
        // 读取指定网络地址中的文件
        BufferedReader bufr = new BufferedReader(new InputStreamReader(conn.getInputStream()));
        String line = null;
        String regex = "[a-zA-Z0-9_-]+@\w+\.[a-z]+(\.[a-z]+)?";    // 匹配email的正则
        Pattern p = Pattern.compile(regex);
        while((line = bufr.readLine()) != null) {
            Matcher m = p.matcher(line);
            while(m.find()) {
                System.out.println(m.group());    // 获得匹配的email
            }
        }
    }
 
}