java爬虫--使用正则表达式获取网页中的email
package com.enation.newtest; import java.io.*; import java.util.regex.*; import java.net.*; public class MailTest{ public static void main(String[] args) throws Exception{ getMailAddr(); } public static void getMailAddr()throws Exception{ URL url=new URL("http://blog.sina.com.cn/s/blog_515617e60101e151.html"); URLConnection con=url.openConnection(); BufferedReader bufIn=new BufferedReader(new InputStreamReader(con.getInputStream())); BufferedWriter bufw=new BufferedWriter(new FileWriter(new File("D:\\360Downloads\\mailaddress2.txt"))); String str=null; String regex="[a-zA-Z0-9_]{6,12}@[a-zA-Z0-9]+(.[a-zA-Z]+)+"; Pattern p=Pattern.compile(regex); System.out.println("start"); while((str=bufIn.readLine())!=null) { Matcher m=p.matcher(str); while(m.find()){ String ss=m.group(); bufw.write(ss,0,ss.length()); bufw.newLine(); bufw.flush(); } } System.out.println("end"); } }
获取网页内容,并将页面中的邮件地址存存放在指定的路径中,写入到txt文件里