#!/usr/bin/env python
# -*- coding:utf-8 -*-
# __author__ = 'kiki'
import urllib2
import time
from bs4 import BeautifulSoup
import sys
reload(sys)
sys.setdefaultencoding('utf8')
def getexpiredate(domain):
url = "http://tool.chinaz.com/DomainDel/?wd=" + domain # domain为txt文件，存储要查询的url
header = {'User-Agent': 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)'}
request = urllib2.Request(url, None, header)
response = urllib2.urlopen(request, None, timeout=30).read()
soup = BeautifulSoup(response, "html.parser", from_encoding='utf-8')
content = soup.find_all('div', attrs={'class': 'fr zTContrig'})
title = '<tr align="center"><td>%s</td>
' % domain
f = open('DomainExpireDate.html', 'a+')
f.write(title)
time.sleep(2)
for div in content:
for i in div.strings:
table_text = "<td>%s</td>
" % i
f.write(table_text)
f.write('</tr>
')
if __name__ == "__main__":
with open('DomainExpireDate.html', 'w') as DomainExpireDate:
head = '<html lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
<title>DomainExpireDate</title>
<style type="text/css">thead {color:green; height:50px;} tbody{color:blue; height:50px}</style></head>
<body>
<table width="1000" border="1" align="center">
<caption align="top">域名过期时间表</caption>
'
table_head = '<thead><tr align="center" bgcolor="#ccc"><th>Domain</th><th>域名年龄</th><th>域名创建时间</th><th>域名过期时间</th><th>域名删除时间</th><th>删除倒计时</tr></tr></thead>
<tbody>
'
DomainExpireDate.write(head)
DomainExpireDate.write(table_head)
with open('domains.txt', 'r') as domains:
for domain in domains.read().splitlines():
getexpiredate(domain)
with open('DomainExpireDate.html', 'a+') as DomainExpireDate:
DomainExpireDate.write('</tbody>
</body>
</html>')
一个最直接的方法就是使用whois模块
import whois a = whois.whois('baidu.com') print(a["expiration_date"][0])