#!/root/.virtualenvs/script/bin/python #coding=utf-8 import re import time, mechanize import urllib2 import random URL = ‘http://whois.chinaz.com/‘ def str_cut(str,startsep,endsep): str1=str.split(startsep)[1] str2=str1.split(endsep)[0] return str2 br = mechanize.Browser() br.set_handle_equiv(True) br.set_handle_gzip(False) br.set_handle_redirect(True) br.set_handle_referer(True) br.set_handle_robots(True) br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1) #br.set_debug_http(True) #br.set_debug_redirects(True) #br.set_debug_responses(True) br.addheaders = [(‘User-agent‘, ‘Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0. 1‘)] domain_list = [你的域名列表] r = br.open(URL) for index, item in enumerate(domain_list): try: br.select_form(nr=0) br.form[‘DomainName‘] = item br.submit() contents = br.response().read() if contents.find(‘<div id="whoisinfo" class="div_whois">‘)==-1: print item + " " + "not found" else: contents=str_cut(contents,‘<div id="whoisinfo" class="div_whois">‘,‘</div>‘) contents=contents.replace(‘<br/>‘,‘,‘)[:-1] a = re.split(‘,‘,contents) for i in a: m = re.match(r"过期时间", i) if m: print ‘域名 : %s, 过期时间 : %s‘ % (item, re.sub(r"年|月", ‘-‘, i[15:-3]).strip()[:10]) br.back() except Exception,e: print Exception,":",e time.sleep(1.27*random.randint(4, 12)) |
本文出自 “xinsz08の平行时空” 博客,请务必保留此出处http://xinsz08.blog.51cto.com/10565212/1915945
原文地址:http://xinsz08.blog.51cto.com/10565212/1915945