#!/usr/bin/env python
#encoding: utf-8
import re
import sys
import json
import time
import requests
import urllib
import requests.packages.urllib3
from multiprocessing import Pool
from BeautifulSoup import BeautifulSoup
requests.packages.urllib3.disable_warnings()
 
headers = {'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20'}
 
def links_ip(host):  
  '''
  查询同IP网站
  '''
  ip2hosts = []
  ip2hosts.append("http://"+host)
  try:
    source = requests.get('http://i.links.cn/sameip/' + host + '.html', headers=headers,verify=False)
    soup = BeautifulSoup(source.text)
    divs = soup.findAll(style="word-break:break-all")
     
    if divs == []: #抓取结果为空
      print 'Sorry! Not found!'
      return ip2hosts 
    for div in divs:
      #print div.a.string
      ip2hosts.append(div.a.string)
  except Exception, e:
    print str(e)
    return ip2hosts
  return ip2hosts
 
def ip2host_get(host):
  ip2hosts = []
  ip2hosts.append("http://"+host)
  try:
    req=requests.get('http://www.ip2hosts.com/search.php"%s" % str(e)
    #print host
    pass
  else:
    print host,server
 
def aizhan(host):
  ip2hosts = []
  ip2hosts.append("http://"+host)
  regexp = r'''<a href="[^']+" rel="external nofollow"  target="_blank">\1</a>'''
  regexp_next = r'''<a href="http://dns.aizhan.com/[^/]+" rel="external nofollow" >%d</a>'''
  url = 'http://dns.aizhan.com/%s/%d/'
 
  page = 1
  while True:
    if page > 2:
      time.sleep(1)  #防止拒绝访问
    req = requests.get(url % (host , page) ,headers=headers ,verify=False)
    try:
      html = req.content.decode('utf-8') #取得页面
      if req.status_code == 400:
        break
    except Exception as e:
      print str(e)
      pass
    for site in re.findall(regexp , html):
      ip2hosts.append("http://"+site)
    if re.search(regexp_next % (page+1 , page+1) , html) is None:
      return ip2hosts
      break
    page += 1
 
  return ip2hosts
 
def chinaz(host):
  ip2hosts = []
  ip2hosts.append("http://"+host)
  regexp = r'''<a href='[^']+"javascript:" rel="external nofollow" val="%d" class="item[^"]*">%d</a>'''
  url = 'http://s.tool.chinaz.com/same"http://"+site)
    if re.search(regexp_next % (page+1 , page+1) , html) is None:
      return ip2hosts
      break
    page += 1
  return ip2hosts
 
def same_ip(host):
  mydomains = []
  mydomains.extend(ip2host_get(host))
  mydomains.extend(links_ip(host))
  mydomains.extend(aizhan(host))
  mydomains.extend(chinaz(host))
  mydomains = list(set(mydomains))
  p = Pool()
  for host in mydomains:
    p.apply_async(filter, args=(host,))
  p.close()
  p.join()
 
 
if __name__=="__main__":
  if len(sys.argv) == 2:
    same_ip(sys.argv[1])
  else:
    print ("usage: %s host" % sys.argv[0])
    sys.exit(-1)