def get_domains_by_ip(self, ip):
print_status('Start get domain by ip through bing...')
url = 'http://cn.bing.com/search?q=ip:%s&first=999999991&FORM=PERE' % ip
html = request(url, 'GET')
domain_regx = r'''
<h2><a\shref="https?://([^"]*?)"\starget="_blank"\sh="ID=[^"]*?">[^<]*?</a></h2>
'''
domain_list = re.findall(domain_regx, html, re.X)
total_page_regx = r'''<span\sclass="sb_count">\d*?\s-\s\d*?\s[^\(]*?\([^\s]*?\s(\d*?)\s[^\)]*?\)</span>'''
result = re.search(total_page_regx, html)
try:
total_num = int(result.group(1).replace(',', ''))
except:
total_num = 9
page_count = total_num / 9
if total_num % 9 > 0:
page_count += 1
print_status('Total pages: %s, Total domains:%s' % (page_count, total_num))
if page_count > 0:
for n in range(total_num-1):
print_status('Get page %s domains...' % str(n+1))
url = 'http://cn.bing.com/search?q=ip:%s&first=%s1&FORM=PERE3' % (ip, n)
html = request(url, 'GET')
new_domain_list = re.findall(domain_regx, html, re.X)
domain_list.extend(new_domain_list)
time.sleep(20)
domain_list = [
Domain.get_domain(domain)
for domain in domain_list
if Domain.get_domain(domain)
]
return list(set(domain_list))
def get_subdomain_by_links(self, domain, level=4):
domain = Domain.get_domain(domain)
url = 'http://i.links.cn/subdomain/'
data = {
'domain': domain,
'b2': 1,
'b3': 1 if level>=3 else 0,
'b4': 1 if level>=4 else 0,
}
html = request(url, 'POST', data=data)
regex = '''<a\shref="http://[^"]*?"\srel=nofollow\starget=_blank>http://([^"]*?)</a></div>'''
try:
result = re.findall(regex, html)
except:
result = []
time.sleep(3)
result.append(domain)
return list(set(result))
def get_subdomain_by_links(self, domain, level=4):
domain = Domain.get_domain(domain)
url = 'http://i.links.cn/subdomain/'
data = {
'domain': domain,
'b2': 1,
'b3': 1 if level >= 3 else 0,
'b4': 1 if level >= 4 else 0,
}
html = request(url, 'POST', data=data)
regex = '''<a\shref="http://[^"]*?"\srel=nofollow\starget=_blank>http://([^"]*?)</a></div>'''
try:
result = re.findall(regex, html)
except:
result = []
time.sleep(3)
result.append(domain)
return list(set(result))
def _get_text_list(self, config, value):
url = config[0] % value
regx = config[1]
text = request(url)
result = re.findall(regx, text, re.I|re.S|re.X)
return result
def _get_text_list(self, config, value):
url = config[0] % value
regx = config[1]
text = request(url)
result = re.findall(regx, text, re.I | re.S | re.X)
return result