def parser(self, response):
npage = re.search('<A href="(.*?)"><b>Next page</b></a>', response)
if npage:
for item in self.get_subdomains(response):
if is_domain(item):
self.subset.append(item)
nurl = '{0}{1}'.format(self.site, npage.group(1))
r = http_request_get(nurl, custom_cookie=self.cookie)
time.sleep(3)
self.parser(r.text)
else:
for item in self.get_subdomains(response):
if is_domain(item):
self.subset.append(item)
def fetch_alexa_cn(self):
"""get subdomains from alexa.cn"""
sign = self.get_sign_alexa_cn()
if sign is None:
raise Exception("sign_fetch_is_failed")
else:
(domain, sig, keyt) = sign
pre_domain = self.domain.split('.')[0]
url = 'http://www.alexa.cn/api_150710.php'
payload = {
'url': domain,
'sig': sig,
'keyt': keyt,
}
r = http_request_post(url, payload=payload).text
for sub in r.split('*')[-1:][0].split('__'):
if sub.split(':')[0:1][0] == 'OTHER':
break
else:
sub_name = sub.split(':')[0:1][0]
sub_name = ''.join((sub_name.split(pre_domain)[0], domain))
if is_domain(sub_name):
self.subset.append(sub_name)
def fetch_alexa_cn(self):
"""get subdomains from alexa.cn"""
sign = self.get_sign_alexa_cn()
if sign is None:
raise Exception("sign_fetch_is_failed")
else:
(domain,sig,keyt) = sign
pre_domain = self.domain.split('.')[0]
url = 'http://www.alexa.cn/api_150710.php'
payload = {
'url': domain,
'sig': sig,
'keyt': keyt,
}
r = http_request_post(url, payload=payload).text
for sub in r.split('*')[-1:][0].split('__'):
if sub.split(':')[0:1][0] == 'OTHER':
break
else:
sub_name = sub.split(':')[0:1][0]
sub_name = ''.join((sub_name.split(pre_domain)[0], domain))
if is_domain(sub_name):
self.subset.append(sub_name)
def fetch_chinaz(self):
"""get subdomains from alexa.chinaz.com"""
url = 'http://alexa.chinaz.com/?domain={0}'.format(self.domain)
r = http_request_get(url).text
subs = re.compile(r'(?<="\>\r\n<li>).*?(?=</li>)')
result = subs.findall(r)
for sub in result:
if is_domain(sub):
self.subset.append(sub)
def fetch_chinaz(self):
"""get subdomains from alexa.chinaz.com"""
url = 'http://alexa.chinaz.com/?domain={0}'.format(self.domain)
r = http_request_get(url).content
subs = re.compile(r'(?<="\>\r\n<li>).*?(?=</li>)')
result = subs.findall(r)
for sub in result:
if is_domain(sub):
self.subset.append(sub)
def run(self):
url = self.site + self.domain
try:
r = http_requests_get(url=url)
results = re.findall('</TD>\n <TD>(.*?)</TD>\n <TD><A',
r.text, re.S)
for result in results:
if is_domain(result):
self.result.append(result)
return list(set(self.result))
except Exception, e:
return self.result
def fetch_ip138(self):
"""get subdomains from ip138.com"""
url = 'http://site.ip138.com/{0}/domain.htm'.format(self.domain)
r = http_request_get(url).content
regx = r'<a.*>(.*\.%s)</a>' % self.domain
# subs = re.compile(r'(?<="\>\r\n<li>).*?(?=</li>)')
result = re.findall(regx, r)
for sub in result:
# print sub
if is_domain(sub):
self.subset.append(sub)
def run(self):
try:
url = "{0}/searchApi/v2/domain/report/?domain={1}".format(self.website, self.domain)
# content = curl_get_content(url).get('resp')
content = http_request_get(url).content
for sub in json.loads(content).get('subdomains'):
if is_domain(sub):
self.subset.append(sub)
return list(set(self.subset))
except Exception as e:
logging.info(str(e))
return self.subset
def run(self):
try:
url = "{0}/searchApi/v2/domain/report/?domain={1}".format(
self.website, self.domain)
# content = curl_get_content(url).get('resp')
content = http_request_get(url).text
for sub in json.loads(content).get('subdomains'):
if is_domain(sub):
self.subset.append(sub)
return list(set(self.subset))
except Exception as e:
return self.subset
def run(self):
print("[*]正在通过ip138查询域名[*]")
url = self.site+self.domain+"/domain.htm"
try:
res = http_requests_get(url = url) #发起请求
r1 = re.findall('target="_blank"\>(.*?)\</a\>\</p\>', res)
#return r1
for result in r1: #循环写入
if is_domain(result): # 判断是否为域名
self.result.append(result) # 将结果添加到列表中
print_try("ip138查询完成,共" + str(len(self.result)) + "个域名")
return list(set(self.result)) #去重
except Exception as e:
return self.result
def run(self):
try:
url = "{0}/getData.php?e=subdomains_container&q={1}&t=0&rt=10&p=1".format(self.website, self.domain)
# content = curl_get_content(url).get('resp')
content = http_request_get(url).content
_regex = re.compile(r'(?<=<a href\="domain.php\?q=).*?(?=">)')
for sub in _regex.findall(content):
if is_domain(sub):
self.subset.append(sub)
return list(set(self.subset))
except Exception as e:
logging.info(str(e))
return self.subset
def run(self):
try:
url = "{0}/getData.php?e=subdomains_container&q={1}&t=0&rt=10&p=1".format(
self.website, self.domain)
# content = curl_get_content(url).get('resp')
content = http_request_get(url).text
_regex = re.compile(r'(?<=<a href\="domain.php\?q=).*?(?=">)')
for sub in _regex.findall(content):
if is_domain(sub):
self.subset.append(sub)
return list(set(self.subset))
except Exception as e:
return self.subset
def run(self):
payload = {
'domain': self.domain,
'b2': 1,
'b3': 1,
'b4': 1,
}
try:
r = http_requests_post(self.site, payload)
results = re.findall('value="http://(.*?)"><input', r.text)
for result in results:
if is_domain(result):
self.result.append(result)
return list(set(self.result))
except Exception, e:
return self.result
def run(self):
print("[*]正在通过yumingco查询域名[*]")
url = self.site + self.domain
try:
res = http_requests_get(url=url) #发起请求
r1 = re.findall('main:(.*)\<br\>', res)
r = re.findall('(.*?)\<br\>', "".join(r1))
#return res.text
#return r
for result in r: #循环写入
if is_domain(result): # 判断是否为域名
self.result.append(result) # 将结果添加到列表中
print_try("yumingco查询完成,共" + str(len(self.result)) + "个域名")
return list(set(self.result)) #去重
except Exception as e:
return self.result
def run(self):
try:
payload = {'b2': 1, 'b3': 1, 'b4': 1, 'domain': self.domain}
r = http_request_post(self.url, payload=payload).text
subs = re.compile(r'(?<=value\=\"http://).*?(?=\"><input)')
for item in subs.findall(r):
if is_domain(item):
self.subset.append(item)
return list(set(self.subset))
except Exception as e:
return self.subset
# ilinks = Ilinks('aliyun.com')
# ilinks.run()
# print(ilinks.subset)
def run(self):
try:
# 此auth 需要自行申请，每个auth 每天有查询次数限制
auth=("*****@*****.**","d160262241ccf53222d42edc6883c129")
payload={"query":"*.%s" % self.domain}
url = "https://api.passivetotal.org/v2/enrichment/subdomains"
response = requests.get(url,auth=auth,params=payload)
for sub in json.loads(response.content)['subdomains']:
sub="%s.%s" %(sub,self.domain)
if is_domain(sub):
self.subset.append(sub)
return list(set(self.subset))
except Exception as e:
logging.info(str(e))
return self.subset
def run(self):
try:
# 此auth 需要自行申请，每个auth 每天有查询次数限制
auth = ("*****@*****.**", "d160262241ccf53222d42edc6883c129")
payload = {"query": "*.%s" % self.domain}
url = "https://api.passivetotal.org/v2/enrichment/subdomains"
response = requests.get(url, auth=auth, params=payload)
for sub in json.loads(response.content)['subdomains']:
sub = "%s.%s" % (sub, self.domain)
if is_domain(sub):
self.subset.append(sub)
return list(set(self.subset))
except Exception as e:
logging.info(str(e))
return self.subset
def run(self):
try:
timestemp = time.time()
url = "{0}?0.{1}&callback=&k={2}&page=1&order=default&sort=desc&action=moreson&_={3}&verify={4}".format(
self.url, timestemp, self.domain, timestemp, self.verify)
result = json.loads(req.get(url).content)
if result.get('status') == '1':
for item in result.get('data'):
if is_domain(item.get('domain')):
self.subset.append(item.get('domain'))
return list(set(self.subset))
elif result.get('status') == 3:
print('get verify_code():', self.verify)
self.verify_code()
self.run()
except Exception as e:
logging.info(str(e))
return self.subset
def run(self):
try:
url = self.site
r = http_requsets_post(url=url,
payload={
'domain': self.domain,
'b2': '1',
'b3': '1',
'b4': '1'
})
# self.result.append(r.content)
results = re.findall('value="http://(.*?)"><input type=hidden',
r.content)
for result in results:
if is_domain(result):
self.result.append(result)
return list(set(self.result))
# return self.result
except Exception, e:
return self.result
def run(self):
try:
timestemp = time.time()
url = "{0}?0.{1}&callback=&k={2}&page=1&order=default&sort=desc&action=moreson&_={3}&verify={4}".format(
self.url, timestemp, self.domain, timestemp, self.verify)
result = json.loads(req.get(url).content)
if result.get('status') == '1':
for item in result.get('data'):
if is_domain(item.get('domain')):
self.subset.append(item.get('domain'))
elif result.get('status') == 3:
logging.info("chaxun.la api block you ip...")
logging.info("input you verify_code in http://subdomain.chaxun.la/wuyun.org/")
# print('get verify_code():', self.verify)
# self.verify_code()
# self.run()
return list(set(self.subset))
except Exception as e:
logging.info(str(e))
return self.subset
def run(self):
try:
payload = {
'b2': 1,
'b3': 1,
'b4': 1,
'domain': self.domain
}
r = http_request_post(self.url,payload=payload).text
subs = re.compile(r'(?<=value\=\"http://).*?(?=\"><input)')
for item in subs.findall(r):
if is_domain(item):
self.subset.append(item)
return list(set(self.subset))
except Exception as e:
logging.info(str(e))
return self.subset
# ilinks = Ilinks('aliyun.com')
# ilinks.run()
# print(ilinks.subset)
