-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdomain_subdomains.py
executable file
·213 lines (164 loc) · 8.1 KB
/
domain_subdomains.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
#!/usr/bin/env python
import sys
import json
import requests
from bs4 import BeautifulSoup
import re
from domain_pagelinks import pagelinks
import config as cfg
import hashlib
from urlparse import urlparse
import urllib
from termcolor import colored
import time
class style:
BOLD = '\033[1m'
END = '\033[0m'
subdomain_list = []
def check_and_append_subdomains(subdomain):
if subdomain not in subdomain_list:
subdomain_list.append(subdomain)
def subdomains(domain):
r = requests.get("https://dnsdumpster.com/")
cookies = {}
if 'csrftoken' in r.cookies.keys():
cookies['csrftoken'] = r.cookies['csrftoken']
data = {}
data['csrfmiddlewaretoken'] = cookies['csrftoken']
data['targetip'] = domain
headers = {}
headers['Referer'] = "https://dnsdumpster.com/"
req = requests.post("https://dnsdumpster.com/", data = data, cookies = cookies, headers = headers)
#print req.content
soup = BeautifulSoup(req.content, 'lxml')
subdomains=soup.findAll('td',{"class":"col-md-4"})
for subd in subdomains:
if domain in subd.text:
#print subd.text.split()[0]
check_and_append_subdomains(subd.text.split()[0])
else:
pass
def find_subdomains_from_wolfram(domain):
'''
Code is not working as of now, need some modifications.
'''
req = requests.get("http://www.wolframalpha.com/input/api/v1/code?ts=%s" % (str(time.time()).split(".")[0]))
code = json.loads(req.content)['code']
proxies = {
'http': 'http://127.0.0.1:8080',
'https': 'http://127.0.0.1:8080'
}
headers = {}
headers['User-Agent'] = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:45.0) Gecko/20100101 Firefox/45.0"
headers['Accept'] = "application/json, text/plain, */*"
headers['Referer'] = "http://www.wolframalpha.com/input/?i=%s" % (domain)
#second request to get recalculate_code
req1 = requests.get("http://www.wolframalpha.com/input/json.jsp?async=true&banners=raw&debuggingdata=false&fbtoken=&format=image,plaintext,imagemap,sound,minput,moutput&formattimeout=8&input=%s&output=JSON&parsetimeout=5&proxycode=%s&scantimeout=0.5&sponsorcategories=true&statemethod=deploybutton&storesubpodexprs=true" % (domain, code), headers=headers, proxies=proxies)
recalculate = json.loads(req1.content)['queryresult']['recalculate']
if recalculate != "":
recalc_code = json.loads(req1.content)['queryresult']['recalculate'].split("=")[1].split("&")[0]
#third request to get calc_id
#print "http://www.wolframalpha.com/input/json.jsp?action=recalc&format=image,plaintext,imagemap,minput,moutput&id=%s&output=JSON&output=JSON&scantimeout=10&statemethod=deploybutton&storesubpodexprs=true" % (recalc_code)
req2 = requests.get("http://www.wolframalpha.com/input/json.jsp?action=recalc&format=image,plaintext,imagemap,minput,moutput&id=%s&output=JSON&output=JSON&scantimeout=10&statemethod=deploybutton&storesubpodexprs=true" % (recalc_code), headers=headers, proxies=proxies)
pods = json.loads(req2.content)['queryresult']['pods']
for x in pods:
if "Web statistics for" in x['title']:
async_code = x['async'].split('=')[1]
#fourth request to get id for subdomains.
req3 = requests.get("http://www.wolframalpha.com/input/json.jsp?action=asyncPod&format=image,plaintext,imagemap,minput,moutput&formattimeout=20&id=%s&output=JSON&podtimeout=20&statemethod=deploybutton&storesubpodexprs=true" % (async_code), headers=headers, proxies=proxies)
for x in json.loads(req3.content)['pods'][0]['deploybuttonstates']:
if x['name'] == "Subdomains":
server_value = json.loads(req3.content)['pods'][0]['server']
sub_code = x['input']
else:
pass
#fifth request to find few subdomains
url = "http://www.wolframalpha.com/input/json.jsp?async=false&dbid=%s&format=image,plaintext,imagemap,sound,minput,moutput&includepodid=WebSiteStatisticsPod:InternetData&input=%s&output=JSON&podTitle=Web+statistics+for+all+of+%s&podstate=%s&s=%s&statemethod=deploybutton&storesubpodexprs=true&text=Subdomains" % (sub_code, domain, domain, sub_code, server_value)
req4 = requests.get(url, headers = headers, proxies = proxies)
servervalue_for_more = json.loads(req4.content)['queryresult']['server']
print servervalue_for_more
for x in json.loads(req4.content)['queryresult']['pods']:
for y in x['subpods']:
if y['title'] == "Subdomains":
temp_subdomain_list = y['plaintext'].split("\n")
del temp_subdomain_list[0]
for x in temp_subdomain_list:
check_and_append_subdomains(x.split('|')[0].strip(" "))
more_code = y['deploybuttonstates'][0]['input']
else:
more_code = "blank_bro"
#wooh, final request bitch.
url = "http://www.wolframalpha.com/input/json.jsp?async=false&dbid=%s&format=image,plaintext,imagemap,sound,minput,moutput&includepodid=WebSiteStatisticsPod:InternetData&input=%s&output=JSON&podTitile=Subdomains&podstate=%s&s=%s&statemethod=deploybutton&storesubpodexprs=true&text=More" % (more_code, domain, more_code, servervalue_for_more)
req5 = requests.get(url, headers = headers, proxies = proxies)
for x in json.loads(req5.content)['queryresult']['subpods']:
if x['title'] == "Subdomains":
temp_subdomain_list = x['plaintext'].split("\n")
del temp_subdomain_list[0]
for y in temp_subdomain_list:
check_and_append_subdomains(y.split('|')[0].strip(" "))
else:
print "Empty Recalculate, Cannot Proceed sire."
#def netcraft_makecookies(cookie):
cookies = dict()
cookies_list = cookie[0:cookie.find(';')].split("=")
cookies[cookies_list[0]] = cookies_list[1]
cookies['netcraft_js_verification_response'] = hashlib.sha1(urllib.unquote(cookies_list[1])).hexdigest()
return cookies
def subdomains_from_netcraft(domain):
target_dom_name = domain.split(".")
#url = "http://searchdns.netcraft.com/?restriction=site+ends+with&host=%s" % (domain)
#req = requests.get(url)
#cookies = netcraft_makecookies(req.headers['set-cookie'])
#req1 = requests.get("http://searchdns.netcraft.com/?host=%s" % (domain), cookies = cookies)
req1 = requests.get("http://searchdns.netcraft.com/?host=%s" % (domain))
link_regx = re.compile('<a href="http://toolbar.netcraft.com/site_report\?url=(.*)">')
links_list = link_regx.findall(req1.content)
for x in links_list:
dom_name = x.split("/")[2].split(".")
if (dom_name[len(dom_name) - 1] == target_dom_name[1]) and (dom_name[len(dom_name) - 2] == target_dom_name[0]):
check_and_append_subdomains(x.split("/")[2])
num_regex = re.compile('Found (.*) site')
num_subdomains = num_regex.findall(req1.content)
if num_subdomains == []:
num_regex = re.compile('First (.*) sites returned')
num_subdomains = num_regex.findall(req1.content)
if num_subdomains:
if num_subdomains[0] != str(0):
num_pages = int(num_subdomains[0])/20+1
if num_pages > 1:
last_regex = re.compile('<td align="left">%s.</td><td align="left">\n<a href="(.*)" rel="nofollow">' % (20))
last_item = last_regex.findall(req1.content)[0].split("/")[2]
next_page = 21
for x in range(2,num_pages):
url = "http://searchdns.netcraft.com/?host=%s&last=%s&from=%s&restriction=site%%20contains" % (domain, last_item, next_page)
req2 = requests.get(url)
link_regx = re.compile('<a href="http://toolbar.netcraft.com/site_report\?url=(.*)">')
links_list = link_regx.findall(req2.content)
for y in links_list:
dom_name1 = y.split("/")[2].split(".")
if (dom_name1[len(dom_name1) - 1] == target_dom_name[1]) and (dom_name1[len(dom_name1) - 2] == target_dom_name[0]):
check_and_append_subdomains(y.split("/")[2])
last_item = links_list[len(links_list) - 1].split("/")[2]
next_page = 20 * x + 1
#print last_item
#print next_page
else:
pass
else:
pass
def main():
domain = sys.argv[1]
#subdomains [to be called before pagelinks so as to avoid repititions.]
print colored(style.BOLD + '---> Finding subdomains, will be back soon with list. \n' + style.END, 'blue')
time.sleep(0.3)
subdomains(domain)
##print "\t\t\t[+] Check_subdomains from wolframalpha"
##find_subdomains_from_wolfram(domain)
#pagelinks_list = pagelinks(domain)
subdomains_from_netcraft(domain)
#printing all subdomains
print colored("List of subdomains found\n", 'green')
for sub in subdomain_list:
print sub
if __name__ == "__main__":
main()