-
-
Notifications
You must be signed in to change notification settings - Fork 339
/
github-endpoints.py
executable file
·320 lines (268 loc) · 9.93 KB
/
github-endpoints.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
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
#!/usr/bin/python3
import os
import sys
import re
import time
import requests
import random
import argparse
from urllib.parse import urlparse
from functools import partial
from colored import fg, bg, attr
from multiprocessing.dummy import Pool
TOKENS_FILE = os.path.dirname(os.path.realpath(__file__))+'/.tokens'
MIN_LENGTH = 5
_url_chars = '[a-zA-Z0-9\-\.\?\#\$&@%=_:/\]\[]'
_not_url_chars = '[^a-zA-Z0-9\-\.\?\#\$&@%=_:/\]\[]'
t_endpoints = []
t_exclude = [
r'^http://$',
r'^https://$',
r'^javascript:$',
r'^tel:$',
r'^mailto:$',
r'^text/javascript$',
r'^application/json$',
r'^application/javascript$',
r'^text/plain$',
r'^text/html$',
r'^text/x-python$',
r'^text/css$',
r'^image/png$',
r'^image/jpeg$',
r'^image/x-icon$',
r'^img/favicon.ico$',
r'^application/x-www-form-urlencoded$',
r'/Users/[0-9a-zA-Z\-\_]/Desktop',
r'www.w3.org',
r'schemas.android.com',
r'www.apple.com',
# r'^#',
# r'^\?',
# r'^javascript:',
# r'^mailto:',
]
t_regexp = [
r'[\'"\(].*(http[s]?://'+_url_chars+'*?)[\'"\)]',
r'[\'"\(](http[s]?://'+_url_chars+'+)',
r'[\'"\(]('+_url_chars+'+\.sdirect'+_url_chars+'*)',
r'[\'"\(]('+_url_chars+'+\.htm'+_url_chars+'*)',
r'[\'"\(]('+_url_chars+'+\.php'+_url_chars+'*)',
r'[\'"\(]('+_url_chars+'+\.asp'+_url_chars+'*)',
r'[\'"\(]('+_url_chars+'+\.js'+_url_chars+'*)',
r'[\'"\(]('+_url_chars+'+\.xml'+_url_chars+'*)',
r'[\'"\(]('+_url_chars+'+\.ini'+_url_chars+'*)',
r'[\'"\(]('+_url_chars+'+\.conf'+_url_chars+'*)',
r'[\'"\(]('+_url_chars+'+\.cfm'+_url_chars+'*)',
r'href\s*[.=]\s*[\'"]('+_url_chars+'+)',
r'src\s*[.=]\s*[\'"]('+_url_chars+'+)',
r'url\s*[:=]\s*[\'"]('+_url_chars+'+)',
r'urlRoot\s*[:=]\s*[\'"]('+_url_chars+'+)',
r'endpoint[s]\s*[:=]\s*[\'"]('+_url_chars+'+)',
r'script[s]\s*[:=]\s*[\'"]('+_url_chars+'+)',
r'\.ajax\s*\(\s*[\'"]('+_url_chars+'+)',
r'\.get\s*\(\s*[\'"]('+_url_chars+'+)',
r'\.post\s*\(\s*[\'"]('+_url_chars+'+)',
r'\.load\s*\(\s*[\'"]('+_url_chars+'+)',
### a bit noisy
# r'[\'"](' + _url_chars + '+/' + _url_chars + '+)?[\'"]',
# r'content\s*[.=]\s*[\'"]('+_url_chars+'+)',
]
def githubApiSearchCode( token, search, page, sort, order ):
headers = { "Authorization":"token "+token }
url = 'https://api.github.com/search/code?per_page=100&s=' + sort + '&type=Code&o=' + order + '&q=' + search + '&page=' + str(page)
# print(">>> "+url)
try:
r = requests.get( url, headers=headers, timeout=5 )
json = r.json()
# print(r.json)
# print(r.text)
return json
except Exception as e:
print( "%s[-] error occurred: %s%s" % (fg('red'),e,attr(0)) )
return False
def getRawUrl( result ):
raw_url = result['html_url']
raw_url = raw_url.replace( 'https://github.com/', 'https://raw.githubusercontent.com/' )
raw_url = raw_url.replace( '/blob/', '/' )
return raw_url
def readCode( regexp, confirm, display_source, display_relative, display_alldomains, result ):
time.sleep( random.random() )
url = getRawUrl( result )
if url in t_history_urls:
return
str = ''
t_local_endpoints = []
t_history_urls.append( url )
code = doGetCode( url )
# print( code )
# print( regexp )
# print( confirm )
# print( display_source )
# print( display_relative )
# print( display_alldomains )
if code:
if display_source:
str = "\n%s>>> %s%s\n\n" % (fg('yellow'),result['html_url'],attr(0))
matches = re.findall( regexp, code, re.IGNORECASE )
if matches:
# domain found in the code
for r in t_regexp:
# looking for endpoints
edpt = re.findall( r, code, re.IGNORECASE )
if edpt:
# endpoints found
for endpoint in edpt:
endpoint = endpoint.strip()
if len(endpoint) >= MIN_LENGTH:
# sys.stdout.write("%s\n" % endpoint)
# continue
goodbye = False
for exclude in t_exclude:
if re.match(exclude,endpoint,re.IGNORECASE):
goodbye = True
break
if goodbye:
continue
if endpoint.lower().startswith('http'):
is_relative = False
else:
is_relative = True
if is_relative and not display_relative:
continue
if endpoint in t_local_endpoints:
continue
# ???
# if not display_source and endpoint in t_endpoints:
# continue
if not display_alldomains and not is_relative:
try:
t_url_parse = urlparse( endpoint )
t_host_parse = tldextract.extract( t_url_parse.netloc )
domain = t_host_parse.domain
# print(domain)
sss = re.findall( regexp, t_url_parse.netloc, re.IGNORECASE )
if not sss:
continue
except Exception as e:
sys.stdout.write( "%s[-] error occurred: %s%s\n" % (fg('red'),e,attr(0)) )
t_endpoints.append( endpoint )
t_local_endpoints.append( endpoint )
str = str + ("%s\n" % endpoint)
# if display_source:
# str = str + ("%s\n" % endpoint)
# else:
# sys.stdout.write( "%s\n" % endpoint )
# if display_source and len(t_local_endpoints):
if len(t_local_endpoints):
sys.stdout.write( str )
def doGetCode( url ):
try:
r = requests.get( url, timeout=5 )
except Exception as e:
sys.stdout.write( "%s[-] error occurred: %s%s\n" % (fg('red'),e,attr(0)) )
return False
return r.text
parser = argparse.ArgumentParser()
parser.add_argument( "-t","--token",help="your github token (required)" )
parser.add_argument( "-d","--domain",help="domain you are looking for (required)" )
parser.add_argument( "-e","--extend",help="also look for <dummy>example.com", action="store_true" )
parser.add_argument( "-a","--all",help="displays urls of all other domains", action="store_true" )
parser.add_argument( "-r","--relative",help="also displays relative urls", action="store_true" )
parser.add_argument( "-s","--source",help="display urls where endpoints are found", action="store_true" )
parser.add_argument( "-v","--verbose",help="verbose mode, for debugging purpose", action="store_true" )
parser.parse_args()
args = parser.parse_args()
t_tokens = []
if args.token:
t_tokens = args.token.split(',')
else:
gh_env = os.getenv('GITHUB_TOKEN')
if gh_env:
t_tokens = gh_env.strip().split(',')
else:
if os.path.isfile(TOKENS_FILE):
fp = open(TOKENS_FILE,'r')
for line in fp:
r = re.search( '^([a-f0-9]{40}|ghp_[a-zA-Z0-9]{36}|github_pat_[_a-zA-Z0-9]{82})$', line )
if r:
t_tokens.append( r.group(1) )
if not len(t_tokens):
parser.error( 'auth token is missing' )
if args.source:
_source = True
else:
_source = False
if args.domain:
_domain = args.domain
else:
parser.error( 'domain is missing' )
if args.relative:
_relative = True
else:
_relative = False
if args.all:
_alldomains = True
else:
_alldomains = False
t_sort_order = [
{ 'sort':'indexed', 'order':'desc', },
{ 'sort':'indexed', 'order':'asc', },
{ 'sort':'', 'order':'desc', }
]
t_history = []
t_history_urls = []
_search = '"' + _domain + '"'
### this is a test, looks like we got more result that way
import tldextract
t_host_parse = tldextract.extract( _domain )
if args.extend:
# which one is
_search = '"' + t_host_parse.domain + '"'
else:
# the most effective ?
_search = '"' + t_host_parse.domain + '.' + t_host_parse.suffix + '"'
# or simply ?
# _search = '"' + _domain + '"'
# print(_search)
# exit()
###
if args.extend:
_regexp = r'(([0-9a-z_\-\.]+\.)?([0-9a-z_\-]+)?'+t_host_parse.domain+'([0-9a-z_\-\.]+)?\.[a-z]{1,5})'
_confirm = t_host_parse.domain
else:
_regexp = r'((([0-9a-z_\-\.]+)\.)?' + _domain.replace('.','\.')+')'
_confirm = _domain
if args.verbose:
print( "Search: %s" % _search )
print( "Regexp: %s" % _regexp)
print( "Confirm: %s" % _confirm)
print( "Relative urls: %s" % _relative)
print( "All domains: %s" % _alldomains)
for so in t_sort_order:
page = 1
if args.verbose:
print( '\n----- %s %s\n' % (so['sort'],so['order']) )
while True:
if args.verbose:
print("page %d" % page)
time.sleep( random.random() )
token = random.choice( t_tokens )
t_json = githubApiSearchCode( token, _search, page, so['sort'], so['order'] )
# print(t_json)
if not t_json or 'documentation_url' in t_json:
if args.verbose:
print(t_json)
t_tokens.remove(token)
if len(t_tokens) == 0:
exit()
continue
page = page + 1
if 'items' in t_json and len(t_json['items']):
pool = Pool( 30 )
pool.map( partial(readCode,_regexp,_confirm,_source,_relative,_alldomains), t_json['items'] )
pool.close()
pool.join()
else:
break
exit()