generated from UnifierHQ/unifier-plugin
-
Notifications
You must be signed in to change notification settings - Fork 0
/
rapidphish.py
187 lines (155 loc) · 7.37 KB
/
rapidphish.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
"""
Unifier - A sophisticated Discord bot uniting servers and platforms
Copyright (C) 2024 Green, ItsAsheer
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as
published by the Free Software Foundation, either version 3 of the
License, or (at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
"""
from urllib.parse import urlparse
import jellyfish
import time
import hashlib
import json
# Official Discord domains to compare the given URLs against
discord_urls = ['discord.gg', 'discord.com', 'discord.gift', 'discord.gifts', 'discordapp.com', 'dis.gd',
'steampowered.com', 'discordapp.net', 'discord.new', 'discordstatus.com']
# Not Discord domains, but safe troll sites that can be safely ignored
# Also contains common false positives
# If there is no TLD, then it is considered as a keyword
whitelist = ['discordgift.site', 'dlscord.life', 'l.discord.ski', 'dis.cord.gifts',
'skribbl.io', 'dsc.gg', 'discord.py', 'disboard']
# Official Discord domains without the TLDs
real_url_names = ['discord', 'discordapp']
# 100% positives - ban these URLs
# Does not override whitelist
blacklist = ['disboard.com', 'spy.pet', 'spying.pet', 'spy.pm']
try:
discord_bl = json.loads(open('hashes.json', 'r', encoding='utf-8').read())
except:
discord_bl = {}
def encrypt_string(hash_string):
sha_signature = \
hashlib.sha256(hash_string.encode()).hexdigest()
return sha_signature
class RapidPhishScan(object):
def __init__(self, data):
self.domain = data['domain']
self.similarity = data['similarity']
self.type = data['type']
self.positive = data['positive']
class RapidPhishResult(object):
def __init__(self, data):
self.url = data['url']
self.verdict = data['verdict']
self.whitelist = data['whitelist_or_real']
self.scans = data['scans']
try:
self.blacklist = data['in_blacklist']
except:
self.blacklist = False
class RapidPhishResults(object):
def __init__(self, results, priority, duration):
self.results = results
self.priority = priority
self.duration = duration
if priority == None:
self.final_verdict = 'safe'
else:
self.final_verdict = 'unsafe'
def compare_urls(urls, threshold, custom_blacklist=[], custom_whitelist=[]):
'''Compares a list of URLs against official Discord domains.'''
results = []
real_urls = discord_urls + custom_blacklist
count = 0
start = time.time()
for url in urls:
if not url.startswith('https://') and not url.startswith('http://'):
urls[count] = f'http://{url}'
count += 1
for url in urls:
t = urlparse(url).netloc
repeat = url.count('.')
if t in whitelist or t in real_urls or t in custom_whitelist:
results.append(RapidPhishResult({'url': url, 'verdict': 'safe', 'whitelist_or_real': True,
'scans': {'full': [], 'nosubd': [], 'nontld': []}}))
else:
t_hash = encrypt_string(t)
if t_hash in discord_bl:
results.append(RapidPhishResult({'url': url, 'verdict': 'unsafe', 'whitelist_or_real': False,
'scans': {'full': [], 'nosubd': [], 'nontld': []},
'in_blacklist': True}))
continue
verdict = 'safe'
result = []
if repeat > 1:
t1 = '.'.join(t.split('.')[1:])
if t1 in real_urls:
results.append(RapidPhishResult({'url': url, 'verdict': 'safe', 'whitelist_or_real': True,
'scans': {'full': [], 'nosubd': [], 'nontld': []}}))
continue
else:
pass
for domain in real_urls:
similarity = jellyfish.jaro_similarity(t, domain)
if similarity >= threshold and not similarity == 1:
verdict = 'unsafe'
result.append(
RapidPhishScan({'domain': domain, 'similarity': similarity, 'type': 'full', 'positive': True}))
else:
result.append(
RapidPhishScan({'domain': domain, 'similarity': similarity, 'type': 'full', 'positive': False}))
if repeat > 1:
t = '.'.join(t.split('.')[1:])
else:
pass
t_hash = encrypt_string(t)
if t_hash in discord_bl:
results.append(RapidPhishResult({'url': url, 'verdict': 'unsafe', 'whitelist_or_real': False,
'scans': {'full': [], 'nosubd': [], 'nontld': []},
'in_blacklist': True}))
continue
for url in blacklist:
if url in t:
results.append(RapidPhishResult({'url': url, 'verdict': 'unsafe', 'whitelist_or_real': False,
'scans': {'full': [], 'nosubd': [], 'nontld': []},
'in_blacklist': True}))
continue
for domain in real_urls:
similarity = jellyfish.jaro_similarity(t, domain)
if similarity >= threshold and not similarity == 1:
verdict = 'unsafe'
result.append(RapidPhishScan(
{'domain': domain, 'similarity': similarity, 'type': 'nosubd', 'positive': True}))
else:
result.append(RapidPhishScan(
{'domain': domain, 'similarity': similarity, 'type': 'nosubd', 'positive': False}))
t2 = t.split('.')[0]
if t2 in whitelist:
results.append(RapidPhishResult({'url': url, 'verdict': 'safe', 'whitelist_or_real': True,
'scans': {'full': [], 'nosubd': [], 'nontld': []}}))
continue
for domain in real_urls:
similarity = jellyfish.jaro_similarity(t2, url)
if similarity >= threshold and not similarity == 1:
verdict = 'unsafe'
result.append(RapidPhishScan(
{'domain': domain, 'similarity': similarity, 'type': 'nontld', 'positive': True}))
else:
result.append(RapidPhishScan(
{'domain': domain, 'similarity': similarity, 'type': 'nontld', 'positive': False}))
results.append(
RapidPhishResult({'url': url, 'verdict': verdict, 'whitelist_or_real': False, 'scans': result}))
priority = None
for result in results:
if result.verdict == 'unsafe':
priority = result
end = time.time()
elapsed = end - start
return RapidPhishResults(results, priority, elapsed)