]> Raphaƫl G. Git Repositories - youtubedl/blob - devscripts/check-porn.py
New upstream version 2019.06.08
[youtubedl] / devscripts / check-porn.py
1 #!/usr/bin/env python
2 from __future__ import unicode_literals
3
4 """
5 This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
6 if we are not 'age_limit' tagging some porn site
7
8 A second approach implemented relies on a list of porn domains, to activate it
9 pass the list filename as the only argument
10 """
11
12 # Allow direct execution
13 import os
14 import sys
15 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
16
17 from test.helper import gettestcases
18 from youtube_dl.utils import compat_urllib_parse_urlparse
19 from youtube_dl.utils import compat_urllib_request
20
21 if len(sys.argv) > 1:
22 METHOD = 'LIST'
23 LIST = open(sys.argv[1]).read().decode('utf8').strip()
24 else:
25 METHOD = 'EURISTIC'
26
27 for test in gettestcases():
28 if METHOD == 'EURISTIC':
29 try:
30 webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
31 except Exception:
32 print('\nFail: {0}'.format(test['name']))
33 continue
34
35 webpage = webpage.decode('utf8', 'replace')
36
37 RESULT = 'porn' in webpage.lower()
38
39 elif METHOD == 'LIST':
40 domain = compat_urllib_parse_urlparse(test['url']).netloc
41 if not domain:
42 print('\nFail: {0}'.format(test['name']))
43 continue
44 domain = '.'.join(domain.split('.')[-2:])
45
46 RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
47
48 if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict']
49 or test['info_dict']['age_limit'] != 18):
50 print('\nPotential missing age_limit check: {0}'.format(test['name']))
51
52 elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict']
53 and test['info_dict']['age_limit'] == 18):
54 print('\nPotential false negative: {0}'.format(test['name']))
55
56 else:
57 sys.stdout.write('.')
58 sys.stdout.flush()
59
60 print()