]> Raphaƫl G. Git Repositories - youtubedl/blob - devscripts/check-porn.py
Merge tag 'upstream/2014.07.15'
[youtubedl] / devscripts / check-porn.py
1 #!/usr/bin/env python
2
3 """
4 This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
5 if we are not 'age_limit' tagging some porn site
6
7 A second approach implemented relies on a list of porn domains, to activate it
8 pass the list filename as the only argument
9 """
10
11 # Allow direct execution
12 import os
13 import sys
14 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
15
16 from test.helper import get_testcases
17 from youtube_dl.utils import compat_urllib_parse_urlparse
18 from youtube_dl.utils import compat_urllib_request
19
20 if len(sys.argv) > 1:
21 METHOD = 'LIST'
22 LIST = open(sys.argv[1]).read().decode('utf8').strip()
23 else:
24 METHOD = 'EURISTIC'
25
26 for test in get_testcases():
27 if METHOD == 'EURISTIC':
28 try:
29 webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
30 except:
31 print('\nFail: {0}'.format(test['name']))
32 continue
33
34 webpage = webpage.decode('utf8', 'replace')
35
36 RESULT = 'porn' in webpage.lower()
37
38 elif METHOD == 'LIST':
39 domain = compat_urllib_parse_urlparse(test['url']).netloc
40 if not domain:
41 print('\nFail: {0}'.format(test['name']))
42 continue
43 domain = '.'.join(domain.split('.')[-2:])
44
45 RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
46
47 if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict']
48 or test['info_dict']['age_limit'] != 18):
49 print('\nPotential missing age_limit check: {0}'.format(test['name']))
50
51 elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict']
52 and test['info_dict']['age_limit'] == 18):
53 print('\nPotential false negative: {0}'.format(test['name']))
54
55 else:
56 sys.stdout.write('.')
57 sys.stdout.flush()
58
59 print()