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
7 A second approach implemented relies on a list of porn domains, to activate it
8 pass the list filename as the only argument
11 # Allow direct execution
14 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
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
22 LIST = open(sys.argv[1]).read().decode('utf8').strip()
26 for test in get_testcases():
27 if METHOD == 'EURISTIC':
29 webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
31 print('\nFail: {0}'.format(test['name']))
34 webpage = webpage.decode('utf8', 'replace')
36 RESULT = 'porn' in webpage.lower()
38 elif METHOD == 'LIST':
39 domain = compat_urllib_parse_urlparse(test['url']).netloc
41 print('\nFail: {0}'.format(test['name']))
43 domain = '.'.join(domain.split('.')[-2:])
45 RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
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']))
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']))