3 This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
4 if we are not 'age_limit' tagging some porn site
6 A second approach implemented relies on a list of porn domains, to activate it
7 pass the list filename as the only argument
10 # Allow direct execution
14 sys
.path
.insert(0, os
.path
.dirname(os
.path
.dirname(os
.path
.abspath(__file__
))))
20 from test
.helper
import gettestcases
24 LIST
= open(sys
.argv
[1]).read().decode('utf8').strip()
28 for test
in gettestcases():
29 if METHOD
== 'EURISTIC':
31 webpage
= urllib
.request
.urlopen(test
['url'], timeout
=10).read()
33 print('\nFail: {}'.format(test
['name']))
36 webpage
= webpage
.decode('utf8', 'replace')
38 RESULT
= 'porn' in webpage
.lower()
40 elif METHOD
== 'LIST':
41 domain
= urllib
.parse
.urlparse(test
['url']).netloc
43 print('\nFail: {}'.format(test
['name']))
45 domain
= '.'.join(domain
.split('.')[-2:])
47 RESULT
= ('.' + domain
+ '\n' in LIST
or '\n' + domain
+ '\n' in LIST
)
49 if RESULT
and ('info_dict' not in test
or 'age_limit' not in test
['info_dict']
50 or test
['info_dict']['age_limit'] != 18):
51 print('\nPotential missing age_limit check: {}'.format(test
['name']))
53 elif not RESULT
and ('info_dict' in test
and 'age_limit' in test
['info_dict']
54 and test
['info_dict']['age_limit'] == 18):
55 print('\nPotential false negative: {}'.format(test
['name']))