yt-dlp/devscripts/check-porn.py
Philipp Hagemeister dcddc10a50 [test_unicode_literals] Arm unicode_literals check
From now on, the line

from __future__ import unicode_literals

should be contained in every single Python file lest we run into any more 2.x/3.x issues.
Going forward, we're likely to develop on 3.x only and would likely miss subtle bugs otherwise.
2014-11-26 20:01:22 +01:00

61 lines
1.9 KiB
Python

#!/usr/bin/env python
from __future__ import unicode_literals
"""
This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
if we are not 'age_limit' tagging some porn site
A second approach implemented relies on a list of porn domains, to activate it
pass the list filename as the only argument
"""
# Allow direct execution
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_testcases
from youtube_dl.utils import compat_urllib_parse_urlparse
from youtube_dl.utils import compat_urllib_request
if len(sys.argv) > 1:
METHOD = 'LIST'
LIST = open(sys.argv[1]).read().decode('utf8').strip()
else:
METHOD = 'EURISTIC'
for test in get_testcases():
if METHOD == 'EURISTIC':
try:
webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
except:
print('\nFail: {0}'.format(test['name']))
continue
webpage = webpage.decode('utf8', 'replace')
RESULT = 'porn' in webpage.lower()
elif METHOD == 'LIST':
domain = compat_urllib_parse_urlparse(test['url']).netloc
if not domain:
print('\nFail: {0}'.format(test['name']))
continue
domain = '.'.join(domain.split('.')[-2:])
RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict']
or test['info_dict']['age_limit'] != 18):
print('\nPotential missing age_limit check: {0}'.format(test['name']))
elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict']
and test['info_dict']['age_limit'] == 18):
print('\nPotential false negative: {0}'.format(test['name']))
else:
sys.stdout.write('.')
sys.stdout.flush()
print()