diff options
author | Jesús <heckyel@hyperbola.info> | 2021-06-09 17:54:27 -0500 |
---|---|---|
committer | Jesús <heckyel@hyperbola.info> | 2021-06-09 17:54:27 -0500 |
commit | 27fe903c511691c078942bef5ee9a05a43b15c8f (patch) | |
tree | 50f30ab2ec749b965869518c0a28651f8677f0d3 /devscripts/check-porn.py | |
download | hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.tar.lz hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.tar.xz hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.zip |
initial
Diffstat (limited to 'devscripts/check-porn.py')
-rw-r--r-- | devscripts/check-porn.py | 60 |
1 files changed, 60 insertions, 0 deletions
diff --git a/devscripts/check-porn.py b/devscripts/check-porn.py new file mode 100644 index 0000000..a62711e --- /dev/null +++ b/devscripts/check-porn.py @@ -0,0 +1,60 @@ +#!/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 gettestcases +from hypervideo_dl.utils import compat_urllib_parse_urlparse +from hypervideo_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 gettestcases(): + if METHOD == 'EURISTIC': + try: + webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read() + except Exception: + 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() |