diff options
author | Filippo Valsorda <filippo.valsorda@gmail.com> | 2013-10-28 01:50:17 -0400 |
---|---|---|
committer | Filippo Valsorda <filippo.valsorda@gmail.com> | 2013-10-28 01:50:17 -0400 |
commit | 750e9833b83c6e17a4efa8d5dac5b3cd848f4603 (patch) | |
tree | e9380854bb2d946aae957507cea63a09adc6d76d /devscripts | |
parent | 82f0ac657c0399659863b0bdec3afea2020ca5a9 (diff) |
Add the missing age_limit tags; added a devscript to do a superficial check for porn sites without the age_limit tag in the test
Diffstat (limited to 'devscripts')
-rw-r--r-- | devscripts/check-porn.py | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/devscripts/check-porn.py b/devscripts/check-porn.py new file mode 100644 index 000000000..63401fe18 --- /dev/null +++ b/devscripts/check-porn.py @@ -0,0 +1,39 @@ +#!/usr/bin/env python + +""" +This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check +if we are not 'age_limit' tagging some porn site +""" + +# 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_request + +for test in get_testcases(): + try: + webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read() + except: + print('\nFail: {0}'.format(test['name'])) + continue + + webpage = webpage.decode('utf8', 'replace') + + if 'porn' in webpage.lower() 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 'porn' not in webpage.lower() 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() |