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

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()

youtube_dl/extractor/keezmovies.py

@@ -6,7 +6,6 @@
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
-    unescapeHTML,
 )
 from ..aes import (
     aes_decrypt_text
@@ -20,6 +19,7 @@ class KeezMoviesIE(InfoExtractor):
         u'md5': u'6e297b7e789329923fcf83abb67c9289',
         u'info_dict': {
             u"title": u"Petite Asian Lady Mai Playing In Bathtub",
+            u"age_limit": 18,
         }
     }
 
@@ -48,6 +48,8 @@ def _real_extract(self, url):
         format = path.split('/')[4].split('_')[:2]
         format = "-".join( format )
 
+        age_limit = self._rta_search(webpage)
+
         return {
             'id': video_id,
             'title': video_title,
@@ -55,4 +57,5 @@ def _real_extract(self, url):
             'ext': extension,
             'format': format,
             'format_id': format,
+            'age_limit': age_limit,
         }

youtube_dl/extractor/pornhub.py

@@ -21,6 +21,7 @@ class PornHubIE(InfoExtractor):
         u'info_dict': {
             u"uploader": u"BABES-COM", 
             u"title": u"Seductive Indian beauty strips down and fingers her pink pussy",
+            u"age_limit": 18
         }
     }
 
@@ -64,4 +65,5 @@ def _real_extract(self, url):
             'title': video_title,
             'thumbnail': thumbnail,
             'formats': formats,
+            'age_limit': 18,
         }

youtube_dl/extractor/pornotube.py

@@ -16,7 +16,8 @@ class PornotubeIE(InfoExtractor):
         u'md5': u'374dd6dcedd24234453b295209aa69b6',
         u'info_dict': {
             u"upload_date": u"20090708", 
-            u"title": u"Marilyn-Monroe-Bathing"
+            u"title": u"Marilyn-Monroe-Bathing",
+            u"age_limit": 18
         }
     }
 

youtube_dl/extractor/spankwire.py

@@ -22,6 +22,7 @@ class SpankwireIE(InfoExtractor):
             u"uploader": u"oreusz", 
             u"title": u"Buckcherry`s X Rated Music Video Crazy Bitch",
             u"description": u"Crazy Bitch X rated music video.",
+            u"age_limit": 18,
         }
     }
 
@@ -60,6 +61,8 @@ def _real_extract(self, url):
             })
         formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
 
+        age_limit = self._rta_search(webpage)
+
         return {
             'id': video_id,
             'uploader': video_uploader,
@@ -67,4 +70,5 @@ def _real_extract(self, url):
             'thumbnail': thumbnail,
             'description': description,
             'formats': formats,
+            'age_limit': age_limit,
         }

youtube_dl/extractor/tube8.py

@@ -22,6 +22,7 @@ class Tube8IE(InfoExtractor):
             u"description": u"hot teen Kasia grinding", 
             u"uploader": u"unknown", 
             u"title": u"Kasia music video",
+            u"age_limit": 18,
         }
     }
 
@@ -60,4 +61,5 @@ def _real_extract(self, url):
             'ext': extension,
             'format': format,
             'format_id': format,
+            'age_limit': 18,
         }

youtube_dl/extractor/youjizz.py

@@ -13,7 +13,8 @@ class YouJizzIE(InfoExtractor):
         u'file': u'2189178.flv',
         u'md5': u'07e15fa469ba384c7693fd246905547c',
         u'info_dict': {
-            u"title": u"Zeichentrick 1"
+            u"title": u"Zeichentrick 1",
+            u"age_limit": 18,
         }
     }
 
@@ -25,6 +26,8 @@ def _real_extract(self, url):
         # Get webpage content
         webpage = self._download_webpage(url, video_id)
 
+        age_limit = self._rta_search(webpage)
+
         # Get the video title
         video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
             webpage, u'title').strip()
@@ -60,6 +63,7 @@ def _real_extract(self, url):
                 'title': video_title,
                 'ext': 'flv',
                 'format': 'flv',
-                'player_url': embed_page_url}
+                'player_url': embed_page_url,
+                'age_limit': age_limit}
 
         return [info]