debian/control: Mark compliance with Debian policy 4.1.5.

[youtubedl] / youtube_dl / extractor / tube8.py

diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index 4053f6c2150ff536cce19a7fede105f0fee5d8d8..368c45729af533eca244f4d0e8a29bfe5f4f7a8a 100644 (file)
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import re
+

 from ..utils import (
     int_or_none,
     str_to_int,
 from ..utils import (
     int_or_none,
     str_to_int,


@@ -21,12 +23,20 @@ class Tube8IE(KeezMoviesIE):
             'title': 'Kasia music video',
             'age_limit': 18,
             'duration': 230,
             'title': 'Kasia music video',
             'age_limit': 18,
             'duration': 230,

-        }
+            'categories': ['Teen'],
+            'tags': ['dancing'],
+        },

     }, {
         'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
         'only_matching': True,
     }]
 
     }, {
         'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
         'only_matching': True,
     }]
 

+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)',
+            webpage)
+

     def _real_extract(self, url):
         webpage, info = self._extract_info(url)
 
     def _real_extract(self, url):
         webpage, info = self._extract_info(url)
 


@@ -51,6 +61,17 @@ class Tube8IE(KeezMoviesIE):
             r'<span id="allCommentsCount">(\d+)</span>',
             webpage, 'comment count', fatal=False))
 
             r'<span id="allCommentsCount">(\d+)</span>',
             webpage, 'comment count', fatal=False))
 

+        category = self._search_regex(
+            r'Category:\s*</strong>\s*<a[^>]+href=[^>]+>([^<]+)',
+            webpage, 'category', fatal=False)
+        categories = [category] if category else None
+
+        tags_str = self._search_regex(
+            r'(?s)Tags:\s*</strong>(.+?)</(?!a)',
+            webpage, 'tags', fatal=False)
+        tags = [t for t in re.findall(
+            r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
+

         info.update({
             'description': description,
             'uploader': uploader,
         info.update({
             'description': description,
             'uploader': uploader,


@@ -58,6 +79,8 @@ class Tube8IE(KeezMoviesIE):
             'like_count': like_count,
             'dislike_count': dislike_count,
             'comment_count': comment_count,
             'like_count': like_count,
             'dislike_count': dislike_count,
             'comment_count': comment_count,

+            'categories': categories,
+            'tags': tags,

         })
 
         return info
         })
 
         return info