Merge tag 'upstream/2014.07.11'

[youtubedl] / youtube_dl / extractor / youjizz.py

diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py
index 1265639e821bd873b74aeea08811f8c22e966ba1..fcb5ff758deae198614e821dc132871e5fb90679 100644 (file)
--- a/youtube_dl/extractor/youjizz.py
+++ b/youtube_dl/extractor/youjizz.py
@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor


@@ -7,13 +9,14 @@ from ..utils import (
 
 
 class YouJizzIE(InfoExtractor):
 
 
 class YouJizzIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'

     _TEST = {
     _TEST = {

-        u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
-        u'file': u'2189178.flv',
-        u'md5': u'07e15fa469ba384c7693fd246905547c',
-        u'info_dict': {
-            u"title": u"Zeichentrick 1"
+        'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
+        'file': '2189178.flv',
+        'md5': '07e15fa469ba384c7693fd246905547c',
+        'info_dict': {
+            "title": "Zeichentrick 1",
+            "age_limit": 18,

         }
     }
 
         }
     }
 


@@ -25,14 +28,16 @@ class YouJizzIE(InfoExtractor):
         # Get webpage content
         webpage = self._download_webpage(url, video_id)
 
         # 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>',
         # Get the video title
         video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',

-            webpage, u'title').strip()
+            webpage, 'title').strip()

 
         # Get the embed page
         result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
         if result is None:
 
         # Get the embed page
         result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
         if result is None:

-            raise ExtractorError(u'ERROR: unable to extract embed page')
+            raise ExtractorError('ERROR: unable to extract embed page')

 
         embed_page_url = result.group(0).strip()
         video_id = result.group('videoid')
 
         embed_page_url = result.group(0).strip()
         video_id = result.group('videoid')


@@ -44,22 +49,23 @@ class YouJizzIE(InfoExtractor):
         if m_playlist is not None:
             playlist_url = m_playlist.group('playlist')
             playlist_page = self._download_webpage(playlist_url, video_id,
         if m_playlist is not None:
             playlist_url = m_playlist.group('playlist')
             playlist_page = self._download_webpage(playlist_url, video_id,

-                                                   u'Downloading playlist page')
+                                                   'Downloading playlist page')

             m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
             if len(m_levels) == 0:
             m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
             if len(m_levels) == 0:

-                raise ExtractorError(u'Unable to extract video url')
+                raise ExtractorError('Unable to extract video url')

             videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
             (_, video_url) = sorted(videos)[0]
             video_url = video_url.replace('%252F', '%2F')
         else:
             video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
             videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
             (_, video_url) = sorted(videos)[0]
             video_url = video_url.replace('%252F', '%2F')
         else:
             video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',

-                                           webpage, u'video URL')
+                                           webpage, 'video URL')

 
 

-        info = {'id': video_id,
-                'url': video_url,
-                'title': video_title,
-                'ext': 'flv',
-                'format': 'flv',
-                'player_url': embed_page_url}
-
-        return [info]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
+            'ext': 'flv',
+            'format': 'flv',
+            'player_url': embed_page_url,
+            'age_limit': age_limit,
+        }