Merge branch 'pornovoisines' of https://github.com/Roman2K/youtube-dl into Roman2K...

[youtube-dl] / youtube_dl / extractor / rtve.py

diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py
index b701a322ae1020d1bcaedcaf35876486ac5c9e16..8d9be1b98ce3adf338e7259c52181f3e2216213c 100644 (file)
--- a/youtube_dl/extractor/rtve.py
+++ b/youtube_dl/extractor/rtve.py
@@ -10,6 +10,7 @@ from ..compat import compat_urlparse
 from ..utils import (
     float_or_none,
     remove_end,
+    std_headers,
     struct_unpack,
 )
 
@@ -84,13 +85,20 @@ class RTVEALaCartaIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _real_initialize(self):
+        user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
+        manager_info = self._download_json(
+            'http://www.rtve.es/odin/loki/' + user_agent_b64,
+            None, 'Fetching manager info')
+        self._manager = manager_info['manager']
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         info = self._download_json(
             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
             video_id)['page']['items'][0]
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
+        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
         png = self._download_webpage(png_url, video_id, 'Downloading url information')
         video_url = _decrypt_url(png)
         if not video_url.endswith('.f4m'):
@@ -126,10 +134,11 @@ class RTVEALaCartaIE(InfoExtractor):
             (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
             for s in subs)
 
+
 class RTVEInfantilIE(InfoExtractor):
-    IE_NAME = 'rtve.es:alacarta'
-    IE_DESC = 'RTVE a la carta'
-    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_tittle>[^/]*)/(?P<id>[0-9]+)/'
+    IE_NAME = 'rtve.es:infantil'
+    IE_DESC = 'RTVE infantil'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
 
     _TESTS = [{
         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
@@ -141,12 +150,10 @@ class RTVEInfantilIE(InfoExtractor):
             'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
             'duration': 357.958,
         },
-    },]
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        short_tittle = mobj.group('short_tittle')
+        video_id = self._match_id(url)
         info = self._download_json(
             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
             video_id)['page']['items'][0]
@@ -169,7 +176,6 @@ class RTVEInfantilIE(InfoExtractor):
         }
 
 
-
 class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'