Merge tag 'upstream/2016.06.25'

[youtubedl] / youtube_dl / extractor / srmediathek.py

diff --git a/youtube_dl/extractor/srmediathek.py b/youtube_dl/extractor/srmediathek.py
index 666a7dcc8a1e7dd425fd1d201ef1b5c1802c6a16..74d01183f5f396fb9499a8426775886faed5961d 100644 (file)
--- a/youtube_dl/extractor/srmediathek.py
+++ b/youtube_dl/extractor/srmediathek.py
@@ -1,17 +1,18 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
 # encoding: utf-8
 from __future__ import unicode_literals
 

-import json
+from .ard import ARDMediathekIE
+from ..utils import (
+    ExtractorError,
+    get_element_by_attribute,
+)

 
 

-from .common import InfoExtractor
-from ..utils import js_to_json

 
 

-
-class SRMediathekIE(InfoExtractor):
-    IE_DESC = 'Süddeutscher Rundfunk'
+class SRMediathekIE(ARDMediathekIE):
+    IE_DESC = 'Saarländischer Rundfunk'

     _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
 
     _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
         'info_dict': {
             'id': '28455',
         'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
         'info_dict': {
             'id': '28455',


@@ -20,24 +21,36 @@ class SRMediathekIE(InfoExtractor):
             'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
             'thumbnail': 're:^https?://.*\.jpg$',
         },
             'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
             'thumbnail': 're:^https?://.*\.jpg$',
         },

-    }
+        'skip': 'no longer available',
+    }, {
+        'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=37682',
+        'info_dict': {
+            'id': '37682',
+            'ext': 'mp4',
+            'title': 'Love, Cakes and Rock\'n\'Roll',
+            'description': 'md5:18bf9763631c7d326c22603681e1123d',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'expected_warnings': ['Unable to download f4m manifest']
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 

-        murls = json.loads(js_to_json(self._search_regex(
-            r'var mediaURLs\s*=\s*(.*?);\n', webpage, 'video URLs')))
-        formats = [{'url': murl} for murl in murls]
-        self._sort_formats(formats)
-
-        title = json.loads(js_to_json(self._search_regex(
-            r'var mediaTitles\s*=\s*(.*?);\n', webpage, 'title')))[0]
+        if '>Der gew&uuml;nschte Beitrag ist leider nicht mehr verf&uuml;gbar.<' in webpage:
+            raise ExtractorError('Video %s is no longer available' % video_id, expected=True)

 
 

-        return {
+        media_collection_url = self._search_regex(
+            r'data-mediacollection-ardplayer="([^"]+)"', webpage, 'media collection url')
+        info = self._extract_media_info(media_collection_url, webpage, video_id)
+        info.update({

             'id': video_id,
             'id': video_id,

-            'title': title,
-            'formats': formats,
+            'title': get_element_by_attribute('class', 'ardplayer-title', webpage),

             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),

-        }
+        })
+        return info