Merge tag 'upstream/2017.02.24.1'

[youtubedl] / youtube_dl / extractor / mpora.py

diff --git a/youtube_dl/extractor/mpora.py b/youtube_dl/extractor/mpora.py
index 39d6feb98d171f16b2ae5d69d71cde67b3a21372..5a1bee5c85ea3e8c6105a58e5d34ab233a1ddbd2 100644 (file)
--- a/youtube_dl/extractor/mpora.py
+++ b/youtube_dl/extractor/mpora.py
@@ -1,21 +1,19 @@
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 from ..utils import int_or_none
 
 
 class MporaIE(InfoExtractor):
-    _VALID_URL = r'^https?://(www\.)?mpora\.(?:com|de)/videos/(?P<id>[^?#/]+)'
+    _VALID_URL = r'https?://(?:www\.)?mpora\.(?:com|de)/videos/(?P<id>[^?#/]+)'
     IE_NAME = 'MPORA'
 
     _TEST = {
         'url': 'http://mpora.de/videos/AAdo8okx4wiz/embed?locale=de',
-        'file': 'AAdo8okx4wiz.mp4',
         'md5': 'a7a228473eedd3be741397cf452932eb',
         'info_dict': {
+            'id': 'AAdo8okx4wiz',
+            'ext': 'mp4',
             'title': 'Katy Curd -  Winter in the Forest',
             'duration': 416,
             'uploader': 'Peter Newman Media',
@@ -23,14 +21,14 @@ class MporaIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        data_json = self._search_regex(
-            r"new FM\.Player\('[^']+',\s*(\{.*?)\);\n", webpage, 'json')
 
-        data = json.loads(data_json)
+        data_json = self._search_regex(
+            [r"new FM\.Player\('[^']+',\s*(\{.*?)\).player;",
+             r"new\s+FM\.Kaltura\.Player\('[^']+'\s*,\s*({.+?})\);"],
+            webpage, 'json')
+        data = self._parse_json(data_json, video_id)
 
         uploader = data['info_overlay'].get('username')
         duration = data['video']['duration'] // 1000
@@ -44,7 +42,7 @@ class MporaIE(InfoExtractor):
                     r'_([0-9]+)\.[a-zA-Z0-9]+$', src['src'],
                     False, default=None)
                 vcodec = src['type'].partition('/')[2]
-                
+
                 formats.append({
                     'format_id': encoding_id + '-' + vcodec,
                     'url': src['src'],