Update upstream source from tag 'upstream/2019.09.28'

[youtubedl] / youtube_dl / extractor / mdr.py

diff --git a/youtube_dl/extractor/mdr.py b/youtube_dl/extractor/mdr.py
index 88334889e950915304bca35c8c42bf104c143307..322e5b45a141bacd327288ac58ed658a46e628f7 100644 (file)
--- a/youtube_dl/extractor/mdr.py
+++ b/youtube_dl/extractor/mdr.py
@@ -14,10 +14,10 @@ from ..utils import (
 
 class MDRIE(InfoExtractor):
     IE_DESC = 'MDR.DE and KiKA'
 
 class MDRIE(InfoExtractor):
     IE_DESC = 'MDR.DE and KiKA'

-    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'
+    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)(?:_.+?)?\.html'

 
     _TESTS = [{
 
     _TESTS = [{

-        # MDR regularily deletes its videos
+        # MDR regularly deletes its videos

         'url': 'http://www.mdr.de/fakt/video189002.html',
         'only_matching': True,
     }, {
         'url': 'http://www.mdr.de/fakt/video189002.html',
         'only_matching': True,
     }, {


@@ -31,6 +31,7 @@ class MDRIE(InfoExtractor):
             'duration': 250,
             'uploader': 'MITTELDEUTSCHER RUNDFUNK',
         },
             'duration': 250,
             'uploader': 'MITTELDEUTSCHER RUNDFUNK',
         },

+        'skip': '404 not found',

     }, {
         'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
         'md5': '4930515e36b06c111213e80d1e4aad0e',
     }, {
         'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
         'md5': '4930515e36b06c111213e80d1e4aad0e',


@@ -41,6 +42,7 @@ class MDRIE(InfoExtractor):
             'duration': 134,
             'uploader': 'KIKA',
         },
             'duration': 134,
             'uploader': 'KIKA',
         },

+        'skip': '404 not found',

     }, {
         'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
         'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
     }, {
         'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
         'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',


@@ -49,17 +51,30 @@ class MDRIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Beutolomäus und der geheime Weihnachtswunsch',
             'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
             'ext': 'mp4',
             'title': 'Beutolomäus und der geheime Weihnachtswunsch',
             'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',

-            'timestamp': 1419047100,
-            'upload_date': '20141220',
+            'timestamp': 1482541200,
+            'upload_date': '20161224',

             'duration': 4628,
             'uploader': 'KIKA',
         },
             'duration': 4628,
             'uploader': 'KIKA',
         },

+    }, {
+        # audio with alternative playerURL pattern
+        'url': 'http://www.mdr.de/kultur/videos-und-audios/audio-radio/operation-mindfuck-robert-wilson100.html',
+        'info_dict': {
+            'id': '100',
+            'ext': 'mp4',
+            'title': 'Feature: Operation Mindfuck - Robert Anton Wilson',
+            'duration': 3239,
+            'uploader': 'MITTELDEUTSCHER RUNDFUNK',
+        },

     }, {
         'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
         'only_matching': True,
     }, {
         'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
         'only_matching': True,
     }, {
         'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
         'only_matching': True,
     }, {
         'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
         'only_matching': True,

+    }, {
+        'url': 'http://www.mdr.de/mediathek/mdr-videos/a/video-1334.html',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):


@@ -68,8 +83,8 @@ class MDRIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         data_url = self._search_regex(
         webpage = self._download_webpage(url, video_id)
 
         data_url = self._search_regex(

-            r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1',
-            webpage, 'data url', group='url')
+            r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+?-avCustom\.xml)\1',
+            webpage, 'data url', group='url').replace(r'\/', '/')

 
         doc = self._download_xml(
             compat_urlparse.urljoin(url, data_url), video_id)
 
         doc = self._download_xml(
             compat_urlparse.urljoin(url, data_url), video_id)