youtube-dl

commit b004d9bbf18ee2b6a9b916657c4d6734ff0d0adb
parent 9b3036bd2e431ed4b037a3df21528a6e9bcb05b8
Author: Remita Amine <remitamine@gmail.com>
Date:   Thu, 19 Apr 2018 15:07:50 +0100

[cbssports] fix extraction(fixes #16217)

Diffstat:
M
youtube_dl/extractor/cbssports.py
 | 
21
+++++++++++++--------

1 file changed, 13 insertions(+), 8 deletions(-)
diff --git a/youtube_dl/extractor/cbssports.py b/youtube_dl/extractor/cbssports.py
@@ -4,28 +4,33 @@ from .cbs import CBSBaseIE
 
 
 class CBSSportsIE(CBSBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/(?:video|news)/(?P<id>[^/?#&]+)'
 
     _TESTS = [{
-        'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast',
+        'url': 'https://www.cbssports.com/nba/video/donovan-mitchell-flashes-star-potential-in-game-2-victory-over-thunder/',
         'info_dict': {
-            'id': '708337219968',
+            'id': '1214315075735',
             'ext': 'mp4',
-            'title': 'Ben Simmons the next LeBron? Not so fast',
-            'description': 'md5:854294f627921baba1f4b9a990d87197',
-            'timestamp': 1466293740,
-            'upload_date': '20160618',
+            'title': 'Donovan Mitchell flashes star potential in Game 2 victory over Thunder',
+            'description': 'md5:df6f48622612c2d6bd2e295ddef58def',
+            'timestamp': 1524111457,
+            'upload_date': '20180419',
             'uploader': 'CBSI-NEW',
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        'url': 'https://www.cbssports.com/nba/news/nba-playoffs-2018-watch-76ers-vs-heat-game-3-series-schedule-tv-channel-online-stream/',
+        'only_matching': True,
     }]
 
     def _extract_video_info(self, filter_query, video_id):
         return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id= self._search_regex([r'(?:=|%26)pcid%3D(\d+)', r'embedVideo(?:Container)?_(\d+)'], webpage, 'video id')
         return self._extract_video_info('byId=%s' % video_id, video_id)