Update upstream source from tag 'upstream/2019.07.02'

[youtubedl] / youtube_dl / extractor / kaltura.py

diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py
index 138d4844d1bbd70e56aff50b5a59ff2ddac8f665..639d7383727bbdb48681827908103361ce6828cc 100644 (file)
--- a/youtube_dl/extractor/kaltura.py
+++ b/youtube_dl/extractor/kaltura.py
@@ -118,29 +118,35 @@ class KalturaIE(InfoExtractor):
                         (?P<q2>['"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
                         (?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
                         (?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
-                """, webpage) or
-            re.search(
+                """, webpage)
+            or re.search(
                 r'''(?xs)
                     (?P<q1>["'])
                         (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
                     (?P=q1).*?
                     (?:
-                        entry_?[Ii]d|
-                        (?P<q2>["'])entry_?[Ii]d(?P=q2)
-                    )\s*:\s*
+                        (?:
+                            entry_?[Ii]d|
+                            (?P<q2>["'])entry_?[Ii]d(?P=q2)
+                        )\s*:\s*|
+                        \[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s*
+                    )
                     (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
-                ''', webpage) or
-            re.search(
+                ''', webpage)
+            or re.search(
                 r'''(?xs)
-                    <iframe[^>]+src=(?P<q1>["'])
-                      (?:https?:)?//(?:www\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
+                    <(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
+                      (?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
+                      (?:(?!(?P=q1)).)*
+                      [?&;]entry_id=(?P<id>(?:(?!(?P=q1))[^&])+)
                       (?:(?!(?P=q1)).)*
-                      [?&]entry_id=(?P<id>(?:(?!(?P=q1))[^&])+)
                     (?P=q1)
                 ''', webpage)
         )
         if mobj:
             embed_info = mobj.groupdict()
+            for k, v in embed_info.items():
+                embed_info[k] = v.strip()
             url = 'kaltura:%(partner_id)s:%(id)s' % embed_info
             escaped_pid = re.escape(embed_info['partner_id'])
             service_url = re.search(
@@ -188,6 +194,8 @@ class KalturaIE(InfoExtractor):
                 'entryId': video_id,
                 'service': 'baseentry',
                 'ks': '{1:result:ks}',
+                'responseProfile:fields': 'createdAt,dataUrl,duration,name,plays,thumbnailUrl,userId',
+                'responseProfile:type': 1,
             },
             {
                 'action': 'getbyentryid',
@@ -287,6 +295,9 @@ class KalturaIE(InfoExtractor):
             # skip for now.
             if f.get('fileExt') == 'chun':
                 continue
+            # DRM-protected video, cannot be decrypted
+            if f.get('fileExt') == 'wvm':
+                continue
             if not f.get('fileExt'):
                 # QT indicates QuickTime; some videos have broken fileExt
                 if f.get('containerFormat') == 'qt':