Update upstream source from tag 'upstream/2019.09.01'

[youtubedl] / youtube_dl / extractor / kaltura.py

diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py
index 91bc3a0a7c0af4690cf1a16713de1e76bccaa67a..0a733424c471e6a0d83b04b7773742353dda5c5a 100644 (file)
--- a/youtube_dl/extractor/kaltura.py
+++ b/youtube_dl/extractor/kaltura.py
@@ -23,11 +23,11 @@ class KalturaIE(InfoExtractor):
                 (?:
                     kaltura:(?P<partner_id>\d+):(?P<id>[0-9a-z_]+)|
                     https?://
-                        (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/
+                        (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
                         (?:
                             (?:
                                 # flash player
-                                index\.php/kwidget|
+                                index\.php/(?:kwidget|extwidget/preview)|
                                 # html5 player
                                 html5/html5lib/[^/]+/mwEmbedFrame\.php
                             )
@@ -91,37 +91,67 @@ class KalturaIE(InfoExtractor):
                     }],
                 },
             },
+            'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
             'params': {
                 'skip_download': True,
             },
+        },
+        {
+            'url': 'https://www.kaltura.com/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
+            'only_matching': True,
+        },
+        {
+            # unavailable source format
+            'url': 'kaltura:513551:1_66x4rg7o',
+            'only_matching': True,
         }
     ]
 
     @staticmethod
     def _extract_url(webpage):
+        # Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
         mobj = (
             re.search(
                 r"""(?xs)
                     kWidget\.(?:thumb)?[Ee]mbed\(
                     \{.*?
-                        (?P<q1>['\"])wid(?P=q1)\s*:\s*
-                        (?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),
-                """, webpage) or
-            re.search(
+                        (?P<q1>['"])wid(?P=q1)\s*:\s*
+                        (?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(
                 r'''(?xs)
-                    (?P<q1>["\'])
-                        (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/(?:(?!(?P=q1)).)*(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
+                    (?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*
-                    (?P<q3>["\'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
-                ''', webpage))
+                        (?:
+                            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(
+                r'''(?xs)
+                    <(?: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)).)*
+                    (?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(
@@ -169,6 +199,8 @@ 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',
@@ -209,6 +241,8 @@ class KalturaIE(InfoExtractor):
                 partner_id = params['wid'][0][1:]
             elif 'p' in params:
                 partner_id = params['p'][0]
+            elif 'partner_id' in params:
+                partner_id = params['partner_id'][0]
             else:
                 raise ExtractorError('Invalid URL', expected=True)
             if 'entry_id' in params:
@@ -266,14 +300,28 @@ 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':
+                    f['fileExt'] = 'mov'
+                else:
+                    f['fileExt'] = 'mp4'
             video_url = sign_url(
                 '%s/flavorId/%s' % (data_url, f['id']))
+            format_id = '%(fileExt)s-%(bitrate)s' % f
+            # Source format may not be available (e.g. kaltura:513551:1_66x4rg7o)
+            if f.get('isOriginal') is True and not self._is_valid_url(
+                    video_url, entry_id, format_id):
+                continue
             # audio-only has no videoCodecId (e.g. kaltura:1926081:0_c03e1b5g
             # -f mp4-56)
             vcodec = 'none' if 'videoCodecId' not in f and f.get(
                 'frameRate') == 0 else f.get('videoCodecId')
             formats.append({
-                'format_id': '%(fileExt)s-%(bitrate)s' % f,
+                'format_id': format_id,
                 'ext': f.get('fileExt'),
                 'tbr': int_or_none(f['bitrate']),
                 'fps': int_or_none(f.get('frameRate')),
@@ -297,7 +345,7 @@ class KalturaIE(InfoExtractor):
         if captions:
             for caption in captions.get('objects', []):
                 # Continue if caption is not ready
-                if f.get('status') != 2:
+                if caption.get('status') != 2:
                     continue
                 if not caption.get('id'):
                     continue
@@ -316,6 +364,6 @@ class KalturaIE(InfoExtractor):
             'thumbnail': info.get('thumbnailUrl'),
             'duration': info.get('duration'),
             'timestamp': info.get('createdAt'),
-            'uploader_id': info.get('userId'),
+            'uploader_id': info.get('userId') if info.get('userId') != 'None' else None,
             'view_count': info.get('plays'),
         }