Update to ytdl-commit-cf2dbec

[yt-dlp.git] / youtube_dlc / extractor / generic.py

diff --git a/youtube_dlc/extractor/generic.py b/youtube_dlc/extractor/generic.py
index 6b4c842614400e08639b92aca255e04f97e28b79..8cde11d2b8d8ba8ff87e9289d4aa1fec822b81d0 100644 (file)
--- a/youtube_dlc/extractor/generic.py
+++ b/youtube_dlc/extractor/generic.py
@@ -130,7 +130,10 @@
 from .gedi import GediEmbedsIE
 from .rcs import RCSEmbedsIE
 from .bitchute import BitChuteIE
+from .rumble import RumbleEmbedIE
 from .arcpublishing import ArcPublishingIE
+from .medialaan import MedialaanIE
+from .simplecast import SimplecastIE
 
 
 class GenericIE(InfoExtractor):
@@ -2224,6 +2227,29 @@ class GenericIE(InfoExtractor):
                 'duration': 1581,
             },
         },
+        {
+            # MyChannels SDK embed
+            # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
+            'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
+            'md5': '90c0699c37006ef18e198c032d81739c',
+            'info_dict': {
+                'id': '194165',
+                'ext': 'mp4',
+                'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
+                'timestamp': 1611740340,
+                'upload_date': '20210127',
+                'duration': 159,
+            },
+        },
+        {
+            # Simplecast player embed
+            'url': 'https://www.bio.org/podcast',
+            'info_dict': {
+                'id': 'podcast',
+                'title': 'I AM BIO Podcast | BIO',
+            },
+            'playlist_mincount': 52,
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -2463,6 +2489,9 @@ def _real_extract(self, url):
         webpage = self._webpage_read_content(
             full_response, url, video_id, prefix=first_bytes)
 
+        if '<title>DPG Media Privacy Gate</title>' in webpage:
+            webpage = self._download_webpage(url, video_id)
+
         self.report_extraction(video_id)
 
         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
@@ -2594,6 +2623,11 @@ def _real_extract(self, url):
         if arc_urls:
             return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
 
+        mychannels_urls = MedialaanIE._extract_urls(webpage)
+        if mychannels_urls:
+            return self.playlist_from_matches(
+                mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
+
         # Look for embedded rtl.nl player
         matches = re.findall(
             r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
@@ -2770,6 +2804,12 @@ def _real_extract(self, url):
             return self.playlist_from_matches(
                 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
 
+        # Look for Simplecast embeds
+        simplecast_urls = SimplecastIE._extract_urls(webpage)
+        if simplecast_urls:
+            return self.playlist_from_matches(
+                simplecast_urls, video_id, video_title)
+
         # Look for BBC iPlayer embed
         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
         if matches:
@@ -3315,6 +3355,13 @@ def _real_extract(self, url):
             return self.playlist_from_matches(
                 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
 
+        rumble_urls = RumbleEmbedIE._extract_urls(webpage)
+        if len(rumble_urls) == 1:
+            return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
+        if rumble_urls:
+            return self.playlist_from_matches(
+                rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
+
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries: