[extractors] Use new framework for existing embeds (#4307)

`Brightcove` is difficult to migrate because it's subclasses may depend
on the signature of the current functions. So it is left as-is for now

Note: Tests have not been migrated

yt_dlp/extractor/_extractors.py

@@ -446,7 +446,7 @@
     DWIE,
     DWArticleIE,
 )
-from .eagleplatform import EaglePlatformIE
+from .eagleplatform import EaglePlatformIE, ClipYouEmbedIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
 from .egghead import (
@@ -1555,6 +1555,7 @@
     SharedIE,
     VivoIE,
 )
+from .sharevideos import ShareVideosEmbedIE
 from .shemaroome import ShemarooMeIE
 from .showroomlive import ShowRoomLiveIE
 from .simplecast import (

yt_dlp/extractor/adobetv.py

@@ -232,6 +232,7 @@ def _real_extract(self, url):
 class AdobeTVVideoIE(AdobeTVBaseIE):
     IE_NAME = 'adobetv:video'
     _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]']
 
     _TEST = {
         # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners

yt_dlp/extractor/ant1newsgr.py

@@ -1,4 +1,3 @@
-import re
 import urllib.parse
 
 from .common import InfoExtractor
@@ -7,7 +6,6 @@
     ExtractorError,
     determine_ext,
     scale_thumbnails_to_max_format_width,
-    unescapeHTML,
 )
 
 
@@ -91,7 +89,7 @@ def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         info = self._search_json_ld(webpage, video_id, expected_type='NewsArticle')
-        embed_urls = list(Ant1NewsGrEmbedIE._extract_urls(webpage))
+        embed_urls = list(Ant1NewsGrEmbedIE._extract_embed_urls(url, webpage))
         if not embed_urls:
             raise ExtractorError('no videos found for %s' % video_id, expected=True)
         return self.playlist_from_matches(
@@ -104,6 +102,7 @@ class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
     IE_DESC = 'ant1news.gr embedded videos'
     _BASE_PLAYER_URL_RE = r'(?:https?:)?//(?:[a-zA-Z0-9\-]+\.)?(?:antenna|ant1news)\.gr/templates/pages/player'
     _VALID_URL = rf'{_BASE_PLAYER_URL_RE}\?([^#]+&)?cid=(?P<id>[^#&]+)'
+    _EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
     _API_PATH = '/news/templates/data/jsonPlayer'
 
     _TESTS = [{
@@ -117,16 +116,6 @@ class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
         },
     }]
 
-    @classmethod
-    def _extract_urls(cls, webpage):
-        _EMBED_URL_RE = rf'{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+'
-        _EMBED_RE = rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_EMBED_URL_RE})(?P=_q1)'
-        for mobj in re.finditer(_EMBED_RE, webpage):
-            url = unescapeHTML(mobj.group('url'))
-            if not cls.suitable(url):
-                continue
-            yield url
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/anvato.py

@@ -340,30 +340,16 @@ def _get_anvato_videos(self, access_key, video_id):
             'subtitles': subtitles,
         }
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(ie, webpage, video_id):
+    def _extract_from_webpage(cls, url, webpage):
-        entries = []
+        for mobj in re.finditer(cls._ANVP_RE, webpage):
-        for mobj in re.finditer(AnvatoIE._ANVP_RE, webpage):
+            anvplayer_data = unescapeHTML(json.loads(mobj.group('anvp'))) or {}
-            anvplayer_data = ie._parse_json(
+            video_id, access_key = anvplayer_data.get('video'), anvplayer_data.get('accessKey')
-                mobj.group('anvp'), video_id, transform_source=unescapeHTML,
-                fatal=False)
-            if not anvplayer_data:
-                continue
-            video = anvplayer_data.get('video')
-            if not isinstance(video, compat_str) or not video.isdigit():
-                continue
-            access_key = anvplayer_data.get('accessKey')
-            if not access_key:
-                mcp = anvplayer_data.get('mcp')
-                if mcp:
-                    access_key = AnvatoIE._MCP_TO_ACCESS_KEY_TABLE.get(
-                        mcp.lower())
             if not access_key:
+                access_key = cls._MCP_TO_ACCESS_KEY_TABLE.get((anvplayer_data.get('mcp') or '').lower())
+            if not (video_id or '').isdigit() or not access_key:
                 continue
-            entries.append(ie.url_result(
+            yield cls.url_result(f'anvato:{access_key}:{video_id}', AnvatoIE, video_id)
-                'anvato:%s:%s' % (access_key, video), ie=AnvatoIE.ie_key(),
-                video_id=video))
-        return entries
 
     def _extract_anvato_videos(self, webpage, video_id):
         anvplayer_data = self._parse_json(

yt_dlp/extractor/apa.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -10,6 +8,7 @@
 
 class APAIE(InfoExtractor):
     _VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1']
     _TESTS = [{
         'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
         'md5': '2b12292faeb0a7d930c778c7a5b4759b',
@@ -30,14 +29,6 @@ class APAIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1',
-                webpage)]
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id, base_url = mobj.group('id', 'base_url')

yt_dlp/extractor/aparat.py

@@ -10,6 +10,7 @@
 
 class AparatIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
+    _EMBED_REGEX = [r'<iframe .*?src="(?P<url>http://www\.aparat\.com/video/[^"]+)"']
 
     _TESTS = [{
         'url': 'http://www.aparat.com/v/wP8On',

yt_dlp/extractor/arcpublishing.py

@@ -70,8 +70,8 @@ class ArcPublishingIE(InfoExtractor):
         ], 'video-api-cdn.%s.arcpublishing.com/api'),
     ]
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
         entries = []
         # https://arcpublishing.atlassian.net/wiki/spaces/POWA/overview
         for powa_el in re.findall(r'(<div[^>]+class="[^"]*\bpowa\b[^"]*"[^>]+data-uuid="%s"[^>]*>)' % ArcPublishingIE._UUID_REGEX, webpage):

yt_dlp/extractor/arkena.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -19,6 +17,8 @@ class ArkenaIE(InfoExtractor):
                                 play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
                             )
                         '''
+    # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1']
     _TESTS = [{
         'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
         'md5': '97f117754e5f3c020f5f26da4a44ebaf',
@@ -50,15 +50,6 @@ class ArkenaIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_url(webpage):
-        # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
-        mobj = re.search(
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1',
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id')

yt_dlp/extractor/arte.py

@@ -204,6 +204,7 @@ def _real_extract(self, url):
 
 class ArteTVEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+'
+    _EMBED_REGEX = [r'<(?:iframe|script)[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+?)\1']
     _TESTS = [{
         'url': 'https://www.arte.tv/player/v5/index.php?json_url=https%3A%2F%2Fapi.arte.tv%2Fapi%2Fplayer%2Fv2%2Fconfig%2Fde%2F100605-013-A&lang=de&autoplay=true&mute=0100605-013-A',
         'info_dict': {
@@ -219,12 +220,6 @@ class ArteTVEmbedIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [url for _, url in re.findall(
-            r'<(?:iframe|script)[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+?)\1',
-            webpage)]
-
     def _real_extract(self, url):
         qs = parse_qs(url)
         json_url = qs['json_url'][0]

yt_dlp/extractor/bandcamp.py

@@ -22,6 +22,7 @@
 
 class BandcampIE(InfoExtractor):
     _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
+    _EMBED_REGEX = [r'<meta property="og:url"[^>]*?content="(?P<url>.*?bandcamp\.com.*?)"']
     _TESTS = [{
         'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
         'md5': 'c557841d5e50261777a6585648adf439',

yt_dlp/extractor/bbc.py

@@ -46,6 +46,7 @@ class BBCCoUkIE(InfoExtractor):
                         )
                         (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
                     ''' % _ID_REGEX
+    _EMBED_REGEX = [r'setPlaylist\("(?P<url>https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)']
 
     _LOGIN_URL = 'https://account.bbc.com/signin'
     _NETRC_MACHINE = 'bbc'

yt_dlp/extractor/bitchute.py

@@ -13,6 +13,7 @@
 
 class BitChuteIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
+    _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
     _TESTS = [{
         'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
         'md5': '7e427d7ed7af5a75b5855705ec750e2b',
@@ -33,14 +34,6 @@ class BitChuteIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>%s)' % BitChuteIE._VALID_URL,
-                webpage)]
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/blogger.py

@@ -1,5 +1,3 @@
-import re
-
 from ..utils import (
     mimetype2ext,
     parse_duration,
@@ -13,7 +11,7 @@
 class BloggerIE(InfoExtractor):
     IE_NAME = 'blogger.com'
     _VALID_URL = r'https?://(?:www\.)?blogger\.com/video\.g\?token=(?P<id>.+)'
-    _VALID_EMBED = r'''<iframe[^>]+src=["']((?:https?:)?//(?:www\.)?blogger\.com/video\.g\?token=[^"']+)["']'''
+    _EMBED_REGEX = [r'''<iframe[^>]+src=["'](?P<url>(?:https?:)?//(?:www\.)?blogger\.com/video\.g\?token=[^"']+)["']''']
     _TESTS = [{
         'url': 'https://www.blogger.com/video.g?token=AD6v5dzEe9hfcARr5Hlq1WTkYy6t-fXH3BBahVhGvVHe5szdEUBEloSEDSTA8-b111089KbfWuBvTN7fnbxMtymsHhXAXwVvyzHH4Qch2cfLQdGxKQrrEuFpC1amSl_9GuLWODjPgw',
         'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
@@ -26,10 +24,6 @@ class BloggerIE(InfoExtractor):
         }
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(BloggerIE._VALID_EMBED, webpage)
-
     def _real_extract(self, url):
         token_id = self._match_id(url)
         webpage = self._download_webpage(url, token_id)

yt_dlp/extractor/buzzfeed.py

@@ -81,7 +81,7 @@ def _real_extract(self, url):
                 continue
             entries.append(self.url_result(video['url']))
 
-        facebook_urls = FacebookIE._extract_urls(webpage)
+        facebook_urls = FacebookIE._extract_embed_urls(url, webpage)
         entries.extend([
             self.url_result(facebook_url)
             for facebook_url in facebook_urls])

yt_dlp/extractor/channel9.py

@@ -14,6 +14,7 @@ class Channel9IE(InfoExtractor):
     IE_DESC = 'Channel 9'
     IE_NAME = 'channel9'
     _VALID_URL = r'https?://(?:www\.)?(?:channel9\.msdn\.com|s\.ch9\.ms)/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>https?://channel9\.msdn\.com/(?:[^/]+/)+)player\b']
 
     _TESTS = [{
         'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
@@ -78,12 +79,6 @@ class Channel9IE(InfoExtractor):
 
     _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+src=["\'](https?://channel9\.msdn\.com/(?:[^/]+/)+)player\b',
-            webpage)
-
     def _extract_list(self, video_id, rss_url=None):
         if not rss_url:
             rss_url = self._RSS_URL % video_id

yt_dlp/extractor/cinchcast.py

@@ -7,6 +7,8 @@
 
 class CinchcastIE(InfoExtractor):
     _VALID_URL = r'https?://player\.cinchcast\.com/.*?(?:assetId|show_id)=(?P<id>[0-9]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1']
+
     _TESTS = [{
         'url': 'http://player.cinchcast.com/?show_id=5258197&platformId=1&assetType=single',
         'info_dict': {

yt_dlp/extractor/cloudflarestream.py

@@ -1,5 +1,4 @@
 import base64
-import re
 
 from .common import InfoExtractor
 
@@ -16,6 +15,7 @@ class CloudflareStreamIE(InfoExtractor):
                         )
                         (?P<id>%s)
                     ''' % (_DOMAIN_RE, _EMBED_RE, _ID_RE)
+    _EMBED_REGEX = [fr'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE}).*?)\1']
     _TESTS = [{
         'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717',
         'info_dict': {
@@ -37,14 +37,6 @@ class CloudflareStreamIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//%s(?:%s).*?)\1' % (CloudflareStreamIE._EMBED_RE, CloudflareStreamIE._ID_RE),
-                webpage)]
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net'

yt_dlp/extractor/common.py

@@ -3882,6 +3882,11 @@ def _extract_embed_urls(cls, url, webpage):
     class StopExtraction(Exception):
         pass
 
+    @classmethod
+    def _extract_url(cls, webpage):  # TODO: Remove
+        """Only for compatibility with some older extractors"""
+        return next(iter(cls._extract_embed_urls(None, webpage) or []), None)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

yt_dlp/extractor/condenast.py

@@ -58,7 +58,10 @@ class CondeNastIE(InfoExtractor):
         )''' % '|'.join(_SITES.keys())
     IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
 
-    EMBED_URL = r'(?:https?:)?//player(?:-backend)?\.(?:%s)\.com/(?:embed(?:js)?|(?:script|inline)/video)/.+?' % '|'.join(_SITES.keys())
+    _EMBED_REGEX = [r'''(?x)
+        <(?:iframe|script)[^>]+?src=(["\'])(?P<url>
+            (?:https?:)?//player(?:-backend)?\.(?:%s)\.com/(?:embed(?:js)?|(?:script|inline)/video)/.+?
+        )\1''' % '|'.join(_SITES.keys())]
 
     _TESTS = [{
         'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',

yt_dlp/extractor/crooksandliars.py

@@ -7,6 +7,8 @@
 
 class CrooksAndLiarsIE(InfoExtractor):
     _VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
+    _EMBED_REGEX = [r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1']
+
     _TESTS = [{
         'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
         'info_dict': {

yt_dlp/extractor/cspan.py

@@ -163,7 +163,7 @@ def add_referer(formats):
                 video_id = m.group('id')
                 video_type = 'program' if m.group('type') == 'prog' else 'clip'
             else:
-                senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+                senate_isvp_url = SenateISVPIE._extract_url(webpage)
                 if senate_isvp_url:
                     title = self._og_search_title(webpage)
                     surl = smuggle_url(senate_isvp_url, {'force_title': title})

yt_dlp/extractor/dailymail.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
@@ -12,6 +10,7 @@
 
 class DailyMailIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P<id>[0-9]+)'
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)']
     _TESTS = [{
         'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html',
         'md5': 'f6129624562251f628296c3a9ffde124',
@@ -26,12 +25,6 @@ class DailyMailIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)',
-            webpage)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)

yt_dlp/extractor/dailymotion.py

@@ -99,6 +99,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                         [/=](?P<id>[^/?_&]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))?
                     '''
     IE_NAME = 'dailymotion'
+    _EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1']
     _TESTS = [{
         'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
         'md5': '074b95bdee76b9e3654137aee9c79dfe',
@@ -208,18 +209,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
       }
       xid'''
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        urls = []
-        # Look for embedded Dailymotion player
         # https://developer.dailymotion.com/player#player-parameters
-        for mobj in re.finditer(
+        yield from super()._extract_embed_urls(url, webpage)
-                r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage):
-            urls.append(unescapeHTML(mobj.group('url')))
         for mobj in re.finditer(
                 r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
-            urls.append('https://www.dailymotion.com/embed/video/' + mobj.group('id'))
+            yield from 'https://www.dailymotion.com/embed/video/' + mobj.group('id')
-        return urls
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url)
@@ -378,6 +374,15 @@ class DailymotionPlaylistIE(DailymotionPlaylistBaseIE):
     }]
     _OBJECT_TYPE = 'collection'
 
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        # Look for embedded Dailymotion playlist player (#3822)
+        for mobj in re.finditer(
+                r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1',
+                webpage):
+            for p in re.findall(r'list\[\]=/playlist/([^/]+)/', unescapeHTML(mobj.group('url'))):
+                yield '//dailymotion.com/playlist/%s' % p
+
 
 class DailymotionUserIE(DailymotionPlaylistBaseIE):
     IE_NAME = 'dailymotion:user'

yt_dlp/extractor/dbtv.py

@@ -1,10 +1,9 @@
-import re
-
 from .common import InfoExtractor
 
 
 class DBTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dagbladet\.no/video/(?:(?:embed|(?P<display_id>[^/]+))/)?(?P<id>[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8})'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dagbladet\.no/video/embed/(?:[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8}).*?)\1']
     _TESTS = [{
         'url': 'https://www.dagbladet.no/video/PynxJnNWChE/',
         'md5': 'b8f850ba1860adbda668d367f9b77699',
@@ -28,12 +27,6 @@ class DBTVIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [url for _, url in re.findall(
-            r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dagbladet\.no/video/embed/(?:[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8}).*?)\1',
-            webpage)]
-
     def _real_extract(self, url):
         display_id, video_id = self._match_valid_url(url).groups()
         info = {

yt_dlp/extractor/digiteka.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import int_or_none
 
@@ -25,6 +23,7 @@ class DigitekaIE(InfoExtractor):
             )
             /id
         )/(?P<id>[\d+a-z]+)'''
+    _EMBED_REGEX = [r'<(?:iframe|script)[^>]+src=["\'](?P<url>(?:https?:)?//(?:www\.)?ultimedia\.com/deliver/(?:generic|musique)(?:/[^/]+)*/(?:src|article)/[\d+a-z]+)']
     _TESTS = [{
         # news
         'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
@@ -58,14 +57,6 @@ class DigitekaIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<(?:iframe|script)[^>]+src=["\'](?P<url>(?:https?:)?//(?:www\.)?ultimedia\.com/deliver/(?:generic|musique)(?:/[^/]+)*/(?:src|article)/[\d+a-z]+)',
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id')

yt_dlp/extractor/drtuber.py

@@ -11,6 +11,7 @@
 
 class DrTuberIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www|m)\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)']
     _TESTS = [{
         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
@@ -33,12 +34,6 @@ class DrTuberIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
-            webpage)
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id')

yt_dlp/extractor/eagleplatform.py

@@ -1,3 +1,4 @@
+import functools
 import re
 
 from .common import InfoExtractor
@@ -5,6 +6,7 @@
 from ..utils import (
     ExtractorError,
     int_or_none,
+    smuggle_url,
     unsmuggle_url,
     url_or_none,
 )
@@ -18,6 +20,7 @@ class EaglePlatformIE(InfoExtractor):
                     )
                     (?P<id>\d+)
                 '''
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1']
     _TESTS = [{
         # http://lenta.ru/news/2015/03/06/navalny/
         'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
@@ -52,14 +55,14 @@ class EaglePlatformIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
+    @classmethod
-    def _extract_url(webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        # Regular iframe embedding
+        add_referer = functools.partial(smuggle_url, data={'referrer': url})
-        mobj = re.search(
+
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1',
+        res = tuple(super()._extract_embed_urls(url, webpage))
-            webpage)
+        if res:
-        if mobj is not None:
+            return map(add_referer, res)
-            return mobj.group('url')
+
         PLAYER_JS_RE = r'''
                         <script[^>]+
                             src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
@@ -74,7 +77,7 @@ def _extract_url(webpage):
                         data-id=["\'](?P<id>\d+)
             ''' % PLAYER_JS_RE, webpage)
         if mobj is not None:
-            return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
+            return [add_referer('eagleplatform:%(host)s:%(id)s' % mobj.groupdict())]
         # Generalization of "Javascript code usage", "Combined usage" and
         # "Usage without attaching to DOM" embeddings (see
         # http://dultonmedia.github.io/eplayer/)
@@ -95,7 +98,7 @@ def _extract_url(webpage):
                     </script>
             ''' % PLAYER_JS_RE, webpage)
         if mobj is not None:
-            return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
+            return [add_referer('eagleplatform:%(host)s:%(id)s' % mobj.groupdict())]
 
     @staticmethod
     def _handle_error(response):
@@ -201,3 +204,14 @@ def _real_extract(self, url):
             'age_limit': age_limit,
             'formats': formats,
         }
+
+
+class ClipYouEmbedIE(InfoExtractor):
+    _VALID_URL = False
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
+        if mobj is not None:
+            yield smuggle_url('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), {'referrer': url})

yt_dlp/extractor/embedly.py

@@ -1,3 +1,5 @@
+import re
+import urllib.parse
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse_unquote
 
@@ -9,5 +11,14 @@ class EmbedlyIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        # Bypass suitable check
+        for mobj in re.finditer(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage):
+            yield mobj.group('url')
+
+        for mobj in re.finditer(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage):
+            yield urllib.parse.unquote(mobj.group('url'))
+
     def _real_extract(self, url):
         return self.url_result(compat_urllib_parse_unquote(self._match_id(url)))

yt_dlp/extractor/ertgr.py

@@ -15,7 +15,6 @@
     parse_iso8601,
     str_or_none,
     try_get,
-    unescapeHTML,
     url_or_none,
     variadic,
 )
@@ -275,6 +274,7 @@ class ERTWebtvEmbedIE(InfoExtractor):
     IE_DESC = 'ert.gr webtv embedded videos'
     _BASE_PLAYER_URL_RE = re.escape('//www.ert.gr/webtv/live-uni/vod/dt-uni-vod.php')
     _VALID_URL = rf'https?:{_BASE_PLAYER_URL_RE}\?([^#]+&)?f=(?P<id>[^#&]+)'
+    _EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>(?:https?:)?{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
 
     _TESTS = [{
         'url': 'https://www.ert.gr/webtv/live-uni/vod/dt-uni-vod.php?f=trailers/E2251_TO_DIKTYO_E09_16-01_1900.mp4&bgimg=/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg',
@@ -287,17 +287,6 @@ class ERTWebtvEmbedIE(InfoExtractor):
         },
     }]
 
-    @classmethod
-    def _extract_urls(cls, webpage):
-        EMBED_URL_RE = rf'(?:https?:)?{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+'
-        EMBED_RE = rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{EMBED_URL_RE})(?P=_q1)'
-
-        for mobj in re.finditer(EMBED_RE, webpage):
-            url = unescapeHTML(mobj.group('url'))
-            if not cls.suitable(url):
-                continue
-            yield url
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         formats, subs = self._extract_m3u8_formats_and_subtitles(

yt_dlp/extractor/expressen.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -17,6 +15,7 @@ class ExpressenIE(InfoExtractor):
                         tv/(?:[^/]+/)*
                         (?P<id>[^/?#&]+)
                     '''
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?(?:expressen|di)\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1']
     _TESTS = [{
         'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/',
         'md5': 'deb2ca62e7b1dcd19fa18ba37523f66e',
@@ -45,13 +44,6 @@ class ExpressenIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url') for mobj in re.finditer(
-                r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?(?:expressen|di)\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1',
-                webpage)]
-
     def _real_extract(self, url):
         display_id = self._match_id(url)
 

yt_dlp/extractor/facebook.py

@@ -57,6 +57,13 @@ class FacebookIE(InfoExtractor):
                 )
                 (?P<id>[0-9]+)
                 '''
+    _EMBED_REGEX = [
+        r'<iframe[^>]+?src=(["\'])(?P<url>https?://www\.facebook\.com/(?:video/embed|plugins/video\.php).+?)\1',
+        # Facebook API embed https://developers.facebook.com/docs/plugins/embedded-video-player
+        r'''(?x)<div[^>]+
+                class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+
+                data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''',
+    ]
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
@@ -311,21 +318,6 @@ class FacebookIE(InfoExtractor):
         'graphURI': '/api/graphql/'
     }
 
-    @staticmethod
-    def _extract_urls(webpage):
-        urls = []
-        for mobj in re.finditer(
-                r'<iframe[^>]+?src=(["\'])(?P<url>https?://www\.facebook\.com/(?:video/embed|plugins/video\.php).+?)\1',
-                webpage):
-            urls.append(mobj.group('url'))
-        # Facebook API embed
-        # see https://developers.facebook.com/docs/plugins/embedded-video-player
-        for mobj in re.finditer(r'''(?x)<div[^>]+
-                class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+
-                data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage):
-            urls.append(mobj.group('url'))
-        return urls
-
     def _perform_login(self, username, password):
         login_page_req = sanitized_Request(self._LOGIN_URL)
         self._set_cookie('facebook.com', 'locale', 'en_US')

yt_dlp/extractor/foxnews.py

@@ -56,8 +56,8 @@ class FoxNewsIE(AMPIE):
         },
     ]
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
         return [
             f'https://video.foxnews.com/v/video-embed.html?video_id={mobj.group("video_id")}'
             for mobj in re.finditer(
@@ -125,4 +125,4 @@ def _real_extract(self, url):
                 'http://video.foxnews.com/v/' + video_id, FoxNewsIE.ie_key())
 
         return self.url_result(
-            FoxNewsIE._extract_urls(webpage)[0], FoxNewsIE.ie_key())
+            FoxNewsIE._extract_embed_urls(url, webpage)[0], FoxNewsIE.ie_key())

yt_dlp/extractor/francetv.py

@@ -32,6 +32,7 @@ class FranceTVIE(InfoExtractor):
                         (?P<id>[^@]+)(?:@(?P<catalog>.+))?
                     )
                     '''
+    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1']
 
     _TESTS = [{
         # without catalog
@@ -370,7 +371,7 @@ def _real_extract(self, url):
 
         webpage = self._download_webpage(url, display_id)
 
-        dailymotion_urls = DailymotionIE._extract_urls(webpage)
+        dailymotion_urls = DailymotionIE._extract_embed_urls(url, webpage)
         if dailymotion_urls:
             return self.playlist_result([
                 self.url_result(dailymotion_url, DailymotionIE.ie_key())

yt_dlp/extractor/gedidigital.py

@@ -11,7 +11,7 @@
 
 
 class GediDigitalIE(InfoExtractor):
-    _VALID_URL = r'''(?x:(?P<url>(?:https?:)//video\.
+    _VALID_URL = r'''(?x:(?P<base_url>(?:https?:)//video\.
         (?:
             (?:
                 (?:espresso\.)?repubblica
@@ -34,6 +34,12 @@ class GediDigitalIE(InfoExtractor):
                 |lasentinella
             )\.gelocal
         )\.it(?:/[^/]+){2,4}/(?P<id>\d+))(?:$|[?&].*))'''
+    _EMBED_REGEX = [rf'''(?x)
+            (?:
+                data-frame-src=|
+                <iframe[^\n]+src=
+            )
+            (["'])(?P<url>{_VALID_URL})\1''']
     _TESTS = [{
         'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
         'md5': '84658d7fb9e55a6e57ecc77b73137494',
@@ -109,22 +115,9 @@ def _sanitize_urls(urls):
             urls[i] = urljoin(base_url(e), url_basename(e))
         return urls
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        entries = [
+        return cls._sanitize_urls(tuple(super()._extract_embed_urls(url, webpage)))
-            mobj.group('eurl')
-            for mobj in re.finditer(r'''(?x)
-            (?:
-                data-frame-src=|
-                <iframe[^\n]+src=
-            )
-            (["'])(?P<eurl>%s)\1''' % GediDigitalIE._VALID_URL, webpage)]
-        return GediDigitalIE._sanitize_urls(entries)
-
-    @staticmethod
-    def _extract_url(webpage):
-        urls = GediDigitalIE._extract_urls(webpage)
-        return urls[0] if urls else None
 
     @staticmethod
     def _clean_formats(formats):
@@ -139,8 +132,7 @@ def _clean_formats(formats):
         formats[:] = clean_formats
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id, url = self._match_valid_url(url).group('id', 'base_url')
-        url = self._match_valid_url(url).group('url')
         webpage = self._download_webpage(url, video_id)
         title = self._html_search_meta(
             ['twitter:title', 'og:title'], webpage, fatal=True)

yt_dlp/extractor/gfycat.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -11,6 +9,7 @@
 
 class GfycatIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?i:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#\."\']+)'
+    _EMBED_REGEX = [rf'<(?:iframe|source)[^>]+\bsrc=["\'](?P<url>{_VALID_URL})']
     _TESTS = [{
         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
         'info_dict': {
@@ -82,14 +81,6 @@ class GfycatIE(InfoExtractor):
         'only_matching': True
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<(?:iframe|source)[^>]+\bsrc=["\'](?P<url>%s)' % GfycatIE._VALID_URL,
-                webpage)]
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/glomex.py

@@ -174,7 +174,7 @@ def build_player_url(cls, video_id, integration, origin_url=None):
         return cls._smuggle_origin_url(f'https:{cls._BASE_PLAYER_URL}?{query_string}', origin_url)
 
     @classmethod
-    def _extract_urls(cls, webpage, origin_url):
+    def _extract_embed_urls(cls, url, webpage):
         # https://docs.glomex.com/publisher/video-player-integration/javascript-api/
         quot_re = r'["\']'
 
@@ -183,9 +183,9 @@ def _extract_urls(cls, webpage, origin_url):
                 (?:https?:)?{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=q)).)+
             )(?P=q)'''
         for mobj in re.finditer(regex, webpage):
-            url = unescapeHTML(mobj.group('url'))
+            embed_url = unescapeHTML(mobj.group('url'))
-            if cls.suitable(url):
+            if cls.suitable(embed_url):
-                yield cls._smuggle_origin_url(url, origin_url)
+                yield cls._smuggle_origin_url(embed_url, url)
 
         regex = fr'''(?x)
             <glomex-player [^>]+?>|
@@ -193,7 +193,7 @@ def _extract_urls(cls, webpage, origin_url):
         for mobj in re.finditer(regex, webpage):
             attrs = extract_attributes(mobj.group(0))
             if attrs.get('data-integration-id') and attrs.get('data-playlist-id'):
-                yield cls.build_player_url(attrs['data-playlist-id'], attrs['data-integration-id'], origin_url)
+                yield cls.build_player_url(attrs['data-playlist-id'], attrs['data-integration-id'], url)
 
         # naive parsing of inline scripts for hard-coded integration parameters
         regex = fr'''(?x)
@@ -206,7 +206,7 @@ def _extract_urls(cls, webpage, origin_url):
                 continue
             playlist_id = re.search(regex % 'playlistId', script)
             if playlist_id:
-                yield cls.build_player_url(playlist_id, integration_id, origin_url)
+                yield cls.build_player_url(playlist_id, integration_id, url)
 
     def _real_extract(self, url):
         url, origin_url = self._unsmuggle_origin_url(url)

yt_dlp/extractor/googledrive.py

@@ -77,13 +77,13 @@ class GoogleDriveIE(InfoExtractor):
     _caption_formats_ext = []
     _captions_xml = None
 
-    @staticmethod
+    @classmethod
-    def _extract_url(webpage):
+    def _extract_embed_urls(cls, url, webpage):
         mobj = re.search(
             r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
             webpage)
         if mobj:
-            return 'https://drive.google.com/file/d/%s' % mobj.group('id')
+            yield 'https://drive.google.com/file/d/%s' % mobj.group('id')
 
     def _download_subtitles_xml(self, video_id, subtitles_id, hl):
         if self._captions_xml:

yt_dlp/extractor/heise.py

@@ -121,7 +121,7 @@ def _make_kaltura_result(kaltura_url):
         if kaltura_id:
             return _make_kaltura_result('kaltura:2238431:%s' % kaltura_id)
 
-        yt_urls = YoutubeIE._extract_urls(webpage)
+        yt_urls = YoutubeIE._extract_embed_urls(url, webpage)
         if yt_urls:
             return self.playlist_from_matches(
                 yt_urls, video_id, title, ie=YoutubeIE.ie_key())

yt_dlp/extractor/huffpost.py

@@ -17,6 +17,7 @@ class HuffPostIE(InfoExtractor):
             HPLEmbedPlayer/\?segmentId=
         )
         (?P<id>[0-9a-f]+)'''
+    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1']
 
     _TEST = {
         'url': 'http://live.huffingtonpost.com/r/segment/legalese-it/52dd3e4b02a7602131000677',

yt_dlp/extractor/indavideo.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
@@ -12,6 +10,14 @@
 
 class IndavideoEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
+    # Some example URLs covered by generic extractor:
+    #   http://indavideo.hu/video/Vicces_cica_1
+    #   http://index.indavideo.hu/video/2015_0728_beregszasz
+    #   http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
+    #   http://erotika.indavideo.hu/video/Amator_tini_punci
+    #   http://film.indavideo.hu/video/f_hrom_nagymamm_volt
+    #   http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/[\da-f]+)']
     _TESTS = [{
         'url': 'http://indavideo.hu/player/video/1bdc3c6d80/',
         'md5': 'c8a507a1c7410685f83a06eaeeaafeab',
@@ -37,20 +43,6 @@ class IndavideoEmbedIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    # Some example URLs covered by generic extractor:
-    #   http://indavideo.hu/video/Vicces_cica_1
-    #   http://index.indavideo.hu/video/2015_0728_beregszasz
-    #   http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
-    #   http://erotika.indavideo.hu/video/Amator_tini_punci
-    #   http://film.indavideo.hu/video/f_hrom_nagymamm_volt
-    #   http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes
-
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/[\da-f]+)',
-            webpage)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/instagram.py

@@ -243,6 +243,7 @@ def _real_extract(self, url):
 
 class InstagramIE(InstagramBaseIE):
     _VALID_URL = r'(?P<url>https?://(?:www\.)?instagram\.com(?:/[^/]+)?/(?:p|tv|reel)/(?P<id>[^/?#&]+))'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?instagram\.com/p/[^/]+/embed.*?)\1']
     _TESTS = [{
         'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
         'md5': '0d2da106a9d2631273e192b372806516',
@@ -346,23 +347,16 @@ class InstagramIE(InstagramBaseIE):
         'only_matching': True,
     }]
 
-    @staticmethod
+    @classmethod
-    def _extract_embed_url(webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        mobj = re.search(
+        res = tuple(super()._extract_embed_urls(url, webpage))
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?instagram\.com/p/[^/]+/embed.*?)\1',
+        if res:
-            webpage)
+            return res
-        if mobj:
-            return mobj.group('url')
 
-        blockquote_el = get_element_by_attribute(
+        mobj = re.search(r'<a[^>]+href=([\'"])(?P<link>[^\'"]+)\1',
-            'class', 'instagram-media', webpage)
+                         get_element_by_attribute('class', 'instagram-media', webpage) or '')
-        if blockquote_el is None:
-            return
-
-        mobj = re.search(
-            r'<a[^>]+href=([\'"])(?P<link>[^\'"]+)\1', blockquote_el)
         if mobj:
-            return mobj.group('link')
+            return [mobj.group('link')]
 
     def _real_extract(self, url):
         video_id, url = self._match_valid_url(url).group('id', 'url')

yt_dlp/extractor/ivi.py

@@ -13,6 +13,7 @@ class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'
     _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
+    _EMBED_REGEX = [r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1']
     _GEO_BYPASS = False
     _GEO_COUNTRIES = ['RU']
     _LIGHT_KEY = b'\xf1\x02\x32\xb7\xbc\x5c\x7a\xe8\xf7\x96\xc1\x33\x2b\x27\xa1\x8c'

yt_dlp/extractor/joj.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
@@ -18,6 +16,7 @@ class JojIE(InfoExtractor):
                     )
                     (?P<id>[^/?#^]+)
                 '''
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//media\.joj\.sk/embed/(?:(?!\1).)+)\1']
     _TESTS = [{
         'url': 'https://media.joj.sk/embed/a388ec4c-6019-4a4a-9312-b1bee194e932',
         'info_dict': {
@@ -38,14 +37,6 @@ class JojIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//media\.joj\.sk/embed/(?:(?!\1).)+)\1',
-                webpage)]
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/jwplatform.py

@@ -22,13 +22,8 @@ class JWPlatformIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
+    @classmethod
-    def _extract_url(webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        urls = JWPlatformIE._extract_urls(webpage)
-        return urls[0] if urls else None
-
-    @staticmethod
-    def _extract_urls(webpage):
         for tag, key in ((r'(?:script|iframe)', 'src'), ('input', 'value')):
             # <input value=URL> is used by hyland.com
             # if we find <iframe>, dont look for <input>

yt_dlp/extractor/kaltura.py

@@ -111,13 +111,8 @@ class KalturaIE(InfoExtractor):
         }
     ]
 
-    @staticmethod
+    @classmethod
-    def _extract_url(webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        urls = KalturaIE._extract_urls(webpage)
-        return urls[0] if urls else None
-
-    @staticmethod
-    def _extract_urls(webpage):
         # Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
         finditer = (
             list(re.finditer(
@@ -159,14 +154,14 @@ def _extract_urls(webpage):
             for k, v in embed_info.items():
                 if v:
                     embed_info[k] = v.strip()
-            url = 'kaltura:%(partner_id)s:%(id)s' % embed_info
+            embed_url = 'kaltura:%(partner_id)s:%(id)s' % embed_info
             escaped_pid = re.escape(embed_info['partner_id'])
             service_mobj = re.search(
                 r'<script[^>]+src=(["\'])(?P<id>(?:https?:)?//(?:(?!\1).)+)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid),
                 webpage)
             if service_mobj:
-                url = smuggle_url(url, {'service_url': service_mobj.group('id')})
+                embed_url = smuggle_url(embed_url, {'service_url': service_mobj.group('id')})
-            urls.append(url)
+            urls.append(embed_url)
         return urls
 
     def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs):

yt_dlp/extractor/kinja.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
@@ -10,8 +8,6 @@
     parse_iso8601,
     strip_or_none,
     try_get,
-    unescapeHTML,
-    urljoin,
 )
 
 
@@ -55,6 +51,7 @@ class KinjaEmbedIE(InfoExtractor):
             vine|
             youtube-(?:list|video)
         )-(?P<id>[^&]+)''' % (_DOMAIN_REGEX, _COMMON_REGEX)
+    _EMBED_REGEX = [rf'(?x)<iframe[^>]+?src=(?P<q>["\'])(?P<url>(?:(?:https?:)?//{_DOMAIN_REGEX})?{_COMMON_REGEX}(?:(?!\1).)+)\1']
     _TESTS = [{
         'url': 'https://kinja.com/ajax/inset/iframe?id=fb-10103303356633621',
         'only_matching': True,
@@ -119,12 +116,6 @@ class KinjaEmbedIE(InfoExtractor):
         'youtube-video': ('youtube.com/embed/', 'Youtube'),
     }
 
-    @staticmethod
-    def _extract_urls(webpage, url):
-        return [urljoin(url, unescapeHTML(mobj.group('url'))) for mobj in re.finditer(
-            r'(?x)<iframe[^>]+?src=(?P<q>["\'])(?P<url>(?:(?:https?:)?//%s)?%s(?:(?!\1).)+)\1' % (KinjaEmbedIE._DOMAIN_REGEX, KinjaEmbedIE._COMMON_REGEX),
-            webpage)]
-
     def _real_extract(self, url):
         video_type, video_id = self._match_valid_url(url).groups()
 

yt_dlp/extractor/libsyn.py

@@ -10,6 +10,7 @@
 
 class LibsynIE(InfoExtractor):
     _VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1']
 
     _TESTS = [{
         'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',

yt_dlp/extractor/limelight.py

@@ -17,7 +17,7 @@ class LimelightBaseIE(InfoExtractor):
     _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
 
     @classmethod
-    def _extract_urls(cls, webpage, source_url):
+    def _extract_embed_urls(cls, url, webpage):
         lm = {
             'Media': 'media',
             'Channel': 'channel',
@@ -25,7 +25,7 @@ def _extract_urls(cls, webpage, source_url):
         }
 
         def smuggle(url):
-            return smuggle_url(url, {'source_url': source_url})
+            return smuggle_url(url, {'source_url': url})
 
         entries = []
         for kind, video_id in re.findall(

yt_dlp/extractor/livestream.py

@@ -23,6 +23,8 @@
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
     _VALID_URL = r'https?://(?:new\.)?livestream\.com/(?:accounts/(?P<account_id>\d+)|(?P<account_name>[^/]+))/(?:events/(?P<event_id>\d+)|(?P<event_name>[^/]+))(?:/videos/(?P<id>\d+))?'
+    _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"']
+
     _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',

yt_dlp/extractor/mainstreaming.py

@@ -14,6 +14,7 @@
 
 class MainStreamingIE(InfoExtractor):
     _VALID_URL = r'https?://(?:webtools-?)?(?P<host>[A-Za-z0-9-]*\.msvdn.net)/(?:embed|amp_embed|content)/(?P<id>\w+)'
+    _EMBED_REGEX = [rf'<iframe[^>]+?src=["\']?(?P<url>{_VALID_URL})["\']?']
     IE_DESC = 'MainStreaming Player'
 
     _TESTS = [
@@ -102,13 +103,6 @@ class MainStreamingIE(InfoExtractor):
         }
     ]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        mobj = re.findall(
-            r'<iframe[^>]+?src=["\']?(?P<url>%s)["\']?' % MainStreamingIE._VALID_URL, webpage)
-        if mobj:
-            return [group[0] for group in mobj]
-
     def _playlist_entries(self, host, playlist_content):
         for entry in playlist_content:
             content_id = entry.get('contentID')

yt_dlp/extractor/mangomolo.py

@@ -3,11 +3,29 @@
     compat_b64decode,
     compat_urllib_parse_unquote,
 )
-from ..utils import int_or_none
+from ..utils import classproperty, int_or_none
 
 
 class MangomoloBaseIE(InfoExtractor):
-    _BASE_REGEX = r'https?://(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)'
+    _BASE_REGEX = r'(?:https?:)?//(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)'
+    _SLUG = None
+
+    @classproperty
+    def _VALID_URL(cls):
+        return f'{cls._BASE_REGEX}{cls._SLUG}'
+
+    @classproperty
+    def _EMBED_REGEX(cls):
+        return [rf'<iframe[^>]+src=(["\'])(?P<url>{cls._VALID_URL}.+?)\1']
+
+    def _extract_from_webpage(self, url, webpage):
+        for res in super()._extract_from_webpage(url, webpage):
+            yield {
+                **res,
+                '_type': 'url_transparent',
+                'id': self._search_regex(self._SLUG, res['url'], 'id', group='id'),
+                'uploader': self._search_regex(r'^(?:https?://)?([^/]*)/.*', url, 'video uploader'),
+            }
 
     def _get_real_id(self, page_id):
         return page_id
@@ -41,14 +59,15 @@ def _real_extract(self, url):
 class MangomoloVideoIE(MangomoloBaseIE):
     _TYPE = 'video'
     IE_NAME = 'mangomolo:' + _TYPE
-    _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'video\?.*?\bid=(?P<id>\d+)'
+    _SLUG = r'video\?.*?\bid=(?P<id>\d+)'
+
     _IS_LIVE = False
 
 
 class MangomoloLiveIE(MangomoloBaseIE):
     _TYPE = 'live'
     IE_NAME = 'mangomolo:' + _TYPE
-    _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'(live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
+    _SLUG = r'(?:live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
     _IS_LIVE = True
 
     def _get_real_id(self, page_id):

yt_dlp/extractor/medialaan.py

@@ -69,8 +69,8 @@ class MedialaanIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
         entries = []
         for element in re.findall(r'(<div[^>]+data-mychannels-type="video"[^>]*>)', webpage):
             mychannels_id = extract_attributes(element).get('data-mychannels-id')

yt_dlp/extractor/mediaset.py

@@ -167,8 +167,7 @@ class MediasetIE(ThePlatformBaseIE):
         'only_matching': True,
     }]
 
-    @staticmethod
+    def _extract_from_webpage(self, url, webpage):
-    def _extract_urls(ie, webpage):
         def _qs(url):
             return parse_qs(url)
 
@@ -188,8 +187,7 @@ def _program_guid(qs):
             video_id = embed_qs.get('id', [None])[0]
             if not video_id:
                 continue
-            urlh = ie._request_webpage(
+            urlh = self._request_webpage(embed_url, video_id, note='Following embed URL redirect')
-                embed_url, video_id, note='Following embed URL redirect')
             embed_url = urlh.geturl()
             program_guid = _program_guid(_qs(embed_url))
             if program_guid:

yt_dlp/extractor/mediasite.py

@@ -13,7 +13,7 @@
     str_or_none,
     try_call,
     try_get,
-    unescapeHTML,
+    smuggle_url,
     unsmuggle_url,
     url_or_none,
     urljoin,
@@ -25,6 +25,7 @@
 
 class MediasiteIE(InfoExtractor):
     _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/[^/#?]+/Presentation)/(?P<id>%s)(?P<query>\?[^#]+|)' % _ID_RE
+    _EMBED_REGEX = [r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/%s(?:\?.*?)?)\1' % _ID_RE]
     _TESTS = [
         {
             'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d',
@@ -112,13 +113,10 @@ class MediasiteIE(InfoExtractor):
         5: 'video3',
     }
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        return [
+        for embed_url in super()._extract_embed_urls(url, webpage):
-            unescapeHTML(mobj.group('url'))
+            yield smuggle_url(embed_url, {'UrlReferrer': url})
-            for mobj in re.finditer(
-                r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/%s(?:\?.*?)?)\1' % _ID_RE,
-                webpage)]
 
     def __extract_slides(self, *, stream_id, snum, Stream, duration, images):
         slide_base_url = Stream['SlideBaseUrl']

yt_dlp/extractor/megaphone.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import js_to_json
 
@@ -8,6 +6,7 @@ class MegaphoneIE(InfoExtractor):
     IE_NAME = 'megaphone.fm'
     IE_DESC = 'megaphone.fm embedded players'
     _VALID_URL = r'https://player\.megaphone\.fm/(?P<id>[A-Z0-9]+)'
+    _EMBED_REGEX = [rf'<iframe[^>]*?\ssrc=["\'](?P<url>{_VALID_URL})']
     _TEST = {
         'url': 'https://player.megaphone.fm/GLT9749789991?"',
         'md5': '4816a0de523eb3e972dc0dda2c191f96',
@@ -45,8 +44,3 @@ def _real_extract(self, url):
             'duration': episode_data['duration'],
             'formats': formats,
         }
-
-    @classmethod
-    def _extract_urls(cls, webpage):
-        return [m[0] for m in re.findall(
-            r'<iframe[^>]*?\ssrc=["\'](%s)' % cls._VALID_URL, webpage)]

yt_dlp/extractor/megatvcom.py

@@ -104,7 +104,7 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
     IE_NAME = 'megatvcom:embed'
     IE_DESC = 'megatv.com embedded videos'
     _VALID_URL = r'(?:https?:)?//(?:www\.)?megatv\.com/embed/?\?p=(?P<id>\d+)'
-    _EMBED_RE = re.compile(rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''')
+    _EMBED_REGEX = [rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''']
 
     _TESTS = [{
         'url': 'https://www.megatv.com/embed/?p=2020520979',
@@ -134,11 +134,6 @@ class MegaTVComEmbedIE(MegaTVComBaseIE):
         },
     }]
 
-    @classmethod
-    def _extract_urls(cls, webpage):
-        for mobj in cls._EMBED_RE.finditer(webpage):
-            yield unescapeHTML(mobj.group('url'))
-
     def _match_canonical_url(self, webpage):
         LINK_RE = r'''(?x)
         <link(?:

yt_dlp/extractor/mlb.py

@@ -92,6 +92,10 @@ class MLBIE(MLBBaseIE):
                             (?P<id>\d+)
                         )
                     '''
+    _EMBED_REGEX = [
+        r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
+        r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
+    ]
     _TESTS = [
         {
             'url': 'https://www.mlb.com/mariners/video/ackleys-spectacular-catch/c-34698933',

yt_dlp/extractor/mofosex.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -59,17 +57,12 @@ def _real_extract(self, url):
 
 class MofosexEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)']
     _TESTS = [{
         'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM',
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)',
-            webpage)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         return self.url_result(

yt_dlp/extractor/mtv.py

@@ -331,6 +331,7 @@ def _real_extract(self, url):
 class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
     IE_NAME = 'mtvservices:embedded'
     _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1']
 
     _TEST = {
         # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
@@ -346,13 +347,6 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
         },
     }
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1', webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _get_feed_url(self, uri, url=None):
         video_id = self._id_from_uri(uri)
         config = self._download_json(

yt_dlp/extractor/myvi.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from .vimple import SprutoBaseIE
 
@@ -26,6 +24,7 @@ class MyviIE(SprutoBaseIE):
                         )
                         (?P<id>[\da-zA-Z_-]+)
                     '''
+    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//myvi\.(?:ru/player|tv)/(?:embed/html|flash)/[^"]+)\1']
     _TESTS = [{
         'url': 'http://myvi.ru/player/embed/html/oOy4euHA6LVwNNAjhD9_Jq5Ha2Qf0rtVMVFMAZav8wObeRTZaCATzucDQIDph8hQU0',
         'md5': '571bbdfba9f9ed229dc6d34cc0f335bf',
@@ -56,13 +55,6 @@ class MyviIE(SprutoBaseIE):
         'only_matching': True,
     }]
 
-    @classmethod
-    def _extract_url(cls, webpage):
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//myvi\.(?:ru/player|tv)/(?:embed/html|flash)/[^"]+)\1', webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/nbc.py

@@ -184,6 +184,7 @@ def _real_extract(self, url):
 class NBCSportsVPlayerIE(InfoExtractor):
     _VALID_URL_BASE = r'https?://(?:vplayer\.nbcsports\.com|(?:www\.)?nbcsports\.com/vplayer)/'
     _VALID_URL = _VALID_URL_BASE + r'(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
+    _EMBED_REGEX = [r'(?:iframe[^>]+|var video|div[^>]+data-(?:mpx-)?)[sS]rc\s?=\s?"(?P<url>%s[^\"]+)' % _VALID_URL_BASE]
 
     _TESTS = [{
         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
@@ -207,13 +208,6 @@ class NBCSportsVPlayerIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_url(webpage):
-        video_urls = re.search(
-            r'(?:iframe[^>]+|var video|div[^>]+data-(?:mpx-)?)[sS]rc\s?=\s?"(?P<url>%s[^\"]+)' % NBCSportsVPlayerIE._VALID_URL_BASE, webpage)
-        if video_urls:
-            return video_urls.group('url')
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
@@ -317,6 +311,7 @@ def _real_extract(self, url):
 
 class NBCNewsIE(ThePlatformIE):
     _VALID_URL = r'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1']
 
     _TESTS = [
         {

yt_dlp/extractor/nexx.py

@@ -114,8 +114,8 @@ def _extract_domain_id(webpage):
             webpage)
         return mobj.group('id') if mobj else None
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
         # Reference:
         # 1. https://nx-s.akamaized.net/files/201510/44.pdf
 
@@ -135,10 +135,6 @@ def _extract_urls(webpage):
 
         return entries
 
-    @staticmethod
-    def _extract_url(webpage):
-        return NexxIE._extract_urls(webpage)[0]
-
     def _handle_error(self, response):
         if traverse_obj(response, ('metadata', 'notice'), expected_type=str):
             self.report_warning('%s said: %s' % (self.IE_NAME, response['metadata']['notice']))
@@ -498,6 +494,8 @@ def find_video(result):
 
 class NexxEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:video/)?(?P<id>[^/?#&]+)'
+    # Reference. https://nx-s.akamaized.net/files/201510/44.pdf
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:(?!\1).)+)\1']
     _TESTS = [{
         'url': 'http://embed.nexx.cloud/748/KC1614647Z27Y7T?autoplay=1',
         'md5': '16746bfc28c42049492385c989b26c4a',
@@ -521,16 +519,6 @@ class NexxEmbedIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        # Reference:
-        # 1. https://nx-s.akamaized.net/files/201510/44.pdf
-
-        # iFrame Embed Integration
-        return [mobj.group('url') for mobj in re.finditer(
-            r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:(?!\1).)+)\1',
-            webpage)]
-
     def _real_extract(self, url):
         embed_id = self._match_id(url)
 

yt_dlp/extractor/nytimes.py

@@ -103,6 +103,7 @@ def get_file_size(file_size):
 
 class NYTimesIE(NYTimesBaseIE):
     _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>']
 
     _TESTS = [{
         'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',

yt_dlp/extractor/odnoklassniki.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..compat import (
     compat_etree_fromstring,
@@ -31,6 +29,7 @@ class OdnoklassnikiIE(InfoExtractor):
                     )
                     (?P<id>[\d-]+)
                 '''
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1']
     _TESTS = [{
         'note': 'Coub embedded',
         'url': 'http://ok.ru/video/1484130554189',
@@ -161,13 +160,6 @@ class OdnoklassnikiIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         try:
             return self._extract_desktop(url)

yt_dlp/extractor/onionstudios.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import js_to_json
@@ -7,6 +5,7 @@
 
 class OnionStudiosIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:video(?:s/[^/]+-|/)|embed\?.*\bid=)(?P<id>\d+)(?!-)'
+    _EMBED_REGEX = [r'(?s)<(?:iframe|bulbs-video)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/(?:embed.+?|video/\d+\.json))\1']
 
     _TESTS = [{
         'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
@@ -29,13 +28,6 @@ class OnionStudiosIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'(?s)<(?:iframe|bulbs-video)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/(?:embed.+?|video/\d+\.json))\1', webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/ooyala.py

@@ -10,6 +10,7 @@
     determine_ext,
     float_or_none,
     int_or_none,
+    smuggle_url,
     try_get,
     unsmuggle_url,
 )
@@ -151,6 +152,29 @@ class OoyalaIE(OoyalaBaseIE):
         }
     ]
 
+    def _extract_from_webpage(self, url, webpage):
+        mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
+                or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
+                or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
+                or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
+                or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+        if mobj is not None:
+            embed_token = self._search_regex(
+                r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
+                webpage, 'ooyala embed token', default=None)
+            yield self._build_url_result(smuggle_url(
+                mobj.group('ec'), {
+                    'domain': url,
+                    'embed_token': embed_token,
+                }))
+            return
+
+        # Look for multiple Ooyala embeds on SBN network websites
+        mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
+        if mobj is not None:
+            for v in self._parse_json(mobj.group(1), self._generic_id(url), fatal=False) or []:
+                yield self._build_url_result(smuggle_url(v['provider_video_id'], {'domain': url}))
+
     @staticmethod
     def _url_for_embed_code(embed_code):
         return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code

yt_dlp/extractor/panopto.py

@@ -1,4 +1,3 @@
-import re
 import calendar
 import json
 import functools
@@ -73,15 +72,10 @@ def _call_api(self, base_url, path, video_id, data=None, fatal=True, **kwargs):
     def _parse_fragment(url):
         return {k: json.loads(v[0]) for k, v in compat_urlparse.parse_qs(compat_urllib_parse_urlparse(url).fragment).items()}
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [m.group('url') for m in re.finditer(
-            r'<iframe[^>]+src=["\'](?P<url>%s/Pages/(Viewer|Embed|Sessions/List)\.aspx[^"\']+)' % PanoptoIE.BASE_URL_RE,
-            webpage)]
-
 
 class PanoptoIE(PanoptoBaseIE):
     _VALID_URL = PanoptoBaseIE.BASE_URL_RE + r'/Pages/(Viewer|Embed)\.aspx.*(?:\?|&)id=(?P<id>[a-f0-9-]+)'
+    _EMBED_REGEX = [rf'<iframe[^>]+src=["\'](?P<url>{PanoptoBaseIE.BASE_URL_RE}/Pages/(Viewer|Embed|Sessions/List)\.aspx[^"\']+)']
     _TESTS = [
         {
             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=26b3ae9e-4a48-4dcc-96ba-0befba08a0fb',

yt_dlp/extractor/peertube.py

@@ -1057,6 +1057,7 @@ class PeerTubeIE(InfoExtractor):
                     )
                     (?P<id>%s)
                     ''' % (_INSTANCES_RE, _UUID_RE)
+    _EMBED_REGEX = [r'''(?x)<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//{_INSTANCES_RE}/videos/embed/{cls._UUID_RE})''']
     _TESTS = [{
         'url': 'https://framatube.org/videos/watch/9c9de5e8-0a1e-484a-b099-e80766180a6d',
         'md5': '8563064d245a4be5705bddb22bb00a28',
@@ -1158,16 +1159,15 @@ def _extract_peertube_url(webpage, source_url):
                 '>We are sorry but it seems that PeerTube is not compatible with your web browser.<')):
             return 'peertube:%s:%s' % mobj.group('host', 'id')
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage, source_url):
+    def _extract_embed_urls(cls, url, webpage):
-        entries = re.findall(
+        embeds = tuple(super()._extract_embed_urls(url, webpage))
-            r'''(?x)<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//%s/videos/embed/%s)'''
+        if embeds:
-            % (PeerTubeIE._INSTANCES_RE, PeerTubeIE._UUID_RE), webpage)
+            return embeds
-        if not entries:
+
-            peertube_url = PeerTubeIE._extract_peertube_url(webpage, source_url)
+        peertube_url = cls._extract_peertube_url(webpage, url)
-            if peertube_url:
+        if peertube_url:
-                entries = [peertube_url]
+            return [peertube_url]
-        return entries
 
     def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True):
         return self._download_json(

yt_dlp/extractor/periscope.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -67,6 +65,7 @@ class PeriscopeIE(PeriscopeBaseIE):
     IE_DESC = 'Periscope'
     IE_NAME = 'periscope'
     _VALID_URL = r'https?://(?:www\.)?(?:periscope|pscp)\.tv/[^/]+/(?P<id>[^/?#]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=([\'"])(?P<url>(?:https?:)?//(?:www\.)?(?:periscope|pscp)\.tv/(?:(?!\1).)+)\1']
     # Alive example URLs can be found here https://www.periscope.tv/
     _TESTS = [{
         'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==',
@@ -92,13 +91,6 @@ class PeriscopeIE(PeriscopeBaseIE):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src=([\'"])(?P<url>(?:https?:)?//(?:www\.)?(?:periscope|pscp)\.tv/(?:(?!\1).)+)\1', webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         token = self._match_id(url)
 

yt_dlp/extractor/piksel.py

@@ -30,6 +30,7 @@ class PikselIE(InfoExtractor):
             )\.jp|
             vidego\.baltimorecity\.gov
         )/v/(?:refid/(?P<refid>[^/]+)/prefid/)?(?P<id>[\w-]+)'''
+    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//player\.piksel\.com/v/[a-z0-9]+)']
     _TESTS = [
         {
             'url': 'http://player.piksel.com/v/ums2867l',
@@ -62,14 +63,6 @@ class PikselIE(InfoExtractor):
         }
     ]
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src=["\'](?P<url>(?:https?:)?//player\.piksel\.com/v/[a-z0-9]+)',
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _call_api(self, app_token, resource, display_id, query, fatal=True):
         response = (self._download_json(
             'http://player.piksel.com/ws/ws_%s/api/%s/mode/json/apiv/5' % (resource, app_token),

yt_dlp/extractor/pladform.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -24,6 +22,7 @@ class PladformIE(InfoExtractor):
                         )
                         (?P<id>\d+)
                     '''
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1']
     _TESTS = [{
         'url': 'http://out.pladform.ru/player?pl=18079&type=html5&videoid=100231282',
         'info_dict': {
@@ -61,13 +60,6 @@ class PladformIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1', webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/playwire.py

@@ -7,6 +7,8 @@
 
 class PlaywireIE(InfoExtractor):
     _VALID_URL = r'https?://(?:config|cdn)\.playwire\.com(?:/v2)?/(?P<publisher_id>\d+)/(?:videos/v2|embed|config)/(?P<id>\d+)'
+    _EMBED_REGEX = [r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1']
+
     _TESTS = [{
         'url': 'http://config.playwire.com/14907/videos/v2/3353705/player.json',
         'md5': 'e6398701e3595888125729eaa2329ed9',

yt_dlp/extractor/pornhub.py

@@ -128,6 +128,7 @@ class PornHubIE(PornHubBaseIE):
                         )
                         (?P<id>[\da-z]+)
                     ''' % PornHubBaseIE._PORNHUB_HOST_RE
+    _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)']
     _TESTS = [{
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
         'md5': 'a6391306d050e4547f62b3f485dd9ba9',
@@ -257,12 +258,6 @@ class PornHubIE(PornHubBaseIE):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
-            webpage)
-
     def _extract_count(self, pattern, webpage, name):
         return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None))
 

yt_dlp/extractor/rcs.py

@@ -281,6 +281,20 @@ class RCSEmbedsIE(RCSBaseIE):
                         (?:gazzanet\.)?gazzetta
                     )\.it)
                     /video-embed/(?P<id>[^/=&\?]+?)(?:$|\?)'''
+    _EMBED_REGEX = [r'''(?x)
+            (?:
+                data-frame-src=|
+                <iframe[^\n]+src=
+            )
+            (["'])
+                (?P<url>(?:https?:)?//video\.
+                    (?:
+                        rcs|
+                        (?:corriere\w+\.)?corriere|
+                        (?:gazzanet\.)?gazzetta
+                    )
+                \.it/video-embed/.+?)
+            \1''']
     _TESTS = [{
         'url': 'https://video.rcs.it/video-embed/iodonna-0001585037',
         'md5': '623ecc8ffe7299b2d0c1046d8331a9df',
@@ -321,30 +335,9 @@ def _sanitize_urls(urls):
             urls[i] = urljoin(base_url(e), url_basename(e))
         return urls
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        entries = [
+        return cls._sanitize_urls(tuple(super()._extract_embed_urls(url, webpage)))
-            mobj.group('url')
-            for mobj in re.finditer(r'''(?x)
-            (?:
-                data-frame-src=|
-                <iframe[^\n]+src=
-            )
-            (["'])
-                (?P<url>(?:https?:)?//video\.
-                    (?:
-                        rcs|
-                        (?:corriere\w+\.)?corriere|
-                        (?:gazzanet\.)?gazzetta
-                    )
-                \.it/video-embed/.+?)
-            \1''', webpage)]
-        return RCSEmbedsIE._sanitize_urls(entries)
-
-    @staticmethod
-    def _extract_url(webpage):
-        urls = RCSEmbedsIE._extract_urls(webpage)
-        return urls[0] if urls else None
 
 
 class RCSIE(RCSBaseIE):

yt_dlp/extractor/redtube.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -14,6 +12,7 @@
 
 class RedTubeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)']
     _TESTS = [{
         'url': 'https://www.redtube.com/38864951',
         'md5': '4fba70cbca3aefd25767ab4b523c9878',
@@ -37,12 +36,6 @@ class RedTubeIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
-            webpage)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(

yt_dlp/extractor/rtlnl.py

@@ -8,6 +8,7 @@
 class RtlNlIE(InfoExtractor):
     IE_NAME = 'rtl.nl'
     IE_DESC = 'rtl.nl and rtlxl.nl'
+    _EMBED_REGEX = [r'<iframe[^>]+?\bsrc=(?P<q1>[\'"])(?P<url>(?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)(?P=q1)']
     _VALID_URL = r'''(?x)
         https?://(?:(?:www|static)\.)?
         (?:

yt_dlp/extractor/rumble.py

@@ -15,6 +15,7 @@
 
 class RumbleEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)'
+    _EMBED_REGEX = [fr'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>{_VALID_URL})']
     _TESTS = [{
         'url': 'https://rumble.com/embed/v5pv5f',
         'md5': '36a18a049856720189f30977ccbb2c34',
@@ -51,11 +52,10 @@ class RumbleEmbedIE(InfoExtractor):
     }]
 
     @classmethod
-    def _extract_urls(cls, webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        embeds = tuple(re.finditer(
+        embeds = tuple(super()._extract_embed_urls(url, webpage))
-            fr'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>{cls._VALID_URL})', webpage))
         if embeds:
-            return [mobj.group('url') for mobj in embeds]
+            return embeds
         return [f'https://rumble.com/embed/{mobj.group("id")}' for mobj in re.finditer(
             r'<script>\s*Rumble\(\s*"play"\s*,\s*{\s*[\'"]video[\'"]\s*:\s*[\'"](?P<id>[0-9a-z]+)[\'"]', webpage)]
 

yt_dlp/extractor/rutube.py

@@ -1,4 +1,3 @@
-import re
 import itertools
 
 from .common import InfoExtractor
@@ -94,6 +93,7 @@ class RutubeIE(RutubeBaseIE):
     IE_NAME = 'rutube'
     IE_DESC = 'Rutube videos'
     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1']
 
     _TESTS = [{
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
@@ -128,12 +128,6 @@ class RutubeIE(RutubeBaseIE):
     def suitable(cls, url):
         return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [mobj.group('url') for mobj in re.finditer(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
-            webpage)]
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         info = self._download_and_extract_info(video_id)

yt_dlp/extractor/rutv.py

@@ -20,6 +20,10 @@ class RUTVIE(InfoExtractor):
                         )
                         (?P<id>\d+)
                     '''
+    _EMBED_URLS = [
+        r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1',
+        r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
+    ]
 
     _TESTS = [
         {
@@ -107,19 +111,6 @@ class RUTVIE(InfoExtractor):
         },
     ]
 
-    @classmethod
-    def _extract_url(cls, webpage):
-        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
-        if mobj:
-            return mobj.group('url')
-
-        mobj = re.search(
-            r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id')

yt_dlp/extractor/ruutu.py

@@ -135,7 +135,7 @@ class RuutuIE(InfoExtractor):
     _API_BASE = 'https://gatling.nelonenmedia.fi'
 
     @classmethod
-    def _extract_urls(cls, webpage):
+    def _extract_embed_urls(cls, url, webpage):
         # nelonen.fi
         settings = try_call(
             lambda: json.loads(re.search(

yt_dlp/extractor/sbs.py

@@ -15,6 +15,12 @@ class SBSIE(InfoExtractor):
                 .*?\bplay=|/watch/
             )|news/(?:embeds/)?video/
         )(?P<id>[0-9]+)'''
+    _EMBED_REGEX = [r'''(?x)]
+            (?:
+                <meta\s+property="og:video"\s+content=|
+                <iframe[^>]+?src=
+            )
+            (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''']
 
     _TESTS = [{
         # Original URL is handled by the generic IE which finds the iframe:

yt_dlp/extractor/senategov.py

@@ -49,6 +49,7 @@
 class SenateISVPIE(InfoExtractor):
     _IE_NAME = 'senate.gov:isvp'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
+    _EMBED_REGEX = [r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]"]
 
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
@@ -87,14 +88,6 @@ class SenateISVPIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _search_iframe_url(webpage):
-        mobj = re.search(
-            r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
 

yt_dlp/extractor/sendtonews.py

@@ -43,14 +43,14 @@ class SendtoNewsIE(InfoExtractor):
     _URL_TEMPLATE = '//embed.sendtonews.com/player2/embedplayer.php?SC=%s'
 
     @classmethod
-    def _extract_url(cls, webpage):
+    def _extract_embed_urls(cls, url, webpage):
         mobj = re.search(r'''(?x)<script[^>]+src=([\'"])
             (?:https?:)?//embed\.sendtonews\.com/player/responsiveembed\.php\?
                 .*\bSC=(?P<SC>[0-9a-zA-Z-]+).*
             \1>''', webpage)
         if mobj:
             sc = mobj.group('SC')
-            return cls._URL_TEMPLATE % sc
+            yield cls._URL_TEMPLATE % sc
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)

yt_dlp/extractor/seznamzpravy.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
@@ -20,6 +18,7 @@ def _raw_id(src_url):
 
 class SeznamZpravyIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?seznamzpravy\.cz/iframe/player\?.*\bsrc='
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?seznamzpravy\.cz/iframe/player\?.*?)\1']
     _TESTS = [{
         'url': 'https://www.seznamzpravy.cz/iframe/player?duration=241&serviceSlug=zpravy&src=https%3A%2F%2Fv39-a.sdn.szn.cz%2Fv_39%2Fvmd%2F5999c902ea707c67d8e267a9%3Ffl%3Dmdk%2C432f65a0%7C&itemType=video&autoPlay=false&title=Sv%C4%9Bt%20bez%20obalu%3A%20%C4%8Ce%C5%A1t%C3%AD%20voj%C3%A1ci%20na%20mis%C3%ADch%20(kr%C3%A1tk%C3%A1%20verze)&series=Sv%C4%9Bt%20bez%20obalu&serviceName=Seznam%20Zpr%C3%A1vy&poster=%2F%2Fd39-a.sdn.szn.cz%2Fd_39%2Fc_img_F_I%2FR5puJ.jpeg%3Ffl%3Dcro%2C0%2C0%2C1920%2C1080%7Cres%2C1200%2C%2C1%7Cjpg%2C80%2C%2C1&width=1920&height=1080&cutFrom=0&cutTo=0&splVersion=VOD&contentId=170889&contextId=35990&showAdvert=true&collocation=&autoplayPossible=true&embed=&isVideoTooShortForPreroll=false&isVideoTooLongForPostroll=true&videoCommentOpKey=&videoCommentId=&version=4.0.76&dotService=zpravy&gemiusPrismIdentifier=bVc1ZIb_Qax4W2v5xOPGpMeCP31kFfrTzj0SqPTLh_b.Z7&zoneIdPreroll=seznam.pack.videospot&skipOffsetPreroll=5&sectionPrefixPreroll=%2Fzpravy',
         'info_dict': {
@@ -48,13 +47,6 @@ class SeznamZpravyIE(InfoExtractor):
         },
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url') for mobj in re.finditer(
-                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?seznamzpravy\.cz/iframe/player\?.*?)\1',
-                webpage)]
-
     def _extract_sdn_formats(self, sdn_url, video_id):
         sdn_data = self._download_json(sdn_url, video_id)
 
@@ -162,5 +154,5 @@ def _real_extract(self, url):
 
         return self.playlist_result([
             self.url_result(entry_url, ie=SeznamZpravyIE.ie_key())
-            for entry_url in SeznamZpravyIE._extract_urls(webpage)],
+            for entry_url in SeznamZpravyIE._extract_embed_urls(url, webpage)],
             article_id, title, description)

yt_dlp/extractor/sharevideos.py

@@ -0,0 +1,6 @@
+from .common import InfoExtractor
+
+
+class ShareVideosEmbedIE(InfoExtractor):
+    _VALID_URL = False
+    _EMBED_REGEX = [r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1']

yt_dlp/extractor/simplecast.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     clean_podcast_url,
@@ -68,6 +66,11 @@ def _parse_episode(self, episode):
 class SimplecastIE(SimplecastBaseIE):
     IE_NAME = 'simplecast'
     _VALID_URL = r'https?://(?:api\.simplecast\.com/episodes|player\.simplecast\.com)/(?P<id>%s)' % SimplecastBaseIE._UUID_REGEX
+    _EMBED_REGEX = [rf'''(?x)<iframe[^>]+src=["\']
+        (?P<url>https?://(?:
+            embed\.simplecast\.com/[0-9a-f]{8}|
+            player\.simplecast\.com/{SimplecastBaseIE._UUID_REGEX}
+        ))''']
     _COMMON_TEST_INFO = {
         'display_id': 'errant-signal-chris-franklin-new-wave-video-essays',
         'id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
@@ -94,15 +97,6 @@ class SimplecastIE(SimplecastBaseIE):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'''(?x)<iframe[^>]+src=["\']
-                (
-                    https?://(?:embed\.simplecast\.com/[0-9a-f]{8}|
-                    player\.simplecast\.com/%s
-                ))''' % SimplecastBaseIE._UUID_REGEX, webpage)
-
     def _real_extract(self, url):
         episode_id = self._match_id(url)
         episode = self._call_api('episodes/%s', episode_id)

yt_dlp/extractor/soundcloud.py

@@ -33,18 +33,13 @@
 
 class SoundcloudEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://(?:w|player|p)\.soundcloud\.com/player/?.*?\burl=(?P<id>.+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1']
     _TEST = {
         # from https://www.soundi.fi/uutiset/ennakkokuuntelussa-timo-kaukolammen-station-to-station-to-station-julkaisua-juhlitaan-tanaan-g-livelabissa/
         'url': 'https://w.soundcloud.com/player/?visual=true&url=https%3A%2F%2Fapi.soundcloud.com%2Fplaylists%2F922213810&show_artwork=true&maxwidth=640&maxheight=960&dnt=1&secret_token=s-ziYey',
         'only_matching': True,
     }
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [m.group('url') for m in re.finditer(
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1',
-            webpage)]
-
     def _real_extract(self, url):
         query = parse_qs(url)
         api_url = query['url'][0]

yt_dlp/extractor/spankwire.py

@@ -21,6 +21,7 @@ class SpankwireIE(InfoExtractor):
                         )
                         (?P<id>\d+)
                     '''
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?spankwire\.com/EmbedPlayer\.aspx/?\?.*?\bArticleId=\d+)']
     _TESTS = [{
         # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
@@ -65,12 +66,6 @@ class SpankwireIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?spankwire\.com/EmbedPlayer\.aspx/?\?.*?\bArticleId=\d+)',
-            webpage)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/sportbox.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -11,6 +9,7 @@
 
 class SportBoxIE(InfoExtractor):
     _VALID_URL = r'https?://(?:news\.sportbox|matchtv)\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://(?:news\.sportbox|matchtv)\.ru/vdl/player[^"]+)"']
     _TESTS = [{
         'url': 'http://news.sportbox.ru/vdl/player/ci/211355',
         'info_dict': {
@@ -42,12 +41,6 @@ class SportBoxIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+src="(https?://(?:news\.sportbox|matchtv)\.ru/vdl/player[^"]+)"',
-            webpage)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/spotify.py

@@ -23,6 +23,7 @@ class SpotifyBaseIE(InfoExtractor):
         'ShowEpisodes': 'e0e5ce27bd7748d2c59b4d44ba245a8992a05be75d6fabc3b20753fc8857444d',
     }
     _VALID_URL_TEMPL = r'https?://open\.spotify\.com/(?:embed-podcast/|embed/|)%s/(?P<id>[^/?&#]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://open\.spotify.com/embed/[^"]+)"']
 
     def _real_initialize(self):
         self._ACCESS_TOKEN = self._download_json(
@@ -97,12 +98,6 @@ def _extract_episode(self, episode, series):
             'series': series,
         }
 
-    @classmethod
-    def _extract_urls(cls, webpage):
-        return re.findall(
-            r'<iframe[^>]+src="(https?://open\.spotify.com/embed/[^"]+)"',
-            webpage)
-
 
 class SpotifyIE(SpotifyBaseIE):
     IE_NAME = 'spotify'

yt_dlp/extractor/springboardplatform.py

@@ -21,6 +21,7 @@ class SpringboardPlatformIE(InfoExtractor):
                             xml_feeds_advanced/index/(?P<index_2>\d+)/rss3/(?P<id_2>\d+)
                         )
                     '''
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cms\.springboardplatform\.com/embed_iframe/\d+/video/\d+.*?)\1']
     _TESTS = [{
         'url': 'http://cms.springboardplatform.com/previews/159/video/981017/0/0/1',
         'md5': '5c3cb7b5c55740d482561099e920f192',
@@ -45,14 +46,6 @@ class SpringboardPlatformIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cms\.springboardplatform\.com/embed_iframe/\d+/video/\d+.*?)\1',
-                webpage)]
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id') or mobj.group('id_2')

yt_dlp/extractor/streamable.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -12,6 +10,7 @@
 
 class StreamableIE(InfoExtractor):
     _VALID_URL = r'https?://streamable\.com/(?:[es]/)?(?P<id>\w+)'
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=(?P<q1>[\'"])(?P<url>(?:https?:)?//streamable\.com/.+?)(?P=q1)']
     _TESTS = [
         {
             'url': 'https://streamable.com/dnd1',
@@ -53,14 +52,6 @@ class StreamableIE(InfoExtractor):
         }
     ]
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src=(?P<q1>[\'"])(?P<src>(?:https?:)?//streamable\.com/(?:(?!\1).+))(?P=q1)',
-            webpage)
-        if mobj:
-            return mobj.group('src')
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/substack.py

@@ -46,14 +46,15 @@ class SubstackIE(InfoExtractor):
     }]
 
     @classmethod
-    def _extract_url(cls, webpage, url):
+    def _extract_embed_urls(cls, url, webpage):
         if not re.search(r'<script[^>]+src=["\']https://substackcdn.com/[^"\']+\.js', webpage):
             return
 
         mobj = re.search(r'{[^}]*["\']subdomain["\']\s*:\s*["\'](?P<subdomain>[^"]+)', webpage)
         if mobj:
             parsed = urllib.parse.urlparse(url)
-            return parsed._replace(netloc=f'{mobj.group("subdomain")}.substack.com').geturl()
+            yield parsed._replace(netloc=f'{mobj.group("subdomain")}.substack.com').geturl()
+            raise cls.StopExtraction()
 
     def _extract_video_formats(self, video_id, username):
         formats, subtitles = [], {}

yt_dlp/extractor/svt.py

@@ -101,6 +101,7 @@ def _extract_video(self, video_info, video_id):
 
 class SVTIE(SVTBaseIE):
     _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
+    _EMBED_REGEX = [r'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % _VALID_URL]
     _TEST = {
         'url': 'http://www.svt.se/wd?widgetId=23991&sectionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
         'md5': '33e9a5d8f646523ce0868ecfb0eed77d',
@@ -113,13 +114,6 @@ class SVTIE(SVTBaseIE):
         },
     }
 
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % SVTIE._VALID_URL, webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         widget_id = mobj.group('widget_id')

yt_dlp/extractor/teachable.py

@@ -140,12 +140,12 @@ def _is_teachable(webpage):
             r'<link[^>]+href=["\']https?://(?:process\.fs|assets)\.teachablecdn\.com',
             webpage)
 
-    @staticmethod
+    @classmethod
-    def _extract_url(webpage, source_url):
+    def _extract_embed_urls(cls, url, webpage):
-        if not TeachableIE._is_teachable(webpage):
+        if cls._is_teachable(webpage):
-            return
+            if re.match(r'https?://[^/]+/(?:courses|p)', url):
-        if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
+                yield f'{cls._URL_PREFIX}{url}'
-            return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
+                raise cls.StopExtraction()
 
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
@@ -160,7 +160,7 @@ def _real_extract(self, url):
 
         webpage = self._download_webpage(url, video_id)
 
-        wistia_urls = WistiaIE._extract_urls(webpage)
+        wistia_urls = WistiaIE._extract_embed_urls(url, webpage)
         if not wistia_urls:
             if any(re.search(p, webpage) for p in (
                     r'class=["\']lecture-contents-locked',

yt_dlp/extractor/ted.py

@@ -215,6 +215,7 @@ def _real_extract(self, url):
 
 class TedEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://embed(?:-ssl)?\.ted\.com/'
+    _EMBED_REGEX = [rf'<iframe[^>]+?src=(["\'])(?P<url>{_VALID_URL}.+?)\1']
 
     _TESTS = [{
         'url': 'https://embed.ted.com/talks/janet_stovall_how_to_get_serious_about_diversity_and_inclusion_in_the_workplace',
@@ -233,10 +234,5 @@ class TedEmbedIE(InfoExtractor):
         },
     }]
 
-    @classmethod
-    def _extract_urls(cls, webpage):
-        return [mobj.group('url') for mobj in re.finditer(
-            fr'<iframe[^>]+?src=(["\'])(?P<url>{cls._VALID_URL}.+?)\1', webpage)]
-
     def _real_extract(self, url):
         return self.url_result(re.sub(r'://embed(-ssl)?', '://www', url), TedTalkIE.ie_key())

yt_dlp/extractor/theplatform.py

@@ -123,6 +123,13 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
         (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
            (?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)?|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
          |theplatform:)(?P<id>[^/\?&]+)'''
+    _EMBED_REGEX = [
+        r'''(?x)
+            <meta\s+
+                property=(["'])(?:og:video(?::(?:secure_)?url)?|twitter:player)\1\s+
+                content=(["'])(?P<url>https?://player\.theplatform\.com/p/.+?)\2''',
+        r'(?s)<(?:iframe|script)[^>]+src=(["\'])(?P<url>(?:https?:)?//player\.theplatform\.com/p/.+?)\1'
+    ]
 
     _TESTS = [{
         # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
@@ -192,22 +199,11 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
     }]
 
     @classmethod
-    def _extract_urls(cls, webpage):
+    def _extract_embed_urls(cls, url, webpage):
-        m = re.search(
-            r'''(?x)
-                    <meta\s+
-                        property=(["'])(?:og:video(?::(?:secure_)?url)?|twitter:player)\1\s+
-                        content=(["'])(?P<url>https?://player\.theplatform\.com/p/.+?)\2
-            ''', webpage)
-        if m:
-            return [m.group('url')]
-
         # Are whitespaces ignored in URLs?
         # https://github.com/ytdl-org/youtube-dl/issues/12044
-        matches = re.findall(
+        for embed_url in super()._extract_embed_urls(url, webpage):
-            r'(?s)<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage)
+            yield re.sub(r'\s', '', embed_url)
-        if matches:
-            return [re.sub(r'\s', '', list(zip(*matches))[1][0])]
 
     @staticmethod
     def _sign_url(url, sig_key, sig_secret, life=600, include_qs=False):

yt_dlp/extractor/threeqsdn.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..compat import compat_HTTPError
 from ..utils import (
@@ -16,6 +14,7 @@ class ThreeQSDNIE(InfoExtractor):
     IE_NAME = '3qsdn'
     IE_DESC = '3Q SDN'
     _VALID_URL = r'https?://playout\.3qsdn\.com/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _EMBED_REGEX = [r'<iframe[^>]+\b(?:data-)?src=(["\'])(?P<url>%s.*?)\1' % _VALID_URL]
     _TESTS = [{
         # https://player.3qsdn.com/demo.html
         'url': 'https://playout.3qsdn.com/7201c779-6b3c-11e7-a40e-002590c750be',
@@ -76,12 +75,13 @@ class ThreeQSDNIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
+    def _extract_from_webpage(self, url, webpage):
-    def _extract_url(webpage):
+        for res in super()._extract_from_webpage(url, webpage):
-        mobj = re.search(
+            yield {
-            r'<iframe[^>]+\b(?:data-)?src=(["\'])(?P<url>%s.*?)\1' % ThreeQSDNIE._VALID_URL, webpage)
+                **res,
-        if mobj:
+                '_type': 'url_transparent',
-            return mobj.group('url')
+                'uploader': self._search_regex(r'^(?:https?://)?([^/]*)/.*', url, 'video uploader'),
+            }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

yt_dlp/extractor/tiktok.py

@@ -1,7 +1,6 @@
 import itertools
 import json
 import random
-import re
 import string
 import time
 
@@ -379,6 +378,7 @@ def _parse_aweme_video_web(self, aweme_detail, webpage_url):
 
 class TikTokIE(TikTokBaseIE):
     _VALID_URL = r'https?://www\.tiktok\.com/(?:embed|@(?P<user_id>[\w\.-]+)/video)/(?P<id>\d+)'
+    _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
 
     _TESTS = [{
         'url': 'https://www.tiktok.com/@leenabhushan/video/6748451240264420610',
@@ -529,11 +529,6 @@ class TikTokIE(TikTokBaseIE):
         'only_matching': True
     }]
 
-    @classmethod
-    def _extract_urls(cls, webpage):
-        return [mobj.group('url') for mobj in re.finditer(
-            rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{cls._VALID_URL})', webpage)]
-
     def _extract_aweme_app(self, aweme_id):
         try:
             aweme_detail = self._call_api('aweme/detail', {'aweme_id': aweme_id}, aweme_id,