[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

1 files changed, 17 insertions, 29 deletions

diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py
index 961734345..1c9e2453a 100644
--- a/yt_dlp/extractor/vimeo.py
+++ b/yt_dlp/extractor/vimeo.py
@@ -30,7 +30,6 @@ from ..utils import (
     unsmuggle_url,
     urlencode_postdata,
     urljoin,
-    unescapeHTML,
     urlhandle_detect_ext,
 )
 
@@ -328,6 +327,14 @@ class VimeoIE(VimeoBaseInfoExtractor):
                         /?(?:[?&].*)?(?:[#].*)?$
                     '''
     IE_NAME = 'vimeo'
+    _EMBED_REGEX = [
+        # iframe
+        r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
+        # Embedded (swf embed) Vimeo player
+        r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
+        # Non-standard embedded Vimeo player
+        r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
+    ]
     _TESTS = [
         {
             'url': 'http://vimeo.com/56015672#at=0',
@@ -729,29 +736,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
         # vimeo embed with check-password page protected by Referer header
     ]
 
-    @staticmethod
-    def _extract_urls(url, webpage):
-        urls = []
-        # Look for embedded (iframe) Vimeo player
-        for mobj in re.finditer(
-                r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
-                webpage):
-            urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
-        PLAIN_EMBED_RE = (
-            # Look for embedded (swf embed) Vimeo player
-            r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
-            # Look more for non-standard embedded Vimeo player
-            r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
-        )
-        for embed_re in PLAIN_EMBED_RE:
-            for mobj in re.finditer(embed_re, webpage):
-                urls.append(mobj.group('url'))
-        return urls
-
-    @staticmethod
-    def _extract_url(url, webpage):
-        urls = VimeoIE._extract_urls(url, webpage)
-        return urls[0] if urls else None
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        for embed_url in super()._extract_embed_urls(url, webpage):
+            yield cls._smuggle_referrer(embed_url, url)
 
     def _verify_player_video_password(self, url, video_id, headers):
         password = self._get_video_password()
@@ -1386,12 +1374,12 @@ class VimeoLikesIE(VimeoChannelIE):
 class VHXEmbedIE(VimeoBaseInfoExtractor):
     IE_NAME = 'vhx:embed'
     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
 
-    @staticmethod
-    def _extract_url(url, webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
-        return VimeoIE._smuggle_referrer(unescapeHTML(mobj.group(1)), url) if mobj else None
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        for embed_url in super()._extract_embed_urls(url, webpage):
+            yield cls._smuggle_referrer(embed_url, url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)