[extractor/youtube] Fix `live_status` extraction for playlist videos

[yt-dlp.git] / yt_dlp / extractor / rcs.py

diff --git a/yt_dlp/extractor/rcs.py b/yt_dlp/extractor/rcs.py
index 7ee351c6047fec9b72aa298c5d63599912992709..d69a1a216cc07affe86ba4147fa6f7f206c4cd0e 100644 (file)
--- a/yt_dlp/extractor/rcs.py
+++ b/yt_dlp/extractor/rcs.py
@@ -1,14 +1,11 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    clean_html,
     ExtractorError,
-    js_to_json,
     base_url,
+    clean_html,
+    js_to_json,
     url_basename,
     urljoin,
 )
@@ -203,8 +200,8 @@ def _create_formats(self, urls, video_id):
         return formats
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        mobj = re.search(self._VALID_URL, url)
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id')
 
         if 'cdn' not in mobj.groupdict():
             raise ExtractorError('CDN not found in url: %s' % url)
@@ -284,6 +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',
@@ -324,30 +335,9 @@ def _sanitize_urls(urls):
             urls[i] = urljoin(base_url(e), url_basename(e))
         return urls
 
-    @staticmethod
-    def _extract_urls(webpage):
-        entries = [
-            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
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        return cls._sanitize_urls(list(super()._extract_embed_urls(url, webpage)))
 
 
 class RCSIE(RCSBaseIE):