Remove afspelen and trailing slashes with one regex

Co-authored-by: dirkf <fieldhouse@gmx.net>

youtube_dl/extractor/npo.py

@@ -11,7 +11,7 @@ from ..utils import ExtractorError
 class NPOIE(InfoExtractor):
     IE_NAME = 'npo'
     IE_DESC = 'npo.nl'
-    _VALID_URL = r'https?://(?:www\.)?npo\.nl/.*'
+    _VALID_URL = r'https?://(?:www\.)?npo\.nl/start/serie/'
 
     _TESTS = [{
         'url': 'https://npo.nl/start/serie/zembla/seizoen-2015/wie-is-de-mol-2/',
@@ -44,19 +44,12 @@ class NPOIE(InfoExtractor):
             note='Downloading token')['token']
 
     def _real_extract(self, url):
-        # You might want to use removesuffix here,
-        # but removesuffix is introduced in Python 3.9
-        # and youtube-dl supports Python 3.2+
-        if url.endswith('/afspelen'):
-            url = url[:-9]
-        elif url.endswith('/afspelen/'):
-            url = url[:-10]
-        url = url.rstrip('/')
+            # Remove /afspelen and/or any trailing `/`s
+            url = re.sub(r'/(?:afspelen)?/*$', '', url)
         slug = url.split('/')[-1]
 
         program_metadata = self._download_json('https://npo.nl/start/api/domain/program-detail',
-                                               slug,
-                                               query={'slug': slug})
+                                               slug, query={'slug': slug})
         product_id = program_metadata.get('productId')
         images = program_metadata.get('images')
         thumbnail = None
@@ -307,7 +300,7 @@ class VPROIE(NPOIE):
     def _real_extract(self, url):
         video_id = url.rstrip('/').split('/')[-1]
         page, _ = self._download_webpage_handle(url, video_id)
-        results = re.findall(r'data-media-id="(.+_.+)"\s', page)
+        results = re.findall(r'data-media-id="([a-zA-Z0-9_]+)"\s', page)
         formats = []
         for result in results:
             formats.extend(self._extract_formats_by_product_id(result, video_id))