Encoding suggestion from PR

youtube_dl/extractor/extractors.py

@@ -847,7 +847,7 @@ from .nowness import (
     NownessSeriesIE,
 )
 from .noz import NozIE
-from .npo import BNNVaraIE, NPOIE
+from .npo import BNNVaraIE, NPOIE, ONIE, VPROIE
 from .npr import NprIE
 from .nrk import (
     NRKIE,

youtube_dl/extractor/npo.py

@@ -1,11 +1,11 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import json
+import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..utils import ExtractorError
-    ExtractorError,
-)
 
 
 class NPOIE(InfoExtractor):
@@ -80,11 +80,9 @@ class NPOIE(InfoExtractor):
                         product_id = entry.get('productId')
                         title = entry.get('title')
                         synopsis = entry.get('synopsis', {})
-                        description = (
+                        description = (synopsis.get('long')
-                                synopsis.get('long')
+                                       or synopsis.get('short')
-                                or synopsis.get('short')
+                                       or synopsis.get('brief'))
-                                or synopsis.get('brief')
-                        )
                         thumbnails = entry.get('images')
                         for thumbnail_entry in thumbnails:
                             if 'url' in thumbnail_entry:
@@ -131,6 +129,9 @@ class BNNVaraIE(NPOIE):
     IE_NAME = 'bnnvara'
     IE_DESC = 'bnnvara.nl'
     _VALID_URL = r'https?://(?:www\.)?bnnvara\.nl/videos/[0-9]*'
+    _TESTS = [{
+        'url': 'https://www.bnnvara.nl/videos/27455',
+    }]
 
     def _real_extract(self, url):
         url = url.rstrip('/')
@@ -161,3 +162,77 @@ class BNNVaraIE(NPOIE):
             'formats': formats,
             'thumbnail': media.get('data', {}).get('player', {}).get('image').get('url'),
         }
+
+
+class ONIE(NPOIE):
+    IE_NAME = 'on'
+    IE_DESC = 'ongehoordnederland.tv'
+    _VALID_URL = r'https?://(?:www\.)?ongehoordnederland.tv/.*'
+    _TESTS = [{
+        'url': 'https://ongehoordnederland.tv/2024/03/01/korte-clips/heeft-preppen-zin-betwijfel-dat-je-daar-echt-iets-aan-zult-hebben-bij-oorlog-lydia-daniel/',
+    }]
+
+    def _real_extract(self, url):
+        video_id = url.rstrip('/').split('/')[-1]
+        page, _ = self._download_webpage_handle(url, video_id)
+        results = re.findall("page: '(.+)'", page)
+        formats = []
+        for result in results:
+            formats.extend(self._download_by_product_id(result, video_id))
+
+        if not formats:
+            raise ExtractorError('Could not find a POMS product id in the provided URL.')
+
+        return {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+        }
+
+
+class VPROIE(NPOIE):
+    IE_NAME = 'vpro'
+    IE_DESC = 'vpro.nl'
+    _VALID_URL = r'https?://(?:www\.)?vpro.nl/.*'
+    _TESTS = [{
+        'url': 'https://www.vpro.nl/programmas/tegenlicht/kijk/afleveringen/2015-2016/offline-als-luxe.html',
+    }]
+
+    def _real_extract(self, url):
+        video_id = url.rstrip('/').split('/')[-1]
+        page, _ = self._download_webpage_handle(url, video_id)
+        results = re.findall('data-media-id="(.+_.+)"\s', page)
+        formats = []
+        for result in results:
+            formats.extend(self._download_by_product_id(result, video_id))
+            break  # TODO find a better solution, VPRO pages can have multiple videos embedded
+
+        if not formats:
+            raise ExtractorError('Could not find a POMS product id in the provided URL.')
+
+        return {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+        }
+
+
+class ZAPPIE(NPOIE):
+    IE_NAME = 'zapp'
+    IE_DESC = 'zapp.nl'
+    _VALID_URL = r'https?://(?:www\.)?zapp.nl/.*'
+
+    _TESTS = [{
+        'url': 'https://www.zapp.nl/programmas/zappsport/gemist/AT_300003973',
+    }]
+
+    def _real_extract(self, url):
+        video_id = url.rstrip('/').split('/')[-1]
+
+        formats = self._download_by_product_id(url, video_id)
+
+        return {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+        }