Merge 7ab6662997 into da252d9d32

Closes #6884
Authored by: bashonly, Grub4K, seproDev

Co-authored-by: Simon Sawicki <contact@grub4k.xyz>
Co-authored-by: sepro <sepro@sepr0.com>

README.md

@@ -342,8 +342,9 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     extractor plugins; postprocessor plugins can
                                     only be loaded from the default plugin
                                     directories
-    --flat-playlist                 Do not extract the videos of a playlist,
+    --flat-playlist                 Do not extract a playlist's URL result
-                                    only list them
+                                    entries; some entry metadata may be missing
+                                    and downloading may be bypassed
     --no-flat-playlist              Fully extract the videos of a playlist
                                     (default)
     --live-from-start               Download livestreams from the start.
@@ -1869,6 +1870,9 @@ The following extractors use this feature:
 #### digitalconcerthall
 * `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats
 
+#### sonylivseries
+* `sort_order`: Episode sort order for series extraction - one of `asc` (ascending, oldest first) or `desc` (descending, newest first). Default is `asc`
+
 **Note**: These options may be changed/removed in the future without concern for backward compatibility
 
 <!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->

devscripts/changelog_override.json

@@ -234,5 +234,10 @@
         "when": "57212a5f97ce367590aaa5c3e9a135eead8f81f7",
         "short": "[ie/vimeo] Fix API retries (#11351)",
         "authors": ["bashonly"]
+    },
+    {
+        "action": "add",
+        "when": "52c0ffe40ad6e8404d93296f575007b05b04c686",
+        "short": "[priority] **Login with OAuth is no longer supported for YouTube**\nDue to a change made by the site, yt-dlp is longer able to support OAuth login for YouTube. [Read more](https://github.com/yt-dlp/yt-dlp/issues/11462#issuecomment-2471703090)"
     }
 ]

test/test_subtitles.py

@@ -11,7 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from test.helper import FakeYDL, is_download_test, md5
 from yt_dlp.extractor import (
     NPOIE,
-    NRKTVIE,
+    NRKIE,
     PBSIE,
     CeskaTelevizeIE,
     ComedyCentralIE,
@@ -299,15 +299,16 @@ class TestMTVSubtitles(BaseTestSubtitles):
 
 @is_download_test
 class TestNRKSubtitles(BaseTestSubtitles):
-    url = 'http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1'
+    url = 'nrk:DMPV73000411'  # http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1
-    IE = NRKTVIE
+    IE = NRKIE
 
     def test_allsubtitles(self):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), {'nb-ttv'})
+        self.assertEqual(set(subtitles.keys()), {'nb-ttv', 'no'})
         self.assertEqual(md5(subtitles['nb-ttv']), '67e06ff02d0deaf975e68f6cb8f6a149')
+        self.assertEqual(md5(subtitles['no']), 'fc01036074116d245ddc6ba6f679263b')
 
 
 @is_download_test

yt_dlp/extractor/_extractors.py

@@ -1402,7 +1402,6 @@ from .nrk import (
     NRKSkoleIE,
     NRKTVDirekteIE,
     NRKTVEpisodeIE,
-    NRKTVEpisodesIE,
     NRKTVSeasonIE,
     NRKTVSeriesIE,
 )

yt_dlp/extractor/bandlab.py

@@ -1,4 +1,3 @@
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,

yt_dlp/extractor/common.py

@@ -3767,7 +3767,7 @@ class InfoExtractor:
         """ Merge subtitle dictionaries, language by language. """
         if target is None:
             target = {}
-        for d in dicts:
+        for d in filter(None, dicts):
             for lang, subs in d.items():
                 target[lang] = cls._merge_subtitle_items(target.get(lang, []), subs)
         return target

yt_dlp/extractor/ctvnews.py

@@ -1,14 +1,27 @@
+import json
 import re
+import urllib.parse
 
 from .common import InfoExtractor
-from ..utils import orderedSet
+from .ninecninemedia import NineCNineMediaIE
+from ..utils import extract_attributes, orderedSet
+from ..utils.traversal import find_element, traverse_obj
 
 
 class CTVNewsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:.+?\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
+    _BASE_REGEX = r'https?://(?:[^.]+\.)?ctvnews\.ca/'
+    _VIDEO_ID_RE = r'(?P<id>\d{5,})'
+    _PLAYLIST_ID_RE = r'(?P<id>\d\.\d{5,})'
+    _VALID_URL = [
+        rf'{_BASE_REGEX}video/c{_VIDEO_ID_RE}',
+        rf'{_BASE_REGEX}video(?:-gallery)?/?\?clipId={_VIDEO_ID_RE}',
+        rf'{_BASE_REGEX}video/?\?(?:playlist|bin)Id={_PLAYLIST_ID_RE}',
+        rf'{_BASE_REGEX}(?!video/)[^?#]*?{_PLAYLIST_ID_RE}/?(?:$|[?#])',
+        rf'{_BASE_REGEX}(?!video/)[^?#]+\?binId={_PLAYLIST_ID_RE}',
+    ]
     _TESTS = [{
         'url': 'http://www.ctvnews.ca/video?clipId=901995',
-        'md5': '9b8624ba66351a23e0b6e1391971f9af',
+        'md5': 'b608f466c7fa24b9666c6439d766ab7e',
         'info_dict': {
             'id': '901995',
             'ext': 'flv',
@@ -16,6 +29,33 @@ class CTVNewsIE(InfoExtractor):
             'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285',
             'timestamp': 1467286284,
             'upload_date': '20160630',
+            'categories': [],
+            'season_number': 0,
+            'season': 'Season 0',
+            'tags': [],
+            'series': 'CTV News National | Archive | Stories 2',
+            'season_id': '57981',
+            'thumbnail': r're:https?://.*\.jpg$',
+            'duration': 764.631,
+        },
+    }, {
+        'url': 'https://barrie.ctvnews.ca/video/c3030933-here_s-what_s-making-news-for-nov--15?binId=1272429',
+        'md5': '8b8c2b33c5c1803e3c26bc74ff8694d5',
+        'info_dict': {
+            'id': '3030933',
+            'ext': 'flv',
+            'title': 'Here’s what’s making news for Nov. 15',
+            'description': 'Here are the top stories we’re working on for CTV News at 11 for Nov. 15',
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2021_2_22_a602e68e-1514-410e-a67a-e1f7cccbacab_png_2000x1125.jpg',
+            'season_id': '58104',
+            'season_number': 0,
+            'tags': [],
+            'season': 'Season 0',
+            'categories': [],
+            'series': 'CTV News Barrie',
+            'upload_date': '20241116',
+            'duration': 42.943,
+            'timestamp': 1731722452,
         },
     }, {
         'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224',
@@ -31,6 +71,72 @@ class CTVNewsIE(InfoExtractor):
             'id': '1.2876780',
         },
         'playlist_mincount': 100,
+    }, {
+        'url': 'https://www.ctvnews.ca/it-s-been-23-years-since-toronto-called-in-the-army-after-a-major-snowstorm-1.5736957',
+        'info_dict':
+        {
+            'id': '1.5736957',
+        },
+        'playlist_mincount': 6,
+    }, {
+        'url': 'https://www.ctvnews.ca/business/respondents-to-bank-of-canada-questionnaire-largely-oppose-creating-a-digital-loonie-1.6665797',
+        'md5': '24bc4b88cdc17d8c3fc01dfc228ab72c',
+        'info_dict': {
+            'id': '2695026',
+            'ext': 'flv',
+            'season_id': '89852',
+            'series': 'From CTV News Channel',
+            'description': 'md5:796a985a23cacc7e1e2fafefd94afd0a',
+            'season': '2023',
+            'title': 'Bank of Canada asks public about digital currency',
+            'categories': [],
+            'tags': [],
+            'upload_date': '20230526',
+            'season_number': 2023,
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'timestamp': 1685105157,
+            'duration': 253.553,
+        },
+    }, {
+        'url': 'https://stox.ctvnews.ca/video-gallery?clipId=582589',
+        'md5': '135cc592df607d29dddc931f1b756ae2',
+        'info_dict': {
+            'id': '582589',
+            'ext': 'flv',
+            'categories': [],
+            'timestamp': 1427906183,
+            'season_number': 0,
+            'duration': 125.559,
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'series': 'CTV News Stox',
+            'description': 'CTV original footage of the rise and fall of the Berlin Wall.',
+            'title': 'Berlin Wall',
+            'season_id': '63817',
+            'season': 'Season 0',
+            'tags': [],
+            'upload_date': '20150401',
+        },
+    }, {
+        'url': 'https://ottawa.ctvnews.ca/features/regional-contact/regional-contact-archive?binId=1.1164587#3023759',
+        'md5': 'a14c0603557decc6531260791c23cc5e',
+        'info_dict': {
+            'id': '3023759',
+            'ext': 'flv',
+            'season_number': 2024,
+            'timestamp': 1731798000,
+            'season': '2024',
+            'episode': 'Episode 125',
+            'description': 'CTV News Ottawa at Six',
+            'duration': 2712.076,
+            'episode_number': 125,
+            'upload_date': '20241116',
+            'title': 'CTV News Ottawa at Six for Saturday, November 16, 2024',
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'categories': [],
+            'tags': [],
+            'series': 'CTV News Ottawa at Six',
+            'season_id': '92667',
+        },
     }, {
         'url': 'http://www.ctvnews.ca/1.810401',
         'only_matching': True,
@@ -42,29 +148,35 @@ class CTVNewsIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _ninecninemedia_url_result(self, clip_id):
+        return self.url_result(f'9c9media:ctvnews_web:{clip_id}', NineCNineMediaIE, clip_id)
+
     def _real_extract(self, url):
         page_id = self._match_id(url)
 
-        def ninecninemedia_url_result(clip_id):
+        if mobj := re.fullmatch(self._VIDEO_ID_RE, urllib.parse.urlparse(url).fragment):
-            return {
+            page_id = mobj.group('id')
-                '_type': 'url_transparent',
-                'id': clip_id,
-                'url': f'9c9media:ctvnews_web:{clip_id}',
-                'ie_key': 'NineCNineMedia',
-            }
 
-        if page_id.isdigit():
+        if re.fullmatch(self._VIDEO_ID_RE, page_id):
-            return ninecninemedia_url_result(page_id)
+            return self._ninecninemedia_url_result(page_id)
-        else:
+
-            webpage = self._download_webpage(f'http://www.ctvnews.ca/{page_id}', page_id, query={
+        webpage = self._download_webpage(f'https://www.ctvnews.ca/{page_id}', page_id, query={
-                'ot': 'example.AjaxPageLayout.ot',
+            'ot': 'example.AjaxPageLayout.ot',
-                'maxItemsPerPage': 1000000,
+            'maxItemsPerPage': 1000000,
-            })
+        })
-            entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet(
+        entries = [self._ninecninemedia_url_result(clip_id)
-                re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
+                   for clip_id in orderedSet(re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
-            if not entries:
+        if not entries:
-                webpage = self._download_webpage(url, page_id)
+            webpage = self._download_webpage(url, page_id)
-                if 'getAuthStates("' in webpage:
+            if 'getAuthStates("' in webpage:
-                    entries = [ninecninemedia_url_result(clip_id) for clip_id in
+                entries = [self._ninecninemedia_url_result(clip_id) for clip_id in
-                               self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')]
+                           self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')]
-            return self.playlist_result(entries, page_id)
+            else:
+                entries = [
+                    self._ninecninemedia_url_result(clip_id) for clip_id in
+                    traverse_obj(webpage, (
+                        {find_element(tag='jasper-player-container', html=True)},
+                        {extract_attributes}, 'axis-ids', {json.loads}, ..., 'axisId', {str}))
+                ]
+
+        return self.playlist_result(entries, page_id)

yt_dlp/extractor/facebook.py

@@ -569,7 +569,7 @@ class FacebookIE(InfoExtractor):
             if dash_manifest:
                 formats.extend(self._parse_mpd_formats(
                     compat_etree_fromstring(urllib.parse.unquote_plus(dash_manifest)),
-                    mpd_url=url_or_none(video.get('dash_manifest_url')) or mpd_url))
+                    mpd_url=url_or_none(vid_data.get('dash_manifest_url')) or mpd_url))
 
         def process_formats(info):
             # Downloads with browser's User-Agent are rate limited. Working around

yt_dlp/extractor/litv.py

@@ -1,30 +1,32 @@
 import json
+import uuid
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    join_nonempty,
     smuggle_url,
     traverse_obj,
     try_call,
     unsmuggle_url,
+    urljoin,
 )
 
 
 class LiTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
+    _VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:[^/?#]+/watch/|vod/[^/?#]+/content\.do\?content_id=)(?P<id>[\w-]+)'
-
+    _URL_TEMPLATE = 'https://www.litv.tv/%s/watch/%s'
-    _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?content_id=%s'
+    _GEO_COUNTRIES = ['TW']
-
     _TESTS = [{
-        'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1',
+        'url': 'https://www.litv.tv/drama/watch/VOD00041610',
         'info_dict': {
             'id': 'VOD00041606',
             'title': '花千骨',
         },
         'playlist_count': 51,  # 50 episodes + 1 trailer
     }, {
-        'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1',
+        'url': 'https://www.litv.tv/drama/watch/VOD00041610',
         'md5': 'b90ff1e9f1d8f5cfcd0a44c3e2b34c7a',
         'info_dict': {
             'id': 'VOD00041610',
@@ -32,16 +34,15 @@ class LiTVIE(InfoExtractor):
             'title': '花千骨第1集',
             'thumbnail': r're:https?://.*\.jpg$',
             'description': '《花千骨》陸劇線上看。十六年前，平靜的村莊內，一名女嬰隨異相出生，途徑此地的蜀山掌門清虛道長算出此女命運非同一般，她體內散發的異香易招惹妖魔。一念慈悲下，他在村莊周邊設下結界阻擋妖魔入侵，讓其年滿十六後去蜀山，並賜名花千骨。',
-            'categories': ['奇幻', '愛情', '中國', '仙俠'],
+            'categories': ['奇幻', '愛情', '仙俠', '古裝'],
             'episode': 'Episode 1',
             'episode_number': 1,
         },
         'params': {
             'noplaylist': True,
         },
-        'skip': 'Georestricted to Taiwan',
     }, {
-        'url': 'https://www.litv.tv/promo/miyuezhuan/?content_id=VOD00044841&',
+        'url': 'https://www.litv.tv/drama/watch/VOD00044841',
         'md5': '88322ea132f848d6e3e18b32a832b918',
         'info_dict': {
             'id': 'VOD00044841',
@@ -55,94 +56,62 @@ class LiTVIE(InfoExtractor):
     def _extract_playlist(self, playlist_data, content_type):
         all_episodes = [
             self.url_result(smuggle_url(
-                self._URL_TEMPLATE % (content_type, episode['contentId']),
+                self._URL_TEMPLATE % (content_type, episode['content_id']),
                 {'force_noplaylist': True}))  # To prevent infinite recursion
-            for episode in traverse_obj(playlist_data, ('seasons', ..., 'episode', lambda _, v: v['contentId']))]
+            for episode in traverse_obj(playlist_data, ('seasons', ..., 'episodes', lambda _, v: v['content_id']))]
 
-        return self.playlist_result(all_episodes, playlist_data['contentId'], playlist_data.get('title'))
+        return self.playlist_result(all_episodes, playlist_data['content_id'], playlist_data.get('title'))
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
-
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
+        vod_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
 
-        if self._search_regex(
+        program_info = traverse_obj(vod_data, ('programInformation', {dict})) or {}
-                r'(?i)<meta\s[^>]*http-equiv="refresh"\s[^>]*content="[0-9]+;\s*url=https://www\.litv\.tv/"',
+        playlist_data = traverse_obj(vod_data, ('seriesTree'))
-                webpage, 'meta refresh redirect', default=False, group=0):
+        if playlist_data and self._yes_playlist(program_info.get('series_id'), video_id, smuggled_data):
-            raise ExtractorError('No such content found', expected=True)
+            return self._extract_playlist(playlist_data, program_info.get('content_type'))
 
-        program_info = self._parse_json(self._search_regex(
+        asset_id = traverse_obj(program_info, ('assets', 0, 'asset_id', {str}))
-            r'var\s+programInfo\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'),
+        if asset_id:  # This is a VOD
-            video_id)
+            media_type = 'vod'
+        else:  # This is a live stream
+            asset_id = program_info['content_id']
+            media_type = program_info['content_type']
+        puid = try_call(lambda: self._get_cookies('https://www.litv.tv/')['PUID'].value)
+        if puid:
+            endpoint = 'get-urls'
+        else:
+            puid = str(uuid.uuid4())
+            endpoint = 'get-urls-no-auth'
+        video_data = self._download_json(
+            f'https://www.litv.tv/api/{endpoint}', video_id,
+            data=json.dumps({'AssetId': asset_id, 'MediaType': media_type, 'puid': puid}).encode(),
+            headers={'Content-Type': 'application/json'})
 
-        # In browsers `getProgramInfo` request is always issued. Usually this
+        if error := traverse_obj(video_data, ('error', {dict})):
-        # endpoint gives the same result as the data embedded in the webpage.
+            error_msg = traverse_obj(error, ('message', {str}))
-        # If, for some reason, there are no embedded data, we do an extra request.
+            if error_msg and 'OutsideRegionError' in error_msg:
-        if 'assetId' not in program_info:
-            program_info = self._download_json(
-                'https://www.litv.tv/vod/ajax/getProgramInfo', video_id,
-                query={'contentId': video_id},
-                headers={'Accept': 'application/json'})
-
-        series_id = program_info['seriesId']
-        if self._yes_playlist(series_id, video_id, smuggled_data):
-            playlist_data = self._download_json(
-                'https://www.litv.tv/vod/ajax/getSeriesTree', video_id,
-                query={'seriesId': series_id}, headers={'Accept': 'application/json'})
-            return self._extract_playlist(playlist_data, program_info['contentType'])
-
-        video_data = self._parse_json(self._search_regex(
-            r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);',
-            webpage, 'video data', default='{}'), video_id)
-        if not video_data:
-            payload = {'assetId': program_info['assetId']}
-            puid = try_call(lambda: self._get_cookies('https://www.litv.tv/')['PUID'].value)
-            if puid:
-                payload.update({
-                    'type': 'auth',
-                    'puid': puid,
-                })
-                endpoint = 'getUrl'
-            else:
-                payload.update({
-                    'watchDevices': program_info['watchDevices'],
-                    'contentType': program_info['contentType'],
-                })
-                endpoint = 'getMainUrlNoAuth'
-            video_data = self._download_json(
-                f'https://www.litv.tv/vod/ajax/{endpoint}', video_id,
-                data=json.dumps(payload).encode(),
-                headers={'Content-Type': 'application/json'})
-
-        if not video_data.get('fullpath'):
-            error_msg = video_data.get('errorMessage')
-            if error_msg == 'vod.error.outsideregionerror':
                 self.raise_geo_restricted('This video is available in Taiwan only')
-            if error_msg:
+            elif error_msg:
                 raise ExtractorError(f'{self.IE_NAME} said: {error_msg}', expected=True)
-            raise ExtractorError(f'Unexpected result from {self.IE_NAME}')
+            raise ExtractorError(f'Unexpected error from {self.IE_NAME}')
 
         formats = self._extract_m3u8_formats(
-            video_data['fullpath'], video_id, ext='mp4',
+            video_data['result']['AssetURLs'][0], video_id, ext='mp4', m3u8_id='hls')
-            entry_protocol='m3u8_native', m3u8_id='hls')
         for a_format in formats:
             # LiTV HLS segments doesn't like compressions
             a_format.setdefault('http_headers', {})['Accept-Encoding'] = 'identity'
 
-        title = program_info['title'] + program_info.get('secondaryMark', '')
-        description = program_info.get('description')
-        thumbnail = program_info.get('imageFile')
-        categories = [item['name'] for item in program_info.get('category', [])]
-        episode = int_or_none(program_info.get('episode'))
-
         return {
             'id': video_id,
             'formats': formats,
-            'title': title,
+            'title': join_nonempty('title', 'secondary_mark', delim='', from_dict=program_info),
-            'description': description,
+            **traverse_obj(program_info, {
-            'thumbnail': thumbnail,
+                'description': ('description', {str}),
-            'categories': categories,
+                'thumbnail': ('picture', {urljoin('https://p-cdnstatic.svc.litv.tv/')}),
-            'episode_number': episode,
+                'categories': ('genres', ..., 'name', {str}),
+                'episode_number': ('episode', {int_or_none}),
+            }),
         }

yt_dlp/extractor/nrk.py

@@ -1,4 +1,5 @@
 import itertools
+import json
 import random
 import re
 
@@ -7,11 +8,12 @@ from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     determine_ext,
+    float_or_none,
     int_or_none,
     parse_duration,
     parse_iso8601,
     str_or_none,
-    try_get,
+    traverse_obj,
     url_or_none,
     urljoin,
 )
@@ -25,18 +27,23 @@ class NRKBaseIE(InfoExtractor):
             nrk-od-no\.telenorcdn\.net|
             minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no
         )/'''
+    _NETRC_MACHINE = 'nrk'
+    _LOGIN_URL = 'https://innlogging.nrk.no/logginn'
+    _AUTH_TOKEN = ''
+    _API_CALL_HEADERS = {'Accept': 'application/json;device=player-core'}
+
+    def _extract_nrk_formats_and_subtitles(self, asset_url, video_id):
 
-    def _extract_nrk_formats(self, asset_url, video_id):
         if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url):
             return self._extract_akamai_formats(asset_url, video_id)
-        asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url)
+        asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only|adap=.+?\b)&?', '', asset_url)
-        formats = self._extract_m3u8_formats(
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
             asset_url, video_id, 'mp4', 'm3u8_native', fatal=False)
         if not formats and re.search(self._CDN_REPL_REGEX, asset_url):
-            formats = self._extract_m3u8_formats(
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
                 re.sub(self._CDN_REPL_REGEX, '://nrk-od-%02d.akamaized.net/no/' % random.randint(0, 99), asset_url),
                 video_id, 'mp4', 'm3u8_native', fatal=False)
-        return formats
+        return formats, subtitles
 
     def _raise_error(self, data):
         MESSAGES = {
@@ -47,7 +54,7 @@ class NRKBaseIE(InfoExtractor):
         }
         message_type = data.get('messageType', '')
         # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
-        if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is True:
+        if 'IsGeoBlocked' in message_type or traverse_obj(data, ('usageRights', 'isGeoBlocked')) is True:
             self.raise_geo_restricted(
                 msg=MESSAGES.get('ProgramIsGeoBlocked'),
                 countries=self._GEO_COUNTRIES)
@@ -58,7 +65,7 @@ class NRKBaseIE(InfoExtractor):
         return self._download_json(
             urljoin('https://psapi.nrk.no/', path),
             video_id, note or f'Downloading {item} JSON',
-            fatal=fatal, query=query)
+            fatal=fatal, query=query, headers=self._API_CALL_HEADERS)
 
 
 class NRKIE(NRKBaseIE):
@@ -73,17 +80,20 @@ class NRKIE(NRKBaseIE):
                             )
                             (?P<id>[^?\#&]+)
                         '''
-
     _TESTS = [{
         # video
         'url': 'http://www.nrk.no/video/PS*150533',
-        'md5': 'f46be075326e23ad0e524edfcb06aeb6',
+        'md5': '2b88a652ad2e275591e61cf550887eec',
         'info_dict': {
             'id': '150533',
             'ext': 'mp4',
             'title': 'Dompap og andre fugler i Piip-Show',
             'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
             'duration': 262,
+            'timestamp': 1395751833,
+            'upload_date': '20140325',
+            'thumbnail': 'https://gfx.nrk.no/0mZgeckEzRU6qTWrbQHD2QcyralHrYB08wBvh-K-AtAQ',
+            'alt_title': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
         },
     }, {
         # audio
@@ -95,6 +105,10 @@ class NRKIE(NRKBaseIE):
             'title': 'Slik høres internett ut når du er blind',
             'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
             'duration': 20,
+            'alt_title': 'Cathrine Lie Wathne er blind, og bruker hurtigtaster for å navigere seg rundt på ulike nettsider.',
+            'upload_date': '20140425',
+            'timestamp': 1398429565,
+            'thumbnail': 'https://gfx.nrk.no/urxQMSXF-WnbfjBH5ke2igLGyN27EdJVWZ6FOsEAclhA',
         },
     }, {
         'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
@@ -144,18 +158,10 @@ class NRKIE(NRKBaseIE):
     def _real_extract(self, url):
         video_id = self._match_id(url).split('/')[-1]
 
-        def call_playback_api(item, query=None):
-            try:
-                return self._call_api(f'playback/{item}/program/{video_id}', video_id, item, query=query)
-            except ExtractorError as e:
-                if isinstance(e.cause, HTTPError) and e.cause.status == 400:
-                    return self._call_api(f'playback/{item}/{video_id}', video_id, item, query=query)
-                raise
-
         # known values for preferredCdn: akamai, iponly, minicdn and telenor
-        manifest = call_playback_api('manifest', {'preferredCdn': 'akamai'})
+        manifest = self._call_api(f'playback/manifest/{video_id}', video_id, 'manifest', query={'preferredCdn': 'akamai'})
 
-        video_id = try_get(manifest, lambda x: x['id'], str) or video_id
+        video_id = manifest.get('id') or video_id
 
         if manifest.get('playability') == 'nonPlayable':
             self._raise_error(manifest['nonPlayable'])
@@ -163,17 +169,22 @@ class NRKIE(NRKBaseIE):
         playable = manifest['playable']
 
         formats = []
-        for asset in playable['assets']:
+        subtitles = {}
-            if not isinstance(asset, dict):
+        has_drm = False
-                continue
+        for asset in traverse_obj(playable, ('assets', ..., {dict})):
-            if asset.get('encrypted'):
+            encryption_scheme = asset.get('encryptionScheme')
+            if encryption_scheme not in (None, 'none', 'statickey'):
+                self.report_warning(f'Skipping asset with unsupported encryption scheme "{encryption_scheme}"')
+                has_drm = True
                 continue
             format_url = url_or_none(asset.get('url'))
             if not format_url:
                 continue
             asset_format = (asset.get('format') or '').lower()
             if asset_format == 'hls' or determine_ext(format_url) == 'm3u8':
-                formats.extend(self._extract_nrk_formats(format_url, video_id))
+                fmts, subs = self._extract_nrk_formats_and_subtitles(format_url, video_id)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
             elif asset_format == 'mp3':
                 formats.append({
                     'url': format_url,
@@ -181,19 +192,22 @@ class NRKIE(NRKBaseIE):
                     'vcodec': 'none',
                 })
 
-        data = call_playback_api('metadata')
+        if not formats and has_drm:
+            self.report_drm(video_id)
 
-        preplay = data['preplay']
+        data = self._call_api(traverse_obj(manifest, ('_links', 'metadata', 'href', {str})), video_id, 'metadata')
-        titles = preplay['titles']
+
-        title = titles['title']
+        preplay = data.get('preplay')
+        titles = preplay.get('titles')
+        title = titles.get('title')
         alt_title = titles.get('subtitle')
 
-        description = try_get(preplay, lambda x: x['description'].replace('\r', '\n'))
+        description = preplay.get('description')
-        duration = parse_duration(playable.get('duration')) or parse_duration(data.get('duration'))
+        # Use m3u8 vod dueration for NRKSkoleIE because of incorrect duration in metadata
+        duration = parse_duration(playable.get('duration')) or parse_duration(data.get('duration')) or self._extract_m3u8_vod_duration(formats[0]['url'], video_id)
 
         thumbnails = []
-        for image in try_get(
+        for image in traverse_obj(preplay, ('poster', 'images', {list})) or []:
-                preplay, lambda x: x['poster']['images'], list) or []:
             if not isinstance(image, dict):
                 continue
             image_url = url_or_none(image.get('url'))
@@ -205,13 +219,13 @@ class NRKIE(NRKBaseIE):
                 'height': int_or_none(image.get('pixelHeight')),
             })
 
-        subtitles = {}
+        for sub in traverse_obj(playable, ('subtitles', {list})) or []:
-        for sub in try_get(playable, lambda x: x['subtitles'], list) or []:
             if not isinstance(sub, dict):
                 continue
             sub_url = url_or_none(sub.get('webVtt'))
             if not sub_url:
                 continue
+
             sub_key = str_or_none(sub.get('language')) or 'nb'
             sub_type = str_or_none(sub.get('type'))
             if sub_type:
@@ -220,8 +234,26 @@ class NRKIE(NRKBaseIE):
                 'url': sub_url,
             })
 
-        legal_age = try_get(
+        chapters = []
-            data, lambda x: x['legalAge']['body']['rating']['code'], str)
+        if data.get('skipDialogInfo'):
+            chapters = [item for item in [{
+                'start_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'startIntroInSeconds'))),
+                'end_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'endIntroInSeconds'))),
+                'title': 'Intro',
+            }, {
+                'start_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'startCreditsInSeconds'))),
+                'end_time': duration,
+                'title': 'Outro',
+            }] if item['start_time'] != item['end_time']]
+        if preplay.get('indexPoints'):
+            seconds_or_none = lambda x: float_or_none(parse_duration(x))
+            chapters += traverse_obj(preplay, ('indexPoints', ..., {
+                'start_time': ('startPoint', {seconds_or_none}),
+                'end_time': ('endPoint', {seconds_or_none}),
+                'title': ('title', {lambda x: x}),
+            }))
+        chapters = sorted(chapters, key=lambda x: x['start_time']) if chapters else None
+        legal_age = traverse_obj(data, ('legalAge', 'body', 'rating', 'code'))
         # https://en.wikipedia.org/wiki/Norwegian_Media_Authority
         age_limit = None
         if legal_age:
@@ -230,7 +262,7 @@ class NRKIE(NRKBaseIE):
             elif legal_age.isdigit():
                 age_limit = int_or_none(legal_age)
 
-        is_series = try_get(data, lambda x: x['_links']['series']['name']) == 'series'
+        is_series = traverse_obj(data, ('_links', 'series', 'name')) == 'series'
 
         info = {
             'id': video_id,
@@ -242,13 +274,23 @@ class NRKIE(NRKBaseIE):
             'age_limit': age_limit,
             'formats': formats,
             'subtitles': subtitles,
-            'timestamp': parse_iso8601(try_get(manifest, lambda x: x['availability']['onDemand']['from'], str)),
+            'chapters': chapters,
+            'timestamp': parse_iso8601(traverse_obj(data, ('availability', 'onDemand', 'from'))),
         }
-
         if is_series:
             series = season_id = season_number = episode = episode_number = None
+
             programs = self._call_api(
                 f'programs/{video_id}', video_id, 'programs', fatal=False)
+            matched_dates = [
+                int(match.group()) // 1000
+                for date in [
+                    traverse_obj(programs, ('firstTimeTransmitted', 'publicationDate')),
+                    traverse_obj(programs, ('usageRights', 'availableFrom')),
+                ] if date for match in [re.search(r'\d+', date)] if match
+            ]
+            if matched_dates:
+                info.update({'timestamp': min(info['timestamp'], *matched_dates)})
             if programs and isinstance(programs, dict):
                 series = str_or_none(programs.get('seriesTitle'))
                 season_id = str_or_none(programs.get('seasonId'))
@@ -284,8 +326,38 @@ class NRKIE(NRKBaseIE):
 
         return info
 
+    def _perform_login(self, username, password):
+        try:
+            self._download_json(
+                self._LOGIN_URL, None, headers={'Content-Type': 'application/json; charset=UTF-8', 'accept': 'application/json; charset=utf-8'},
+                data=json.dumps({
+                    'clientId': '',
+                    'hashedPassword': {'current': {
+                        'hash': password,
+                        'recipe': {
+                            'algorithm': 'cleartext',
+                            'salt': '',
+                        },
+                    },
+                    },
+                    'password': password,
+                    'username': username,
+                }).encode())
 
-class NRKTVIE(InfoExtractor):
+            self._download_webpage('https://tv.nrk.no/auth/web/login/opsession', None)
+            response = self._download_json('https://tv.nrk.no/auth/session/tokenforsub/_', None)
+            self._AUTH_TOKEN = traverse_obj(response, ('session', 'accessToken'))
+            self._API_CALL_HEADERS['authorization'] = f'Bearer {self._AUTH_TOKEN}'
+        except ExtractorError as e:
+            message = None
+            if isinstance(e.cause, HTTPError) and e.cause.status in (401, 400):
+                resp = self._parse_json(
+                    e.cause.response.read().decode(), None, fatal=False) or {}
+                message = next((error['message'] for error in resp['errors'] if error['field'] == 'Password'), None)
+            self.report_warning(message or 'Unable to log in')
+
+
+class NRKTVIE(NRKBaseIE):
     IE_DESC = 'NRK TV and NRK Radio'
     _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
     _VALID_URL = rf'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*{_EPISODE_RE}'
@@ -307,6 +379,14 @@ class NRKTVIE(InfoExtractor):
                     'ext': 'vtt',
                 }],
             },
+            'upload_date': '20170627',
+            'chapters': [{'start_time': 0, 'end_time': 2213.0, 'title': '<Untitled Chapter 1>'}, {'start_time': 2213.0, 'end_time': 2223.44, 'title': 'Outro'}],
+            'timestamp': 1498591822,
+            'thumbnail': 'https://gfx.nrk.no/myRSc4vuFlahB60P3n6swwRTQUZI1LqJZl9B7icZFgzA',
+            'alt_title': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
+        },
+        'params': {
+            'skip_download': True,
         },
     }, {
         'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
@@ -318,9 +398,31 @@ class NRKTVIE(InfoExtractor):
             'alt_title': '23. mai 2014',
             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
             'duration': 1741,
+            'age_limit': 0,
             'series': '20 spørsmål',
             'episode': '23. mai 2014',
-            'age_limit': 0,
+            'upload_date': '20140523',
+            'thumbnail': 'https://gfx.nrk.no/u7uCe79SEfPVGRAGVp2_uAZnNc4mfz_kjXg6Bgek8lMQ',
+            'season_id': '126936',
+            'season_number': 2014,
+            'season': 'Season 2014',
+            'chapters': [
+                {'start_time': 0.0, 'end_time': 39.0, 'title': 'Intro'},
+                {'start_time': 0.0, 'title': 'Velkommen', 'end_time': 152.32},
+                {'start_time': 152.32, 'title': 'Tannpirker', 'end_time': 304.76},
+                {'start_time': 304.76, 'title': 'Orgelbrus', 'end_time': 513.48},
+                {'start_time': 513.48, 'title': 'G-streng', 'end_time': 712.96},
+                {'start_time': 712.96, 'title': 'Medalje', 'end_time': 837.76},
+                {'start_time': 837.76, 'title': 'Globus', 'end_time': 1124.48},
+                {'start_time': 1124.48, 'title': 'Primstav', 'end_time': 1417.4},
+                {'start_time': 1417.4, 'title': 'Fyr', 'end_time': 1721.0},
+                {'start_time': 1721.0, 'end_time': 1741.0, 'title': 'Outro'},
+            ],
+            'episode_number': 3,
+            'timestamp': 1400871900,
+        },
+        'params': {
+            'skip_download': True,
         },
     }, {
         'url': 'https://tv.nrk.no/program/mdfp15000514',
@@ -333,6 +435,18 @@ class NRKTVIE(InfoExtractor):
             'series': 'Kunnskapskanalen',
             'episode': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
             'age_limit': 0,
+            'upload_date': '20140524',
+            'episode_number': 17,
+            'chapters': [
+                {'start_time': 0, 'end_time': 4595.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 4595.0, 'end_time': 4605.08, 'title': 'Outro'},
+            ],
+            'season': 'Season 2014',
+            'timestamp': 1400937600,
+            'thumbnail': 'https://gfx.nrk.no/D2u6-EyVUZpVCq0PdSNHRgdBZCV40ekpk6s9fZWiMtyg',
+            'season_number': 2014,
+            'season_id': '39240',
+            'alt_title': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
         },
         'params': {
             'skip_download': True,
@@ -343,23 +457,51 @@ class NRKTVIE(InfoExtractor):
         'info_dict': {
             'id': 'MSPO40010515',
             'ext': 'mp4',
-            'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
+            'title': 'Tour de Ski - Sprint fri teknikk, kvinner og menn',
-            'description': 'md5:c03aba1e917561eface5214020551b7a',
+            'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
             'age_limit': 0,
+            'episode': 'Sprint fri teknikk, kvinner og menn',
+            'series': 'Tour de Ski',
+            'thumbnail': 'https://gfx.nrk.no/s9vNwGPGN-Un-UCvitD09we9HRLDxisnipA9K__d5c3Q',
+            'season_id': '53512',
+            'chapters': [
+                {'start_time': 0, 'end_time': 6938.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 6938.0, 'end_time': 6947.52, 'title': 'Outro'},
+            ],
+            'season_number': 2015,
+            'episode_number': 5,
+            'upload_date': '20150106',
+            'duration': 6947.52,
+            'timestamp': 1420545563,
+            'alt_title': 'Sprint fri teknikk, kvinner og menn',
+            'season': 'Season 2015',
         },
         'params': {
             'skip_download': True,
         },
-        'expected_warnings': ['Failed to download m3u8 information'],
-        'skip': 'particular part is not supported currently',
     }, {
         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
         'info_dict': {
             'id': 'MSPO40010515',
             'ext': 'mp4',
-            'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
+            'title': 'Tour de Ski - Sprint fri teknikk, kvinner og menn',
-            'description': 'md5:c03aba1e917561eface5214020551b7a',
+            'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
             'age_limit': 0,
+            'episode': 'Sprint fri teknikk, kvinner og menn',
+            'series': 'Tour de Ski',
+            'thumbnail': 'https://gfx.nrk.no/s9vNwGPGN-Un-UCvitD09we9HRLDxisnipA9K__d5c3Q',
+            'season_id': '53512',
+            'chapters': [
+                {'start_time': 0, 'end_time': 6938.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 6938.0, 'end_time': 6947.52, 'title': 'Outro'},
+            ],
+            'season_number': 2015,
+            'episode_number': 5,
+            'upload_date': '20150106',
+            'duration': 6947.52,
+            'timestamp': 1420545563,
+            'alt_title': 'Sprint fri teknikk, kvinner og menn',
+            'season': 'Season 2015',
         },
         'expected_warnings': ['Failed to download m3u8 information'],
         'skip': 'Ikke tilgjengelig utenfor Norge',
@@ -380,6 +522,7 @@ class NRKTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'ProgramRightsHasExpired',
     }, {
         'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
         'info_dict': {
@@ -413,7 +556,7 @@ class NRKTVIE(InfoExtractor):
             f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id)
 
 
-class NRKTVEpisodeIE(InfoExtractor):
+class NRKTVEpisodeIE(NRKBaseIE):
     _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/(?P<season_number>\d+)/episode/(?P<episode_number>\d+))'
     _TESTS = [{
         'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
@@ -421,13 +564,24 @@ class NRKTVEpisodeIE(InfoExtractor):
             'id': 'MUHH36005220',
             'ext': 'mp4',
             'title': 'Hellums kro - 2. Kro, krig og kjærlighet',
-            'description': 'md5:ad92ddffc04cea8ce14b415deef81787',
+            'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350',
             'duration': 1563.92,
             'series': 'Hellums kro',
             'season_number': 1,
             'episode_number': 2,
             'episode': '2. Kro, krig og kjærlighet',
             'age_limit': 6,
+            'timestamp': 1572584520,
+            'upload_date': '20191101',
+            'thumbnail': 'https://gfx.nrk.no/2_4mhU2JhR-8IYRC_OMmAQDbbOHgwcHqgi2sBrNrsjkg',
+            'alt_title': '2. Kro, krig og kjærlighet',
+            'season': 'Season 1',
+            'season_id': '124163',
+            'chapters': [
+                {'start_time': 0, 'end_time': 29.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 29.0, 'end_time': 50.0, 'title': 'Intro'},
+                {'start_time': 1530.0, 'end_time': 1563.92, 'title': 'Outro'},
+            ],
         },
         'params': {
             'skip_download': True,
@@ -453,26 +607,14 @@ class NRKTVEpisodeIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        display_id, season_number, episode_number = self._match_valid_url(url).groups()
+        # HEADRequest(url) only works if a regular GET request was recently made by anyone for the specific URL being requested.
+        response = self._request_webpage(url, None, expected_status=True)
 
-        webpage = self._download_webpage(url, display_id)
+        nrk_id = self._match_id(url)
 
-        info = self._search_json_ld(webpage, display_id, default={})
+        return self.url_result(
-        nrk_id = info.get('@id') or self._html_search_meta(
+            response.url, NRKTVIE.ie_key(), nrk_id, url_transparent=True,
-            'nrk:program-id', webpage, default=None) or self._search_regex(
+        )
-            rf'data-program-id=["\']({NRKTVIE._EPISODE_RE})', webpage,
-            'nrk id')
-        assert re.match(NRKTVIE._EPISODE_RE, nrk_id)
-
-        info.update({
-            '_type': 'url',
-            'id': nrk_id,
-            'url': f'nrk:{nrk_id}',
-            'ie_key': NRKIE.ie_key(),
-            'season_number': int(season_number),
-            'episode_number': int(episode_number),
-        })
-        return info
 
 
 class NRKTVSerieBaseIE(NRKBaseIE):
@@ -482,6 +624,9 @@ class NRKTVSerieBaseIE(NRKBaseIE):
         entries = []
         for episode in entry_list:
             nrk_id = episode.get('prfId') or episode.get('episodeId')
+            if traverse_obj(episode, ('availability', 'status')) == 'expired':
+                self.report_warning(episode['availability'].get('label'), nrk_id)
+                continue
             if not nrk_id or not isinstance(nrk_id, str):
                 continue
             entries.append(self.url_result(
@@ -508,18 +653,18 @@ class NRKTVSerieBaseIE(NRKBaseIE):
             if not assets_key:
                 break
             # Extract entries
-            entries = try_get(
+            entries = traverse_obj(
                 embedded,
-                (lambda x: x[assets_key]['_embedded'][assets_key],
+                (assets_key, '_embedded', assets_key, {list}),
-                 lambda x: x[assets_key]),
+                (assets_key, {list}),
-                list)
+            )
             yield from self._extract_entries(entries)
             # Find next URL
-            next_url_path = try_get(
+            next_url_path = traverse_obj(
                 data,
-                (lambda x: x['_links']['next']['href'],
+                ('_links', 'next', 'href'),
-                 lambda x: x['_embedded'][assets_key]['_links']['next']['href']),
+                ('_embedded', assets_key, '_links', 'next', 'href'),
-                str)
+            )
             if not next_url_path:
                 break
             data = self._call_api(
@@ -548,6 +693,27 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
             'title': 'Sesong 1',
         },
         'playlist_mincount': 30,
+    }, {
+        'url': 'https://tv.nrk.no/serie/presten/sesong/ekstramateriale',
+        'info_dict': {
+            'id': 'MUHH47005117',
+            'ext': 'mp4',
+            'description': '',
+            'thumbnail': 'https://gfx.nrk.no/sJZroQqD2P8wGMMl5ADznwqiIlAXaCpNofA2pIhe3udA',
+            'alt_title': 'Bloopers: Episode 1',
+            'chapters': [
+                {'start_time': 0, 'end_time': 356.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 356.0, 'end_time': 365.8, 'title': 'Outro'},
+            ],
+            'upload_date': '20180302',
+            'timestamp': 1519966800,
+            'title': 'Presten',
+            'age_limit': 0,
+            'duration': 365.8,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         # no /sesong/ in path
         'url': 'https://tv.nrk.no/serie/lindmo/2016',
@@ -572,6 +738,7 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
             'title': 'September 2015',
         },
         'playlist_mincount': 841,
+        'skip': 'ProgramRightsHasExpired',
     }, {
         # 180 entries, single page
         'url': 'https://tv.nrk.no/serie/spangas/sesong/1',
@@ -594,21 +761,20 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
                 else super().suitable(url))
 
     def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
+        domain, serie_kind, serie, season_id, season_id_2 = self._match_valid_url(url).group(
-        domain = mobj.group('domain')
+            'domain', 'serie_kind', 'serie', 'id', 'id_2')
-        serie_kind = mobj.group('serie_kind')
+        season_id = season_id or season_id_2
-        serie = mobj.group('serie')
-        season_id = mobj.group('id') or mobj.group('id_2')
         display_id = f'{serie}/{season_id}'
 
+        api_suffix = f'/seasons/{season_id}' if season_id != 'ekstramateriale' else '/extramaterial'
+
         data = self._call_api(
-            f'{domain}/catalog/{self._catalog_name(serie_kind)}/{serie}/seasons/{season_id}',
+            f'{domain}/catalog/{self._catalog_name(serie_kind)}/{serie}{api_suffix}',
             display_id, 'season', query={'pageSize': 50})
 
-        title = try_get(data, lambda x: x['titles']['title'], str) or display_id
         return self.playlist_result(
-            self._entries(data, display_id),
+            self._entries(data, display_id), display_id,
-            display_id, title)
+            title=traverse_obj(data, ('titles', 'title', {str})))
 
 
 class NRKTVSeriesIE(NRKTVSerieBaseIE):
@@ -666,7 +832,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
         'info_dict': {
             'id': 'dickie-dick-dickens',
             'title': 'Dickie Dick Dickens',
-            'description': 'md5:19e67411ffe57f7dce08a943d7a0b91f',
+            'description': 'md5:605464fab26d06b1ce6a11c3ea37d36d',
         },
         'playlist_mincount': 8,
     }, {
@@ -676,6 +842,8 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
         'url': 'https://radio.nrk.no/podkast/ulrikkes_univers',
         'info_dict': {
             'id': 'ulrikkes_univers',
+            'title': 'Ulrikkes univers',
+            'description': 'md5:8af9fc2ee4aecd7f91777383fde50dcc',
         },
         'playlist_mincount': 10,
     }, {
@@ -699,16 +867,18 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
         series = self._call_api(
             f'{domain}/catalog/{self._catalog_name(serie_kind)}/{series_id}',
             series_id, 'serie', query={size_prefix + 'ageSize': 50})
-        titles = try_get(series, [
+        titles = traverse_obj(
-            lambda x: x['titles'],
+            series,
-            lambda x: x[x['type']]['titles'],
+            (..., 'titles'),
-            lambda x: x[x['seriesType']]['titles'],
+            (..., 'type', 'titles'),
-        ]) or {}
+            (..., 'seriesType', 'titles'),
+            get_all=False,
 
+        )
         entries = []
         entries.extend(self._entries(series, series_id))
         embedded = series.get('_embedded') or {}
-        linked_seasons = try_get(series, lambda x: x['_links']['seasons']) or []
+        linked_seasons = traverse_obj(series, ('_links', 'seasons')) or []
         embedded_seasons = embedded.get('seasons') or []
         if len(linked_seasons) > len(embedded_seasons):
             for season in linked_seasons:
@@ -731,7 +901,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
             entries, series_id, titles.get('title'), titles.get('subtitle'))
 
 
-class NRKTVDirekteIE(NRKTVIE):  # XXX: Do not subclass from concrete IE
+class NRKTVDirekteIE(NRKBaseIE):
     IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'
     _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
 
@@ -743,21 +913,29 @@ class NRKTVDirekteIE(NRKTVIE):  # XXX: Do not subclass from concrete IE
         'only_matching': True,
     }]
 
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result(
+            f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id)
 
-class NRKRadioPodkastIE(InfoExtractor):
+
+class NRKRadioPodkastIE(NRKBaseIE):
     _VALID_URL = r'https?://radio\.nrk\.no/pod[ck]ast/(?:[^/]+/)+(?P<id>l_[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
 
     _TESTS = [{
         'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
-        'md5': '8d40dab61cea8ab0114e090b029a0565',
+        'md5': 'a68c3564be2f4426254f026c95a06348',
         'info_dict': {
-            'id': 'MUHH48000314AA',
+            'id': 'l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
-            'ext': 'mp4',
+            'ext': 'mp3',
-            'title': '20 spørsmål 23.05.2014',
+            'timestamp': 1522897200,
-            'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
+            'alt_title': 'md5:06eae9f8c8ccf0718b54c83654e65550',
-            'duration': 1741,
+            'upload_date': '20180405',
-            'series': '20 spørsmål',
+            'thumbnail': 'https://gfx.nrk.no/CEDlVkEKxLYiBZ-CXjxSxgduDdaL-a4XTZlar9AoJFOA',
-            'episode': '23.05.2014',
+            'description': '',
+            'title': 'Jeg er sinna og det må du tåle!',
+            'age_limit': 0,
+            'duration': 1682.0,
         },
     }, {
         'url': 'https://radio.nrk.no/podcast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
@@ -776,15 +954,16 @@ class NRKRadioPodkastIE(InfoExtractor):
             f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id)
 
 
-class NRKPlaylistBaseIE(InfoExtractor):
+class NRKPlaylistBaseIE(NRKBaseIE):
     def _extract_description(self, webpage):
         pass
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, playlist_id)
+        # Uses the render HTML endpoint instead of the regular article URL to prevent unrelated videos from being downloaded
-
+        # if .rich[data-video-id] elements appear in the "related articles" section too instead of just the main article.
+        webpage = self._download_webpage(f'https://www.nrk.no/serum/api/render/{playlist_id.split("-")[-1]}', playlist_id)
         entries = [
             self.url_result(f'nrk:{video_id}', NRKIE.ie_key())
             for video_id in re.findall(self._ITEM_RE, webpage)
@@ -800,6 +979,8 @@ class NRKPlaylistBaseIE(InfoExtractor):
 class NRKPlaylistIE(NRKPlaylistBaseIE):
     _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
     _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
+    _TITLE_RE = r'class="[^"]*\barticle-title\b[^"]*"[^>]*>([^<]+)<'
+    _DESCRIPTION_RE = r'class="[^"]*[\s"]article-lead[\s"][^>]*>[^<]*<p>([^<]*)<'
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
         'info_dict': {
@@ -819,42 +1000,29 @@ class NRKPlaylistIE(NRKPlaylistBaseIE):
     }]
 
     def _extract_title(self, webpage):
-        return self._og_search_title(webpage, fatal=False)
+        return re.search(self._TITLE_RE, webpage).group(1)
 
     def _extract_description(self, webpage):
-        return self._og_search_description(webpage)
+        return re.search(self._DESCRIPTION_RE, webpage).group(1)
 
 
-class NRKTVEpisodesIE(NRKPlaylistBaseIE):
+class NRKSkoleIE(NRKBaseIE):
-    _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
-    _ITEM_RE = rf'data-episode=["\']{NRKTVIE._EPISODE_RE}'
-    _TESTS = [{
-        'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
-        'info_dict': {
-            'id': '69031',
-            'title': 'Nytt på nytt, sesong: 201210',
-        },
-        'playlist_count': 4,
-    }]
-
-    def _extract_title(self, webpage):
-        return self._html_search_regex(
-            r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
-
-
-class NRKSkoleIE(InfoExtractor):
     IE_DESC = 'NRK Skole'
     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
-        'md5': '18c12c3d071953c3bf8d54ef6b2587b7',
+        'md5': '1d54ec4cff70d8f2c7909d1922514af2',
         'info_dict': {
             'id': '6021',
             'ext': 'mp4',
             'title': 'Genetikk og eneggede tvillinger',
-            'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
+            'description': 'md5:7c0cc42d35d99bbc58f45639cdbcc163',
             'duration': 399,
+            'thumbnail': 'https://gfx.nrk.no/5SN-Uq11iR3ADwrCwTv0bAKbbBXXNpVJsaCLGiU8lFoQ',
+            'timestamp': 1205622000,
+            'upload_date': '20080315',
+            'alt_title': '',
         },
     }, {
         'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
@@ -863,9 +1031,14 @@ class NRKSkoleIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
+        response = self._download_json(
-        nrk_id = self._download_json(
             f'https://nrkno-skole-prod.kube.nrk.no/skole/api/media/{video_id}',
-            video_id)['psId']
+            video_id)
-
+        nrk_id = response['psId']
-        return self.url_result(f'nrk:{nrk_id}')
+        return self.url_result(
+            f'nrk:{nrk_id}', NRKIE, nrk_id, url_transparent=True,
+            **traverse_obj(response, {
+                'title': ('title', {str}),
+                'timestamp': ('airedDate', {parse_iso8601}),
+                'description': ('summary', {str}),
+            }))

yt_dlp/extractor/rutube.py

@@ -13,7 +13,10 @@ from ..utils import (
     unified_timestamp,
     url_or_none,
 )
-from ..utils.traversal import traverse_obj
+from ..utils.traversal import (
+    subs_list_to_dict,
+    traverse_obj,
+)
 
 
 class RutubeBaseIE(InfoExtractor):
@@ -92,11 +95,11 @@ class RutubeBaseIE(InfoExtractor):
                 hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls')
             formats.extend(fmts)
             self._merge_subtitles(subs, target=subtitles)
-        for caption in traverse_obj(options, ('captions', lambda _, v: url_or_none(v['file']))):
+        self._merge_subtitles(traverse_obj(options, ('captions', ..., {
-            subtitles.setdefault(caption.get('code') or 'ru', []).append({
+            'id': 'code',
-                'url': caption['file'],
+            'url': 'file',
-                'name': caption.get('langTitle'),
+            'name': ('langTitle', {str}),
-            })
+        }, all, {subs_list_to_dict(lang='ru')})), target=subtitles)
         return formats, subtitles
 
     def _download_and_extract_formats_and_subtitles(self, video_id, query=None):

yt_dlp/extractor/sonyliv.py

@@ -199,8 +199,9 @@ class SonyLIVSeriesIE(InfoExtractor):
         },
     }]
     _API_BASE = 'https://apiv2.sonyliv.com/AGL'
+    _SORT_ORDERS = ('asc', 'desc')
 
-    def _entries(self, show_id):
+    def _entries(self, show_id, sort_order):
         headers = {
             'Accept': 'application/json, text/plain, */*',
             'Referer': 'https://www.sonyliv.com',
@@ -215,6 +216,9 @@ class SonyLIVSeriesIE(InfoExtractor):
                 'from': '0',
                 'to': '49',
             }), ('resultObj', 'containers', 0, 'containers', lambda _, v: int_or_none(v['id'])))
+
+        if sort_order == 'desc':
+            seasons = reversed(seasons)
         for season in seasons:
             season_id = str(season['id'])
             note = traverse_obj(season, ('metadata', 'title', {str})) or 'season'
@@ -226,7 +230,7 @@ class SonyLIVSeriesIE(InfoExtractor):
                         'from': str(cursor),
                         'to': str(cursor + 99),
                         'orderBy': 'episodeNumber',
-                        'sortOrder': 'asc',
+                        'sortOrder': sort_order,
                     }), ('resultObj', 'containers', 0, 'containers', lambda _, v: int_or_none(v['id'])))
                 if not episodes:
                     break
@@ -237,4 +241,10 @@ class SonyLIVSeriesIE(InfoExtractor):
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
-        return self.playlist_result(self._entries(show_id), playlist_id=show_id)
+
+        sort_order = self._configuration_arg('sort_order', [self._SORT_ORDERS[0]])[0]
+        if sort_order not in self._SORT_ORDERS:
+            raise ValueError(
+                f'Invalid sort order "{sort_order}". Allowed values are: {", ".join(self._SORT_ORDERS)}')
+
+        return self.playlist_result(self._entries(show_id, sort_order), playlist_id=show_id)

yt_dlp/extractor/soundcloud.py

@@ -241,7 +241,7 @@ class SoundcloudBaseIE(InfoExtractor):
                     format_urls.add(format_url)
                     formats.append({
                         'format_id': 'download',
-                        'ext': urlhandle_detect_ext(urlh) or 'mp3',
+                        'ext': urlhandle_detect_ext(urlh, default='mp3'),
                         'filesize': int_or_none(urlh.headers.get('Content-Length')),
                         'url': format_url,
                         'quality': 10,

yt_dlp/options.py

@@ -419,7 +419,9 @@ def create_parser():
     general.add_option(
         '--flat-playlist',
         action='store_const', dest='extract_flat', const='in_playlist', default=False,
-        help='Do not extract the videos of a playlist, only list them')
+        help=(
+            'Do not extract a playlist\'s URL result entries; '
+            'some entry metadata may be missing and downloading may be bypassed'))
     general.add_option(
         '--no-flat-playlist',
         action='store_false', dest='extract_flat',