Merge fca99e1433 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,
-                                    only list them
+    --flat-playlist                 Do not extract a playlist's URL result
+                                    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)"
     }
 ]

yt_dlp/extractor/_extractors.py

@@ -1849,6 +1849,11 @@ from .shahid import (
 from .sharepoint import SharePointIE
 from .sharevideos import ShareVideosEmbedIE
 from .shemaroome import ShemarooMeIE
+from .shouttv import (
+    ShoutTVIE,
+    ShoutTVSeasonIE,
+    ShoutTVSeriesIE,
+)
 from .showroomlive import ShowRoomLiveIE
 from .sibnet import SibnetEmbedIE
 from .simplecast import (

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

@@ -1,11 +1,24 @@
+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': 'b608f466c7fa24b9666c6439d766ab7e',
@@ -17,13 +30,32 @@ class CTVNewsIE(InfoExtractor):
             'timestamp': 1467286284,
             'upload_date': '20160630',
             'categories': [],
-            'tags': [],
-            'season_id': 57981,
-            'duration': 764.631,
-            'series': 'CTV News National story',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'season': 'Season 0',
             'season_number': 0,
+            'season': 'Season 0',
+            'tags': [],
+            'series': 'CTV News National | Archive | Stories 2',
+            'season_id': '57981',
+            'thumbnail': r're:https?://.*\.jpg$',
+            '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',
@@ -46,6 +78,65 @@ class CTVNewsIE(InfoExtractor):
             '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,
@@ -57,29 +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):
-            return {
-                '_type': 'url_transparent',
-                'id': clip_id,
-                'url': f'9c9media:ctvnews_web:{clip_id}',
-                'ie_key': 'NineCNineMedia',
-            }
+        if mobj := re.fullmatch(self._VIDEO_ID_RE, urllib.parse.urlparse(url).fragment):
+            page_id = mobj.group('id')
 
-        if page_id.isdigit():
-            return ninecninemedia_url_result(page_id)
-        else:
-            webpage = self._download_webpage(f'http://www.ctvnews.ca/{page_id}', page_id, query={
-                'ot': 'example.AjaxPageLayout.ot',
-                'maxItemsPerPage': 1000000,
-            })
-            entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet(
-                re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
-            if not entries:
-                webpage = self._download_webpage(url, page_id)
-                if 'getAuthStates("' in webpage:
-                    entries = [ninecninemedia_url_result(clip_id) for clip_id in
-                               self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')]
-            return self.playlist_result(entries, page_id)
+        if re.fullmatch(self._VIDEO_ID_RE, page_id):
+            return self._ninecninemedia_url_result(page_id)
+
+        webpage = self._download_webpage(f'https://www.ctvnews.ca/{page_id}', page_id, query={
+            'ot': 'example.AjaxPageLayout.ot',
+            'maxItemsPerPage': 1000000,
+        })
+        entries = [self._ninecninemedia_url_result(clip_id)
+                   for clip_id in orderedSet(re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
+        if not entries:
+            webpage = self._download_webpage(url, page_id)
+            if 'getAuthStates("' in webpage:
+                entries = [self._ninecninemedia_url_result(clip_id) for clip_id in
+                           self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')]
+            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>[^&]+)'
-
-    _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?content_id=%s'
-
+    _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'
+    _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(
-                r'(?i)<meta\s[^>]*http-equiv="refresh"\s[^>]*content="[0-9]+;\s*url=https://www\.litv\.tv/"',
-                webpage, 'meta refresh redirect', default=False, group=0):
-            raise ExtractorError('No such content found', expected=True)
+        program_info = traverse_obj(vod_data, ('programInformation', {dict})) or {}
+        playlist_data = traverse_obj(vod_data, ('seriesTree'))
+        if playlist_data and self._yes_playlist(program_info.get('series_id'), video_id, smuggled_data):
+            return self._extract_playlist(playlist_data, program_info.get('content_type'))
 
-        program_info = self._parse_json(self._search_regex(
-            r'var\s+programInfo\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'),
-            video_id)
+        asset_id = traverse_obj(program_info, ('assets', 0, 'asset_id', {str}))
+        if asset_id:  # This is a VOD
+            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
-        # endpoint gives the same result as the data embedded in the webpage.
-        # If, for some reason, there are no embedded data, we do an extra request.
-        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':
+        if error := traverse_obj(video_data, ('error', {dict})):
+            error_msg = traverse_obj(error, ('message', {str}))
+            if error_msg and 'OutsideRegionError' in error_msg:
                 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',
-            entry_protocol='m3u8_native', m3u8_id='hls')
+            video_data['result']['AssetURLs'][0], video_id, ext='mp4', 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,
-            'description': description,
-            'thumbnail': thumbnail,
-            'categories': categories,
-            'episode_number': episode,
+            'title': join_nonempty('title', 'secondary_mark', delim='', from_dict=program_info),
+            **traverse_obj(program_info, {
+                'description': ('description', {str}),
+                'thumbnail': ('picture', {urljoin('https://p-cdnstatic.svc.litv.tv/')}),
+                'categories': ('genres', ..., 'name', {str}),
+                'episode_number': ('episode', {int_or_none}),
+            }),
         }

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']))):
-            subtitles.setdefault(caption.get('code') or 'ru', []).append({
-                'url': caption['file'],
-                'name': caption.get('langTitle'),
-            })
+        self._merge_subtitles(traverse_obj(options, ('captions', ..., {
+            'id': 'code',
+            'url': 'file',
+            '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/shouttv.py

@@ -0,0 +1,352 @@
+import itertools
+import json
+import re
+import time
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    filter_dict,
+    int_or_none,
+    jwt_decode_hs256,
+    parse_age_limit,
+    str_or_none,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class ShoutTVBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'shouttv'
+    _API_BASE_URL = 'https://dce-frontoffice.imggaming.com/api'
+    # version and key taken from https://watch.shout-tv.com/code/js/app.3b4ef510d0048f672e1d.js
+    _APP_VERSION = '6.57.10.65bab8b'  # 'OUTPUT_FOLDER' in JS
+    _API_KEY = '857a1e5d-e35e-4fdf-805b-a87b6f8364bf'  # 'API_KEY' in JS
+    _API_REALM = 'dce.shout'
+    _API_HEADERS = {
+        'Accept': 'application/json',
+        'Origin': 'https://watch.shout-tv.com',
+        'Referer': 'https://watch.shout-tv.com/',
+        'app': 'dice',
+        'x-api-key': _API_KEY,
+        'x-app-var': _APP_VERSION,
+    }
+    _ACCESS_TOKEN = None
+    _ACCESS_EXPIRY = 0
+    _REFRESH_TOKEN = None
+    _is_logged_in = False
+
+    def _set_tokens(self, auth_data):
+        ShoutTVBaseIE._ACCESS_TOKEN = auth_data['authorisationToken']  # 10 minute TTL
+        ShoutTVBaseIE._ACCESS_EXPIRY = jwt_decode_hs256(ShoutTVBaseIE._ACCESS_TOKEN)['exp']
+        if refresh_token := traverse_obj(auth_data, ('refreshToken', {str})):
+            self.write_debug('New refresh token granted')
+            ShoutTVBaseIE._REFRESH_TOKEN = refresh_token  # 2 month TTL
+        username, _ = self._get_login_info()
+        if username and ShoutTVBaseIE._is_logged_in:
+            tokens = self.cache.load(self._NETRC_MACHINE, 'tokens', default={})
+            tokens[username] = [ShoutTVBaseIE._ACCESS_TOKEN, ShoutTVBaseIE._REFRESH_TOKEN]
+            self.cache.store(self._NETRC_MACHINE, 'tokens', tokens)
+
+    def _fetch_access_token(self, content_id=None):
+        if ShoutTVBaseIE._ACCESS_TOKEN and ShoutTVBaseIE._ACCESS_EXPIRY - 10 > time.time():
+            return
+
+        headers = self._API_HEADERS.copy()
+        if ShoutTVBaseIE._REFRESH_TOKEN and ShoutTVBaseIE._ACCESS_TOKEN:
+            headers.update({
+                'Authorization': f'Mixed {ShoutTVBaseIE._ACCESS_TOKEN} {ShoutTVBaseIE._REFRESH_TOKEN}',
+                'Realm': self._API_REALM,
+            })
+        self._set_tokens(self._download_json(
+            f'{self._API_BASE_URL}/v1/init/', content_id,
+            'Fetching access token', 'Unable to fetch token',
+            headers=headers, query={
+                'lk': 'language',
+                'pk': ['subTitleLanguage', 'audioLanguage', 'autoAdvance', 'pluginAccessTokens'],
+                'readLicences': 'true',
+                'countEvents': 'LIVE',
+                'menuTargetPlatform': 'WEB',
+            })['authentication'])
+
+    def _perform_login(self, username, password):
+        self.report_login()
+        cached_tokens = self.cache.load(self._NETRC_MACHINE, 'tokens', default={}).get(username) or []
+        if (len(cached_tokens) == 2) and (jwt_decode_hs256(cached_tokens[1])['exp'] - 60 > time.time()):
+            ShoutTVBaseIE._ACCESS_TOKEN, ShoutTVBaseIE._REFRESH_TOKEN = cached_tokens
+            ShoutTVBaseIE._is_logged_in = True
+            self.write_debug('Cached refresh token is still valid')
+            return
+
+        self._fetch_access_token()
+        try:
+            login_data = self._download_json(
+                f'{self._API_BASE_URL}/v2/login', None, 'Submitting credentials',
+                'Unable to log in', headers={
+                    **self._API_HEADERS,
+                    'Authorization': f'Bearer {ShoutTVBaseIE._ACCESS_TOKEN}',
+                    'Content-Type': 'application/json',
+                    'Realm': self._API_REALM,
+                }, data=json.dumps({
+                    'id': username,
+                    'secret': password,
+                }, separators=(',', ':')).encode())
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 404:
+                raise ExtractorError('Invalid username or password', expected=True)
+            raise
+        ShoutTVBaseIE._is_logged_in = True
+        self._set_tokens(login_data)
+
+    def _call_api(self, content_id, content_type, note='API JSON', query=None, headers=None):
+        endpoint = {
+            'video': 'vod',
+            'live': 'event',
+        }.get(content_type, content_type)
+        self._fetch_access_token(content_id)
+        return self._download_json(
+            f'{self._API_BASE_URL}/v4/{endpoint}/{content_id}', content_id,
+            f'Downloading {note}', f'Unable to download {note}', query=query,
+            headers={
+                **self._API_HEADERS,
+                'Authorization': f'Bearer {ShoutTVBaseIE._ACCESS_TOKEN}',
+                **(headers or {}),
+                'Realm': self._API_REALM,
+            })
+
+    @staticmethod
+    def _parse_details(details):
+        return traverse_obj(details, {
+            'id': ('id', {int}, {str_or_none}),
+            'title': ('title', {str}),
+            'description': ('description', {str}),
+            'duration': ('duration', {int_or_none}),
+            'categories': ('categories', ..., {str}, filter),
+            'thumbnails': (('thumbnailUrl', 'posterUrl', 'coverUrl'), {'url': {url_or_none}}),
+            'age_limit': (('rating', 'contentRating'), 'rating', {parse_age_limit}, any),
+            'episode_number': ('episodeInformation', 'episodeNumber', {int_or_none}),
+            'season_number': ('episodeInformation', 'seasonNumber', {int_or_none}),
+            'season_id': ('episodeInformation', 'season', {int}, {str_or_none}),
+            'season': ('episodeInformation', 'seasonTitle', {str}),
+            'series_id': ('episodeInformation', 'seriesInformation', 'id', {int}, {str_or_none}),
+            'series': ('episodeInformation', 'seriesInformation', 'title', {str}),
+        })
+
+    def _extract_vod_formats_and_subtitles(self, player, video_id):
+        formats, subtitles = [], {}
+        # XXX: 'subtitles' array fields are alongside the 'url' fields in both 'hls and 'dash',
+        #      but couldn't find any examples where the arrays were not empty
+        for idx, m3u8_url in enumerate(traverse_obj(player, ('hls', ..., 'url', {url_or_none})), start=1):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                m3u8_url, video_id, 'mp4', m3u8_id=f'hls-{idx}', fatal=False)
+            # This site's HLS manifests do not provide any audio codec/bitrate info
+            # The audio formats are given a GROUP-ID to pair them to video formats w/the same GROUP-ID
+            # Worst quality audio is paired to worst quality video, ba paired to bv, etc
+            # 'audio-1' is usually the worst quality and 'audio-3' is usually the best quality
+            for fmt in fmts:
+                if mobj := re.search(r'-audio-(?P<quality>\d+)', fmt['format_id']):
+                    fmt['quality'] = int(mobj.group('quality'))
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        for idx, mpd_url in enumerate(traverse_obj(player, ('dash', ..., 'url', {url_or_none})), start=1):
+            fmts, subs = self._extract_mpd_formats_and_subtitles(
+                mpd_url, video_id, mpd_id=f'dash-{idx}', fatal=False)
+            # DASH audio formats will always be sorted below HLS unless we also set 'quality'
+            for q, fmt in enumerate(sorted(traverse_obj(fmts, (
+                    lambda _, v: v['tbr'] and v['vcodec'] == 'none')), key=lambda x: x['tbr'])):
+                fmt['quality'] = q
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+
+        return formats, subtitles
+
+
+class ShoutTVIE(ShoutTVBaseIE):
+    IE_NAME = 'shouttv'
+    IE_DESC = 'Shout! TV video-on-demand on live channels'
+    _VALID_URL = r'https?://watch\.shout-tv\.com/(?P<type>video|live)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://watch.shout-tv.com/video/640292',
+        'info_dict': {
+            'id': '640292',
+            'ext': 'mp4',
+            'title': 'Pee-wee\'s Playhouse Christmas Special',
+            'description': 'Pee-Wee Herman throws a Christmas party at his playhouse with his friends and some celebrity guests.',
+            'duration': 2879,
+            'thumbnail': 'https://dve-images.imggaming.com/original/p/2024/05/30/HE2kpg3EjcjrQJb2dSctUVhzpyz7rCXn-1717027231485.jpg',
+            'age_limit': 0,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://watch.shout-tv.com/video/691416?seasonId=26337',
+        'info_dict': {
+            'id': '691416',
+            'ext': 'mp4',
+            'title': 'The Commish: S1 E1 - In The Best Of Families',
+            'description': 'md5:d61403fb8ddaaeb1100228ac146f5a0c',
+            'episode': 'Episode 0',
+            'episode_number': 0,
+            'season': 'The Commish: Season 1',
+            'season_number': 1,
+            'season_id': '26337',
+            'series': 'The Commish',
+            'series_id': '2695',
+            'duration': 2785,
+            'thumbnail': 'https://dve-images.imggaming.com/original/p/2024/09/23/wgpGQ1Vr3DPG6sHnmbGpsKZqMkcosJND-1727130957509.jpg',
+            'age_limit': 14,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://watch.shout-tv.com/live/265692',
+        'info_dict': {
+            'id': '265692',
+            'ext': 'mp4',
+            'title': r're:MST3K \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'live_status': 'is_live',
+            'thumbnail': 'https://img.dge-prod.dicelaboratory.com/thumbnails/265692/original/latest.jpg',
+        },
+        'params': {'skip_download': 'livestream'},
+    }]
+
+    def _real_extract(self, url):
+        video_id, video_type = self._match_valid_url(url).group('id', 'type')
+        details = self._call_api(
+            video_id, video_type, query={'includePlaybackDetails': 'URL'},
+            headers={
+                'CM-APP-NAME': 'Website',
+                'CM-APP-VERSION': self._APP_VERSION,
+                'CM-CST-TCF': '',
+                'CM-CST-USP': '',
+                'CM-DVC-DNT': '1',
+                'CM-DVC-H': '1080',
+                'CM-DVC-LANG': 'en-US',
+                'CM-DVC-OS': '14',
+                'CM-DVC-TYPE': '2',
+                'CM-DVC-W': '1920',
+                'CM-WEB-MBL': '0',
+                'CM-WEB-PAGE': f'/{video_type}/{video_id}',
+            })
+
+        access_level = traverse_obj(details, ('accessLevel', {str}))
+        if access_level == 'GRANTED_ON_SIGN_IN':
+            self.raise_login_required(method='password')
+        elif access_level != 'GRANTED':
+            self.report_warning(f'Unknown access level "{access_level}"')
+
+        player = self._download_json(
+            details['playerUrlCallback'], video_id, 'Downloading player JSON',
+            'Unable to download player JSON', headers={'Accept': 'application/json'})
+        is_live = {
+            'VOD': False,
+            'LIVE': True,
+        }.get(details.get('type'), video_type == 'live')
+
+        if is_live:
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                player['hlsUrl'], video_id, 'mp4', m3u8_id='hls', live=True)
+        else:
+            formats, subtitles = self._extract_vod_formats_and_subtitles(player, video_id)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': is_live,
+            **self._parse_details(details),
+        }
+
+
+class ShoutTVPlaylistBaseIE(ShoutTVBaseIE):
+    """Subclasses must set _PAGE_SIZE, _PLAYLIST_TYPE, _ENTRIES_KEY"""
+
+    def _create_entry(self, entry):
+        raise NotImplementedError('This method must be implemented by subclasses')
+
+    def _fetch_page(self, playlist_id, page=1, last_seen=None):
+        return self._call_api(
+            playlist_id, self._PLAYLIST_TYPE, note=f'{self._PLAYLIST_TYPE} page {page}',
+            query=filter_dict({'rpp': self._PAGE_SIZE, 'lastSeen': last_seen}))
+
+    def _entries(self, playlist_id, first_page):
+        last_seen = None
+        for page in itertools.count(1):
+            data = first_page if page == 1 else self._fetch_page(playlist_id, page, last_seen)
+            for entry in traverse_obj(data, (self._ENTRIES_KEY, lambda _, v: v['id'] is not None)):
+                yield self._create_entry(entry)
+
+            last_seen = traverse_obj(data, ('paging', 'lastSeen', {int}, {str_or_none}))
+            if not traverse_obj(data, ('paging', 'moreDataAvailable', {bool})) or not last_seen:
+                break
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        first_page = self._fetch_page(playlist_id)
+
+        return self.playlist_result(
+            self._entries(playlist_id, first_page), playlist_id,
+            **traverse_obj(first_page, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'thumbnails': (('titleUrl', 'posterUrl', 'coverUrl'), {'url': {url_or_none}}),
+                'series': ('series', 'title', {str}),
+                'series_id': ('series', 'seriesId', {int}, {str_or_none}),
+                'season_number': (
+                    'seasonNumber', {int_or_none},
+                    {lambda x: x if self._PLAYLIST_TYPE == 'season' else None}),
+            }))
+
+
+class ShoutTVSeasonIE(ShoutTVPlaylistBaseIE):
+    IE_NAME = 'shouttv:season'
+    IE_DESC = 'Shout! TV seasons'
+    _VALID_URL = r'https?://watch\.shout-tv\.com/season/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://watch.shout-tv.com/season/26338',
+        'info_dict': {
+            'id': '26338',
+            'title': 'The Commish: Season 2',
+            'description': 'md5:a5f99159e36d23af97a63137712c3b04',
+            'series': 'The Commish',
+            'series_id': '2695',
+            'season_number': 2,
+        },
+        'playlist_count': 22,
+    }]
+    _PAGE_SIZE = 5
+    _PLAYLIST_TYPE = 'season'
+    _ENTRIES_KEY = 'episodes'
+
+    def _create_entry(self, entry):
+        return self.url_result(
+            f'https://watch.shout-tv.com/video/{entry["id"]}', ShoutTVIE,
+            **self._parse_details(entry))
+
+
+class ShoutTVSeriesIE(ShoutTVPlaylistBaseIE):
+    IE_NAME = 'shouttv:series'
+    IE_DESC = 'Shout! TV series'
+    _VALID_URL = r'https?://watch\.shout-tv\.com/series/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://watch.shout-tv.com/series/2695',
+        'info_dict': {
+            'id': '2695',
+            'title': 'The Commish',
+            'description': 'md5:a5f99159e36d23af97a63137712c3b04',
+        },
+        'playlist_count': 5,
+    }]
+    _PAGE_SIZE = 20
+    _PLAYLIST_TYPE = 'series'
+    _ENTRIES_KEY = 'seasons'
+
+    def _create_entry(self, entry):
+        return self.url_result(
+            f'https://watch.shout-tv.com/season/{entry["id"]}', ShoutTVSeasonIE,
+            **traverse_obj(entry, {
+                'id': ('id', {int}, {str_or_none}),
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'season_id': ('id', {int}, {str_or_none}),
+                'season_number': ('seasonNumber', {int_or_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',