Merge f242b7c42d into da252d9d32

[cleanup] Misc (#11554 )
Closes #6884 Authored by: bashonly, Grub4K, seproDev Co-authored-by: Simon Sawicki <contact@grub4k.xyz> Co-authored-by: sepro <sepro@sepr0.com>
2024-11-24 00:01:54 +01:00 · 2024-11-18 02:47:53 +02:00 · 2024-11-17 23:25:05 +00:00 · 2024-11-17 21:37:15 +00:00 · 2024-11-17 21:16:22 +00:00 · 2024-11-17 21:06:50 +00:00
12 changed files with 322 additions and 166 deletions
--- a/README.md
+++ b/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 -->
--- a/devscripts/changelog_override.json
+++ b/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)"
    }
 ]
--- a/yt_dlp/extractor/alphaporno.py
+++ b/yt_dlp/extractor/alphaporno.py
@ -1,70 +1,136 @@
+import re
+
 from .common import InfoExtractor
 from ..utils import (
    int_or_none,
    parse_duration,
    parse_filesize,
-    parse_iso8601,
+    parse_resolution,
+    unified_timestamp,
+    urljoin,
 )


 class AlphaPornoIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
-    _TEST = {
-        'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
-        'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
-        'info_dict': {
-            'id': '258807',
-            'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
-            'ext': 'mp4',
-            'title': 'Sensual striptease porn with Samantha Alexandra',
-            'thumbnail': r're:https?://.*\.jpg$',
-            'timestamp': 1418694611,
-            'upload_date': '20141216',
-            'duration': 387,
-            'filesize_approx': 54120000,
-            'tbr': 1145,
-            'categories': list,
-            'age_limit': 18,
+    _TESTS = [
+        {
+            'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
+            'md5': '7e6a1cdd48fa67362a5a11d7039164e7',
+            'info_dict': {
+                'id': '258807',
+                'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
+                'ext': 'mp4',
+                'title': 'Sensual striptease porn with Samantha Alexandra',
+                'description': 'md5:3c6d31008980654acaeb11451454a62c',
+                'thumbnail': r're:https?://.*\.jpg$',
+                'timestamp': 1418701811,
+                'upload_date': '20141216',
+                'duration': 387,
+                'categories': list,
+                'age_limit': 18,
+            },
        },
-    }
+        {
+            'url': 'https://www.alphaporno.com/videos/amazing-inches-hammering-her-pussy-in-such-addictive-ways/',
+            'info_dict': {
+                'id': '433761',
+                'ext': 'mp4',
+                'title': 'Amazing inches hammering her pussy in such addictive ways',
+                'display_id': 'amazing-inches-hammering-her-pussy-in-such-addictive-ways',
+                'timestamp': 1641065820,
+                'upload_date': '20220101',
+                'description': 'md5:8bf8e04807b890b847cc9238c445783a',
+                'categories': 'count:12',
+                'age_limit': 18,
+                'thumbnail': r're:https?://.*\.jpg$',
+                'duration': 298.0,
+            },
+        },
+        {
+            'url': 'https://www.alphaporno.com/videos/anal-threesome-for-girls-younger-than-the-average/',
+            'info_dict': {
+                'id': '435603',
+                'ext': 'mp4',
+                'duration': 358.0,
+                'description': 'md5:bf8ca502575c20e15f4f33740cd20a94',
+                'categories': 'count:21',
+                'title': 'Anal threesome for girls y***er than the average',
+                'display_id': 'anal-threesome-for-girls-younger-than-the-average',
+                'upload_date': '20220209',
+                'thumbnail': r're:https?://.*\.jpg$',
+                'age_limit': 18,
+                'timestamp': 1644387720,
+            },
+        },
+    ]

    def _real_extract(self, url):
        display_id = self._match_id(url)

-        webpage = self._download_webpage(url, display_id)
+        webpage, urlh = self._download_webpage_handle(url, display_id)

+        info = {
+            'display_id': display_id,
+        }
        video_id = self._search_regex(
            r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
+        if video_id:
+            info['url'] = self._search_regex(
+                r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
+            info['ext'] = self._html_search_meta(
+                'encodingFormat', webpage, 'ext', default='.mp4')[1:]
+        else:
+            video_id = self._search_regex(
+                r'video_id=(\d+)\b', webpage, 'video id')
+            formats = []
+            joined_url = urljoin(urlh.url, rf'/get_file/\d.+?/{video_id}/{video_id}_(\w+)\..+?')
+            for video_url, res in re.findall(rf'''({joined_url})(?:'|"|\b)\s''', webpage):
+                fmt = {
+                    'format_id': f'f{res}',
+                    'url': video_url,
+                }
+                fmt.update(parse_resolution(res) or {})
+                formats.append(fmt)
+            info['formats'] = formats

-        video_url = self._search_regex(
-            r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
-        ext = self._html_search_meta(
-            'encodingFormat', webpage, 'ext', default='.mp4')[1:]
-
-        title = self._search_regex(
-            [r'<meta content="([^"]+)" itemprop="description">',
-             r'class="title" itemprop="name">([^<]+)<'],
-            webpage, 'title')
-        thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
-        timestamp = parse_iso8601(self._html_search_meta(
-            'uploadDate', webpage, 'upload date'))
-        duration = parse_duration(self._html_search_meta(
-            'duration', webpage, 'duration'))
+        title = (
+            self._html_search_regex(r'<title[^>]*>([^<]+?)(?:\s*-\s*Alpha\s*Porno\s*)?<', webpage, 'title', default=None)
+            or self._og_search_title(webpage, default=None)
+            or self._search_regex(
+                (r'<meta content="([^"]+)" itemprop="description">',
+                 r'class="title" itemprop="name">([^<]+)<'),
+                webpage, 'title')
+        )
+        description = (
+            self._og_search_description(webpage)
+            or self._search_regex(
+                r'<meta content="([^"]+)" itemprop="description">',
+                webpage, 'description')
+        )
+        thumbnail = (
+            self._og_search_thumbnail(webpage)
+            or self._html_search_meta('thumbnail', webpage, 'thumbnail')
+        )
+        timestamp = unified_timestamp(self._og_search_property('video:release_date', webpage)
+                                      or self._html_search_meta('uploadDate', webpage, 'upload date'))
+        duration = parse_duration(self._og_search_property('video:duration', webpage)
+                                  or self._html_search_meta('duration', webpage, 'duration'))
        filesize_approx = parse_filesize(self._html_search_meta(
-            'contentSize', webpage, 'file size'))
+            'contentSize', webpage, 'file size', default=None))
        bitrate = int_or_none(self._html_search_meta(
-            'bitrate', webpage, 'bitrate'))
-        categories = self._html_search_meta(
-            'keywords', webpage, 'categories', default='').split(',')
+            'bitrate', webpage, 'bitrate', default=None))
+        categories = re.split(
+            r'\s*,\s*',
+            self._html_search_meta(
+                'keywords', webpage, 'categories', default=''))

        age_limit = self._rta_search(webpage)

-        return {
+        info.update({
            'id': video_id,
-            'display_id': display_id,
-            'url': video_url,
-            'ext': ext,
            'title': title,
+            'description': description,
            'thumbnail': thumbnail,
            'timestamp': timestamp,
            'duration': duration,
@ -72,4 +138,5 @@ class AlphaPornoIE(InfoExtractor):
            'tbr': bitrate,
            'categories': categories,
            'age_limit': age_limit,
-        }
+        })
+        return info
--- a/yt_dlp/extractor/bandlab.py
+++ b/yt_dlp/extractor/bandlab.py
@ -1,4 +1,3 @@
-
 from .common import InfoExtractor
 from ..utils import (
    ExtractorError,
--- a/yt_dlp/extractor/common.py
+++ b/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
--- a/yt_dlp/extractor/ctvnews.py
+++ b/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)
--- a/yt_dlp/extractor/facebook.py
+++ b/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
--- a/yt_dlp/extractor/litv.py
+++ b/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}),
+            }),
        }
--- a/yt_dlp/extractor/rutube.py
+++ b/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):
--- a/yt_dlp/extractor/sonyliv.py
+++ b/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)
--- a/yt_dlp/extractor/soundcloud.py
+++ b/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,
--- a/yt_dlp/options.py
+++ b/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',
Author	SHA1	Message	Date
Jackson Humphrey	1e35d320f3	Merge `f242b7c42d` into `da252d9d32`	2024-11-18 02:47:53 +02:00
bashonly	da252d9d32	[cleanup] Misc (#11554 ) Closes #6884 Authored by: bashonly, Grub4K, seproDev Co-authored-by: Simon Sawicki <contact@grub4k.xyz> Co-authored-by: sepro <sepro@sepr0.com>	2024-11-17 23:25:05 +00:00
gillux	e079ffbda6	[ie/litv] Fix extractor (#11071 ) Authored by: jiru	2024-11-17 21:37:15 +00:00
bashonly	2009cb27e1	[ie/SonyLIVSeries] Add `sort_order` extractor-arg (#11569 ) Authored by: bashonly	2024-11-17 21:16:22 +00:00
Jackson Humphrey	f351440f1d	[ie/ctvnews] Fix extractor (#11534 ) Closes #8689 Authored by: jshumphrey, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>	2024-11-17 21:06:50 +00:00
Jackson Humphrey	f242b7c42d	Added a test for the URL referenced in Issue #2702 .	2024-11-13 16:15:41 -06:00
Jackson Humphrey	d45461e4b3	Added a test for the URL reported in youtube-dl Issue #30458 .	2024-11-13 16:12:55 -06:00
Jackson Humphrey	10834f196d	Removed deprecated constructions to satisfy DeprecationWarnings when running tests. Tests now pass.	2024-11-13 16:00:29 -06:00
Jackson Humphrey	e719bf1fbb	Applied the patch provided by dirkf in https://github.com/ytdl-org/youtube-dl/issues/30458 .	2024-11-13 15:59:21 -06:00