Merge c59ce7d6a6 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

@@ -285,6 +285,16 @@ from .bloomberg import BloombergIE
 from .bluesky import BlueskyIE
 from .bokecc import BokeCCIE
 from .bongacams import BongaCamsIE
+from .boomplay import (
+    BoomplayEpisodeIE,
+    BoomplayGenericPlaylistIE,
+    BoomplayMusicIE,
+    BoomplayPlaylistIE,
+    BoomplayPodcastIE,
+    BoomplaySearchIE,
+    BoomplaySearchURLIE,
+    BoomplayVideoIE,
+)
 from .boosty import BoostyIE
 from .bostonglobe import BostonGlobeIE
 from .box import BoxIE

yt_dlp/extractor/bandlab.py

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

yt_dlp/extractor/boomplay.py

@@ -0,0 +1,511 @@
+import base64
+import functools
+import json
+import re
+import urllib.parse
+
+from .common import InfoExtractor, SearchInfoExtractor
+from ..aes import aes_cbc_decrypt_bytes, aes_cbc_encrypt_bytes, unpad_pkcs7
+from ..utils import (
+    ExtractorError,
+    classproperty,
+    clean_html,
+    extract_attributes,
+    get_elements_text_and_html_by_attribute,
+    int_or_none,
+    join_nonempty,
+    merge_dicts,
+    parse_count,
+    parse_duration,
+    smuggle_url,
+    strip_or_none,
+    unified_strdate,
+    unsmuggle_url,
+    url_or_none,
+    urlencode_postdata,
+    urljoin,
+    variadic,
+)
+from ..utils.traversal import traverse_obj
+
+
+class BoomplayBaseIE(InfoExtractor):
+    # Calculated from const values, see lhx.AESUtils.encrypt in public.js
+    # Note that the real key/iv differs from `lhx.AESUtils.key`/`lhx.AESUtils.iv`
+    _KEY = b'boomplayVr3xopAM'
+    _IV = b'boomplay8xIsKTn9'
+    _BASE = 'https://www.boomplay.com'
+    _MEDIA_TYPES = ('songs', 'video', 'episode', 'podcasts', 'playlists', 'artists', 'albums')
+    _GEO_COUNTRIES = ['NG']
+
+    @staticmethod
+    def __yield_elements_text_and_html_by_class_and_tag(class_, tag, html):
+        """
+        Yields content of all element matching `tag.class_` in html
+        class_ must be re escaped
+        """
+        # get_elements_text_and_html_by_attribute returns a generator
+        return get_elements_text_and_html_by_attribute(
+            attribute='class', value=rf'''[^'"]*(?<=['"\s]){class_}(?=['"\s])[^'"]*''', html=html,
+            tag=tag, escape_value=False)
+
+    @classmethod
+    def __yield_elements_by_class_and_tag(cls, *args, **kwargs):
+        return (content for content, _ in cls.__yield_elements_text_and_html_by_class_and_tag(*args, **kwargs))
+
+    @classmethod
+    def __yield_elements_html_by_class_and_tag(cls, *args, **kwargs):
+        return (whole for _, whole in cls.__yield_elements_text_and_html_by_class_and_tag(*args, **kwargs))
+
+    @classmethod
+    def _get_elements_by_class_and_tag(cls, class_, tag, html):
+        return list(cls.__yield_elements_by_class_and_tag(class_, tag, html))
+
+    @classmethod
+    def _get_element_by_class_and_tag(cls, class_, tag, html):
+        return next(cls.__yield_elements_by_class_and_tag(class_, tag, html), None)
+
+    @classmethod
+    def _urljoin(cls, path):
+        return url_or_none(urljoin(base=cls._BASE, path=path))
+
+    def _get_playurl(self, item_id, item_type):
+        resp = self._download_json(
+            'https://www.boomplay.com/getResourceAddr', item_id,
+            note='Downloading play URL', errnote='Failed to download play URL',
+            data=urlencode_postdata({
+                'param': base64.b64encode(aes_cbc_encrypt_bytes(json.dumps({
+                    'itemID': item_id,
+                    'itemType': item_type,
+                }).encode(), self._KEY, self._IV)).decode(),
+            }), headers={
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+            })
+        if not (source := resp.get('source')) and (code := resp.get('code')):
+            if 'unavailable in your country' in (desc := resp.get('desc')) or '':
+                # since NG must have failed ...
+                self.raise_geo_restricted(countries=['GH', 'KE', 'TZ', 'CM', 'CI'])
+            else:
+                raise ExtractorError(desc or f'Failed to get play url, code: {code}')
+        return unpad_pkcs7(aes_cbc_decrypt_bytes(
+            base64.b64decode(source),
+            self._KEY, self._IV)).decode()
+
+    def _extract_formats(self, item_id, item_type='MUSIC', **kwargs):
+        if url := url_or_none(self._get_playurl(item_id, item_type)):
+            return [{
+                'format_id': '0',
+                'url': url,
+                'http_headers': {
+                    'Origin': 'https://www.boomplay.com',
+                    'Referer': 'https://www.boomplay.com',
+                    'X-Boomplay-Ref': 'Boomplay_WEBV1',
+                },
+                **kwargs,
+            }]
+        else:
+            self.raise_no_formats('No formats found')
+
+    def _extract_page_metadata(self, webpage, item_id):
+        metadata_div = self._get_element_by_class_and_tag('summary', 'div', webpage) or ''
+        metadata_entries = re.findall(r'(?si)<strong>(?P<entry>.*?)</strong>', metadata_div) or []
+        description = re.sub(
+            r'(?i)Listen and download music for free on Boomplay!', '',
+            clean_html(self._get_element_by_class_and_tag(
+                'description_content', 'span', webpage)) or '') or None
+
+        details_section = self._get_element_by_class_and_tag('songDetailInfo', 'section', webpage) or ''
+        metadata_entries.extend(re.findall(r'(?si)<li>(?P<entry>.*?)</li>', details_section) or [])
+        page_metadata = {
+            'id': item_id,
+            **self._extract_title_from_webpage(webpage),
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image'],
+                                                webpage, 'thumbnail', default=None),
+            'like_count': parse_count(self._get_element_by_class_and_tag('btn_favorite', 'button', metadata_div)),
+            'repost_count': parse_count(self._get_element_by_class_and_tag('btn_share', 'button', metadata_div)),
+            'comment_count': parse_count(self._get_element_by_class_and_tag('btn_comment', 'button', metadata_div)),
+            'duration': parse_duration(self._get_element_by_class_and_tag('btn_duration', 'button', metadata_div)),
+            'upload_date': unified_strdate(strip_or_none(
+                self._get_element_by_class_and_tag('btn_pubDate', 'button', metadata_div))),
+            'description': description,
+        }
+        for metadata_entry in metadata_entries:
+            if ':' not in metadata_entry:
+                continue
+            k, v = clean_html(metadata_entry).split(':', 1)
+            v = v.strip()
+            if 'artist' in k.lower():
+                page_metadata['artists'] = [v]
+            elif 'album' in k.lower():
+                page_metadata['album'] = v
+            elif 'genre' in k.lower():
+                page_metadata['genres'] = [v]
+            elif 'year of release' in k.lower():
+                page_metadata['release_year'] = int_or_none(v)
+        return page_metadata
+
+    def _extract_title_from_webpage(self, webpage):
+        if h1_title := self._html_search_regex(r'(?i)<h1[^>]*>([^<]+)</h1>', webpage, 'title', default=None):
+            return {'title': h1_title}
+        else:
+            return self._fix_title(
+                self._html_search_meta(['og:title', 'twitter:title'], webpage, 'title', default=None)
+                or self._html_search_regex(r'(?i)<title[^>]*>([^<]+)</title>', webpage, 'title', default=None))
+
+    @staticmethod
+    def _fix_title(title):
+        """
+        fix various types of titles(og:title, twitter:title, title tag in html head)
+        """
+        if not title:
+            return {}
+
+        title_patterns = (
+            r'^(?P<title>(?P<artist>.+)) Songs MP3 Download, New Songs \& Albums \| Boomplay$',  # artists
+            r'^(?P<artist>.+?) - (?P<title>.+) MP3\ Download \& Lyrics \| Boomplay$',  # music
+            r'^Download (?P<artist>.+) album songs: (?P<title>.+?) \| Boomplay Music$',  # album
+            r'^Search:(?P<title>.+) \| Boomplay Music$',  # search url
+            r'^(?P<title>.+) \| Podcast \| Boomplay$',  # podcast, episode
+            r'^(?P<title>.+) \| Boomplay(?: Music)?$',  # video, playlist, generic playlists
+        )
+
+        for pattern in title_patterns:
+            if match := re.search(pattern, title):
+                return {
+                    'title': match.group('title'),
+                    'artists': [match.group('artist')] if 'artist' in match.groupdict() else None,
+                }
+
+        return {'title': title}
+
+    @classmethod
+    def _extract_from_webpage(cls, url, webpage, **kwargs):
+        if kwargs:
+            url = smuggle_url(url, kwargs)
+        return super()._extract_from_webpage(url, webpage)
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        url, smuggled_data = unsmuggle_url(url)
+        media_types = variadic(smuggled_data.get('media_types', cls._MEDIA_TYPES))
+        media_types = join_nonempty(*(
+            re.escape(v)for v in media_types if v in cls._MEDIA_TYPES),
+            delim='|')
+
+        for mobj in re.finditer(
+                rf'''(?ix)
+                <a
+                    (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
+                        (?<=\s)href\s*=\s*(?P<_q>['"])
+                            (?P<href>/(?:{media_types})/\d+/?[\-\w=?&#:;@]*)
+                        (?P=_q)
+                    (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
+                >''', webpage):
+            if url := cls._urljoin(mobj.group('href')):
+                yield url
+
+    @classmethod
+    def _extract_playlist_entries(cls, webpage, media_types, warn=True):
+        song_list = strip_or_none(
+            cls._get_element_by_class_and_tag('morePart_musics', 'ol', webpage)
+            or cls._get_element_by_class_and_tag('morePart', 'ol', webpage)
+            or '')
+
+        entries = traverse_obj(cls.__yield_elements_html_by_class_and_tag(
+            'songName', 'a', song_list),
+            (..., {extract_attributes}, 'href', {cls._urljoin}, {cls.url_result}))
+        if not entries:
+            if warn:
+                cls.report_warning('Failed to extract playlist entries, finding suitable links instead!')
+
+            def strip_ie(entry):
+                # All our IEs have a _VALID_URL and set a key: don't use it
+                entry.pop('ie_key', None)
+                return entry
+
+            return (strip_ie(result) for result in
+                    cls._extract_from_webpage(cls._BASE, webpage, media_types=media_types))
+
+        return entries
+
+
+class BoomplayMusicIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/songs/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/songs/165481965',
+        'md5': 'c5fb4f23e6aae98064230ef3c39c2178',
+        'info_dict': {
+            'title': 'Rise of the Fallen Heroes',
+            'ext': 'mp3',
+            'id': '165481965',
+            'artists': ['fatbunny'],
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/04/29/375ecda38f6f48179a93c72ab909118f_464_464.jpg',
+            'channel_url': 'https://www.boomplay.com/artists/52723101',
+            'duration': 125.0,
+            'release_year': 2024,
+            'comment_count': int,
+            'like_count': int,
+            'repost_count': int,
+            'album': 'Legendary Battle',
+            'genres': ['Metal'],
+        },
+    }]
+
+    def _real_extract(self, url):
+        song_id = self._match_id(url)
+        webpage = self._download_webpage(url, song_id)
+        ld_json_meta = next(self._yield_json_ld(webpage, song_id))
+        # TODO: extract comments(and lyrics? they don't have timestamps)
+        # example: https://www.boomplay.com/songs/96352673?from=home
+        return merge_dicts(
+            self._extract_page_metadata(webpage, song_id),
+            traverse_obj(ld_json_meta, {
+                'title': 'name',
+                'thumbnail': 'image',
+                'channel_url': ('byArtist', 0, '@id'),
+                'artists': ('byArtist', ..., 'name'),
+                'duration': ('duration', {parse_duration}),
+            }), {
+                'formats': self._extract_formats(song_id, 'MUSIC', vcodec='none'),
+            })
+
+
+class BoomplayVideoIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/video/1154892',
+        'md5': 'd9b67ad333d2292a82922062d065352d',
+        'info_dict': {
+            'id': '1154892',
+            'ext': 'mp4',
+            'title': 'Autumn blues',
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/10/10/2171dee9e1f8452e84021560729edb88.jpg',
+            'upload_date': '20241010',
+            'timestamp': 1728599214,
+            'view_count': int,
+            'duration': 177.0,
+            'description': 'Autumn blues by Lugo',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        return merge_dicts(
+            self._extract_page_metadata(webpage, video_id),
+            self._search_json_ld(webpage, video_id), {
+                'formats': self._extract_formats(video_id, 'VIDEO', ext='mp4'),
+            })
+
+
+class BoomplayEpisodeIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/episode/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/episode/7132706',
+        'md5': 'f26e236b764baa53d7a2cbb7e9ce6dc4',
+        'info_dict': {
+            'id': '7132706',
+            'ext': 'mp3',
+            'title': 'Letting Go',
+            'repost_count': int,
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/05/06/fc535eaa25714b43a47185a9831887a5_320_320.jpg',
+            'comment_count': int,
+            'duration': 921.0,
+            'upload_date': '20240506',
+            'description': 'md5:5ec684b281fa0f9e4c31b3ee20c5e57a',
+        },
+    }]
+
+    def _real_extract(self, url):
+        ep_id = self._match_id(url)
+        webpage = self._download_webpage(url, ep_id)
+        return merge_dicts(
+            self._extract_page_metadata(webpage, ep_id), {
+                'description': self._html_search_meta(
+                    ['description', 'og:description', 'twitter:description'], webpage),
+                'formats': self._extract_formats(ep_id, 'EPISODE', vcodec='none'),
+            })
+
+
+class BoomplayPodcastIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/podcasts/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/podcasts/5372',
+        'playlist_count': 200,
+        'info_dict': {
+            'id': '5372',
+            'title': 'TED Talks Daily',
+            'description': r're:(?s)Every weekday, TED Talks Daily brings you the latest talks .{328} learn something new\.$',
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/12/22/6f9cf97ad6f846a0a7882c98dfcf4f8c_320_320.jpg',
+            'repost_count': int,
+            'comment_count': int,
+            'like_count': int,
+        },
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        song_list = self._get_element_by_class_and_tag('morePart_musics', 'ol', webpage)
+        song_list = traverse_obj(re.finditer(
+            r'''(?ix)
+            <li
+                (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
+                    \sdata-id\s*=\s*
+                        (?P<_q>['"]?)
+                            (?P<id>\d+)
+                        (?P=_q)
+                (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
+            >''',
+            song_list),
+            (..., 'id', {
+                lambda x: self.url_result(
+                    f'https://www.boomplay.com/episode/{x}', BoomplayEpisodeIE, x),
+            }))
+        return self.playlist_result(
+            song_list, playlist_id,
+            **self._extract_page_metadata(webpage, playlist_id))
+
+
+class BoomplayPlaylistIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/(?:playlists|artists|albums)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/playlists/33792494',
+        'info_dict': {
+            'id': '33792494',
+            'title': 'Daily Trending Indonesia',
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/08/19/d05d431ee616412caeacd7f78f4f68f5_320_320.jpeg',
+            'repost_count': int,
+            'comment_count': int,
+            'like_count': int,
+            'description': 'md5:7ebdffc5137c77acb62acb3c89248445',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.boomplay.com/artists/52723101',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.boomplay.com/albums/89611238?from=home#google_vignette',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        json_ld_metadata = next(self._yield_json_ld(webpage, playlist_id))
+        # schema `MusicGroup` not supported by self._json_ld()
+
+        return self.playlist_result(**merge_dicts(
+            self._extract_page_metadata(webpage, playlist_id),
+            traverse_obj(json_ld_metadata, {
+                'entries': ('track', ..., 'url', {
+                    functools.partial(self.url_result, ie=BoomplayMusicIE),
+                }),
+                'playlist_title': 'name',
+                'thumbnail': 'image',
+                'artists': ('byArtist', ..., 'name'),
+                'channel_url': ('byArtist', 0, '@id'),
+            })))
+
+
+class BoomplayGenericPlaylistIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/.+'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/new-songs',
+        'playlist_mincount': 20,
+        'info_dict': {
+            'id': 'new-songs',
+            'title': 'New Songs',
+            'thumbnail': 'http://www.boomplay.com/pc/img/og_default_v3.jpg',
+        },
+    }, {
+        'url': 'https://www.boomplay.com/trending-songs',
+        'playlist_mincount': 20,
+        'info_dict': {
+            'id': 'trending-songs',
+            'title': 'Trending Songs',
+            'thumbnail': 'http://www.boomplay.com/pc/img/og_default_v3.jpg',
+        },
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return super().suitable(url) and all(not ie.suitable(url) for ie in (
+            BoomplayEpisodeIE,
+            BoomplayMusicIE,
+            BoomplayPlaylistIE,
+            BoomplayPodcastIE,
+            BoomplaySearchURLIE,
+            BoomplayVideoIE,
+        ))
+
+    def _real_extract(self, url):
+        playlist_id = self._generic_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        return self.playlist_result(
+            self._extract_playlist_entries(webpage, self._MEDIA_TYPES),
+            **self._extract_page_metadata(webpage, playlist_id))
+
+
+class BoomplaySearchURLIE(BoomplayBaseIE):
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/search/default/%20Rise%20of%20the%20Falletesn%20Heroes%20fatbunny',
+        'md5': 'c5fb4f23e6aae98064230ef3c39c2178',
+        'info_dict': {
+            'id': '165481965',
+            'ext': 'mp3',
+            'title': 'Rise of the Fallen Heroes',
+            'duration': 125.0,
+            'genres': ['Metal'],
+            'artists': ['fatbunny'],
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/04/29/375ecda38f6f48179a93c72ab909118f_464_464.jpg',
+            'channel_url': 'https://www.boomplay.com/artists/52723101',
+            'comment_count': int,
+            'repost_count': int,
+            'album': 'Legendary Battle',
+            'release_year': 2024,
+            'like_count': int,
+        },
+    }, {
+        'url': 'https://www.boomplay.com/search/video/%20Autumn%20blues',
+        'md5': 'd9b67ad333d2292a82922062d065352d',
+        'info_dict': {
+            'id': '1154892',
+            'title': 'Autumn blues',
+            'ext': 'mp4',
+            'timestamp': 1728599214,
+            'view_count': int,
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/10/10/2171dee9e1f8452e84021560729edb88.jpg',
+            'description': 'Autumn blues by Lugo',
+            'upload_date': '20241010',
+            'duration': 177.0,
+        },
+        'params': {'playlist_items': '1'},
+    }]
+
+    @classproperty
+    def _VALID_URL(cls):
+        return r'https?://(?:www\.)?boomplay\.com/search/(?P<media_type>default|video|episode|podcasts|playlists|artists|albums)/(?P<query>[^?&#/]+)'
+
+    def _real_extract(self, url):
+        media_type, query = self._match_valid_url(url).group('media_type', 'query')
+        if media_type == 'default':
+            media_type = 'songs'
+        webpage = self._download_webpage(url, query)
+        return self.playlist_result(
+            self._extract_playlist_entries(webpage, media_type, warn=media_type == 'songs'),
+            **self._extract_page_metadata(webpage, query))
+
+
+class BoomplaySearchIE(SearchInfoExtractor):
+    _SEARCH_KEY = 'boomplaysearch'
+    _RETURN_TYPE = 'url'
+    _TESTS = [{
+        'url': 'boomplaysearch:rise of the fallen heroes',
+        'only_matching': True,
+    }]
+
+    def _search_results(self, query):
+        yield self.url_result(
+            f'https://www.boomplay.com/search/default/{urllib.parse.quote(query)}',
+            BoomplaySearchURLIE)

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={
+        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 = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet(
-                re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
+        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 = [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(',')]
+            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)
-
-        # 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']}
+        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:
-                payload.update({
-                    'type': 'auth',
-                    'puid': puid,
-                })
-                endpoint = 'getUrl'
+            endpoint = 'get-urls'
         else:
-                payload.update({
-                    'watchDevices': program_info['watchDevices'],
-                    'contentType': program_info['contentType'],
-                })
-                endpoint = 'getMainUrlNoAuth'
+            puid = str(uuid.uuid4())
+            endpoint = 'get-urls-no-auth'
         video_data = self._download_json(
-                f'https://www.litv.tv/vod/ajax/{endpoint}', video_id,
-                data=json.dumps(payload).encode(),
+            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'})
 
-        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/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',