Merge a060e2681e into eb15fd5a32

Closes #3937
Authored by: krichbanana, pzhlkj6612

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>

yt_dlp/extractor/_extractors.py

@@ -946,6 +946,10 @@ from .kaltura import KalturaIE
 from .kankanews import KankaNewsIE
 from .karaoketv import KaraoketvIE
 from .kelbyone import KelbyOneIE
+from .kenh14 import (
+    Kenh14PlaylistIE,
+    Kenh14VideoIE,
+)
 from .khanacademy import (
     KhanAcademyIE,
     KhanAcademyUnitIE,
@@ -1987,6 +1991,10 @@ from .streetvoice import StreetVoiceIE
 from .stretchinternet import StretchInternetIE
 from .stripchat import StripchatIE
 from .stv import STVPlayerIE
+from .subsplash import (
+    SubsplashPlaylistIE,
+    SubsplashVideoIE,
+)
 from .substack import SubstackIE
 from .sunporno import SunPornoIE
 from .sverigesradio import (

yt_dlp/extractor/chaturbate.py

@@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor):
             'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
         }
 
-    def _extract_from_webpage(self, video_id, tld):
+    def _extract_from_html(self, video_id, tld):
         webpage = self._download_webpage(
             f'https://chaturbate.{tld}/{video_id}/', video_id,
             headers=self.geo_verification_headers(), impersonate=True)
@@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id, tld = self._match_valid_url(url).group('id', 'tld')
-        return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)
+        return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)

yt_dlp/extractor/kenh14.py

@@ -0,0 +1,160 @@
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_attribute,
+    get_elements_html_by_class,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    remove_start,
+    strip_or_none,
+    unescapeHTML,
+    update_url,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class Kenh14VideoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
+    _TESTS = [{
+        'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
+        'md5': '1ed67f9c3a1e74acf15db69590cf6210',
+        'info_dict': {
+            'id': '316173',
+            'ext': 'mp4',
+            'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
+            'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
+            'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
+            'tags': [],
+            'uploader': 'Unbox Therapy',
+            'upload_date': '20220517',
+            'view_count': int,
+            'duration': 722.86,
+            'timestamp': 1652764468,
+        },
+    }, {
+        'url': 'https://video.kenh14.vn/video-316174.chn',
+        'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
+        'info_dict': {
+            'id': '316174',
+            'ext': 'mp4',
+            'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
+            'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
+            'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
+            'tags': [],
+            'upload_date': '20220517',
+            'view_count': int,
+            'duration': 70.04,
+            'timestamp': 1652766021,
+        },
+    }, {
+        'url': 'https://video.kenh14.vn/0-344740.chn',
+        'md5': 'b843495d5e728142c8870c09b46df2a9',
+        'info_dict': {
+            'id': '344740',
+            'ext': 'mov',
+            'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
+            'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
+            'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
+            'uploader': 'Quang Vũ',
+            'upload_date': '20241024',
+            'view_count': int,
+            'duration': 198.88,
+            'timestamp': 1729741590,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
+        direct_url = attrs['data-vid']
+
+        metadata = self._download_json(
+            'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
+                remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
+
+        formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}]
+        subtitles = {}
+        video_data = self._download_json(
+            f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False)
+        if hls_url := traverse_obj(video_data, ('hls', {url_or_none})):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                hls_url, video_id, m3u8_id='hls', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})):
+            fmts, subs = self._extract_mpd_formats_and_subtitles(
+                dash_url, video_id, mpd_id='dash', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+
+        return {
+            **traverse_obj(metadata, {
+                'duration': ('duration', {parse_duration}),
+                'uploader': ('author', {strip_or_none}),
+                'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}),
+                'view_count': ('views', {int_or_none}),
+            }),
+            'id': video_id,
+            'title': (
+                traverse_obj(metadata, ('title', {strip_or_none}))
+                or clean_html(self._og_search_title(webpage))
+                or clean_html(get_element_by_class('vdbw-title', webpage))),
+            'formats': formats,
+            'subtitles': subtitles,
+            'description': (
+                clean_html(self._og_search_description(webpage))
+                or clean_html(get_element_by_class('vdbw-sapo', webpage))),
+            'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
+            'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
+                {lambda x: x.split(';')}, ..., filter)),
+        }
+
+
+class Kenh14PlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
+    _TESTS = [{
+        'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
+        'info_dict': {
+            'id': '71',
+            'title': 'Trần Tình (Naked love) mùa 2',
+            'description': 'md5:e9522339304956dea931722dd72eddb2',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
+        },
+        'playlist_count': 9,
+    }, {
+        'url': 'https://video.kenh14.vn/playlist/0-72.chn',
+        'info_dict': {
+            'id': '72',
+            'title': 'Lau Lại Đầu Từ',
+            'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
+        },
+        'playlist_count': 6,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        category_detail = get_element_by_class('category-detail', webpage) or ''
+        embed_info = traverse_obj(
+            self._yield_json_ld(webpage, playlist_id),
+            (lambda _, v: v['name'] and v['alternateName'], any)) or {}
+
+        return self.playlist_from_matches(
+            get_elements_html_by_class('video-item', webpage), playlist_id,
+            (clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
+            getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
+            ie=Kenh14VideoIE, playlist_description=(
+                clean_html(get_element_by_class('description', category_detail))
+                or unescapeHTML(embed_info.get('alternateName'))),
+            thumbnail=traverse_obj(
+                self._og_search_thumbnail(webpage),
+                ({url_or_none}, {update_url(query=None)})))

yt_dlp/extractor/subsplash.py

@@ -0,0 +1,112 @@
+import functools
+import math
+
+from .common import InfoExtractor
+from ..utils import (
+    InAdvancePagedList,
+    int_or_none,
+    str_or_none,
+    traverse_obj,
+    unified_strdate,
+    url_or_none,
+)
+
+
+class SubsplashVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?subsplash\.com/u/[^/]+/media/d/(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://subsplash.com/u/skywatchtv/media/d/5whnx5s-the-grand-delusion-taking-place-right-now',
+        'md5': '2d67c50deac3c6c49c6e25c4a5b25afe',
+        'info_dict': {
+            'id': '33f8d305-68ab-414c-acf2-f2317a0abe21',
+            'ext': 'mp4',
+            'title': 'THE GRAND DELUSION TAKING PLACE RIGHT NOW!',
+            'description': 'md5:220a630865c3697b0ec9dcb3a70cbc33',
+            'upload_date': '20240901',
+            'duration': 1710,
+            'thumbnail': r're:https?://.*\.(?:jpg|png)$',
+        },
+    }, {
+        'url': 'https://subsplash.com/u/prophecywatchers/media/d/n4dr8b2-the-transhumanist-plan-for-humanity-billy-crone',
+        'md5': 'f7b4109ba7f012dff953391d6b400730',
+        'info_dict': {
+            'id': 'e16348f1-040e-4596-b922-77b45fa8d253',
+            'ext': 'mp4',
+            'title': 'The Transhumanist Plan for Humanity | Billy Crone',
+            'description': None,
+            'upload_date': '20240903',
+            'duration': 1709,
+            'thumbnail': r're:https?://.*\.(?:jpg|png)$',
+        },
+    }]
+
+    def _fetch_json(self, url, display_id, token):
+        return self._download_json(url, display_id, headers={'Authorization': f'Bearer {token}'})
+
+    def _extract_metadata(self, data, display_id):
+        return traverse_obj(data, {
+            'id': ('id', {str_or_none}),
+            'title': ('title', {str_or_none}),
+            'description': ('summary_text', {str_or_none}),
+            'thumbnail': ('_embedded', 'images', 0, '_links', 'related', 'href', {url_or_none}),
+            'duration': ('_embedded', 'video', 'duration', {lambda x: int_or_none(x, 1000)}),
+            'upload_date': ('published_at', {unified_strdate}),
+            'formats': ('_embedded', 'video', '_embedded', 'playlists', 0, '_links', 'related', 'href',
+                        {lambda url: self._extract_m3u8_formats(url, display_id)}),
+        })
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage, urlh = self._download_webpage_handle(url, display_id)
+        token = urlh.get_header('set-cookie').split(';')[0].split('=')[1].strip()
+        metadata_url = f'https://core.subsplash.com/media/v1/media-items?filter[short_code]={display_id}&include=images,audio.audio-outputs,audio.video,video.video-outputs,video.playlists,document,broadcast'
+        metadata = self._fetch_json(metadata_url, display_id, token)
+        return self._extract_metadata(traverse_obj(metadata, ('_embedded', 'media-items', 0, {dict})), display_id)
+
+
+class SubsplashPlaylistIE(SubsplashVideoIE):
+    IE_NAME = 'subsplash:playlist'
+    _VALID_URL = r'https?://(?:www\.)?subsplash\.com/[^/]+/(?:our-videos|media)/ms/\+(?P<id>\w+)'
+    _PAGE_SIZE = 15
+    _TESTS = [{
+        'url': 'https://subsplash.com/skywatchtv/our-videos/ms/+dbyjzp8',
+        'info_dict': {
+            'id': 'dbyjzp8',
+            'title': 'Five in Ten',
+        },
+        'playlist_mincount': 24,
+    }, {
+        'url': 'https://subsplash.com/prophecywatchers/media/ms/+n42mr48',
+        'info_dict': {
+            'id': 'n42mr48',
+            'title': 'Road to Zion Series',
+        },
+        'playlist_mincount': 13,
+    }, {
+        'url': 'https://subsplash.com/prophecywatchers/media/ms/+918b9f6',
+        'only_matching': True,
+    }]
+
+    def _get_entries(self, token, series_id, page):
+        url = f'https://core.subsplash.com/media/v1/media-items?filter[broadcast.status|broadcast.status]=null|on-demand&filter[media_series]={series_id}&filter[status]=published&include=images,audio.audio-outputs,audio.video,video.video-outputs,video.playlists,document&page[number]={page + 1}&page[size]={self._PAGE_SIZE}&sort=-position'
+        data = self._fetch_json(url, f'{series_id}_{page}', token)
+        entries = traverse_obj(data, ('_embedded', 'media-items', {list}))
+        for entry in entries:
+            yield self._extract_metadata(entry, series_id)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage, urlh = self._download_webpage_handle(url, display_id)
+        token = urlh.get_header('x-api-token')
+
+        series_url = f'https://core.subsplash.com/media/v1/media-series?filter[short_code]={display_id}'
+        json_data = self._fetch_json(series_url, display_id, token)
+        series_data = traverse_obj(json_data, ('_embedded', 'media-series', 0, {
+            'id': ('id', {str}),
+            'title': ('title', {str}),
+            'count': ('media_items_count', {int}),
+        }))
+        total_pages = math.ceil(series_data['count'] / self._PAGE_SIZE)
+
+        entries = InAdvancePagedList(functools.partial(self._get_entries, token, series_data['id']), total_pages, self._PAGE_SIZE)
+        return self.playlist_result(entries, display_id, series_data['title'])