Merge branch 'yt-dlp:master' into onsen

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,

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/onsen.py

@@ -20,40 +20,40 @@ class OnsenIE(InfoExtractor):
     _NETRC_MACHINE = 'onsen'
     _VALID_URL = r'https?://(?:(?:share|www)\.)onsen\.ag/program/(?P<id>[\w-]+)'
     _TESTS = [{
-        'url': 'https://share.onsen.ag/program/tricolor?p=393&c=MTk2NjE',
+        'url': 'https://share.onsen.ag/program/onsenking?p=90&c=MTA0NjI',
         'info_dict': {
-            'id': '19661',
+            'id': '10462',
-            'title': '第0回',
-            'cast': ['礒部花凜', '土屋李央', '林鼓子'],
             'ext': 'm4a',
-            'description': 'md5:8435d68dcb7a43bc2c993911b0db245b',
+            'title': '第SP回',
-            'display_id': 'MTk2NjE=',
+            'cast': ['下野紘', '佐藤元', '守屋亨香'],
+            'description': 'md5:083c1eddf198694cd3cc83f4d5c03863',
+            'display_id': 'MTA0NjI=',
             'http_headers': {'Referer': 'https://www.onsen.ag/'},
             'media_type': 'sound',
-            'tags': ['かりこ'],
-            'thumbnail': 'https://d3bzklg4lms4gh.cloudfront.net/program_info/image/default/production/31/ea/c1db117c9b41655120d3a212b2038d15811f/image',
             'section_start': 0,
-            'series': '礒部花凜・土屋李央・林鼓子 トリコロールカラー',
+            'series': '音泉キング「下野紘」のラジオ きみはもちろん、＜音泉＞ファミリーだよね？',
-            'series_id': 'tricolor',
+            'series_id': 'onsenking',
-            'upload_date': '20240907',
+            'tags': ['音泉キング', '音泉ジュニア'],
-            'webpage_url': 'https://www.onsen.ag/program/tricolor?c=MTk2NjE=',
+            'thumbnail': r're:https://d3bzklg4lms4gh\.cloudfront\.net/program_info/image/default/production/.+$',
+            'upload_date': '20220627',
+            'webpage_url': 'https://www.onsen.ag/program/onsenking?c=MTA0NjI=',
         },
     }, {
         'url': 'https://share.onsen.ag/program/girls-band-cry-radio?p=370&c=MTgwMDE',
         'info_dict': {
             'id': '18001',
+            'ext': 'mp4',
             'title': '第4回',
             'cast': ['夕莉', '理名', '朱李', '凪都', '美怜'],
-            'ext': 'mp4',
             'description': 'md5:1d7f6a2f1f5a3e2a8ada4e9f652262dd',
             'display_id': 'MTgwMDE=',
             'http_headers': {'Referer': 'https://www.onsen.ag/'},
             'media_type': 'movie',
-            'tags': ['ガールズバンドクライ', 'ガルクラ', 'ガルクラジオ'],
-            'thumbnail': 'https://d3bzklg4lms4gh.cloudfront.net/program_info/image/default/production/95/a7/6a848c87bebf3ec085d8890f3ce038f9b4dd/image',
             'section_start': 0,
             'series': 'TVアニメ『ガールズバンドクライ』WEBラジオ「ガールズバンドクライ～ラジオにも全部ぶち込め。～」',
             'series_id': 'girls-band-cry-radio',
+            'tags': ['ガールズバンドクライ', 'ガルクラ', 'ガルクラジオ'],
+            'thumbnail': r're:https://d3bzklg4lms4gh\.cloudfront\.net/program_info/image/default/production/.+$',
             'upload_date': '20240425',
             'webpage_url': 'https://www.onsen.ag/program/girls-band-cry-radio?c=MTgwMDE=',
         },
@@ -83,7 +83,7 @@ class OnsenIE(InfoExtractor):
 
     def _get_info(self, program, program_id, metadata):
         m3u8 = program['streaming_url']
-        rd = self._search_regex(f'{program_id}(\\d{{6}})', m3u8, 'release_date', default=None)
+        rd = self._search_regex(rf'{program_id}(\d{{6}})', m3u8, 'release_date', default=None)
         display_id = base64.b64encode(str(program['id']).encode()).decode()
 
         return {
@@ -96,8 +96,8 @@ class OnsenIE(InfoExtractor):
             **traverse_obj(program, {
                 'id': ('id', {str_or_none}),
                 'title': ('title', {strip_or_none}),
-                'thumbnail': ('poster_image_url', {lambda x: x.split('?')[0]}),
                 'media_type': ('media_type', {str}),
+                'thumbnail': ('poster_image_url', {lambda x: x.split('?')[0]}),
             }),
             'cast': metadata['cast'] + traverse_obj(program, ('guests', ..., 'name', {str})),
         }