Merge 8cbf4659bd 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,

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/fox.py

@@ -7,17 +7,19 @@ from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     int_or_none,
+    join_nonempty,
     parse_age_limit,
     parse_duration,
     traverse_obj,
     try_get,
     unified_timestamp,
     url_or_none,
+    urljoin,
 )
 
 
 class FOXIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?fox(?:sports)?\.com/(?:watch|replay)/(?P<id>[\da-fA-F]+)'
+    _VALID_URL = r'https?://(?:www\.)?fox(?:sports)?\.com/(?:watch|replay)/(?!play-)(?P<id>[\w-]+)'
     _TESTS = [{
         # clip
         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
@@ -30,8 +32,9 @@ class FOXIE(InfoExtractor):
             'duration': 102,
             'timestamp': 1504291893,
             'upload_date': '20170901',
-            'creator': 'FOX',
-            'series': 'Gotham',
+            'creators': ['FOX'],
+            # actual series name 'Gotham' is no longer returned by the API
+            'series': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
             'age_limit': 14,
             'episode': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
             'thumbnail': r're:^https?://.*\.jpg$',
@@ -39,6 +42,24 @@ class FOXIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # XML endpoint
+        'url': 'https://www.foxsports.com/watch/fmc-m2du80v5ewz11pbw',
+        'md5': '5451a633a5ca87b582a4d025df6852e6',
+        'info_dict': {
+            'id': 'fmc-m2du80v5ewz11pbw',
+            'ext': 'mp4',
+            'title': 'WWE FRIDAY NIGHT SMACKDOWN',
+            'description': 'From Fiserv Forum in Milwaukee, WI',
+            'duration': 5367,
+            'timestamp': 1698176671,
+            'upload_date': '20231024',
+            'creators': ['fox-digital'],
+            'series': 'WWE FRIDAY NIGHT SMACKDOWN',
+            'age_limit': 0,
+            'episode': 'WWE FRIDAY NIGHT SMACKDOWN',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
     }, {
         # episode, geo-restricted
         'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
@@ -54,9 +75,13 @@ class FOXIE(InfoExtractor):
     }]
     _GEO_BYPASS = False
     _HOME_PAGE_URL = 'https://www.fox.com/'
-    _API_KEY = '6E9S4bmcoNnZwVLOHywOv8PJEdu76cM9'
+    _API_KEY = '6E9S4bmcoNnZwVLOHywOv8PJEdu76cM9'  # sports: 'cf289e299efdfa39fb6316f259d1de93'
     _access_token = None
     _device_id = str(uuid.uuid4())
+    _XML_NS = {
+        'vmap': 'http://www.iab.net/videosuite/vmap',
+        'yospacenet': 'http://www.yospace.com/extension',
+    }
 
     def _call_api(self, path, video_id, data=None):
         headers = {
@@ -66,7 +91,7 @@ class FOXIE(InfoExtractor):
             headers['Authorization'] = 'Bearer ' + self._access_token
         try:
             return self._download_json(
-                'https://api3.fox.com/v2.0/' + path,
+                urljoin('https://api3.fox.com/v2.0/', path),
                 video_id, data=data, headers=headers)
         except ExtractorError as e:
             if isinstance(e.cause, HTTPError) and e.cause.status == 403:
@@ -100,8 +125,8 @@ class FOXIE(InfoExtractor):
             f'previewpassmvpd?device_id={self._device_id}&mvpd_id=TempPass_fbcfox_60min',
             video_id)['accessToken']
 
-        video = self._call_api('watch', video_id, data=json.dumps({
-            'capabilities': ['drm/widevine', 'fsdk/yo'],
+        video = self._call_api('https://prod.api.video.fox/v2.0/watch', video_id, data=json.dumps({
+            'capabilities': ['fsdk/yo/v3'],
             'deviceWidth': 1280,
             'deviceHeight': 720,
             'maxRes': '720p',
@@ -116,13 +141,16 @@ class FOXIE(InfoExtractor):
             'privacy': {'us': '1---'},
             'siteSection': '',
             'streamType': 'vod',
-            'streamId': video_id}).encode())
-
-        title = video['name']
-        release_url = video['url']
+            'streamId': video_id,
+        }).encode())
 
         try:
-            m3u8_url = self._download_json(release_url, video_id)['playURL']
+            if playback_url := traverse_obj(video, ('playbackUrl', {url_or_none})):
+                xml_data = self._download_xml(playback_url, video_id)
+                stream = xml_data.find('vmap:Extensions/vmap:Extension/yospacenet:Stream', self._XML_NS)
+                m3u8_url = join_nonempty('https://', stream.get('urlDomain'), stream.get('urlSuffix'), delim='')
+            else:
+                m3u8_url = self._download_json(video['url'], video_id)['playURL']
         except ExtractorError as e:
             if isinstance(e.cause, HTTPError) and e.cause.status == 403:
                 error = self._parse_json(e.cause.response.read().decode(), video_id)
@@ -130,9 +158,11 @@ class FOXIE(InfoExtractor):
                     self.raise_geo_restricted(countries=['US'])
                 raise ExtractorError(error['description'], expected=True)
             raise
-        formats = self._extract_m3u8_formats(
-            m3u8_url, video_id, 'mp4',
-            entry_protocol='m3u8_native', m3u8_id='hls')
+
+        if not m3u8_url or m3u8_url == 'https://':
+            raise ExtractorError('Unable to extract m3u8 url')
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls')
 
         data = try_get(
             video, lambda x: x['trackingData']['properties'], dict) or {}
@@ -157,7 +187,7 @@ class FOXIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': title,
+            'title': video.get('name'),
             'formats': formats,
             'description': video.get('description'),
             'duration': duration,

yt_dlp/extractor/foxsports.py

@@ -5,7 +5,7 @@ from ..utils import float_or_none, make_archive_id, smuggle_url
 
 
 class FoxSportsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?foxsports\.com/watch/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?foxsports\.com/watch/(?P<id>play-[\w-]+)'
     _TESTS = [{
         'url': 'https://www.foxsports.com/watch/play-612168c6700004b',
         'info_dict': {

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)})))