Merge 0b6d13c289 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,
@@ -1005,6 +1009,7 @@ from .lecture2go import Lecture2GoIE
 from .lecturio import (
     LecturioCourseIE,
     LecturioDeCourseIE,
+    LecturioDeIE,
     LecturioIE,
 )
 from .leeco 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/lecturio.py

@@ -18,6 +18,19 @@ class LecturioBaseIE(InfoExtractor):
     _API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
     _LOGIN_URL = 'https://app.lecturio.com/en/login'
     _NETRC_MACHINE = 'lecturio'
+    _CC_LANGS = {
+        'Arabic': 'ar',
+        'Bulgarian': 'bg',
+        'German': 'de',
+        'English': 'en',
+        'Spanish': 'es',
+        'Persian': 'fa',
+        'French': 'fr',
+        'Japanese': 'ja',
+        'Polish': 'pl',
+        'Pashto': 'ps',
+        'Russian': 'ru',
+    }
 
     def _perform_login(self, username, password):
         # Sets some cookies
@@ -52,57 +65,14 @@ class LecturioBaseIE(InfoExtractor):
             raise ExtractorError(f'Unable to login: {errors}', expected=True)
         raise ExtractorError('Unable to log in')
 
-
-class LecturioIE(LecturioBaseIE):
-    _VALID_URL = r'''(?x)
-                    https://
-                        (?:
-                            app\.lecturio\.com/([^/?#]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
-                            (?:www\.)?lecturio\.de/(?:[^/?#]+/)+(?P<nt_de>[^/?#&]+)\.vortrag
-                        )
-                    '''
-    _TESTS = [{
-        'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
-        'md5': '9a42cf1d8282a6311bf7211bbde26fde',
-        'info_dict': {
-            'id': '39634',
-            'ext': 'mp4',
-            'title': 'Important Concepts and Terms — Introduction to Microbiology',
-        },
-        'skip': 'Requires lecturio account credentials',
-    }, {
-        'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.lecturio.de/jura/oeffentliches-recht-at-1-staatsexamen/oeffentliches-recht-staatsexamen.vortrag',
-        'only_matching': True,
-    }, {
-        'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
-        'only_matching': True,
-    }]
-
-    _CC_LANGS = {
-        'Arabic': 'ar',
-        'Bulgarian': 'bg',
-        'German': 'de',
-        'English': 'en',
-        'Spanish': 'es',
-        'Persian': 'fa',
-        'French': 'fr',
-        'Japanese': 'ja',
-        'Polish': 'pl',
-        'Pashto': 'ps',
-        'Russian': 'ru',
-    }
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
-        nt = mobj.group('nt') or mobj.group('nt_de')
+        nt = mobj.group('nt')
         lecture_id = mobj.group('id')
         display_id = nt or lecture_id
         api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
-        video = self._download_json(
+
-            self._API_BASE_URL + api_path, display_id)
+        video = self._download_json(self._API_BASE_URL + api_path, display_id)
         title = video['title'].strip()
         if not lecture_id:
             pid = video.get('productId') or video.get('uid')
@@ -171,6 +141,33 @@ class LecturioIE(LecturioBaseIE):
         }
 
 
+class LecturioIE(LecturioBaseIE):
+    _VALID_URL = r'https?://app\.lecturio\.com/([^/?#]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))'
+    _TESTS = [{
+        'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
+        'md5': '9a42cf1d8282a6311bf7211bbde26fde',
+        'info_dict': {
+            'id': '39634',
+            'ext': 'mp4',
+            'title': 'Important Concepts and Terms — Introduction to Microbiology',
+        },
+        'skip': 'Requires lecturio account credentials',
+    }, {
+        'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
+        'only_matching': True,
+    }]
+
+
+class LecturioDeIE(LecturioBaseIE):
+    _VALID_URL = r'https?://www\.lecturio\.de/[^/?#]+/(?P<id>)(?P<nt>[^/?#&]+)\.vortrag'
+    _TESTS = [{
+        'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
+        'only_matching': True,
+    }]
+    _API_BASE_URL = 'https://lecturio.de/api/de/latest/html5/'
+    _LOGIN_URL = 'https://www.lecturio.de/anmelden.html'
+
+
 class LecturioCourseIE(LecturioBaseIE):
     _VALID_URL = r'https?://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
     _TESTS = [{
@@ -208,12 +205,12 @@ class LecturioCourseIE(LecturioBaseIE):
             clean_html(course.get('description')))
 
 
-class LecturioDeCourseIE(LecturioBaseIE):
+class LecturioDeCourseIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
+    _VALID_URL = r'https?://(?:www\.)?lecturio\.de/[^/?#]+/(?P<id>[^/?#&]+)\.kurs'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
         'only_matching': True,
-    }
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -227,7 +224,7 @@ class LecturioDeCourseIE(LecturioBaseIE):
             lecture_url = urljoin(url, mobj.group('url'))
             lecture_id = mobj.group('id')
             entries.append(self.url_result(
-                lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
+                lecture_url, LecturioDeIE, video_id=lecture_id))
 
         title = self._search_regex(
             r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)