Merge 3e1c1f2e39 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/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/senategov.py

@@ -9,37 +9,37 @@ from ..utils import (
 )
 
 _COMMITTEES = {
-    'ag': ('76440', 'http://ag-f.akamaihd.net'),
-    'aging': ('76442', 'http://aging-f.akamaihd.net'),
-    'approps': ('76441', 'http://approps-f.akamaihd.net'),
-    'arch': ('', 'http://ussenate-f.akamaihd.net'),
-    'armed': ('76445', 'http://armed-f.akamaihd.net'),
-    'banking': ('76446', 'http://banking-f.akamaihd.net'),
-    'budget': ('76447', 'http://budget-f.akamaihd.net'),
-    'cecc': ('76486', 'http://srs-f.akamaihd.net'),
-    'commerce': ('80177', 'http://commerce1-f.akamaihd.net'),
-    'csce': ('75229', 'http://srs-f.akamaihd.net'),
-    'dpc': ('76590', 'http://dpc-f.akamaihd.net'),
-    'energy': ('76448', 'http://energy-f.akamaihd.net'),
-    'epw': ('76478', 'http://epw-f.akamaihd.net'),
-    'ethics': ('76449', 'http://ethics-f.akamaihd.net'),
-    'finance': ('76450', 'http://finance-f.akamaihd.net'),
-    'foreign': ('76451', 'http://foreign-f.akamaihd.net'),
-    'govtaff': ('76453', 'http://govtaff-f.akamaihd.net'),
-    'help': ('76452', 'http://help-f.akamaihd.net'),
-    'indian': ('76455', 'http://indian-f.akamaihd.net'),
-    'intel': ('76456', 'http://intel-f.akamaihd.net'),
-    'intlnarc': ('76457', 'http://intlnarc-f.akamaihd.net'),
-    'jccic': ('85180', 'http://jccic-f.akamaihd.net'),
-    'jec': ('76458', 'http://jec-f.akamaihd.net'),
-    'judiciary': ('76459', 'http://judiciary-f.akamaihd.net'),
-    'rpc': ('76591', 'http://rpc-f.akamaihd.net'),
-    'rules': ('76460', 'http://rules-f.akamaihd.net'),
-    'saa': ('76489', 'http://srs-f.akamaihd.net'),
-    'smbiz': ('76461', 'http://smbiz-f.akamaihd.net'),
-    'srs': ('75229', 'http://srs-f.akamaihd.net'),
-    'uscc': ('76487', 'http://srs-f.akamaihd.net'),
-    'vetaff': ('76462', 'http://vetaff-f.akamaihd.net'),
+    'ag': ('76440', 'https://ag-f.akamaihd.net', '2036803', 'agriculture'),
+    'aging': ('76442', 'https://aging-f.akamaihd.net', '2036801', 'aging'),
+    'approps': ('76441', 'https://approps-f.akamaihd.net', '2036802', 'appropriations'),
+    'arch': ('', 'https://ussenate-f.akamaihd.net/', '', 'arch'),
+    'armed': ('76445', 'https://armed-f.akamaihd.net', '2036800', 'armedservices'),
+    'banking': ('76446', 'https://banking-f.akamaihd.net', '2036799', 'banking'),
+    'budget': ('76447', 'https://budget-f.akamaihd.net', '2036798', 'budget'),
+    'cecc': ('76486', 'https://srs-f.akamaihd.net', '2036782', 'srs_cecc'),
+    'commerce': ('80177', 'https://commerce1-f.akamaihd.net', '2036779', 'commerce'),
+    'csce': ('75229', 'https://srs-f.akamaihd.net', '2036777', 'srs_srs'),
+    'dpc': ('76590', 'https://dpc-f.akamaihd.net', '', 'dpc'),
+    'energy': ('76448', 'https://energy-f.akamaihd.net', '2036797', 'energy'),
+    'epw': ('76478', 'https://epw-f.akamaihd.net', '2036783', 'environment'),
+    'ethics': ('76449', 'https://ethics-f.akamaihd.net', '2036796', 'ethics'),
+    'finance': ('76450', 'https://finance-f.akamaihd.net', '2036795', 'finance_finance'),
+    'foreign': ('76451', 'https://foreign-f.akamaihd.net', '2036794', 'foreignrelations'),
+    'govtaff': ('76453', 'https://govtaff-f.akamaihd.net', '2036792', 'hsgac'),
+    'help': ('76452', 'https://help-f.akamaihd.net', '2036793', 'help'),
+    'indian': ('76455', 'https://indian-f.akamaihd.net', '2036791', 'indianaffairs'),
+    'intel': ('76456', 'https://intel-f.akamaihd.net', '2036790', 'intelligence'),
+    'intlnarc': ('76457', 'https://intlnarc-f.akamaihd.net', '', 'internationalnarcoticscaucus'),
+    'jccic': ('85180', 'https://jccic-f.akamaihd.net', '2036778', 'jccic'),
+    'jec': ('76458', 'https://jec-f.akamaihd.net', '2036789', 'jointeconomic'),
+    'judiciary': ('76459', 'https://judiciary-f.akamaihd.net', '2036788', 'judiciary'),
+    'rpc': ('76591', 'https://rpc-f.akamaihd.net', '', 'rpc'),
+    'rules': ('76460', 'https://rules-f.akamaihd.net', '2036787', 'rules'),
+    'saa': ('76489', 'https://srs-f.akamaihd.net', '2036780', 'srs_saa'),
+    'smbiz': ('76461', 'https://smbiz-f.akamaihd.net', '2036786', 'smallbusiness'),
+    'srs': ('75229', 'https://srs-f.akamaihd.net', '2031966', 'srs_srs'),
+    'uscc': ('76487', 'https://srs-f.akamaihd.net', '2036781', 'srs_uscc'),
+    'vetaff': ('76462', 'https://vetaff-f.akamaihd.net', '2036785', 'veteransaffairs'),
 }
 
 
@@ -173,15 +173,23 @@ class SenateGovIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._generic_id(url)
         webpage = self._download_webpage(url, display_id)
-        parse_info = parse_qs(self._search_regex(
-            r'<iframe class="[^>"]*streaminghearing[^>"]*"\s[^>]*\bsrc="([^">]*)', webpage, 'hearing URL'))
-
-        stream_num, stream_domain = _COMMITTEES[parse_info['comm'][-1]]
+        iframe_src = self._search_regex(
+            (r'<iframe class="[^>"]*streaminghearing[^>"]*"\s[^>]*\bsrc="([^">]*)',
+             r'<iframe title="[^>"]*[^>"]*"\s[^>]*\bsrc="([^">]*)'),
+            webpage, 'hearing URL').replace('&amp;', '&')
+        parse_info = parse_qs(iframe_src)
+        comm = parse_info['comm'][-1]
+        stream_num, stream_domain, stream_id, msl3 = _COMMITTEES[comm]
         filename = parse_info['filename'][-1]
 
-        formats = self._extract_m3u8_formats(
-            f'{stream_domain}/i/{filename}_1@{stream_num}/master.m3u8',
-            display_id, ext='mp4')
+        urls_alternatives = [f'https://www-senate-gov-media-srs.akamaized.net/hls/live/{stream_id}/{comm}/{filename}/master.m3u8',
+                             f'https://www-senate-gov-msl3archive.akamaized.net/{msl3}/{filename}_1/master.m3u8',
+                             f'{stream_domain}/i/{filename}_1@{stream_num}/master.m3u8',
+                             f'{stream_domain}/i/{filename}.mp4/master.m3u8']
+        for video_url in urls_alternatives:
+            formats = self._extract_m3u8_formats(video_url, display_id, ext='mp4', fatal=False)
+            if formats:
+                break
 
         title = self._html_search_regex(
             (*self._og_regexes('title'), r'(?s)<title>([^<]*?)</title>'), webpage, 'video title')