Merge e767973d8c into eb15fd5a32

[ie/kenh14] Add extractor (#3996 )
Closes #3937 Authored by: krichbanana, pzhlkj6612 Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
2024-11-25 00:31:26 +01:00 · 2024-11-17 17:03:36 +01:00 · 2024-11-17 14:12:26 +00:00 · 2024-11-17 13:32:12 +01:00 · 2024-11-16 07:57:41 +00:00 · 2024-11-16 07:57:30 +00:00
5 changed files with 342 additions and 136 deletions
--- a/yt_dlp/extractor/_extractors.py
+++ b/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,
@ -1089,10 +1093,6 @@ from .manoto import (
 )
 from .manyvids import ManyVidsIE
 from .maoritv import MaoriTVIE
-from .markiza import (
-    MarkizaIE,
-    MarkizaPageIE,
-)
 from .massengeschmacktv import MassengeschmackTVIE
 from .masters import MastersIE
 from .matchtv import MatchTVIE
--- a/yt_dlp/extractor/chaturbate.py
+++ b/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)
--- a/yt_dlp/extractor/kenh14.py
+++ b/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$',
+        },
+        'playlist_count': 6,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        category_detail = get_element_by_class('category-detail', webpage) or ''
+        embed_info = traverse_obj(
+            self._yield_json_ld(webpage, playlist_id),
+            (lambda _, v: v['name'] and v['alternateName'], any)) or {}
+
+        return self.playlist_from_matches(
+            get_elements_html_by_class('video-item', webpage), playlist_id,
+            (clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
+            getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
+            ie=Kenh14VideoIE, playlist_description=(
+                clean_html(get_element_by_class('description', category_detail))
+                or unescapeHTML(embed_info.get('alternateName'))),
+            thumbnail=traverse_obj(
+                self._og_search_thumbnail(webpage),
+                ({url_or_none}, {update_url(query=None)})))
--- a/yt_dlp/extractor/markiza.py
+++ b/yt_dlp/extractor/markiza.py
@ -1,123 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    orderedSet,
-    parse_duration,
-    try_get,
-)
-
-
-class MarkizaIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'https?://(?:www\.)?videoarchiv\.markiza\.sk/(?:video/(?:[^/]+/)*|embed/)(?P<id>\d+)(?:[_/]|$)'
-    _TESTS = [{
-        'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723_oteckovia-109',
-        'md5': 'ada4e9fad038abeed971843aa028c7b0',
-        'info_dict': {
-            'id': '139078',
-            'ext': 'mp4',
-            'title': 'Oteckovia 109',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 2760,
-        },
-    }, {
-        'url': 'http://videoarchiv.markiza.sk/video/televizne-noviny/televizne-noviny/85430_televizne-noviny',
-        'info_dict': {
-            'id': '85430',
-            'title': 'Televízne noviny',
-        },
-        'playlist_count': 23,
-    }, {
-        'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723',
-        'only_matching': True,
-    }, {
-        'url': 'http://videoarchiv.markiza.sk/video/84723',
-        'only_matching': True,
-    }, {
-        'url': 'http://videoarchiv.markiza.sk/video/filmy/85190_kamenak',
-        'only_matching': True,
-    }, {
-        'url': 'http://videoarchiv.markiza.sk/video/reflex/zo-zakulisia/84651_pribeh-alzbetky',
-        'only_matching': True,
-    }, {
-        'url': 'http://videoarchiv.markiza.sk/embed/85295',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        data = self._download_json(
-            'http://videoarchiv.markiza.sk/json/video_jwplayer7.json',
-            video_id, query={'id': video_id})
-
-        info = self._parse_jwplayer_data(data, m3u8_id='hls', mpd_id='dash')
-
-        if info.get('_type') == 'playlist':
-            info.update({
-                'id': video_id,
-                'title': try_get(
-                    data, lambda x: x['details']['name'], str),
-            })
-        else:
-            info['duration'] = parse_duration(
-                try_get(data, lambda x: x['details']['duration'], str))
-        return info
-
-
-class MarkizaPageIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:[^/]+\.)?markiza|tvnoviny)\.sk/(?:[^/]+/)*(?P<id>\d+)_'
-    _TESTS = [{
-        'url': 'http://www.markiza.sk/soubiz/zahranicny/1923705_oteckovia-maju-svoj-den-ti-slavni-nie-su-o-nic-menej-rozkosni',
-        'md5': 'ada4e9fad038abeed971843aa028c7b0',
-        'info_dict': {
-            'id': '139355',
-            'ext': 'mp4',
-            'title': 'Oteckovia 110',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 2604,
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://dajto.markiza.sk/filmy-a-serialy/1774695_frajeri-vo-vegas',
-        'only_matching': True,
-    }, {
-        'url': 'http://superstar.markiza.sk/aktualne/1923870_to-je-ale-telo-spevacka-ukazala-sexy-postavicku-v-bikinach',
-        'only_matching': True,
-    }, {
-        'url': 'http://hybsa.markiza.sk/aktualne/1923790_uzasna-atmosfera-na-hybsa-v-poprade-superstaristi-si-prve-koncerty-pred-davom-ludi-poriadne-uzili',
-        'only_matching': True,
-    }, {
-        'url': 'http://doma.markiza.sk/filmy/1885250_moja-vysnivana-svadba',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.tvnoviny.sk/domace/1923887_po-smrti-manzela-ju-cakalo-poriadne-prekvapenie',
-        'only_matching': True,
-    }]
-
-    @classmethod
-    def suitable(cls, url):
-        return False if MarkizaIE.suitable(url) else super().suitable(url)
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-
-        webpage = self._download_webpage(
-            # Downloading for some hosts (e.g. dajto, doma) fails with 500
-            # although everything seems to be OK, so considering 500
-            # status code to be expected.
-            url, playlist_id, expected_status=500)
-
-        entries = [
-            self.url_result(f'http://videoarchiv.markiza.sk/video/{video_id}')
-            for video_id in orderedSet(re.findall(
-                r'(?:initPlayer_|data-entity=["\']|id=["\']player_)(\d+)',
-                webpage))]
-
-        return self.playlist_result(entries, playlist_id)
--- a/yt_dlp/extractor/nova.py
+++ b/yt_dlp/extractor/nova.py
@ -6,14 +6,20 @@ from ..utils import (
    determine_ext,
    int_or_none,
    js_to_json,
-    traverse_obj,
+    strip_or_none,
    unified_strdate,
    url_or_none,
 )
+from ..utils.traversal import traverse_obj


 class NovaEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://media(?:tn)?\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
+    _DOMAINS = [
+        r'media(?:tn)?\.cms\.nova\.cz',
+        r'media\.cms\.(?:markiza|tvnoviny)\.sk',
+    ]
+    _VALID_URL = [rf'https?://{domain}/embed/(?P<id>[^/?#&"\']+)' for domain in _DOMAINS]
+    _EMBED_REGEX = [rf'(?x)<iframe[^>]+\b(?:data-)?src=["\'](?P<url>{url})' for url in _VALID_URL]
    _TESTS = [{
        'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
        'info_dict': {
@ -43,19 +49,179 @@ class NovaEmbedIE(InfoExtractor):
            'id': 'EU5ELEsmOHt',
            'ext': 'mp4',
            'title': 'Haptické křeslo, bionická ruka nebo roboti. Reportérka se podívala na Týden inovací',
-            'thumbnail': r're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://cloudia\.cms\.nova\.cz/.+',
            'duration': 1780,
        },
        'params': {'skip_download': 'm3u8'},
    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'http://www.markiza.sk/soubiz/zahranicny/1923705_oteckovia-maju-svoj-den-ti-slavni-nie-su-o-nic-menej-rozkosni',
+        'md5': 'a478390ea7f36aeb36004a107db8b031',
+        'info_dict': {
+            'id': '4q3zP2DsORO',
+            'ext': 'mp4',
+            'title': 'Oteckovia 110',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 2603,
+        },
+    }, {
+        'url': 'https://tvnoviny.sk/domace/clanok/141815-byvaly-sportovec-udajne-vyrabal-mast-z-marihuany-sud-mu-vymeral-20-rocny-trest-a-vzal-aj-rodinny-dom',
+        'md5': '51de0754352a36b4d623f98c9636a5e1',
+        'info_dict': {
+            'id': '2LcfYRqGuYP',
+            'ext': 'mp4',
+            'title': 'Marihuanový mastičkár si vypočul vysoký trest a prepad majetku',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 119,
+        },
+    }, {
+        'url': 'https://tvnoviny.sk/domace/clanok/144055-robert-z-kosic-dostal-najnizsi-mozny-trest-za-to-co-spravil-je-to-aj-tak-vela-tvrdia-blizki',
+        'md5': 'c9a8467b37951877336a9ae6309558b0',
+        'info_dict': {
+            'id': '82N7FrJK7cR',
+            'ext': 'mp4',
+            'title': 'Robovi z Košíc znížili trest za marihuanu, odsúdili ho na päť rokov',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 152,
+        },
+    }, {
+        'url': 'https://tvnoviny.sk/domace/clanok/338907-preco-sa-mnozia-utoky-tinedzerov-podla-psychologiciek-je-za-tym-rastuca-frustracia',
+        'md5': '869b589e99d7c19dd66f024a7d088502',
+        'info_dict': {
+            'id': 'DeiezcjCJmg',
+            'ext': 'mp4',
+            'title': '2022-11-03-TN-2-Nasilie-medzi-mladymi',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 142,
+        },
+    }, {
+        'url': 'http://tvnoviny.sk/domace/clanok/890183-vlada-chysta-postavit-novu-nemocnicu-v-presove-informoval-premier-robert-fico',
+        'md5': 'b9ef0b4917deee2c930f2248b568a90c',
+        'info_dict': {
+            'id': '7VCyuyfGsNZ',
+            'ext': 'mp4',
+            'title': '2024-04-15-PTN-1-Co-caka-zdravotnictvo',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 137,
+        },
+    }, {
+        'url': 'https://www.markiza.sk/live/1-markiza',
+        'info_dict': {
+            'id': 'markiza-live',
+            'ext': 'mp4',
+            'title': r're:^CRA Markiza SD \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'thumbnail': r're:^https?://cloudia\.cms\.markiza\.sk/.+',
+            'live_status': 'is_live',
+        },
+    }, {
+        'url': 'http://www.tvnoviny.sk/domace/1923887_po-smrti-manzela-ju-cakalo-poriadne-prekvapenie',
+        'md5': 'e3e0f1e98172ea64147cada308276df8',
+        'info_dict': {
+            'id': 'JxqRvQkFwHK',
+            'ext': 'mp4',
+            'title': 'Po smrti manžela ju čakalo prekvapenie',
+            'thumbnail': r're:^https?://.*\.(?:jpg)',
+            'duration': 108,
+        },
+    }, {
+        'url': 'http://videoarchiv.markiza.sk/video/reflex/zo-zakulisia/84651_pribeh-alzbetky',
+        'md5': 'b40d04d5cb4cf529e2ff14d6726a3548',
+        'info_dict': {
+            'id': '9ZnlOQp2MRa',
+            'ext': 'mp4',
+            'title': 'Príbeh Alžbetky',
+            'thumbnail': r're:^https?://.*\.(?:jpg)',
+            'duration': 361,
+        },
+    }, {
+        'url': 'https://www.markiza.sk/relacie/superstar/clanok/549972-v-zakulisi-superstar-to-bolo-obcas-drsne-moderator-priznal-ze-musel-pouzit-aj-hrubu-silu',
+        'info_dict': {
+            'id': '549972-v-zakulisi-superstar-to-bolo-obcas-drsne-moderator-priznal-ze-musel-pouzit-aj-hrubu-silu',
+            'title': 'V zákulisí SuperStar to bolo občas drsné. Moderátor priznal, že musel použiť aj hrubú silu | TV Markíza',
+            'description': 'md5:02e240e302bddfd0cd352bc886d95161',
+            'thumbnail': r're:^https?://cmesk-ott-images-avod\.ssl\.cdn\.cra\.cz/.+',
+            'age_limit': 0,
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'https://voyo.markiza.sk/filmy/6702-vysnivana-svadba',
+        'info_dict': {
+            'id': '20kSOHBD8DQ',
+            'title': 'Vysnívaná svadba - 0000',
+            'thumbnail': r're:^https?://.*\.(?:jpg)',
+            'duration': 4924,
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'expected_warnings': [
+            'Requested format is not available',
+            'This video is DRM protected',
+        ],
+        'skip': 'premium member only',
+    }, {
+        # Another URLs:
+        #   http://videoarchiv.markiza.sk/video/84723
+        'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723_oteckovia-109',
+        'info_dict': {
+            'id': '2a5fQmhjvYm',
+            'title': 'Oteckovia 109',
+            'thumbnail': r're:^https?://.*\.(?:jpg)',
+            'duration': 2759,
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'expected_warnings': [
+            'Requested format is not available',
+            'This video is DRM protected',
+        ],
+        'skip': 'premium member only',
+    }, {
+        'url': 'https://voyo.markiza.sk/filmy/1377-frajeri-vo-vegas#player-fullscreen',
+        'info_dict': {
+            'id': '1377-frajeri-vo-vegas#player-fullscreen',
+            'title': 'Frajeri vo Vegas | Voyo',
+            'description': 'md5:7f16168f669f144986d862312949627c',
+            'thumbnail': r're:^https?://cmesk-ott-images-svod\.ssl\.cdn\.cra\.cz/.+',
+            'age_limit': 0,
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'K8H4IvKNBbw',
+                'ext': 'mp4',
+                'title': 'frajeri-vo-vegas-hd-15_frajeri-trailer',
+                'duration': 90,
+                'thumbnail': r're:^https?://.*\.(?:jpg)',
+            },
+        },
+            # BUG: The 2nd item (CDjGcqcCYKy) is the movie itself and it's DRM-protected.
+            #      The "ext" field can neither be here nor omitted.
+        ],
+        'playlist_count': 2,
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'expected_warnings': [
+            'Requested format is not available',
+            'This video is DRM protected',
+        ],
+        'skip': 'premium member only',
+    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)
+        if 'player_not_logged_in' in webpage:
+            self.raise_login_required()

        has_drm = False
        duration = None
+        is_live = False
        formats = []

        def process_format_list(format_list, format_id=''):
@ -77,11 +243,11 @@ class NovaEmbedIE(InfoExtractor):
                    formats.extend(self._extract_m3u8_formats(
                        format_url, video_id, 'mp4',
                        entry_protocol='m3u8_native', m3u8_id='hls',
-                        fatal=False))
+                        fatal=False, headers={'Referer': url}))
                elif (format_type == 'application/dash+xml'
                      or format_id == 'DASH' or ext == 'mpd'):
                    formats.extend(self._extract_mpd_formats(
-                        format_url, video_id, mpd_id='dash', fatal=False))
+                        format_url, video_id, mpd_id='dash', fatal=False, headers={'Referer': url}))
                else:
                    formats.append({
                        'url': format_url,
@ -93,6 +259,7 @@ class NovaEmbedIE(InfoExtractor):
            for src in traverse_obj(player, ('lib', 'source', 'sources', ...)):
                process_format_list(src)
            duration = traverse_obj(player, ('sourceInfo', 'duration', {int_or_none}))
+            is_live = player.get('isLive', False)
        if not formats and not has_drm:
            # older code path, in use before August 2023
            player = self._parse_json(
@ -108,11 +275,11 @@ class NovaEmbedIE(InfoExtractor):
        if not formats and has_drm:
            self.report_drm(video_id)

-        title = self._og_search_title(
+        title = strip_or_none(self._og_search_title(
            webpage, default=None) or self._search_regex(
            (r'<value>(?P<title>[^<]+)',
             r'videoTitle\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
-            'title', group='value')
+            'title', group='value'))
        thumbnail = self._og_search_thumbnail(
            webpage, default=None) or self._search_regex(
            r'poster\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
@ -127,6 +294,8 @@ class NovaEmbedIE(InfoExtractor):
            'thumbnail': thumbnail,
            'duration': duration,
            'formats': formats,
+            'http_headers': {'Referer': url},
+            'is_live': is_live,
        }
Author	SHA1	Message	Date
Mozi	a52172fc19	Merge `e767973d8c` into `eb15fd5a32`	2024-11-17 17:03:36 +01:00
krichbanana	eb15fd5a32	[ie/kenh14] Add extractor (#3996 ) Closes #3937 Authored by: krichbanana, pzhlkj6612 Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>	2024-11-17 14:12:26 +00:00
sepro	7cecd299e4	[ie/chaturbate] Don't break embed detection (#11565 ) Bugfix for `720b3dc453` Authored by: seproDev	2024-11-17 13:32:12 +01:00
Mozi	e767973d8c	merge 'master'	2024-11-16 07:57:41 +00:00
Mozi	dc2239391b	imports	2024-11-16 07:57:30 +00:00
Mozi	507b7c6d4a	[ie/nova:embed] Support live and VOD on markiza.sk and tvnoviny.sk	2024-10-13 10:01:53 +00:00