[yt-dlp.git] / yt_dlp / extractor / cbs.py

from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from .theplatform import ThePlatformFeedIE
from .youtube import YoutubeIE
from ..utils import (
    ExtractorError,
    extract_attributes,
    get_element_html_by_id,
    int_or_none,
    find_xpath_attr,
    smuggle_url,
    xpath_element,
    xpath_text,
    update_url_query,
    url_or_none,
)


class CBSBaseIE(ThePlatformFeedIE):  # XXX: Do not subclass from concrete IE
    def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
        subtitles = {}
        for k, ext in [('sMPTE-TTCCURL', 'tt'), ('ClosedCaptionURL', 'ttml'), ('webVTTCaptionURL', 'vtt')]:
            cc_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', k)
            if cc_e is not None:
                cc_url = cc_e.get('value')
                if cc_url:
                    subtitles.setdefault(subtitles_lang, []).append({
                        'ext': ext,
                        'url': cc_url,
                    })
        return subtitles

    def _extract_common_video_info(self, content_id, asset_types, mpx_acc, extra_info):
        tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
        tp_release_url = f'https://link.theplatform.com/s/{tp_path}'
        info = self._extract_theplatform_metadata(tp_path, content_id)

        formats, subtitles = [], {}
        last_e = None
        for asset_type, query in asset_types.items():
            try:
                tp_formats, tp_subtitles = self._extract_theplatform_smil(
                    update_url_query(tp_release_url, query), content_id,
                    'Downloading %s SMIL data' % asset_type)
            except ExtractorError as e:
                last_e = e
                if asset_type != 'fallback':
                    continue
                query['formats'] = ''  # blank query to check if expired
                try:
                    tp_formats, tp_subtitles = self._extract_theplatform_smil(
                        update_url_query(tp_release_url, query), content_id,
                        'Downloading %s SMIL data, trying again with another format' % asset_type)
                except ExtractorError as e:
                    last_e = e
                    continue
            formats.extend(tp_formats)
            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
        if last_e and not formats:
            self.raise_no_formats(last_e, True, content_id)

        extra_info.update({
            'id': content_id,
            'formats': formats,
            'subtitles': subtitles,
        })
        info.update({k: v for k, v in extra_info.items() if v is not None})
        return info

    def _extract_video_info(self, *args, **kwargs):
        # Extract assets + metadata and call _extract_common_video_info
        raise NotImplementedError('This method must be implemented by subclasses')

    def _real_extract(self, url):
        return self._extract_video_info(self._match_id(url))


class CBSIE(CBSBaseIE):
    _VALID_URL = r'''(?x)
        (?:
            cbs:|
            https?://(?:www\.)?(?:
                cbs\.com/(?:shows|movies)/(?:video|[^/]+/video|[^/]+)/|
                colbertlateshow\.com/(?:video|podcasts)/)
        )(?P<id>[\w-]+)'''

    # All tests are blocked outside US
    _TESTS = [{
        'url': 'https://www.cbs.com/shows/video/xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R/',
        'info_dict': {
            'id': 'xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R',
            'ext': 'mp4',
            'title': 'Tough As Nails - Dreams Never Die',
            'description': 'md5:a3535a62531cdd52b0364248a2c1ae33',
            'duration': 2588,
            'timestamp': 1639015200,
            'upload_date': '20211209',
            'uploader': 'CBSI-NEW',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }, {
        'url': 'https://www.cbs.com/shows/video/sZH1MGgomIosZgxGJ1l263MFq16oMtW1/',
        'info_dict': {
            'id': 'sZH1MGgomIosZgxGJ1l263MFq16oMtW1',
            'title': 'The Late Show - 3/16/22 (Michael Buble, Rose Matafeo)',
            'timestamp': 1647488100,
            'description': 'md5:d0e6ec23c544b7fa8e39a8e6844d2439',
            'uploader': 'CBSI-NEW',
            'upload_date': '20220317',
        },
        'params': {
            'ignore_no_formats_error': True,
            'skip_download': True,
        },
        'expected_warnings': [
            'This content expired on', 'No video formats found', 'Requested format is not available'],
    }, {
        'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
        'only_matching': True,
    }, {
        'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
        'only_matching': True,
    }]

    def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
        items_data = self._download_xml(
            'https://can.cbs.com/thunder/player/videoPlayerService.php',
            content_id, query={'partner': site, 'contentId': content_id})
        video_data = xpath_element(items_data, './/item')
        title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')

        asset_types = {}
        has_drm = False
        for item in items_data.findall('.//item'):
            asset_type = xpath_text(item, 'assetType')
            query = {
                'mbr': 'true',
                'assetTypes': asset_type,
            }
            if not asset_type:
                # fallback for content_ids that videoPlayerService doesn't return anything for
                asset_type = 'fallback'
                query['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3'
                del query['assetTypes']
            if asset_type in asset_types:
                continue
            elif any(excluded in asset_type for excluded in ('HLS_FPS', 'DASH_CENC', 'OnceURL')):
                if 'DASH_CENC' in asset_type:
                    has_drm = True
                continue
            if asset_type.startswith('HLS') or 'StreamPack' in asset_type:
                query['formats'] = 'MPEG4,M3U'
            elif asset_type in ('RTMP', 'WIFI', '3G'):
                query['formats'] = 'MPEG4,FLV'
            asset_types[asset_type] = query

        if not asset_types and has_drm:
            self.report_drm(content_id)

        return self._extract_common_video_info(content_id, asset_types, mpx_acc, extra_info={
            'title': title,
            'series': xpath_text(video_data, 'seriesTitle'),
            'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
            'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
            'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
            'thumbnail': url_or_none(xpath_text(video_data, 'previewImageURL')),
        })


class ParamountPressExpressIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?paramountpressexpress\.com(?:/[\w-]+)+/(?P<yt>yt-)?video/?\?watch=(?P<id>[\w-]+)'
    _TESTS = [{
        'url': 'https://www.paramountpressexpress.com/cbs-entertainment/shows/survivor/video/?watch=pnzew7e2hx',
        'md5': '56631dbcadaab980d1fc47cb7b76cba4',
        'info_dict': {
            'id': '6322981580112',
            'ext': 'mp4',
            'title': 'I’m Felicia',
            'description': 'md5:88fad93f8eede1c9c8f390239e4c6290',
            'uploader_id': '6055873637001',
            'upload_date': '20230320',
            'timestamp': 1679334960,
            'duration': 49.557,
            'thumbnail': r're:^https://.+\.jpg',
            'tags': [],
        },
    }, {
        'url': 'https://www.paramountpressexpress.com/cbs-entertainment/video/?watch=2s5eh8kppc',
        'md5': 'edcb03e3210b88a3e56c05aa863e0e5b',
        'info_dict': {
            'id': '6323036027112',
            'ext': 'mp4',
            'title': '‘Y&R’ Set Visit: Jerry O’Connell Quizzes Cast on Pre-Love Scene Rituals and More',
            'description': 'md5:b929867a357aac5544b783d834c78383',
            'uploader_id': '6055873637001',
            'upload_date': '20230321',
            'timestamp': 1679430180,
            'duration': 132.032,
            'thumbnail': r're:^https://.+\.jpg',
            'tags': [],
        },
    }, {
        'url': 'https://www.paramountpressexpress.com/paramount-plus/yt-video/?watch=OX9wJWOcqck',
        'info_dict': {
            'id': 'OX9wJWOcqck',
            'ext': 'mp4',
            'title': 'Rugrats | Season 2 Official Trailer | Paramount+',
            'description': 'md5:1f7e26f5625a9f0d6564d9ad97a9f7de',
            'uploader': 'Paramount Plus',
            'uploader_id': '@paramountplus',
            'uploader_url': 'http://www.youtube.com/@paramountplus',
            'channel': 'Paramount Plus',
            'channel_id': 'UCrRttZIypNTA1Mrfwo745Sg',
            'channel_url': 'https://www.youtube.com/channel/UCrRttZIypNTA1Mrfwo745Sg',
            'upload_date': '20230316',
            'duration': 88,
            'age_limit': 0,
            'availability': 'public',
            'live_status': 'not_live',
            'playable_in_embed': True,
            'view_count': int,
            'like_count': int,
            'channel_follower_count': int,
            'thumbnail': 'https://i.ytimg.com/vi/OX9wJWOcqck/maxresdefault.jpg',
            'categories': ['Entertainment'],
            'tags': ['Rugrats'],
        },
    }, {
        'url': 'https://www.paramountpressexpress.com/showtime/yt-video/?watch=_ljssSoDLkw',
        'info_dict': {
            'id': '_ljssSoDLkw',
            'ext': 'mp4',
            'title': 'Lavell Crawford: THEE Lavell Crawford Comedy Special Official Trailer | SHOWTIME',
            'description': 'md5:39581bcc3fd810209b642609f448af70',
            'uploader': 'SHOWTIME',
            'uploader_id': '@Showtime',
            'uploader_url': 'http://www.youtube.com/@Showtime',
            'channel': 'SHOWTIME',
            'channel_id': 'UCtwMWJr2BFPkuJTnSvCESSQ',
            'channel_url': 'https://www.youtube.com/channel/UCtwMWJr2BFPkuJTnSvCESSQ',
            'upload_date': '20230209',
            'duration': 49,
            'age_limit': 0,
            'availability': 'public',
            'live_status': 'not_live',
            'playable_in_embed': True,
            'view_count': int,
            'like_count': int,
            'comment_count': int,
            'channel_follower_count': int,
            'thumbnail': 'https://i.ytimg.com/vi_webp/_ljssSoDLkw/maxresdefault.webp',
            'categories': ['People & Blogs'],
            'tags': 'count:27',
        },
    }]

    def _real_extract(self, url):
        display_id, is_youtube = self._match_valid_url(url).group('id', 'yt')
        if is_youtube:
            return self.url_result(display_id, YoutubeIE)

        webpage = self._download_webpage(url, display_id)
        video_id = self._search_regex(
            r'\bvideo_id\s*=\s*["\'](\d+)["\']\s*,', webpage, 'Brightcove ID')
        token = self._search_regex(r'\btoken\s*=\s*["\']([\w.-]+)["\']', webpage, 'token')

        player = extract_attributes(get_element_html_by_id('vcbrightcoveplayer', webpage) or '')
        account_id = player.get('data-account') or '6055873637001'
        player_id = player.get('data-player') or 'OtLKgXlO9F'
        embed = player.get('data-embed') or 'default'

        return self.url_result(smuggle_url(
            f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}',
            {'token': token}), BrightcoveNewIE)
Commit	Line	Data
44369c9a	1	from .brightcove import BrightcoveNewIE
44369c9a	2	from .common import InfoExtractor
43518503	3	from .theplatform import ThePlatformFeedIE
44369c9a	4	from .youtube import YoutubeIE
5c2266df	5	from ..utils import (
21dedcb5	6	ExtractorError,
44369c9a	7	extract_attributes,
44369c9a	8	get_element_html_by_id,
63c55e9f	9	int_or_none,
63c55e9f	10	find_xpath_attr,
44369c9a	11	smuggle_url,
45cae3b0 RA	12	xpath_element,
	13	xpath_text,
	14	update_url_query,
6e6e0d95	15	url_or_none,
5c2266df	16	)
fa3ae234 PH	17
fa3ae234 PH	18
6368e2e6	19	class CBSBaseIE(ThePlatformFeedIE): # XXX: Do not subclass from concrete IE
3e0c3d14	20	def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
180a9dff RA	21	subtitles = {}
	22	for k, ext in [('sMPTE-TTCCURL', 'tt'), ('ClosedCaptionURL', 'ttml'), ('webVTTCaptionURL', 'vtt')]:
	23	cc_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', k)
	24	if cc_e is not None:
	25	cc_url = cc_e.get('value')
	26	if cc_url:
	27	subtitles.setdefault(subtitles_lang, []).append({
	28	'ext': ext,
	29	'url': cc_url,
	30	})
	31	return subtitles
3e0c3d14	32
6e6e0d95	33	def _extract_common_video_info(self, content_id, asset_types, mpx_acc, extra_info):
	34	tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
	35	tp_release_url = f'https://link.theplatform.com/s/{tp_path}'
	36	info = self._extract_theplatform_metadata(tp_path, content_id)
	37
	38	formats, subtitles = [], {}
	39	last_e = None
	40	for asset_type, query in asset_types.items():
	41	try:
	42	tp_formats, tp_subtitles = self._extract_theplatform_smil(
	43	update_url_query(tp_release_url, query), content_id,
	44	'Downloading %s SMIL data' % asset_type)
	45	except ExtractorError as e:
	46	last_e = e
	47	if asset_type != 'fallback':
	48	continue
	49	query['formats'] = '' # blank query to check if expired
	50	try:
	51	tp_formats, tp_subtitles = self._extract_theplatform_smil(
	52	update_url_query(tp_release_url, query), content_id,
	53	'Downloading %s SMIL data, trying again with another format' % asset_type)
	54	except ExtractorError as e:
	55	last_e = e
	56	continue
	57	formats.extend(tp_formats)
	58	subtitles = self._merge_subtitles(subtitles, tp_subtitles)
	59	if last_e and not formats:
	60	self.raise_no_formats(last_e, True, content_id)
6e6e0d95	61
	62	extra_info.update({
	63	'id': content_id,
	64	'formats': formats,
	65	'subtitles': subtitles,
	66	})
	67	info.update({k: v for k, v in extra_info.items() if v is not None})
	68	return info
	69
	70	def _extract_video_info(self, args, *kwargs):
	71	# Extract assets + metadata and call _extract_common_video_info
	72	raise NotImplementedError('This method must be implemented by subclasses')
	73
	74	def _real_extract(self, url):
	75	return self._extract_video_info(self._match_id(url))
	76
3e0c3d14	77
3e0c3d14	78	class CBSIE(CBSBaseIE):
c755f190	79	_VALID_URL = r'''(?x)
	80	(?:
	81	cbs:\|
	82	https?://(?:www\.)?(?:
43c38abd	83	cbs\.com/(?:shows\|movies)/(?:video\|[^/]+/video\|[^/]+)/\|
c755f190	84	colbertlateshow\.com/(?:video\|podcasts)/)
c755f190	85	)(?P<id>[\w-]+)'''
fa3ae234	86
6e6e0d95	87	# All tests are blocked outside US
2871d489	88	_TESTS = [{
43c38abd	89	'url': 'https://www.cbs.com/shows/video/xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R/',
e42a692f	90	'info_dict': {
43c38abd	91	'id': 'xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R',
63c55e9f	92	'ext': 'mp4',
43c38abd S	93	'title': 'Tough As Nails - Dreams Never Die',
	94	'description': 'md5:a3535a62531cdd52b0364248a2c1ae33',
	95	'duration': 2588,
	96	'timestamp': 1639015200,
	97	'upload_date': '20211209',
79ba9140	98	'uploader': 'CBSI-NEW',
fa3ae234	99	},
dabe1570 RA	100	'params': {
	101	# m3u8 download
	102	'skip_download': True,
	103	},
68f5867c	104	}, {
43c38abd	105	'url': 'https://www.cbs.com/shows/video/sZH1MGgomIosZgxGJ1l263MFq16oMtW1/',
68f5867c	106	'info_dict': {
43c38abd S	107	'id': 'sZH1MGgomIosZgxGJ1l263MFq16oMtW1',
	108	'title': 'The Late Show - 3/16/22 (Michael Buble, Rose Matafeo)',
	109	'timestamp': 1647488100,
	110	'description': 'md5:d0e6ec23c544b7fa8e39a8e6844d2439',
68f5867c	111	'uploader': 'CBSI-NEW',
43c38abd	112	'upload_date': '20220317',
68f5867c L	113	},
	114	'params': {
	115	'ignore_no_formats_error': True,
	116	'skip_download': True,
	117	},
	118	'expected_warnings': [
	119	'This content expired on', 'No video formats found', 'Requested format is not available'],
9bf99891 S	120	}, {
	121	'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
	122	'only_matching': True,
	123	}, {
9d581f3d	124	'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
9bf99891	125	'only_matching': True,
2871d489	126	}]
dabe1570	127
96820c1c	128	def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
45cae3b0	129	items_data = self._download_xml(
2c736b4f	130	'https://can.cbs.com/thunder/player/videoPlayerService.php',
96820c1c	131	content_id, query={'partner': site, 'contentId': content_id})
45cae3b0	132	video_data = xpath_element(items_data, './/item')
430c2757	133	title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
45cae3b0	134
6e6e0d95	135	asset_types = {}
8f70b0b8	136	has_drm = False
45cae3b0 RA	137	for item in items_data.findall('.//item'):
45cae3b0 RA	138	asset_type = xpath_text(item, 'assetType')
45cae3b0 RA	139	query = {
	140	'mbr': 'true',
	141	'assetTypes': asset_type,
	142	}
68f5867c L	143	if not asset_type:
68f5867c L	144	# fallback for content_ids that videoPlayerService doesn't return anything for
68f5867c L	145	asset_type = 'fallback'
	146	query['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3'
	147	del query['assetTypes']
6e6e0d95	148	if asset_type in asset_types:
68f5867c L	149	continue
68f5867c L	150	elif any(excluded in asset_type for excluded in ('HLS_FPS', 'DASH_CENC', 'OnceURL')):
8f70b0b8	151	if 'DASH_CENC' in asset_type:
8f70b0b8	152	has_drm = True
68f5867c	153	continue
68f5867c	154	if asset_type.startswith('HLS') or 'StreamPack' in asset_type:
45cae3b0 RA	155	query['formats'] = 'MPEG4,M3U'
	156	elif asset_type in ('RTMP', 'WIFI', '3G'):
	157	query['formats'] = 'MPEG4,FLV'
6e6e0d95	158	asset_types[asset_type] = query
45cae3b0	159
8f70b0b8	160	if not asset_types and has_drm:
	161	self.report_drm(content_id)
	162
6e6e0d95	163	return self._extract_common_video_info(content_id, asset_types, mpx_acc, extra_info={
	164	'title': title,
	165	'series': xpath_text(video_data, 'seriesTitle'),
	166	'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
	167	'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
	168	'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
	169	'thumbnail': url_or_none(xpath_text(video_data, 'previewImageURL')),
dabe1570	170	})
44369c9a	171
	172
	173	class ParamountPressExpressIE(InfoExtractor):
	174	_VALID_URL = r'https?://(?:www\.)?paramountpressexpress\.com(?:/[\w-]+)+/(?P<yt>yt-)?video/?\?watch=(?P<id>[\w-]+)'
	175	_TESTS = [{
	176	'url': 'https://www.paramountpressexpress.com/cbs-entertainment/shows/survivor/video/?watch=pnzew7e2hx',
	177	'md5': '56631dbcadaab980d1fc47cb7b76cba4',
	178	'info_dict': {
	179	'id': '6322981580112',
	180	'ext': 'mp4',
	181	'title': 'I’m Felicia',
	182	'description': 'md5:88fad93f8eede1c9c8f390239e4c6290',
	183	'uploader_id': '6055873637001',
	184	'upload_date': '20230320',
	185	'timestamp': 1679334960,
	186	'duration': 49.557,
	187	'thumbnail': r're:^https://.+\.jpg',
	188	'tags': [],
	189	},
	190	}, {
	191	'url': 'https://www.paramountpressexpress.com/cbs-entertainment/video/?watch=2s5eh8kppc',
	192	'md5': 'edcb03e3210b88a3e56c05aa863e0e5b',
	193	'info_dict': {
	194	'id': '6323036027112',
	195	'ext': 'mp4',
	196	'title': '‘Y&R’ Set Visit: Jerry O’Connell Quizzes Cast on Pre-Love Scene Rituals and More',
	197	'description': 'md5:b929867a357aac5544b783d834c78383',
	198	'uploader_id': '6055873637001',
	199	'upload_date': '20230321',
	200	'timestamp': 1679430180,
	201	'duration': 132.032,
	202	'thumbnail': r're:^https://.+\.jpg',
	203	'tags': [],
	204	},
	205	}, {
	206	'url': 'https://www.paramountpressexpress.com/paramount-plus/yt-video/?watch=OX9wJWOcqck',
	207	'info_dict': {
	208	'id': 'OX9wJWOcqck',
	209	'ext': 'mp4',
	210	'title': 'Rugrats \| Season 2 Official Trailer \| Paramount+',
	211	'description': 'md5:1f7e26f5625a9f0d6564d9ad97a9f7de',
	212	'uploader': 'Paramount Plus',
	213	'uploader_id': '@paramountplus',
	214	'uploader_url': 'http://www.youtube.com/@paramountplus',
	215	'channel': 'Paramount Plus',
	216	'channel_id': 'UCrRttZIypNTA1Mrfwo745Sg',
	217	'channel_url': 'https://www.youtube.com/channel/UCrRttZIypNTA1Mrfwo745Sg',
	218	'upload_date': '20230316',
	219	'duration': 88,
	220	'age_limit': 0,
	221	'availability': 'public',
	222	'live_status': 'not_live',
	223	'playable_in_embed': True,
	224	'view_count': int,
	225	'like_count': int,
	226	'channel_follower_count': int,
	227	'thumbnail': 'https://i.ytimg.com/vi/OX9wJWOcqck/maxresdefault.jpg',
	228	'categories': ['Entertainment'],
	229	'tags': ['Rugrats'],
	230	},
	231	}, {
	232	'url': 'https://www.paramountpressexpress.com/showtime/yt-video/?watch=_ljssSoDLkw',
	233	'info_dict': {
	234	'id': '_ljssSoDLkw',
235	'ext': 'mp4',
236	'title': 'Lavell Crawford: THEE Lavell Crawford Comedy Special Official Trailer \| SHOWTIME',
237	'description': 'md5:39581bcc3fd810209b642609f448af70',
238	'uploader': 'SHOWTIME',
239	'uploader_id': '@Showtime',
240	'uploader_url': 'http://www.youtube.com/@Showtime',
241	'channel': 'SHOWTIME',
242	'channel_id': 'UCtwMWJr2BFPkuJTnSvCESSQ',
243	'channel_url': 'https://www.youtube.com/channel/UCtwMWJr2BFPkuJTnSvCESSQ',
244	'upload_date': '20230209',
245	'duration': 49,
246	'age_limit': 0,
247	'availability': 'public',
248	'live_status': 'not_live',
249	'playable_in_embed': True,
250	'view_count': int,
251	'like_count': int,
252	'comment_count': int,
253	'channel_follower_count': int,
254	'thumbnail': 'https://i.ytimg.com/vi_webp/_ljssSoDLkw/maxresdefault.webp',
255	'categories': ['People & Blogs'],
256	'tags': 'count:27',
257	},
258	}]
259
260	def _real_extract(self, url):
261	display_id, is_youtube = self._match_valid_url(url).group('id', 'yt')
262	if is_youtube:
263	return self.url_result(display_id, YoutubeIE)
264
265	webpage = self._download_webpage(url, display_id)
266	video_id = self._search_regex(
267	r'\bvideo_id\s=\s["\'](\d+)["\']\s*,', webpage, 'Brightcove ID')
268	token = self._search_regex(r'\btoken\s=\s["\']([\w.-]+)["\']', webpage, 'token')
269
270	player = extract_attributes(get_element_html_by_id('vcbrightcoveplayer', webpage) or '')
271	account_id = player.get('data-account') or '6055873637001'
272	player_id = player.get('data-player') or 'OtLKgXlO9F'
273	embed = player.get('data-embed') or 'default'
274
275	return self.url_result(smuggle_url(
276	f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}',
277	{'token': token}), BrightcoveNewIE)