[yt-dlp.git] / yt_dlp / extractor / tv2.py

import re

from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
    determine_ext,
    ExtractorError,
    int_or_none,
    float_or_none,
    js_to_json,
    parse_iso8601,
    remove_end,
    strip_or_none,
    try_get,
)


class TV2IE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?tv2\.no/v(?:ideo)?\d*/(?:[^?#]+/)*(?P<id>\d+)'
    _TESTS = [{
        'url': 'http://www.tv2.no/v/1791207/',
        'info_dict': {
            'id': '1791207',
            'ext': 'mp4',
            'title': 'Her kolliderer romsonden med asteroiden ',
            'description': 'En romsonde har krasjet inn i en asteroide i verdensrommet. Kollisjonen skjedde klokken 01:14 natt til tirsdag 27. september norsk tid. \n\nNasa kaller det sitt første forsøk på planetforsvar.',
            'timestamp': 1664238190,
            'upload_date': '20220927',
            'duration': 146,
            'thumbnail': r're:^https://.*$',
            'view_count': int,
            'categories': list,
        },
    }, {
        'url': 'http://www.tv2.no/v2/916509',
        'only_matching': True,
    }, {
        'url': 'https://www.tv2.no/video/nyhetene/her-kolliderer-romsonden-med-asteroiden/1791207/',
        'only_matching': True,
    }]
    _PROTOCOLS = ('HLS', 'DASH')
    _GEO_COUNTRIES = ['NO']

    def _real_extract(self, url):
        video_id = self._match_id(url)
        asset = self._download_json('https://sumo.tv2.no/rest/assets/' + video_id, video_id,
                                    'Downloading metadata JSON')
        title = asset['title']
        is_live = asset.get('live') is True

        formats = []
        format_urls = []
        for protocol in self._PROTOCOLS:
            try:
                data = self._download_json('https://api.sumo.tv2.no/play/%s?stream=%s' % (video_id, protocol),
                                           video_id, 'Downloading playabck JSON',
                                           headers={'content-type': 'application/json'},
                                           data='{"device":{"id":"1-1-1","name":"Nettleser (HTML)"}}'.encode())['playback']
            except ExtractorError as e:
                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
                    error = self._parse_json(e.cause.read().decode(), video_id)['error']
                    error_code = error.get('code')
                    if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
                        self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
                    elif error_code == 'SESSION_NOT_AUTHENTICATED':
                        self.raise_login_required()
                    raise ExtractorError(error['description'])
                raise
            items = data.get('streams', [])
            for item in items:
                video_url = item.get('url')
                if not video_url or video_url in format_urls:
                    continue
                format_id = '%s-%s' % (protocol.lower(), item.get('type'))
                if not self._is_valid_url(video_url, video_id, format_id):
                    continue
                format_urls.append(video_url)
                ext = determine_ext(video_url)
                if ext == 'f4m':
                    formats.extend(self._extract_f4m_formats(
                        video_url, video_id, f4m_id=format_id, fatal=False))
                elif ext == 'm3u8':
                    if not data.get('drmProtected'):
                        formats.extend(self._extract_m3u8_formats(
                            video_url, video_id, 'mp4', live=is_live, m3u8_id=format_id, fatal=False))
                elif ext == 'mpd':
                    formats.extend(self._extract_mpd_formats(
                        video_url, video_id, format_id, fatal=False))
                elif ext == 'ism' or video_url.endswith('.ism/Manifest'):
                    pass
                else:
                    formats.append({
                        'url': video_url,
                        'format_id': format_id,
                    })
        if not formats and data.get('drmProtected'):
            self.report_drm(video_id)

        thumbnails = [{
            'id': type,
            'url': thumb_url,
        } for type, thumb_url in (asset.get('images') or {}).items()]

        return {
            'id': video_id,
            'url': video_url,
            'title': title,
            'description': strip_or_none(asset.get('description')),
            'thumbnails': thumbnails,
            'timestamp': parse_iso8601(asset.get('live_broadcast_time') or asset.get('update_time')),
            'duration': float_or_none(asset.get('accurateDuration') or asset.get('duration')),
            'view_count': int_or_none(asset.get('views')),
            'categories': asset.get('tags', '').split(','),
            'formats': formats,
            'is_live': is_live,
        }


class TV2ArticleIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?tv2\.no/(?!v(?:ideo)?\d*/)[^?#]+/(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://www.tv2.no/underholdning/forraeder/katarina-flatland-angrer-etter-forraeder-exit/15095188/',
        'info_dict': {
            'id': '15095188',
            'title': 'Katarina Flatland angrer etter Forræder-exit',
            'description': 'SANDEFJORD (TV 2): Katarina Flatland (33) måtte følge i sine fars fotspor, da hun ble forvist fra Forræder.',
        },
        'playlist_count': 2,
    }, {
        'url': 'http://www.tv2.no/a/6930542',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(url, playlist_id)

        # Old embed pattern (looks unused nowadays)
        assets = re.findall(r'data-assetid=["\'](\d+)', webpage)

        if not assets:
            # New embed pattern
            for v in re.findall(r'(?s)(?:TV2ContentboxVideo|TV2\.TV2Video)\(({.+?})\)', webpage):
                video = self._parse_json(
                    v, playlist_id, transform_source=js_to_json, fatal=False)
                if not video:
                    continue
                asset = video.get('assetId')
                if asset:
                    assets.append(asset)

        entries = [
            self.url_result('http://www.tv2.no/v/%s' % asset_id, 'TV2')
            for asset_id in assets]

        title = remove_end(self._og_search_title(webpage), ' - TV2.no')
        description = remove_end(self._og_search_description(webpage), ' - TV2.no')

        return self.playlist_result(entries, playlist_id, title, description)


class KatsomoIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-|(?:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
        'info_dict': {
            'id': '1181321',
            'ext': 'mp4',
            'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle',
            'description': 'Päätöksen teki Pelicansin hallitus.',
            'timestamp': 1575116484,
            'upload_date': '20191130',
            'duration': 37.12,
            'view_count': int,
            'categories': list,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }, {
        'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa',
        'only_matching': True,
    }, {
        'url': 'https://www.mtvuutiset.fi/video/prog1311159',
        'only_matching': True,
    }, {
        'url': 'https://www.katsomo.fi/#!/jakso/1311159',
        'only_matching': True,
    }]
    _API_DOMAIN = 'api.katsomo.fi'
    _PROTOCOLS = ('HLS', 'MPD')
    _GEO_COUNTRIES = ['FI']

    def _real_extract(self, url):
        video_id = self._match_id(url)
        api_base = 'http://%s/api/web/asset/%s' % (self._API_DOMAIN, video_id)

        asset = self._download_json(
            api_base + '.json', video_id,
            'Downloading metadata JSON')['asset']
        title = asset.get('subtitle') or asset['title']
        is_live = asset.get('live') is True

        formats = []
        format_urls = []
        for protocol in self._PROTOCOLS:
            try:
                data = self._download_json(
                    api_base + '/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % protocol,
                    video_id, 'Downloading play JSON')['playback']
            except ExtractorError as e:
                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
                    error = self._parse_json(e.cause.read().decode(), video_id)['error']
                    error_code = error.get('code')
                    if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
                        self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
                    elif error_code == 'SESSION_NOT_AUTHENTICATED':
                        self.raise_login_required()
                    raise ExtractorError(error['description'])
                raise
            items = try_get(data, lambda x: x['items']['item'])
            if not items:
                continue
            if not isinstance(items, list):
                items = [items]
            for item in items:
                if not isinstance(item, dict):
                    continue
                video_url = item.get('url')
                if not video_url or video_url in format_urls:
                    continue
                format_id = '%s-%s' % (protocol.lower(), item.get('mediaFormat'))
                if not self._is_valid_url(video_url, video_id, format_id):
                    continue
                format_urls.append(video_url)
                ext = determine_ext(video_url)
                if ext == 'f4m':
                    formats.extend(self._extract_f4m_formats(
                        video_url, video_id, f4m_id=format_id, fatal=False))
                elif ext == 'm3u8':
                    if not data.get('drmProtected'):
                        formats.extend(self._extract_m3u8_formats(
                            video_url, video_id, 'mp4', live=is_live, m3u8_id=format_id, fatal=False))
                elif ext == 'mpd':
                    formats.extend(self._extract_mpd_formats(
                        video_url, video_id, format_id, fatal=False))
                elif ext == 'ism' or video_url.endswith('.ism/Manifest'):
                    pass
                else:
                    formats.append({
                        'url': video_url,
                        'format_id': format_id,
                        'tbr': int_or_none(item.get('bitrate')),
                        'filesize': int_or_none(item.get('fileSize')),
                    })
        if not formats and data.get('drmProtected'):
            self.report_drm(video_id)

        thumbnails = [{
            'id': thumbnail.get('@type'),
            'url': thumbnail.get('url'),
        } for _, thumbnail in (asset.get('imageVersions') or {}).items()]

        return {
            'id': video_id,
            'url': video_url,
            'title': title,
            'description': strip_or_none(asset.get('description')),
            'thumbnails': thumbnails,
            'timestamp': parse_iso8601(asset.get('createTime')),
            'duration': float_or_none(asset.get('accurateDuration') or asset.get('duration')),
            'view_count': int_or_none(asset.get('views')),
            'categories': asset.get('keywords', '').split(','),
            'formats': formats,
            'is_live': is_live,
        }


class MTVUutisetArticleIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',
        'info_dict': {
            'id': '1311159',
            'ext': 'mp4',
            'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
            'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
            'timestamp': 1600608966,
            'upload_date': '20200920',
            'duration': 153.7886666,
            'view_count': int,
            'categories': list,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }, {
        # multiple Youtube embeds
        'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        article_id = self._match_id(url)
        article = self._download_json(
            'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id,
            article_id)

        def entries():
            for video in (article.get('videos') or []):
                video_type = video.get('videotype')
                video_url = video.get('url')
                if not (video_url and video_type in ('katsomo', 'youtube')):
                    continue
                yield self.url_result(
                    video_url, video_type.capitalize(), video.get('video_id'))

        return self.playlist_result(
            entries(), article_id, article.get('title'), article.get('description'))
Commit	Line	Data
588b82bb S	1	import re
588b82bb S	2
bc0f937b	3	from .common import InfoExtractor
8d3a3a99	4	from ..compat import compat_HTTPError
bc0f937b S	5	from ..utils import (
bc0f937b S	6	determine_ext,
8d3a3a99	7	ExtractorError,
bc0f937b S	8	int_or_none,
bc0f937b S	9	float_or_none,
481c5c51	10	js_to_json,
bc0f937b	11	parse_iso8601,
588b82bb	12	remove_end,
8d3a3a99	13	strip_or_none,
9a621ddc	14	try_get,
bc0f937b S	15	)
	16
	17
	18	class TV2IE(InfoExtractor):
acf306d1	19	_VALID_URL = r'https?://(?:www\.)?tv2\.no/v(?:ideo)?\d/(?:[^?#]+/)(?P<id>\d+)'
2181983a	20	_TESTS = [{
acf306d1	21	'url': 'http://www.tv2.no/v/1791207/',
bc0f937b	22	'info_dict': {
acf306d1	23	'id': '1791207',
ea81966e	24	'ext': 'mp4',
acf306d1	25	'title': 'Her kolliderer romsonden med asteroiden ',
	26	'description': 'En romsonde har krasjet inn i en asteroide i verdensrommet. Kollisjonen skjedde klokken 01:14 natt til tirsdag 27. september norsk tid. \n\nNasa kaller det sitt første forsøk på planetforsvar.',
	27	'timestamp': 1664238190,
	28	'upload_date': '20220927',
	29	'duration': 146,
	30	'thumbnail': r're:^https://.*$',
bc0f937b S	31	'view_count': int,
bc0f937b S	32	'categories': list,
ed1a3905	33	},
e5d731f3	34	}, {
	35	'url': 'http://www.tv2.no/v2/916509',
	36	'only_matching': True,
acf306d1	37	}, {
	38	'url': 'https://www.tv2.no/video/nyhetene/her-kolliderer-romsonden-med-asteroiden/1791207/',
	39	'only_matching': True,
2181983a	40	}]
ea81966e	41	_PROTOCOLS = ('HLS', 'DASH')
8d3a3a99	42	_GEO_COUNTRIES = ['NO']
bc0f937b S	43
	44	def _real_extract(self, url):
	45	video_id = self._match_id(url)
ea81966e A	46	asset = self._download_json('https://sumo.tv2.no/rest/assets/' + video_id, video_id,
	47	'Downloading metadata JSON')
	48	title = asset['title']
2181983a	49	is_live = asset.get('live') is True
2181983a	50
bc0f937b S	51	formats = []
bc0f937b S	52	format_urls = []
8d3a3a99 RA	53	for protocol in self._PROTOCOLS:
8d3a3a99 RA	54	try:
ea81966e A	55	data = self._download_json('https://api.sumo.tv2.no/play/%s?stream=%s' % (video_id, protocol),
	56	video_id, 'Downloading playabck JSON',
	57	headers={'content-type': 'application/json'},
	58	data='{"device":{"id":"1-1-1","name":"Nettleser (HTML)"}}'.encode())['playback']
8d3a3a99 RA	59	except ExtractorError as e:
	60	if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
	61	error = self._parse_json(e.cause.read().decode(), video_id)['error']
	62	error_code = error.get('code')
	63	if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
	64	self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
	65	elif error_code == 'SESSION_NOT_AUTHENTICATED':
	66	self.raise_login_required()
	67	raise ExtractorError(error['description'])
	68	raise
ea81966e	69	items = data.get('streams', [])
9a621ddc	70	for item in items:
bc0f937b S	71	video_url = item.get('url')
	72	if not video_url or video_url in format_urls:
	73	continue
ea81966e	74	format_id = '%s-%s' % (protocol.lower(), item.get('type'))
bc0f937b S	75	if not self._is_valid_url(video_url, video_id, format_id):
	76	continue
	77	format_urls.append(video_url)
	78	ext = determine_ext(video_url)
	79	if ext == 'f4m':
	80	formats.extend(self._extract_f4m_formats(
dbc0b39b	81	video_url, video_id, f4m_id=format_id, fatal=False))
bc0f937b	82	elif ext == 'm3u8':
0b25af9b RA	83	if not data.get('drmProtected'):
0b25af9b RA	84	formats.extend(self._extract_m3u8_formats(
a5c0c202	85	video_url, video_id, 'mp4', live=is_live, m3u8_id=format_id, fatal=False))
8d3a3a99 RA	86	elif ext == 'mpd':
	87	formats.extend(self._extract_mpd_formats(
	88	video_url, video_id, format_id, fatal=False))
bc0f937b S	89	elif ext == 'ism' or video_url.endswith('.ism/Manifest'):
	90	pass
	91	else:
	92	formats.append({
	93	'url': video_url,
	94	'format_id': format_id,
bc0f937b	95	})
0b25af9b	96	if not formats and data.get('drmProtected'):
88acdbc2	97	self.report_drm(video_id)
bc0f937b	98
bc0f937b	99	thumbnails = [{
ea81966e A	100	'id': type,
	101	'url': thumb_url,
	102	} for type, thumb_url in (asset.get('images') or {}).items()]
bc0f937b S	103
	104	return {
	105	'id': video_id,
	106	'url': video_url,
39ca3b5c	107	'title': title,
8d3a3a99	108	'description': strip_or_none(asset.get('description')),
bc0f937b	109	'thumbnails': thumbnails,
ea81966e	110	'timestamp': parse_iso8601(asset.get('live_broadcast_time') or asset.get('update_time')),
8d3a3a99 RA	111	'duration': float_or_none(asset.get('accurateDuration') or asset.get('duration')),
8d3a3a99 RA	112	'view_count': int_or_none(asset.get('views')),
ea81966e	113	'categories': asset.get('tags', '').split(','),
bc0f937b	114	'formats': formats,
2181983a	115	'is_live': is_live,
bc0f937b	116	}
588b82bb S	117
	118
	119	class TV2ArticleIE(InfoExtractor):
acf306d1	120	_VALID_URL = r'https?://(?:www\.)?tv2\.no/(?!v(?:ideo)?\d*/)[^?#]+/(?P<id>\d+)'
588b82bb	121	_TESTS = [{
acf306d1	122	'url': 'https://www.tv2.no/underholdning/forraeder/katarina-flatland-angrer-etter-forraeder-exit/15095188/',
588b82bb	123	'info_dict': {
acf306d1	124	'id': '15095188',
	125	'title': 'Katarina Flatland angrer etter Forræder-exit',
	126	'description': 'SANDEFJORD (TV 2): Katarina Flatland (33) måtte følge i sine fars fotspor, da hun ble forvist fra Forræder.',
588b82bb S	127	},
	128	'playlist_count': 2,
	129	}, {
	130	'url': 'http://www.tv2.no/a/6930542',
	131	'only_matching': True,
	132	}]
	133
	134	def _real_extract(self, url):
	135	playlist_id = self._match_id(url)
	136
	137	webpage = self._download_webpage(url, playlist_id)
	138
481c5c51 S	139	# Old embed pattern (looks unused nowadays)
	140	assets = re.findall(r'data-assetid=["\'](\d+)', webpage)
	141
	142	if not assets:
	143	# New embed pattern
acf306d1	144	for v in re.findall(r'(?s)(?:TV2ContentboxVideo\|TV2\.TV2Video)\(({.+?})\)', webpage):
481c5c51 S	145	video = self._parse_json(
	146	v, playlist_id, transform_source=js_to_json, fatal=False)
	147	if not video:
	148	continue
	149	asset = video.get('assetId')
	150	if asset:
	151	assets.append(asset)
	152
588b82bb	153	entries = [
481c5c51 S	154	self.url_result('http://www.tv2.no/v/%s' % asset_id, 'TV2')
481c5c51 S	155	for asset_id in assets]
588b82bb S	156
	157	title = remove_end(self._og_search_title(webpage), ' - TV2.no')
	158	description = remove_end(self._og_search_description(webpage), ' - TV2.no')
	159
	160	return self.playlist_result(entries, playlist_id, title, description)
8d3a3a99 RA	161
8d3a3a99 RA	162
ea81966e	163	class KatsomoIE(InfoExtractor):
2181983a	164	_VALID_URL = r'https?://(?:www\.)?(?:katsomo\|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-\|(?:#!/)?jakso/(?:\d+/[^/]+/)?\|video/prog)(?P<id>\d+)'
2181983a	165	_TESTS = [{
8d3a3a99 RA	166	'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
	167	'info_dict': {
	168	'id': '1181321',
	169	'ext': 'mp4',
2181983a	170	'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle',
8d3a3a99 RA	171	'description': 'Päätöksen teki Pelicansin hallitus.',
	172	'timestamp': 1575116484,
	173	'upload_date': '20191130',
	174	'duration': 37.12,
	175	'view_count': int,
	176	'categories': list,
	177	},
	178	'params': {
	179	# m3u8 download
	180	'skip_download': True,
	181	},
2181983a	182	}, {
	183	'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa',
	184	'only_matching': True,
	185	}, {
	186	'url': 'https://www.mtvuutiset.fi/video/prog1311159',
	187	'only_matching': True,
	188	}, {
	189	'url': 'https://www.katsomo.fi/#!/jakso/1311159',
	190	'only_matching': True,
	191	}]
8d3a3a99 RA	192	_API_DOMAIN = 'api.katsomo.fi'
	193	_PROTOCOLS = ('HLS', 'MPD')
	194	_GEO_COUNTRIES = ['FI']
2181983a	195
ea81966e A	196	def _real_extract(self, url):
	197	video_id = self._match_id(url)
	198	api_base = 'http://%s/api/web/asset/%s' % (self._API_DOMAIN, video_id)
	199
	200	asset = self._download_json(
	201	api_base + '.json', video_id,
	202	'Downloading metadata JSON')['asset']
	203	title = asset.get('subtitle') or asset['title']
	204	is_live = asset.get('live') is True
	205
	206	formats = []
	207	format_urls = []
	208	for protocol in self._PROTOCOLS:
	209	try:
	210	data = self._download_json(
	211	api_base + '/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % protocol,
	212	video_id, 'Downloading play JSON')['playback']
	213	except ExtractorError as e:
	214	if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
	215	error = self._parse_json(e.cause.read().decode(), video_id)['error']
	216	error_code = error.get('code')
	217	if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
	218	self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
	219	elif error_code == 'SESSION_NOT_AUTHENTICATED':
	220	self.raise_login_required()
	221	raise ExtractorError(error['description'])
	222	raise
	223	items = try_get(data, lambda x: x['items']['item'])
	224	if not items:
	225	continue
	226	if not isinstance(items, list):
	227	items = [items]
	228	for item in items:
	229	if not isinstance(item, dict):
	230	continue
	231	video_url = item.get('url')
	232	if not video_url or video_url in format_urls:
	233	continue
	234	format_id = '%s-%s' % (protocol.lower(), item.get('mediaFormat'))
	235	if not self._is_valid_url(video_url, video_id, format_id):
	236	continue
	237	format_urls.append(video_url)
	238	ext = determine_ext(video_url)
	239	if ext == 'f4m':
	240	formats.extend(self._extract_f4m_formats(
	241	video_url, video_id, f4m_id=format_id, fatal=False))
	242	elif ext == 'm3u8':
	243	if not data.get('drmProtected'):
	244	formats.extend(self._extract_m3u8_formats(
a5c0c202	245	video_url, video_id, 'mp4', live=is_live, m3u8_id=format_id, fatal=False))
ea81966e A	246	elif ext == 'mpd':
	247	formats.extend(self._extract_mpd_formats(
	248	video_url, video_id, format_id, fatal=False))
	249	elif ext == 'ism' or video_url.endswith('.ism/Manifest'):
	250	pass
	251	else:
	252	formats.append({
	253	'url': video_url,
	254	'format_id': format_id,
	255	'tbr': int_or_none(item.get('bitrate')),
	256	'filesize': int_or_none(item.get('fileSize')),
	257	})
	258	if not formats and data.get('drmProtected'):
	259	self.report_drm(video_id)
ea81966e A	260
	261	thumbnails = [{
	262	'id': thumbnail.get('@type'),
	263	'url': thumbnail.get('url'),
	264	} for _, thumbnail in (asset.get('imageVersions') or {}).items()]
	265
	266	return {
	267	'id': video_id,
	268	'url': video_url,
39ca3b5c	269	'title': title,
ea81966e A	270	'description': strip_or_none(asset.get('description')),
	271	'thumbnails': thumbnails,
	272	'timestamp': parse_iso8601(asset.get('createTime')),
	273	'duration': float_or_none(asset.get('accurateDuration') or asset.get('duration')),
	274	'view_count': int_or_none(asset.get('views')),
	275	'categories': asset.get('keywords', '').split(','),
	276	'formats': formats,
	277	'is_live': is_live,
	278	}
	279
2181983a	280
	281	class MTVUutisetArticleIE(InfoExtractor):
	282	_VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
	283	_TESTS = [{
	284	'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',
	285	'info_dict': {
	286	'id': '1311159',
	287	'ext': 'mp4',
	288	'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
	289	'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
	290	'timestamp': 1600608966,
	291	'upload_date': '20200920',
	292	'duration': 153.7886666,
	293	'view_count': int,
	294	'categories': list,
	295	},
	296	'params': {
	297	# m3u8 download
	298	'skip_download': True,
	299	},
	300	}, {
	301	# multiple Youtube embeds
	302	'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962',
	303	'only_matching': True,
	304	}]
	305
	306	def _real_extract(self, url):
	307	article_id = self._match_id(url)
	308	article = self._download_json(
	309	'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id,
	310	article_id)
	311
	312	def entries():
	313	for video in (article.get('videos') or []):
	314	video_type = video.get('videotype')
	315	video_url = video.get('url')
	316	if not (video_url and video_type in ('katsomo', 'youtube')):
	317	continue
	318	yield self.url_result(
	319	video_url, video_type.capitalize(), video.get('video_id'))
	320
	321	return self.playlist_result(
	322	entries(), article_id, article.get('title'), article.get('description'))