]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/tv2.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_HTTPError
21 class TV2IE(InfoExtractor
):
22 _VALID_URL
= r
'https?://(?:www\.)?tv2\.no/v/(?P<id>\d+)'
24 'url': 'http://www.tv2.no/v/916509/',
28 'title': 'Se Frode Gryttens hyllest av Steven Gerrard',
29 'description': 'TV 2 Sportens huspoet tar avskjed med Liverpools kaptein Steven Gerrard.',
30 'timestamp': 1431715610,
31 'upload_date': '20150515',
37 _API_DOMAIN
= 'sumo.tv2.no'
38 _PROTOCOLS
= ('HDS', 'HLS', 'DASH')
39 _GEO_COUNTRIES
= ['NO']
41 def _real_extract(self
, url
):
42 video_id
= self
._match
_id
(url
)
43 api_base
= 'http://%s/api/web/asset/%s' % (self
._API
_DOMAIN
, video_id
)
45 asset
= self
._download
_json
(
46 api_base
+ '.json', video_id
,
47 'Downloading metadata JSON')['asset']
48 title
= asset
.get('subtitle') or asset
['title']
49 is_live
= asset
.get('live') is True
53 for protocol
in self
._PROTOCOLS
:
55 data
= self
._download
_json
(
56 api_base
+ '/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % protocol
,
57 video_id
, 'Downloading play JSON')['playback']
58 except ExtractorError
as e
:
59 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
60 error
= self
._parse
_json
(e
.cause
.read().decode(), video_id
)['error']
61 error_code
= error
.get('code')
62 if error_code
== 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
63 self
.raise_geo_restricted(countries
=self
._GEO
_COUNTRIES
)
64 elif error_code
== 'SESSION_NOT_AUTHENTICATED':
65 self
.raise_login_required()
66 raise ExtractorError(error
['description'])
68 items
= try_get(data
, lambda x
: x
['items']['item'])
71 if not isinstance(items
, list):
74 if not isinstance(item
, dict):
76 video_url
= item
.get('url')
77 if not video_url
or video_url
in format_urls
:
79 format_id
= '%s-%s' % (protocol
.lower(), item
.get('mediaFormat'))
80 if not self
._is
_valid
_url
(video_url
, video_id
, format_id
):
82 format_urls
.append(video_url
)
83 ext
= determine_ext(video_url
)
85 formats
.extend(self
._extract
_f
4m
_formats
(
86 video_url
, video_id
, f4m_id
=format_id
, fatal
=False))
88 if not data
.get('drmProtected'):
89 formats
.extend(self
._extract
_m
3u8_formats
(
90 video_url
, video_id
, 'mp4',
91 'm3u8' if is_live
else 'm3u8_native',
92 m3u8_id
=format_id
, fatal
=False))
94 formats
.extend(self
._extract
_mpd
_formats
(
95 video_url
, video_id
, format_id
, fatal
=False))
96 elif ext
== 'ism' or video_url
.endswith('.ism/Manifest'):
101 'format_id': format_id
,
102 'tbr': int_or_none(item
.get('bitrate')),
103 'filesize': int_or_none(item
.get('fileSize')),
105 if not formats
and data
.get('drmProtected'):
106 self
.raise_no_formats('This video is DRM protected.', expected
=True)
107 self
._sort
_formats
(formats
)
110 'id': thumbnail
.get('@type'),
111 'url': thumbnail
.get('url'),
112 } for _
, thumbnail
in (asset
.get('imageVersions') or {}).items()]
117 'title': self
._live
_title
(title
) if is_live
else title
,
118 'description': strip_or_none(asset
.get('description')),
119 'thumbnails': thumbnails
,
120 'timestamp': parse_iso8601(asset
.get('createTime')),
121 'duration': float_or_none(asset
.get('accurateDuration') or asset
.get('duration')),
122 'view_count': int_or_none(asset
.get('views')),
123 'categories': asset
.get('keywords', '').split(','),
129 class TV2ArticleIE(InfoExtractor
):
130 _VALID_URL
= r
'https?://(?:www\.)?tv2\.no/(?:a|\d{4}/\d{2}/\d{2}(/[^/]+)+)/(?P<id>\d+)'
132 'url': 'http://www.tv2.no/2015/05/16/nyheter/alesund/krim/pingvin/6930542',
135 'title': 'Russen hetses etter pingvintyveri - innrømmer å ha åpnet luken på buret',
136 'description': 'De fire siktede nekter fortsatt for å ha stjålet pingvinbabyene, men innrømmer å ha åpnet luken til de små kyllingene.',
140 'url': 'http://www.tv2.no/a/6930542',
141 'only_matching': True,
144 def _real_extract(self
, url
):
145 playlist_id
= self
._match
_id
(url
)
147 webpage
= self
._download
_webpage
(url
, playlist_id
)
149 # Old embed pattern (looks unused nowadays)
150 assets
= re
.findall(r
'data-assetid=["\'](\d
+)', webpage)
154 for v in re.findall(r'(?s
)TV2ContentboxVideo\
(({.+?}
)\
)', webpage):
155 video = self._parse_json(
156 v, playlist_id, transform_source=js_to_json, fatal=False)
159 asset = video.get('assetId
')
164 self.url_result('http
://www
.tv2
.no
/v
/%s' % asset_id, 'TV2
')
165 for asset_id in assets]
167 title = remove_end(self._og_search_title(webpage), ' - TV2
.no
')
168 description = remove_end(self._og_search_description(webpage), ' - TV2
.no
')
170 return self.playlist_result(entries, playlist_id, title, description)
173 class KatsomoIE(TV2IE):
174 _VALID_URL = r'https?
://(?
:www\
.)?
(?
:katsomo|
mtv(uutiset
)?
)\
.fi
/(?
:sarja
/[0-9a
-z
-]+-\d
+/[0-9a
-z
-]+-|
(?
:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P<id>\d+)'
176 'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
180 'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle',
181 'description': 'Päätöksen teki Pelicansin hallitus.',
182 'timestamp': 1575116484,
183 'upload_date': '20191130',
190 'skip_download': True,
193 'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa',
194 'only_matching': True,
196 'url': 'https://www.mtvuutiset.fi/video/prog1311159',
197 'only_matching': True,
199 'url': 'https://www.katsomo.fi/#!/jakso/1311159',
200 'only_matching': True,
202 _API_DOMAIN
= 'api.katsomo.fi'
203 _PROTOCOLS
= ('HLS', 'MPD')
204 _GEO_COUNTRIES
= ['FI']
207 class MTVUutisetArticleIE(InfoExtractor
):
208 _VALID_URL
= r
'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
210 'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',
214 'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
215 'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
216 'timestamp': 1600608966,
217 'upload_date': '20200920',
218 'duration': 153.7886666,
224 'skip_download': True,
227 # multiple Youtube embeds
228 'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962',
229 'only_matching': True,
232 def _real_extract(self
, url
):
233 article_id
= self
._match
_id
(url
)
234 article
= self
._download
_json
(
235 'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id
,
239 for video
in (article
.get('videos') or []):
240 video_type
= video
.get('videotype')
241 video_url
= video
.get('url')
242 if not (video_url
and video_type
in ('katsomo', 'youtube')):
244 yield self
.url_result(
245 video_url
, video_type
.capitalize(), video
.get('video_id'))
247 return self
.playlist_result(
248 entries(), article_id
, article
.get('title'), article
.get('description'))