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\d*/(?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 'url': 'http://www.tv2.no/v2/916509',
38 'only_matching': True,
40 _PROTOCOLS
= ('HLS', 'DASH')
41 _GEO_COUNTRIES
= ['NO']
43 def _real_extract(self
, url
):
44 video_id
= self
._match
_id
(url
)
45 asset
= self
._download
_json
('https://sumo.tv2.no/rest/assets/' + video_id
, video_id
,
46 'Downloading metadata JSON')
47 title
= asset
['title']
48 is_live
= asset
.get('live') is True
52 for protocol
in self
._PROTOCOLS
:
54 data
= self
._download
_json
('https://api.sumo.tv2.no/play/%s?stream=%s' % (video_id
, protocol
),
55 video_id
, 'Downloading playabck JSON',
56 headers
={'content-type': 'application/json'}
,
57 data
='{"device":{"id":"1-1-1","name":"Nettleser (HTML)"}}'.encode())['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
= data
.get('streams', [])
70 video_url
= item
.get('url')
71 if not video_url
or video_url
in format_urls
:
73 format_id
= '%s-%s' % (protocol
.lower(), item
.get('type'))
74 if not self
._is
_valid
_url
(video_url
, video_id
, format_id
):
76 format_urls
.append(video_url
)
77 ext
= determine_ext(video_url
)
79 formats
.extend(self
._extract
_f
4m
_formats
(
80 video_url
, video_id
, f4m_id
=format_id
, fatal
=False))
82 if not data
.get('drmProtected'):
83 formats
.extend(self
._extract
_m
3u8_formats
(
84 video_url
, video_id
, 'mp4',
85 'm3u8' if is_live
else 'm3u8_native',
86 m3u8_id
=format_id
, fatal
=False))
88 formats
.extend(self
._extract
_mpd
_formats
(
89 video_url
, video_id
, format_id
, fatal
=False))
90 elif ext
== 'ism' or video_url
.endswith('.ism/Manifest'):
95 'format_id': format_id
,
97 if not formats
and data
.get('drmProtected'):
98 self
.report_drm(video_id
)
99 self
._sort
_formats
(formats
)
104 } for type, thumb_url
in (asset
.get('images') or {}).items()]
110 'description': strip_or_none(asset
.get('description')),
111 'thumbnails': thumbnails
,
112 'timestamp': parse_iso8601(asset
.get('live_broadcast_time') or asset
.get('update_time')),
113 'duration': float_or_none(asset
.get('accurateDuration') or asset
.get('duration')),
114 'view_count': int_or_none(asset
.get('views')),
115 'categories': asset
.get('tags', '').split(','),
121 class TV2ArticleIE(InfoExtractor
):
122 _VALID_URL
= r
'https?://(?:www\.)?tv2\.no/(?:a|\d{4}/\d{2}/\d{2}(/[^/]+)+)/(?P<id>\d+)'
124 'url': 'http://www.tv2.no/2015/05/16/nyheter/alesund/krim/pingvin/6930542',
127 'title': 'Russen hetses etter pingvintyveri - innrømmer å ha åpnet luken på buret',
128 'description': 'De fire siktede nekter fortsatt for å ha stjålet pingvinbabyene, men innrømmer å ha åpnet luken til de små kyllingene.',
132 'url': 'http://www.tv2.no/a/6930542',
133 'only_matching': True,
136 def _real_extract(self
, url
):
137 playlist_id
= self
._match
_id
(url
)
139 webpage
= self
._download
_webpage
(url
, playlist_id
)
141 # Old embed pattern (looks unused nowadays)
142 assets
= re
.findall(r
'data-assetid=["\'](\d
+)', webpage)
146 for v in re.findall(r'(?s
)TV2ContentboxVideo\
(({.+?}
)\
)', webpage):
147 video = self._parse_json(
148 v, playlist_id, transform_source=js_to_json, fatal=False)
151 asset = video.get('assetId
')
156 self.url_result('http
://www
.tv2
.no
/v
/%s' % asset_id, 'TV2
')
157 for asset_id in assets]
159 title = remove_end(self._og_search_title(webpage), ' - TV2
.no
')
160 description = remove_end(self._og_search_description(webpage), ' - TV2
.no
')
162 return self.playlist_result(entries, playlist_id, title, description)
165 class KatsomoIE(InfoExtractor):
166 _VALID_URL = r'https?
://(?
:www\
.)?
(?
:katsomo|
mtv(uutiset
)?
)\
.fi
/(?
:sarja
/[0-9a
-z
-]+-\d
+/[0-9a
-z
-]+-|
(?
:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P<id>\d+)'
168 'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
172 'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle',
173 'description': 'Päätöksen teki Pelicansin hallitus.',
174 'timestamp': 1575116484,
175 'upload_date': '20191130',
182 'skip_download': True,
185 'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa',
186 'only_matching': True,
188 'url': 'https://www.mtvuutiset.fi/video/prog1311159',
189 'only_matching': True,
191 'url': 'https://www.katsomo.fi/#!/jakso/1311159',
192 'only_matching': True,
194 _API_DOMAIN
= 'api.katsomo.fi'
195 _PROTOCOLS
= ('HLS', 'MPD')
196 _GEO_COUNTRIES
= ['FI']
198 def _real_extract(self
, url
):
199 video_id
= self
._match
_id
(url
)
200 api_base
= 'http://%s/api/web/asset/%s' % (self
._API
_DOMAIN
, video_id
)
202 asset
= self
._download
_json
(
203 api_base
+ '.json', video_id
,
204 'Downloading metadata JSON')['asset']
205 title
= asset
.get('subtitle') or asset
['title']
206 is_live
= asset
.get('live') is True
210 for protocol
in self
._PROTOCOLS
:
212 data
= self
._download
_json
(
213 api_base
+ '/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % protocol
,
214 video_id
, 'Downloading play JSON')['playback']
215 except ExtractorError
as e
:
216 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
217 error
= self
._parse
_json
(e
.cause
.read().decode(), video_id
)['error']
218 error_code
= error
.get('code')
219 if error_code
== 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
220 self
.raise_geo_restricted(countries
=self
._GEO
_COUNTRIES
)
221 elif error_code
== 'SESSION_NOT_AUTHENTICATED':
222 self
.raise_login_required()
223 raise ExtractorError(error
['description'])
225 items
= try_get(data
, lambda x
: x
['items']['item'])
228 if not isinstance(items
, list):
231 if not isinstance(item
, dict):
233 video_url
= item
.get('url')
234 if not video_url
or video_url
in format_urls
:
236 format_id
= '%s-%s' % (protocol
.lower(), item
.get('mediaFormat'))
237 if not self
._is
_valid
_url
(video_url
, video_id
, format_id
):
239 format_urls
.append(video_url
)
240 ext
= determine_ext(video_url
)
242 formats
.extend(self
._extract
_f
4m
_formats
(
243 video_url
, video_id
, f4m_id
=format_id
, fatal
=False))
245 if not data
.get('drmProtected'):
246 formats
.extend(self
._extract
_m
3u8_formats
(
247 video_url
, video_id
, 'mp4',
248 'm3u8' if is_live
else 'm3u8_native',
249 m3u8_id
=format_id
, fatal
=False))
251 formats
.extend(self
._extract
_mpd
_formats
(
252 video_url
, video_id
, format_id
, fatal
=False))
253 elif ext
== 'ism' or video_url
.endswith('.ism/Manifest'):
258 'format_id': format_id
,
259 'tbr': int_or_none(item
.get('bitrate')),
260 'filesize': int_or_none(item
.get('fileSize')),
262 if not formats
and data
.get('drmProtected'):
263 self
.report_drm(video_id
)
264 self
._sort
_formats
(formats
)
267 'id': thumbnail
.get('@type'),
268 'url': thumbnail
.get('url'),
269 } for _
, thumbnail
in (asset
.get('imageVersions') or {}).items()]
275 'description': strip_or_none(asset
.get('description')),
276 'thumbnails': thumbnails
,
277 'timestamp': parse_iso8601(asset
.get('createTime')),
278 'duration': float_or_none(asset
.get('accurateDuration') or asset
.get('duration')),
279 'view_count': int_or_none(asset
.get('views')),
280 'categories': asset
.get('keywords', '').split(','),
286 class MTVUutisetArticleIE(InfoExtractor
):
287 _VALID_URL
= r
'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
289 'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',
293 'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
294 'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
295 'timestamp': 1600608966,
296 'upload_date': '20200920',
297 'duration': 153.7886666,
303 'skip_download': True,
306 # multiple Youtube embeds
307 'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962',
308 'only_matching': True,
311 def _real_extract(self
, url
):
312 article_id
= self
._match
_id
(url
)
313 article
= self
._download
_json
(
314 'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id
,
318 for video
in (article
.get('videos') or []):
319 video_type
= video
.get('videotype')
320 video_url
= video
.get('url')
321 if not (video_url
and video_type
in ('katsomo', 'youtube')):
323 yield self
.url_result(
324 video_url
, video_type
.capitalize(), video
.get('video_id'))
326 return self
.playlist_result(
327 entries(), article_id
, article
.get('title'), article
.get('description'))