2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
9 compat_urllib_parse_urlparse
,
23 class SVTBaseIE(InfoExtractor
):
24 _GEO_COUNTRIES
= ['SE']
26 def _extract_video(self
, video_info
, video_id
):
27 is_live
= dict_get(video_info
, ('live', 'simulcast'), default
=False)
28 m3u8_protocol
= 'm3u8' if is_live
else 'm3u8_native'
30 for vr
in video_info
['videoReferences']:
31 player_type
= vr
.get('playerType') or vr
.get('format')
33 ext
= determine_ext(vurl
)
35 formats
.extend(self
._extract
_m
3u8_formats
(
37 ext
='mp4', entry_protocol
=m3u8_protocol
,
38 m3u8_id
=player_type
, fatal
=False))
40 formats
.extend(self
._extract
_f
4m
_formats
(
41 vurl
+ '?hdcore=3.3.0', video_id
,
42 f4m_id
=player_type
, fatal
=False))
44 if player_type
== 'dashhbbtv':
45 formats
.extend(self
._extract
_mpd
_formats
(
46 vurl
, video_id
, mpd_id
=player_type
, fatal
=False))
49 'format_id': player_type
,
52 if not formats
and video_info
.get('rights', {}).get('geoBlockedSweden'):
53 self
.raise_geo_restricted(
54 'This video is only available in Sweden',
55 countries
=self
._GEO
_COUNTRIES
)
56 self
._sort
_formats
(formats
)
59 subtitle_references
= dict_get(video_info
, ('subtitles', 'subtitleReferences'))
60 if isinstance(subtitle_references
, list):
61 for sr
in subtitle_references
:
62 subtitle_url
= sr
.get('url')
63 subtitle_lang
= sr
.get('language', 'sv')
65 if determine_ext(subtitle_url
) == 'm3u8':
66 # TODO(yan12125): handle WebVTT in m3u8 manifests
69 subtitles
.setdefault(subtitle_lang
, []).append({'url': subtitle_url}
)
71 title
= video_info
.get('title')
73 series
= video_info
.get('programTitle')
74 season_number
= int_or_none(video_info
.get('season'))
75 episode
= video_info
.get('episodeTitle')
76 episode_number
= int_or_none(video_info
.get('episodeNumber'))
78 duration
= int_or_none(dict_get(video_info
, ('materialLength', 'contentDuration')))
81 video_info
, ('inappropriateForChildren', 'blockedForChildren'),
82 skip_false_values
=False)
84 age_limit
= 18 if adult
else 0
90 'subtitles': subtitles
,
92 'age_limit': age_limit
,
94 'season_number': season_number
,
96 'episode_number': episode_number
,
101 class SVTIE(SVTBaseIE
):
102 _VALID_URL
= r
'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
104 'url': 'http://www.svt.se/wd?widgetId=23991§ionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
105 'md5': '33e9a5d8f646523ce0868ecfb0eed77d',
109 'title': 'Stjärnorna skojar till det - under SVT-intervjun',
116 def _extract_url(webpage
):
118 r
'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % SVTIE
._VALID
_URL
, webpage
)
120 return mobj
.group('url')
122 def _real_extract(self
, url
):
123 mobj
= re
.match(self
._VALID
_URL
, url
)
124 widget_id
= mobj
.group('widget_id')
125 article_id
= mobj
.group('id')
127 info
= self
._download
_json
(
128 'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id
, article_id
),
131 info_dict
= self
._extract
_video
(info
['video'], article_id
)
132 info_dict
['title'] = info
['context']['title']
136 class SVTPlayBaseIE(SVTBaseIE
):
137 _SVTPLAY_RE
= r
'root\s*\[\s*(["\'])_
*svtplay\
1\s
*\
]\s
*=\s
*(?P
<json
>{.+?}
)\s
*;\s
*\n'
140 class SVTPlayIE(SVTPlayBaseIE):
141 IE_DESC = 'SVT Play
and Öppet arkiv
'
142 _VALID_URL = r'''(?x)
144 svt:(?P<svt_id>[^/?#&]+)|
145 https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)
149 'url
': 'http
://www
.svtplay
.se
/video
/5996901/flygplan
-till
-haile
-selassie
/flygplan
-till
-haile
-selassie
-2',
150 'md5
': '2b6704fe4a28801e1a098bbf3c5ac611
',
154 'title
': 'Flygplan till Haile Selassie
',
156 'thumbnail
': r're
:^https?
://.*[\
.-]jpg$
',
165 # geo restricted to Sweden
166 'url
': 'http
://www
.oppetarkiv
.se
/video
/5219710/trollflojten
',
167 'only_matching
': True,
169 'url
': 'http
://www
.svtplay
.se
/klipp
/9023742/stopptid
-om
-bjorn
-borg
',
170 'only_matching
': True,
172 'url
': 'https
://www
.svtplay
.se
/kanaler
/svt1
',
173 'only_matching
': True,
175 'url
': 'svt
:1376446-003A
',
176 'only_matching
': True,
178 'url
': 'svt
:14278044',
179 'only_matching
': True,
182 def _adjust_title(self, info):
184 info['title
'] = self._live_title(info['title
'])
186 def _extract_by_video_id(self, video_id, webpage=None):
187 data = self._download_json(
188 'https
://api
.svt
.se
/videoplayer
-api
/video
/%s' % video_id,
189 video_id, headers=self.geo_verification_headers())
190 info_dict = self._extract_video(data, video_id)
191 if not info_dict.get('title
'):
192 title = dict_get(info_dict, ('episode
', 'series
'))
193 if not title and webpage:
195 r'\s
*\|\s
*.+?$
', '', self._og_search_title(webpage))
198 info_dict['title
'] = title
199 self._adjust_title(info_dict)
202 def _real_extract(self, url):
203 mobj = re.match(self._VALID_URL, url)
204 video_id, svt_id = mobj.group('id', 'svt_id
')
207 return self._extract_by_video_id(svt_id)
209 webpage = self._download_webpage(url, video_id)
211 data = self._parse_json(
213 self._SVTPLAY_RE, webpage, 'embedded data
', default='{}',
215 video_id, fatal=False)
217 thumbnail = self._og_search_thumbnail(webpage)
220 video_info = try_get(
221 data, lambda x: x['context
']['dispatcher
']['stores
']['VideoTitlePageStore
']['data
']['video
'],
224 info_dict = self._extract_video(video_info, video_id)
226 'title
': data['context
']['dispatcher
']['stores
']['MetaStore
']['title
'],
227 'thumbnail
': thumbnail,
229 self._adjust_title(info_dict)
232 svt_id = self._search_regex(
233 r'<video
[^
>]+data
-video
-id=["\']([\da-zA-Z-]+)',
236 return self._extract_by_video_id(svt_id, webpage)
239 class SVTSeriesIE(SVTPlayBaseIE):
240 _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)'
242 'url': 'https://www.svtplay.se/rederiet',
246 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
248 'playlist_mincount': 318,
250 'url': 'https://www.svtplay.se/rederiet?tab=sasong2',
252 'id': 'rederiet-sasong2',
253 'title': 'Rederiet - Säsong 2',
254 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
256 'playlist_count': 12,
260 def suitable(cls, url):
261 return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url)
263 def _real_extract(self, url):
264 series_id = self._match_id(url)
266 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
267 season_slug = qs.get('tab', [None])[0]
270 series_id += '-%s' % season_slug
272 webpage = self._download_webpage(
273 url, series_id, 'Downloading series page')
275 root = self._parse_json(
277 self._SVTPLAY_RE, webpage, 'content', group='json'),
283 for season in root['relatedVideoContent']['relatedVideosAccordion']:
284 if not isinstance(season, dict):
287 if season.get('slug') != season_slug:
289 season_name = season.get('name')
290 videos = season.get('videos')
291 if not isinstance(videos, list):
294 content_url = video.get('contentUrl')
295 if not content_url or not isinstance(content_url, compat_str):
299 urljoin(url, content_url),
300 ie=SVTPlayIE.ie_key(),
301 video_title=video.get('title')
304 metadata = root.get('metaData')
305 if not isinstance(metadata, dict):
308 title = metadata.get('title')
309 season_name = season_name or season_slug
311 if title and season_name:
312 title = '%s - %s' % (title, season_name)
316 return self.playlist_result(
317 entries, series_id, title, metadata.get('description'))
320 class SVTPageIE(InfoExtractor):
321 _VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P<id>[^/?&#]+)'
323 'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
325 'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
326 'title': 'GUIDE: Sommarträning du kan göra var och när du vill',
330 'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
332 'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
333 'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”',
338 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
342 'title': 'Stjärnorna skojar till det - under SVT-intervjun',
347 'url': 'https://www.svt.se/nyheter/lokalt/vast/svt-testar-tar-nagon-upp-skrapet-1',
348 'only_matching': True,
350 'url': 'https://www.svt.se/vader/manadskronikor/maj2018',
351 'only_matching': True,
355 def suitable(cls, url):
356 return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
358 def _real_extract(self, url):
359 playlist_id = self._match_id(url)
361 webpage = self._download_webpage(url, playlist_id)
365 'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id)
366 for video_id in orderedSet(re.findall(
367 r'data-video-id=["\'](\d
+)', webpage))]
369 title = strip_or_none(self._og_search_title(webpage, default=None))
371 return self.playlist_result(entries, playlist_id, title)