2 from __future__ import unicode_literals
6 from .common import InfoExtractor
17 class SVTBaseIE(InfoExtractor):
18 _GEO_COUNTRIES = ['SE']
20 def _extract_video(self, video_info, video_id):
22 for vr in video_info['videoReferences']:
23 player_type = vr.get('playerType') or vr.get('format')
25 ext = determine_ext(vurl)
27 formats.extend(self._extract_m3u8_formats(
29 ext='mp4', entry_protocol='m3u8_native',
30 m3u8_id=player_type, fatal=False))
32 formats.extend(self._extract_f4m_formats(
33 vurl + '?hdcore=3.3.0', video_id,
34 f4m_id=player_type, fatal=False))
36 if player_type == 'dashhbbtv':
37 formats.extend(self._extract_mpd_formats(
38 vurl, video_id, mpd_id=player_type, fatal=False))
41 'format_id': player_type,
44 if not formats and video_info.get('rights', {}).get('geoBlockedSweden'):
45 self.raise_geo_restricted(
46 'This video is only available in Sweden',
47 countries=self._GEO_COUNTRIES)
48 self._sort_formats(formats)
51 subtitle_references = dict_get(video_info, ('subtitles', 'subtitleReferences'))
52 if isinstance(subtitle_references, list):
53 for sr in subtitle_references:
54 subtitle_url = sr.get('url')
55 subtitle_lang = sr.get('language', 'sv')
57 if determine_ext(subtitle_url) == 'm3u8':
58 # TODO(yan12125): handle WebVTT in m3u8 manifests
61 subtitles.setdefault(subtitle_lang, []).append({'url': subtitle_url})
63 title = video_info.get('title')
65 series = video_info.get('programTitle')
66 season_number = int_or_none(video_info.get('season'))
67 episode = video_info.get('episodeTitle')
68 episode_number = int_or_none(video_info.get('episodeNumber'))
70 duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration')))
73 video_info, ('inappropriateForChildren', 'blockedForChildren'),
74 skip_false_values=False)
76 age_limit = 18 if adult else 0
82 'subtitles': subtitles,
84 'age_limit': age_limit,
86 'season_number': season_number,
88 'episode_number': episode_number,
92 class SVTIE(SVTBaseIE):
93 _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
95 'url': 'http://www.svt.se/wd?widgetId=23991§ionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
96 'md5': '33e9a5d8f646523ce0868ecfb0eed77d',
100 'title': 'Stjärnorna skojar till det - under SVT-intervjun',
107 def _extract_url(webpage):
109 r'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % SVTIE._VALID_URL, webpage)
111 return mobj.group('url')
113 def _real_extract(self, url):
114 mobj = re.match(self._VALID_URL, url)
115 widget_id = mobj.group('widget_id')
116 article_id = mobj.group('id')
118 info = self._download_json(
119 'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id),
122 info_dict = self._extract_video(info['video'], article_id)
123 info_dict['title'] = info['context']['title']
127 class SVTPlayIE(SVTBaseIE):
128 IE_DESC = 'SVT Play and Öppet arkiv'
129 _VALID_URL = r'https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp)/(?P<id>[0-9]+)'
131 'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
132 'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
136 'title': 'Flygplan till Haile Selassie',
138 'thumbnail': r're:^https?://.*[\.-]jpg$',
147 # geo restricted to Sweden
148 'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
149 'only_matching': True,
151 'url': 'http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg',
152 'only_matching': True,
155 def _real_extract(self, url):
156 video_id = self._match_id(url)
158 webpage = self._download_webpage(url, video_id)
160 data = self._parse_json(
162 r'root\["__svtplay"\]\s*=\s*([^;]+);',
163 webpage, 'embedded data', default='{}'),
164 video_id, fatal=False)
166 thumbnail = self._og_search_thumbnail(webpage)
169 video_info = try_get(
170 data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'],
173 info_dict = self._extract_video(video_info, video_id)
175 'title': data['context']['dispatcher']['stores']['MetaStore']['title'],
176 'thumbnail': thumbnail,
180 video_id = self._search_regex(
181 r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
182 webpage, 'video id', default=None)
185 data = self._download_json(
186 'https://api.svt.se/videoplayer-api/video/%s' % video_id,
187 video_id, headers=self.geo_verification_headers())
188 info_dict = self._extract_video(data, video_id)
189 if not info_dict.get('title'):
190 info_dict['title'] = re.sub(
192 info_dict.get('episode') or self._og_search_title(webpage))
196 class SVTSeriesIE(InfoExtractor):
197 _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)'
199 'url': 'https://www.svtplay.se/rederiet',
203 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
205 'playlist_mincount': 318,
209 def suitable(cls, url):
210 return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url)
212 def _real_extract(self, url):
213 video_id = self._match_id(url)
215 webpage = self._download_webpage(
216 url, video_id, 'Downloading serie page')
218 root = self._parse_json(
220 r'root\[\s*(["\'])_*svtplay\1\s*\]\s*=\s*(?P<json>{.+?})\s*;\s*\n',
221 webpage, 'content', group='json'),
225 for season in root['relatedVideoContent']['relatedVideosAccordion']:
226 videos = season.get('videos')
227 if not isinstance(videos, list):
230 content_url = video.get('contentUrl')
231 if not content_url or not isinstance(content_url, compat_str):
235 urljoin(url, content_url),
236 ie=SVTPlayIE.ie_key(),
237 video_title=video.get('title')
240 metadata = root.get('metaData')
241 if not isinstance(metadata, dict):
244 return self.playlist_result(
245 entries, video_id, metadata.get('title'),
246 metadata.get('description'))