2 from __future__ import unicode_literals
6 from .common import InfoExtractor
26 class TVPlayIE(InfoExtractor):
28 IE_DESC = 'MTG services'
35 tvplay(?:\.skaties)?\.lv/parraides|
36 (?:tv3play|play\.tv3)\.lt/programos|
37 tv3play(?:\.tv3)?\.ee/sisu|
38 (?:tv(?:3|6|8|10)play|viafree)\.se/program|
39 (?:(?:tv3play|viasat4play|tv6play|viafree)\.no|(?:tv3play|viafree)\.dk)/programmer|
40 play\.novatv\.bg/programi
48 'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
49 'md5': 'a1612fe0849455423ad8718fe049be21',
53 'title': 'Kādi ir īri? - Viņas melo labāk',
54 'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.',
55 'series': 'Viņas melo labāk',
59 'timestamp': 1406097056,
60 'upload_date': '20140723',
64 'url': 'http://play.tv3.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
68 'title': 'Moterys meluoja geriau',
69 'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
70 'series': 'Moterys meluoja geriau',
72 'season': '1 sezonas',
75 'timestamp': 1403769181,
76 'upload_date': '20140626',
80 'skip_download': True,
84 'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
88 'title': 'Kodu keset linna 398537',
89 'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
91 'timestamp': 1292449761,
92 'upload_date': '20101215',
96 'skip_download': True,
100 'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
104 'title': 'Husräddarna S02E07',
105 'description': 'md5:f210c6c89f42d4fc39faa551be813777',
107 'timestamp': 1400596321,
108 'upload_date': '20140520',
111 'skip_download': True,
115 'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
119 'title': 'Den sista dokusåpan S01E08',
120 'description': 'md5:295be39c872520221b933830f660b110',
122 'timestamp': 1330522854,
123 'upload_date': '20120229',
127 'skip_download': True,
131 'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
135 'title': 'Antikjakten S01E10',
136 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
138 'timestamp': 1348575868,
139 'upload_date': '20120925',
142 'skip_download': True,
146 'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
150 'title': 'Anna Anka søker assistent - Ep. 8',
151 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
153 'timestamp': 1277720005,
154 'upload_date': '20100628',
157 'skip_download': True,
161 'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
165 'title': 'Budbringerne program 10',
166 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
168 'timestamp': 1254205102,
169 'upload_date': '20090929',
172 'skip_download': True,
176 'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
180 'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
181 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
183 'timestamp': 1393236292,
184 'upload_date': '20140224',
187 'skip_download': True,
191 'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
195 'title': 'Здравей, България (12.06.2015 г.) ',
196 'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
198 'timestamp': 1434100372,
199 'upload_date': '20150612',
203 'skip_download': True,
207 'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
208 'only_matching': True,
212 'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
213 'only_matching': True,
216 'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
217 'only_matching': True,
220 'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
221 'only_matching': True,
225 'only_matching': True,
229 def _real_extract(self, url):
230 url, smuggled_data = unsmuggle_url(url, {})
231 self._initialize_geo_bypass({
232 'countries': smuggled_data.get('geo_countries'),
235 video_id = self._match_id(url)
236 geo_country = self._search_regex(
237 r'https?://[^/]+\.([a-z]{2})', url,
238 'geo country', default=None)
240 self._initialize_geo_bypass({'countries': [geo_country.upper()]})
241 video = self._download_json(
242 'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
244 title = video['title']
247 streams = self._download_json(
248 'http://playapi.mtgx.tv/v3/videos/stream/%s' % video_id,
249 video_id, 'Downloading streams JSON')
250 except ExtractorError as e:
251 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
252 msg = self._parse_json(e.cause.read().decode('utf-8'), video_id)
253 raise ExtractorError(msg['msg'], expected=True)
256 quality = qualities(['hls', 'medium', 'high'])
258 for format_id, video_url in streams.get('streams', {}).items():
259 video_url = url_or_none(video_url)
262 ext = determine_ext(video_url)
264 formats.extend(self._extract_f4m_formats(
265 update_url_query(video_url, {
267 'plugin': 'aasp-3.5.0.151.81'
268 }), video_id, f4m_id='hds', fatal=False))
270 formats.extend(self._extract_m3u8_formats(
271 video_url, video_id, 'mp4', 'm3u8_native',
272 m3u8_id='hls', fatal=False))
275 'format_id': format_id,
276 'quality': quality(format_id),
279 if video_url.startswith('rtmp'):
280 if smuggled_data.get('skip_rtmp'):
283 r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
288 'url': m.group('url'),
289 'app': m.group('app'),
290 'play_path': m.group('playpath'),
298 if not formats and video.get('is_geo_blocked'):
299 self.raise_geo_restricted(
300 'This content might not be available in your country due to copyright reasons')
302 self._sort_formats(formats)
304 # TODO: webvtt in m3u8
306 sami_path = video.get('sami_path')
308 lang = self._search_regex(
309 r'_([a-z]{2})\.xml', sami_path, 'lang',
310 default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
315 series = video.get('format_title')
316 episode_number = int_or_none(video.get('format_position', {}).get('episode'))
317 season = video.get('_embedded', {}).get('season', {}).get('title')
318 season_number = int_or_none(video.get('format_position', {}).get('season'))
323 'description': video.get('description'),
325 'episode_number': episode_number,
327 'season_number': season_number,
328 'duration': int_or_none(video.get('duration')),
329 'timestamp': parse_iso8601(video.get('created_at')),
330 'view_count': try_get(video, lambda x: x['views']['total'], int),
331 'age_limit': int_or_none(video.get('age_limit', 0)),
333 'subtitles': subtitles,
337 class ViafreeIE(InfoExtractor):
338 _VALID_URL = r'''(?x)
343 (?:dk|no)/programmer|
346 /(?:[^/]+/)+(?P<id>[^/?#&]+)
349 'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
353 'title': 'Husräddarna S02E02',
354 'description': 'md5:4db5c933e37db629b5a2f75dfb34829e',
355 'series': 'Husräddarna',
356 'season': 'Säsong 2',
359 'timestamp': 1400596321,
360 'upload_date': '20140520',
363 'skip_download': True,
365 'add_ie': [TVPlayIE.ie_key()],
368 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
372 'title': 'Sommaren med YouTube-stjärnorna S01E01',
373 'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
374 'series': 'Sommaren med YouTube-stjärnorna',
375 'season': 'Säsong 1',
378 'timestamp': 1470905572,
379 'upload_date': '20160811',
382 'skip_download': True,
384 'add_ie': [TVPlayIE.ie_key()],
386 # Different og:image URL schema
387 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
388 'only_matching': True,
390 'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
391 'only_matching': True,
393 'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
394 'only_matching': True,
398 def suitable(cls, url):
399 return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
401 def _real_extract(self, url):
402 video_id = self._match_id(url)
404 webpage = self._download_webpage(url, video_id)
406 data = self._parse_json(
408 r'(?s)window\.App\s*=\s*({.+?})\s*;\s*</script',
409 webpage, 'data', default='{}'),
410 video_id, transform_source=lambda x: re.sub(
411 r'(?s)function\s+[a-zA-Z_][\da-zA-Z_]*\s*\([^)]*\)\s*{[^}]*}\s*',
412 'null', x), fatal=False)
418 data, lambda x: x['context']['dispatcher']['stores'][
419 'ContentPageProgramStore']['currentVideo']['id'],
422 # Fallback #1 (extract from og:image URL schema)
424 thumbnail = self._og_search_thumbnail(webpage, default=None)
426 video_id = self._search_regex(
428 # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/inbox/765166/a2e95e5f1d735bab9f309fa345cc3f25.jpg
429 # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/seasons/15204/758770/4a5ba509ca8bc043e1ebd1a76131cdf2.jpg
430 r'https?://[^/]+/imagecache/(?:[^/]+/)+(\d{6,})/',
431 thumbnail, 'video id', default=None)
433 # Fallback #2. Extract from raw JSON string.
434 # May extract wrong video id if relatedClips is present.
436 video_id = self._search_regex(
437 r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
440 return self.url_result(
445 compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]],
446 # rtmp host mtgfs.fplive.net for viafree is unresolvable
449 ie=TVPlayIE.ie_key(), video_id=video_id)