]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tvplay.py
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\.nova(?:tv)?\.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': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
208 'only_matching': True,
211 'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
212 'only_matching': True,
215 'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true',
216 'only_matching': True,
220 'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
221 'only_matching': True,
224 'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
225 'only_matching': True,
228 'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
229 'only_matching': True,
233 'only_matching': True,
237 def _real_extract(self
, url
):
238 url
, smuggled_data
= unsmuggle_url(url
, {})
239 self
._initialize
_geo
_bypass
({
240 'countries': smuggled_data
.get('geo_countries'),
243 video_id
= self
._match
_id
(url
)
244 geo_country
= self
._search
_regex
(
245 r
'https?://[^/]+\.([a-z]{2})', url
,
246 'geo country', default
=None)
248 self
._initialize
_geo
_bypass
({'countries': [geo_country
.upper()]})
249 video
= self
._download
_json
(
250 'http://playapi.mtgx.tv/v3/videos/%s' % video_id
, video_id
, 'Downloading video JSON')
252 title
= video
['title']
255 streams
= self
._download
_json
(
256 'http://playapi.mtgx.tv/v3/videos/stream/%s' % video_id
,
257 video_id
, 'Downloading streams JSON')
258 except ExtractorError
as e
:
259 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 403:
260 msg
= self
._parse
_json
(e
.cause
.read().decode('utf-8'), video_id
)
261 raise ExtractorError(msg
['msg'], expected
=True)
264 quality
= qualities(['hls', 'medium', 'high'])
266 for format_id
, video_url
in streams
.get('streams', {}).items():
267 video_url
= url_or_none(video_url
)
270 ext
= determine_ext(video_url
)
272 formats
.extend(self
._extract
_f
4m
_formats
(
273 update_url_query(video_url
, {
275 'plugin': 'aasp-3.5.0.151.81'
276 }), video_id
, f4m_id
='hds', fatal
=False))
278 formats
.extend(self
._extract
_m
3u8_formats
(
279 video_url
, video_id
, 'mp4', 'm3u8_native',
280 m3u8_id
='hls', fatal
=False))
283 'format_id': format_id
,
284 'quality': quality(format_id
),
287 if video_url
.startswith('rtmp'):
288 if smuggled_data
.get('skip_rtmp'):
291 r
'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url
)
296 'url': m
.group('url'),
297 'app': m
.group('app'),
298 'play_path': m
.group('playpath'),
307 if not formats
and video
.get('is_geo_blocked'):
308 self
.raise_geo_restricted(
309 'This content might not be available in your country due to copyright reasons')
311 self
._sort
_formats
(formats
)
313 # TODO: webvtt in m3u8
315 sami_path
= video
.get('sami_path')
317 lang
= self
._search
_regex
(
318 r
'_([a-z]{2})\.xml', sami_path
, 'lang',
319 default
=compat_urlparse
.urlparse(url
).netloc
.rsplit('.', 1)[-1])
324 series
= video
.get('format_title')
325 episode_number
= int_or_none(video
.get('format_position', {}).get('episode'))
326 season
= video
.get('_embedded', {}).get('season', {}).get('title')
327 season_number
= int_or_none(video
.get('format_position', {}).get('season'))
332 'description': video
.get('description'),
334 'episode_number': episode_number
,
336 'season_number': season_number
,
337 'duration': int_or_none(video
.get('duration')),
338 'timestamp': parse_iso8601(video
.get('created_at')),
339 'view_count': try_get(video
, lambda x
: x
['views']['total'], int),
340 'age_limit': int_or_none(video
.get('age_limit', 0)),
342 'subtitles': subtitles
,
346 class ViafreeIE(InfoExtractor
):
347 _VALID_URL
= r
'''(?x)
352 (?:dk|no)/programmer|
355 /(?:[^/]+/)+(?P<id>[^/?#&]+)
358 'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
362 'title': 'Husräddarna S02E02',
363 'description': 'md5:4db5c933e37db629b5a2f75dfb34829e',
364 'series': 'Husräddarna',
365 'season': 'Säsong 2',
368 'timestamp': 1400596321,
369 'upload_date': '20140520',
372 'skip_download': True,
374 'add_ie': [TVPlayIE
.ie_key()],
377 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
381 'title': 'Sommaren med YouTube-stjärnorna S01E01',
382 'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
383 'series': 'Sommaren med YouTube-stjärnorna',
384 'season': 'Säsong 1',
387 'timestamp': 1470905572,
388 'upload_date': '20160811',
391 'skip_download': True,
393 'add_ie': [TVPlayIE
.ie_key()],
395 # Different og:image URL schema
396 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
397 'only_matching': True,
399 'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
400 'only_matching': True,
402 'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
403 'only_matching': True,
407 def suitable(cls
, url
):
408 return False if TVPlayIE
.suitable(url
) else super(ViafreeIE
, cls
).suitable(url
)
410 def _real_extract(self
, url
):
411 video_id
= self
._match
_id
(url
)
413 webpage
= self
._download
_webpage
(url
, video_id
)
415 data
= self
._parse
_json
(
417 r
'(?s)window\.App\s*=\s*({.+?})\s*;\s*</script',
418 webpage
, 'data', default
='{}'),
419 video_id
, transform_source
=lambda x
: re
.sub(
420 r
'(?s)function\s+[a-zA-Z_][\da-zA-Z_]*\s*\([^)]*\)\s*{[^}]*}\s*',
421 'null', x
), fatal
=False)
427 data
, lambda x
: x
['context']['dispatcher']['stores'][
428 'ContentPageProgramStore']['currentVideo']['id'],
431 # Fallback #1 (extract from og:image URL schema)
433 thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
435 video_id
= self
._search
_regex
(
437 # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/inbox/765166/a2e95e5f1d735bab9f309fa345cc3f25.jpg
438 # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/seasons/15204/758770/4a5ba509ca8bc043e1ebd1a76131cdf2.jpg
439 r
'https?://[^/]+/imagecache/(?:[^/]+/)+(\d{6,})/',
440 thumbnail
, 'video id', default
=None)
442 # Fallback #2. Extract from raw JSON string.
443 # May extract wrong video id if relatedClips is present.
445 video_id
= self
._search
_regex
(
446 r
'currentVideo["\']\s
*:\s
*.+?
["\']id["\']\s
*:\s
*["\'](\d{6,})',
449 return self.url_result(
454 compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]],
455 # rtmp host mtgfs.fplive.net for viafree is unresolvable
458 ie=TVPlayIE.ie_key(), video_id=video_id)
461 class TVPlayHomeIE(InfoExtractor):
462 _VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)'
464 'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
468 'title': 'Aferistai',
469 'description': 'Aferistai. Kalėdinė pasaka.',
470 'series': 'Aferistai [N-7]',
471 'season': '1 sezonas',
474 'timestamp': 1394209658,
475 'upload_date': '20140307',
479 'skip_download': True,
481 'add_ie': [TVPlayIE.ie_key()],
483 'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
484 'only_matching': True,
486 'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
487 'only_matching': True,
490 def _real_extract(self, url):
491 video_id = self._match_id(url)
493 webpage = self._download_webpage(url, video_id)
495 video_id = self._search_regex(
496 r'data-asset-id\s*=\s*["\'](\d
{5,})\b', webpage, 'video
id')
498 if len(video_id) < 8:
499 return self.url_result(
500 'mtg
:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
502 m3u8_url = self._search_regex(
503 r'data
-file\s
*=\s
*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
504 'm3u8 url', group='url')
506 formats = self._extract_m3u8_formats(
507 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
509 self._sort_formats(formats)
511 title = self._search_regex(
512 r'data-title\s*=\s*(["\'])(?P
<value
>(?
:(?
!\
1).)+)\
1', webpage,
513 'title
', default=None, group='value
') or self._html_search_meta(
514 'title
', webpage, default=None) or self._og_search_title(
517 description = self._html_search_meta(
518 'description
', webpage,
519 default=None) or self._og_search_description(webpage)
521 thumbnail = self._search_regex(
522 r'data
-image\s
*=\s
*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
523 'thumbnail', default=None, group='url') or self._html_search_meta(
524 'thumbnail', webpage, default=None) or self._og_search_thumbnail(
527 duration = int_or_none(self._search_regex(
528 r'data-duration\s*=\s*["\'](\d
+)', webpage, 'duration
',
531 season = self._search_regex(
532 (r'data
-series
-title\s
*=\s
*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
533 r'\bseason\s*:\s*(["\'])(?P
<value
>(?
:(?
!\
1).)+)\
1'), webpage,
534 'season
', default=None, group='value
')
535 season_number = int_or_none(self._search_regex(
536 r'(\d
+)(?
:[.\s
]+sezona|\s
+HOOAEG
)', season or '', 'season number
',
538 episode = self._search_regex(
539 (r'\bepisode\s
*:\s
*(["\'])(?P<value>(?:(?!\1).)+)\1',
540 r'data-subtitle\s*=\s*(["\'])(?P
<value
>(?
:(?
!\
1).)+)\
1'), webpage,
541 'episode
', default=None, group='value
')
542 episode_number = int_or_none(self._search_regex(
543 r'(?
:S
[eē
]rija|Osa
)\s
+(\d
+)', episode or '', 'episode number
',
549 'description
': description,
550 'thumbnail
': thumbnail,
551 'duration
': duration,
553 'season_number
': season_number,
555 'episode_number
': episode_number,