[youtube] Add ability to authenticate with cookies
[youtube-dl] / youtube_dl / extractor / tvplay.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import (
8     compat_HTTPError,
9     compat_str,
10     compat_urlparse,
11 )
12 from ..utils import (
13     determine_ext,
14     ExtractorError,
15     int_or_none,
16     parse_iso8601,
17     qualities,
18     smuggle_url,
19     try_get,
20     unsmuggle_url,
21     update_url_query,
22 )
23
24
25 class TVPlayIE(InfoExtractor):
26     IE_NAME = 'mtg'
27     IE_DESC = 'MTG services'
28     _VALID_URL = r'''(?x)
29                     (?:
30                         mtg:|
31                         https?://
32                             (?:www\.)?
33                             (?:
34                                 tvplay(?:\.skaties)?\.lv/parraides|
35                                 (?:tv3play|play\.tv3)\.lt/programos|
36                                 tv3play(?:\.tv3)?\.ee/sisu|
37                                 (?:tv(?:3|6|8|10)play|viafree)\.se/program|
38                                 (?:(?:tv3play|viasat4play|tv6play|viafree)\.no|(?:tv3play|viafree)\.dk)/programmer|
39                                 play\.novatv\.bg/programi
40                             )
41                             /(?:[^/]+/)+
42                         )
43                         (?P<id>\d+)
44                     '''
45     _TESTS = [
46         {
47             'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
48             'md5': 'a1612fe0849455423ad8718fe049be21',
49             'info_dict': {
50                 'id': '418113',
51                 'ext': 'mp4',
52                 'title': 'Kādi ir īri? - Viņas melo labāk',
53                 'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.',
54                 'series': 'Viņas melo labāk',
55                 'season': '2.sezona',
56                 'season_number': 2,
57                 'duration': 25,
58                 'timestamp': 1406097056,
59                 'upload_date': '20140723',
60             },
61         },
62         {
63             'url': 'http://play.tv3.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
64             'info_dict': {
65                 'id': '409229',
66                 'ext': 'flv',
67                 'title': 'Moterys meluoja geriau',
68                 'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
69                 'series': 'Moterys meluoja geriau',
70                 'episode_number': 47,
71                 'season': '1 sezonas',
72                 'season_number': 1,
73                 'duration': 1330,
74                 'timestamp': 1403769181,
75                 'upload_date': '20140626',
76             },
77             'params': {
78                 # rtmp download
79                 'skip_download': True,
80             },
81         },
82         {
83             'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
84             'info_dict': {
85                 'id': '238551',
86                 'ext': 'flv',
87                 'title': 'Kodu keset linna 398537',
88                 'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
89                 'duration': 1257,
90                 'timestamp': 1292449761,
91                 'upload_date': '20101215',
92             },
93             'params': {
94                 # rtmp download
95                 'skip_download': True,
96             },
97         },
98         {
99             'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
100             'info_dict': {
101                 'id': '395385',
102                 'ext': 'mp4',
103                 'title': 'Husräddarna S02E07',
104                 'description': 'md5:f210c6c89f42d4fc39faa551be813777',
105                 'duration': 2574,
106                 'timestamp': 1400596321,
107                 'upload_date': '20140520',
108             },
109             'params': {
110                 'skip_download': True,
111             },
112         },
113         {
114             'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
115             'info_dict': {
116                 'id': '266636',
117                 'ext': 'mp4',
118                 'title': 'Den sista dokusåpan S01E08',
119                 'description': 'md5:295be39c872520221b933830f660b110',
120                 'duration': 1492,
121                 'timestamp': 1330522854,
122                 'upload_date': '20120229',
123                 'age_limit': 18,
124             },
125             'params': {
126                 'skip_download': True,
127             },
128         },
129         {
130             'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
131             'info_dict': {
132                 'id': '282756',
133                 'ext': 'mp4',
134                 'title': 'Antikjakten S01E10',
135                 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
136                 'duration': 2646,
137                 'timestamp': 1348575868,
138                 'upload_date': '20120925',
139             },
140             'params': {
141                 'skip_download': True,
142             },
143         },
144         {
145             'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
146             'info_dict': {
147                 'id': '230898',
148                 'ext': 'mp4',
149                 'title': 'Anna Anka søker assistent - Ep. 8',
150                 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
151                 'duration': 2656,
152                 'timestamp': 1277720005,
153                 'upload_date': '20100628',
154             },
155             'params': {
156                 'skip_download': True,
157             },
158         },
159         {
160             'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
161             'info_dict': {
162                 'id': '21873',
163                 'ext': 'mp4',
164                 'title': 'Budbringerne program 10',
165                 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
166                 'duration': 1297,
167                 'timestamp': 1254205102,
168                 'upload_date': '20090929',
169             },
170             'params': {
171                 'skip_download': True,
172             },
173         },
174         {
175             'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
176             'info_dict': {
177                 'id': '361883',
178                 'ext': 'mp4',
179                 'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
180                 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
181                 'duration': 2594,
182                 'timestamp': 1393236292,
183                 'upload_date': '20140224',
184             },
185             'params': {
186                 'skip_download': True,
187             },
188         },
189         {
190             'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
191             'info_dict': {
192                 'id': '624952',
193                 'ext': 'flv',
194                 'title': 'Здравей, България (12.06.2015 г.) ',
195                 'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
196                 'duration': 8838,
197                 'timestamp': 1434100372,
198                 'upload_date': '20150612',
199             },
200             'params': {
201                 # rtmp download
202                 'skip_download': True,
203             },
204         },
205         {
206             'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
207             'only_matching': True,
208         },
209         {
210             # views is null
211             'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
212             'only_matching': True,
213         },
214         {
215             'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
216             'only_matching': True,
217         },
218         {
219             'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
220             'only_matching': True,
221         },
222         {
223             'url': 'mtg:418113',
224             'only_matching': True,
225         }
226     ]
227
228     def _real_extract(self, url):
229         url, smuggled_data = unsmuggle_url(url, {})
230         self._initialize_geo_bypass(smuggled_data.get('geo_countries'))
231
232         video_id = self._match_id(url)
233         geo_country = self._search_regex(
234             r'https?://[^/]+\.([a-z]{2})', url,
235             'geo country', default=None)
236         if geo_country:
237             self._initialize_geo_bypass([geo_country.upper()])
238         video = self._download_json(
239             'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
240
241         title = video['title']
242
243         try:
244             streams = self._download_json(
245                 'http://playapi.mtgx.tv/v3/videos/stream/%s' % video_id,
246                 video_id, 'Downloading streams JSON')
247         except ExtractorError as e:
248             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
249                 msg = self._parse_json(e.cause.read().decode('utf-8'), video_id)
250                 raise ExtractorError(msg['msg'], expected=True)
251             raise
252
253         quality = qualities(['hls', 'medium', 'high'])
254         formats = []
255         for format_id, video_url in streams.get('streams', {}).items():
256             if not video_url or not isinstance(video_url, compat_str):
257                 continue
258             ext = determine_ext(video_url)
259             if ext == 'f4m':
260                 formats.extend(self._extract_f4m_formats(
261                     update_url_query(video_url, {
262                         'hdcore': '3.5.0',
263                         'plugin': 'aasp-3.5.0.151.81'
264                     }), video_id, f4m_id='hds', fatal=False))
265             elif ext == 'm3u8':
266                 formats.extend(self._extract_m3u8_formats(
267                     video_url, video_id, 'mp4', 'm3u8_native',
268                     m3u8_id='hls', fatal=False))
269             else:
270                 fmt = {
271                     'format_id': format_id,
272                     'quality': quality(format_id),
273                     'ext': ext,
274                 }
275                 if video_url.startswith('rtmp'):
276                     if smuggled_data.get('skip_rtmp'):
277                         continue
278                     m = re.search(
279                         r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
280                     if not m:
281                         continue
282                     fmt.update({
283                         'ext': 'flv',
284                         'url': m.group('url'),
285                         'app': m.group('app'),
286                         'play_path': m.group('playpath'),
287                     })
288                 else:
289                     fmt.update({
290                         'url': video_url,
291                     })
292                 formats.append(fmt)
293
294         if not formats and video.get('is_geo_blocked'):
295             self.raise_geo_restricted(
296                 'This content might not be available in your country due to copyright reasons')
297
298         self._sort_formats(formats)
299
300         # TODO: webvtt in m3u8
301         subtitles = {}
302         sami_path = video.get('sami_path')
303         if sami_path:
304             lang = self._search_regex(
305                 r'_([a-z]{2})\.xml', sami_path, 'lang',
306                 default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
307             subtitles[lang] = [{
308                 'url': sami_path,
309             }]
310
311         series = video.get('format_title')
312         episode_number = int_or_none(video.get('format_position', {}).get('episode'))
313         season = video.get('_embedded', {}).get('season', {}).get('title')
314         season_number = int_or_none(video.get('format_position', {}).get('season'))
315
316         return {
317             'id': video_id,
318             'title': title,
319             'description': video.get('description'),
320             'series': series,
321             'episode_number': episode_number,
322             'season': season,
323             'season_number': season_number,
324             'duration': int_or_none(video.get('duration')),
325             'timestamp': parse_iso8601(video.get('created_at')),
326             'view_count': try_get(video, lambda x: x['views']['total'], int),
327             'age_limit': int_or_none(video.get('age_limit', 0)),
328             'formats': formats,
329             'subtitles': subtitles,
330         }
331
332
333 class ViafreeIE(InfoExtractor):
334     _VALID_URL = r'''(?x)
335                     https?://
336                         (?:www\.)?
337                         viafree\.
338                         (?:
339                             (?:dk|no)/programmer|
340                             se/program
341                         )
342                         /(?:[^/]+/)+(?P<id>[^/?#&]+)
343                     '''
344     _TESTS = [{
345         'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
346         'info_dict': {
347             'id': '395375',
348             'ext': 'mp4',
349             'title': 'Husräddarna S02E02',
350             'description': 'md5:4db5c933e37db629b5a2f75dfb34829e',
351             'series': 'Husräddarna',
352             'season': 'Säsong 2',
353             'season_number': 2,
354             'duration': 2576,
355             'timestamp': 1400596321,
356             'upload_date': '20140520',
357         },
358         'params': {
359             'skip_download': True,
360         },
361         'add_ie': [TVPlayIE.ie_key()],
362     }, {
363         # with relatedClips
364         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
365         'info_dict': {
366             'id': '758770',
367             'ext': 'mp4',
368             'title': 'Sommaren med YouTube-stjärnorna S01E01',
369             'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
370             'series': 'Sommaren med YouTube-stjärnorna',
371             'season': 'Säsong 1',
372             'season_number': 1,
373             'duration': 1326,
374             'timestamp': 1470905572,
375             'upload_date': '20160811',
376         },
377         'params': {
378             'skip_download': True,
379         },
380         'add_ie': [TVPlayIE.ie_key()],
381     }, {
382         # Different og:image URL schema
383         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
384         'only_matching': True,
385     }, {
386         'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
387         'only_matching': True,
388     }, {
389         'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
390         'only_matching': True,
391     }]
392
393     @classmethod
394     def suitable(cls, url):
395         return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
396
397     def _real_extract(self, url):
398         video_id = self._match_id(url)
399
400         webpage = self._download_webpage(url, video_id)
401
402         data = self._parse_json(
403             self._search_regex(
404                 r'(?s)window\.App\s*=\s*({.+?})\s*;\s*</script',
405                 webpage, 'data', default='{}'),
406             video_id, transform_source=lambda x: re.sub(
407                 r'(?s)function\s+[a-zA-Z_][\da-zA-Z_]*\s*\([^)]*\)\s*{[^}]*}\s*',
408                 'null', x), fatal=False)
409
410         video_id = None
411
412         if data:
413             video_id = try_get(
414                 data, lambda x: x['context']['dispatcher']['stores'][
415                     'ContentPageProgramStore']['currentVideo']['id'],
416                 compat_str)
417
418         # Fallback #1 (extract from og:image URL schema)
419         if not video_id:
420             thumbnail = self._og_search_thumbnail(webpage, default=None)
421             if thumbnail:
422                 video_id = self._search_regex(
423                     # Patterns seen:
424                     #  http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/inbox/765166/a2e95e5f1d735bab9f309fa345cc3f25.jpg
425                     #  http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/seasons/15204/758770/4a5ba509ca8bc043e1ebd1a76131cdf2.jpg
426                     r'https?://[^/]+/imagecache/(?:[^/]+/)+(\d{6,})/',
427                     thumbnail, 'video id', default=None)
428
429         # Fallback #2. Extract from raw JSON string.
430         # May extract wrong video id if relatedClips is present.
431         if not video_id:
432             video_id = self._search_regex(
433                 r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
434                 webpage, 'video id')
435
436         return self.url_result(
437             smuggle_url(
438                 'mtg:%s' % video_id,
439                 {
440                     'geo_countries': [
441                         compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]],
442                     # rtmp host mtgfs.fplive.net for viafree is unresolvable
443                     'skip_rtmp': True,
444                 }),
445             ie=TVPlayIE.ie_key(), video_id=video_id)