yt_dlp/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_urlparse,
  10 )
  11 from ..utils import (
  12     determine_ext,
  13     ExtractorError,
  14     int_or_none,
  15     parse_duration,
  16     parse_iso8601,
  17     qualities,
  18     try_get,
  19     update_url_query,
  20     url_or_none,
  21     urljoin,
  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\.nova(?:tv)?\.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': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
 207             'only_matching': True,
 208         },
 209         {
 210             'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
 211             'only_matching': True,
 212         },
 213         {
 214             'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true',
 215             'only_matching': True,
 216         },
 217         {
 218             # views is null
 219             'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
 220             'only_matching': True,
 221         },
 222         {
 223             'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
 224             'only_matching': True,
 225         },
 226         {
 227             'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
 228             'only_matching': True,
 229         },
 230         {
 231             'url': 'mtg:418113',
 232             'only_matching': True,
 233         }
 234     ]
 235
 236     def _real_extract(self, url):
 237         video_id = self._match_id(url)
 238         geo_country = self._search_regex(
 239             r'https?://[^/]+\.([a-z]{2})', url,
 240             'geo country', default=None)
 241         if geo_country:
 242             self._initialize_geo_bypass({'countries': [geo_country.upper()]})
 243         video = self._download_json(
 244             'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
 245
 246         title = video['title']
 247
 248         try:
 249             streams = self._download_json(
 250                 'http://playapi.mtgx.tv/v3/videos/stream/%s' % video_id,
 251                 video_id, 'Downloading streams JSON')
 252         except ExtractorError as e:
 253             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 254                 msg = self._parse_json(e.cause.read().decode('utf-8'), video_id)
 255                 raise ExtractorError(msg['msg'], expected=True)
 256             raise
 257
 258         quality = qualities(['hls', 'medium', 'high'])
 259         formats = []
 260         for format_id, video_url in streams.get('streams', {}).items():
 261             video_url = url_or_none(video_url)
 262             if not video_url:
 263                 continue
 264             ext = determine_ext(video_url)
 265             if ext == 'f4m':
 266                 formats.extend(self._extract_f4m_formats(
 267                     update_url_query(video_url, {
 268                         'hdcore': '3.5.0',
 269                         'plugin': 'aasp-3.5.0.151.81'
 270                     }), video_id, f4m_id='hds', fatal=False))
 271             elif ext == 'm3u8':
 272                 formats.extend(self._extract_m3u8_formats(
 273                     video_url, video_id, 'mp4', 'm3u8_native',
 274                     m3u8_id='hls', fatal=False))
 275             else:
 276                 fmt = {
 277                     'format_id': format_id,
 278                     'quality': quality(format_id),
 279                     'ext': ext,
 280                 }
 281                 if video_url.startswith('rtmp'):
 282                     m = re.search(
 283                         r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
 284                     if not m:
 285                         continue
 286                     fmt.update({
 287                         'ext': 'flv',
 288                         'url': m.group('url'),
 289                         'app': m.group('app'),
 290                         'play_path': m.group('playpath'),
 291                         'preference': -1,
 292                     })
 293                 else:
 294                     fmt.update({
 295                         'url': video_url,
 296                     })
 297                 formats.append(fmt)
 298
 299         if not formats and video.get('is_geo_blocked'):
 300             self.raise_geo_restricted(
 301                 'This content might not be available in your country due to copyright reasons',
 302                 metadata_available=True)
 303
 304         self._sort_formats(formats)
 305
 306         # TODO: webvtt in m3u8
 307         subtitles = {}
 308         sami_path = video.get('sami_path')
 309         if sami_path:
 310             lang = self._search_regex(
 311                 r'_([a-z]{2})\.xml', sami_path, 'lang',
 312                 default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
 313             subtitles[lang] = [{
 314                 'url': sami_path,
 315             }]
 316
 317         series = video.get('format_title')
 318         episode_number = int_or_none(video.get('format_position', {}).get('episode'))
 319         season = video.get('_embedded', {}).get('season', {}).get('title')
 320         season_number = int_or_none(video.get('format_position', {}).get('season'))
 321
 322         return {
 323             'id': video_id,
 324             'title': title,
 325             'description': video.get('description'),
 326             'series': series,
 327             'episode_number': episode_number,
 328             'season': season,
 329             'season_number': season_number,
 330             'duration': int_or_none(video.get('duration')),
 331             'timestamp': parse_iso8601(video.get('created_at')),
 332             'view_count': try_get(video, lambda x: x['views']['total'], int),
 333             'age_limit': int_or_none(video.get('age_limit', 0)),
 334             'formats': formats,
 335             'subtitles': subtitles,
 336         }
 337
 338
 339 class ViafreeIE(InfoExtractor):
 340     _VALID_URL = r'''(?x)
 341                     https?://
 342                         (?:www\.)?
 343                         viafree\.(?P<country>dk|no|se)
 344                         /(?P<id>program(?:mer)?/(?:[^/]+/)+[^/?#&]+)
 345                     '''
 346     _TESTS = [{
 347         'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
 348         'info_dict': {
 349             'id': '757786',
 350             'ext': 'mp4',
 351             'title': 'Det beste vorspielet - Sesong 2 - Episode 1',
 352             'description': 'md5:b632cb848331404ccacd8cd03e83b4c3',
 353             'series': 'Det beste vorspielet',
 354             'season_number': 2,
 355             'duration': 1116,
 356             'timestamp': 1471200600,
 357             'upload_date': '20160814',
 358         },
 359         'params': {
 360             'skip_download': True,
 361         },
 362     }, {
 363         # with relatedClips
 364         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
 365         'only_matching': True,
 366     }, {
 367         # Different og:image URL schema
 368         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
 369         'only_matching': True,
 370     }, {
 371         'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
 372         'only_matching': True,
 373     }, {
 374         'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
 375         'only_matching': True,
 376     }]
 377     _GEO_BYPASS = False
 378
 379     @classmethod
 380     def suitable(cls, url):
 381         return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
 382
 383     def _real_extract(self, url):
 384         country, path = re.match(self._VALID_URL, url).groups()
 385         content = self._download_json(
 386             'https://viafree-content.mtg-api.com/viafree-content/v1/%s/path/%s' % (country, path), path)
 387         program = content['_embedded']['viafreeBlocks'][0]['_embedded']['program']
 388         guid = program['guid']
 389         meta = content['meta']
 390         title = meta['title']
 391
 392         try:
 393             stream_href = self._download_json(
 394                 program['_links']['streamLink']['href'], guid,
 395                 headers=self.geo_verification_headers())['embedded']['prioritizedStreams'][0]['links']['stream']['href']
 396         except ExtractorError as e:
 397             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 398                 self.raise_geo_restricted(countries=[country])
 399             raise
 400
 401         formats = self._extract_m3u8_formats(stream_href, guid, 'mp4')
 402         self._sort_formats(formats)
 403         episode = program.get('episode') or {}
 404
 405         return {
 406             'id': guid,
 407             'title': title,
 408             'thumbnail': meta.get('image'),
 409             'description': meta.get('description'),
 410             'series': episode.get('seriesTitle'),
 411             'episode_number': int_or_none(episode.get('episodeNumber')),
 412             'season_number': int_or_none(episode.get('seasonNumber')),
 413             'duration': int_or_none(try_get(program, lambda x: x['video']['duration']['milliseconds']), 1000),
 414             'timestamp': parse_iso8601(try_get(program, lambda x: x['availability']['start'])),
 415             'formats': formats,
 416         }
 417
 418
 419 class TVPlayHomeIE(InfoExtractor):
 420     _VALID_URL = r'https?://(?:tv3?)?play\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/(?:[^/]+/)*[^/?#&]+-(?P<id>\d+)'
 421     _TESTS = [{
 422         'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
 423         'info_dict': {
 424             'id': '366367',
 425             'ext': 'mp4',
 426             'title': 'Aferistai',
 427             'description': 'Aferistai. Kalėdinė pasaka.',
 428             'series': 'Aferistai [N-7]',
 429             'season': '1 sezonas',
 430             'season_number': 1,
 431             'duration': 464,
 432             'timestamp': 1394209658,
 433             'upload_date': '20140307',
 434             'age_limit': 18,
 435         },
 436         'params': {
 437             'skip_download': True,
 438         },
 439     }, {
 440         'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
 441         'only_matching': True,
 442     }, {
 443         'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
 444         'only_matching': True,
 445     }, {
 446         'url': 'https://play.tv3.lt/aferistai-10047125',
 447         'only_matching': True,
 448     }, {
 449         'url': 'https://tv3play.skaties.lv/vinas-melo-labak-10280317',
 450         'only_matching': True,
 451     }, {
 452         'url': 'https://play.tv3.ee/cool-d-ga-mehhikosse-10044354',
 453         'only_matching': True,
 454     }]
 455
 456     def _real_extract(self, url):
 457         video_id = self._match_id(url)
 458
 459         asset = self._download_json(
 460             urljoin(url, '/sb/public/asset/' + video_id), video_id)
 461
 462         m3u8_url = asset['movie']['contentUrl']
 463         video_id = asset['assetId']
 464         asset_title = asset['title']
 465         title = asset_title['title']
 466
 467         formats = self._extract_m3u8_formats(
 468             m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
 469         self._sort_formats(formats)
 470
 471         thumbnails = None
 472         image_url = asset.get('imageUrl')
 473         if image_url:
 474             thumbnails = [{
 475                 'url': urljoin(url, image_url),
 476                 'ext': 'jpg',
 477             }]
 478
 479         metadata = asset.get('metadata') or {}
 480
 481         return {
 482             'id': video_id,
 483             'title': title,
 484             'description': asset_title.get('summaryLong') or asset_title.get('summaryShort'),
 485             'thumbnails': thumbnails,
 486             'duration': parse_duration(asset_title.get('runTime')),
 487             'series': asset.get('tvSeriesTitle'),
 488             'season': asset.get('tvSeasonTitle'),
 489             'season_number': int_or_none(metadata.get('seasonNumber')),
 490             'episode': asset_title.get('titleBrief'),
 491             'episode_number': int_or_none(metadata.get('episodeNumber')),
 492             'formats': formats,
 493         }