yt_dlp/extractor/tvplay.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_HTTPError,
   6     compat_urlparse,
   7 )
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  12     parse_iso8601,
  13     qualities,
  14     traverse_obj,
  15     try_get,
  16     update_url_query,
  17     url_or_none,
  18     urljoin,
  19 )
  20
  21
  22 class TVPlayIE(InfoExtractor):
  23     IE_NAME = 'mtg'
  24     IE_DESC = 'MTG services'
  25     _VALID_URL = r'''(?x)
  26                     (?:
  27                         mtg:|
  28                         https?://
  29                             (?:www\.)?
  30                             (?:
  31                                 tvplay(?:\.skaties)?\.lv(?:/parraides)?|
  32                                 (?:tv3play|play\.tv3)\.lt(?:/programos)?|
  33                                 tv3play(?:\.tv3)?\.ee/sisu|
  34                                 (?:tv(?:3|6|8|10)play)\.se/program|
  35                                 (?:(?:tv3play|viasat4play|tv6play)\.no|(?:tv3play)\.dk)/programmer|
  36                                 play\.nova(?:tv)?\.bg/programi
  37                             )
  38                             /(?:[^/]+/)+
  39                         )
  40                         (?P<id>\d+)
  41                     '''
  42     _TESTS = [
  43         {
  44             'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
  45             'md5': 'a1612fe0849455423ad8718fe049be21',
  46             'info_dict': {
  47                 'id': '418113',
  48                 'ext': 'mp4',
  49                 'title': 'Kādi ir īri? - Viņas melo labāk',
  50                 'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.',
  51                 'series': 'Viņas melo labāk',
  52                 'season': '2.sezona',
  53                 'season_number': 2,
  54                 'duration': 25,
  55                 'timestamp': 1406097056,
  56                 'upload_date': '20140723',
  57             },
  58         },
  59         {
  60             'url': 'http://play.tv3.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
  61             'info_dict': {
  62                 'id': '409229',
  63                 'ext': 'flv',
  64                 'title': 'Moterys meluoja geriau',
  65                 'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
  66                 'series': 'Moterys meluoja geriau',
  67                 'episode_number': 47,
  68                 'season': '1 sezonas',
  69                 'season_number': 1,
  70                 'duration': 1330,
  71                 'timestamp': 1403769181,
  72                 'upload_date': '20140626',
  73             },
  74             'params': {
  75                 # rtmp download
  76                 'skip_download': True,
  77             },
  78         },
  79         {
  80             'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
  81             'info_dict': {
  82                 'id': '238551',
  83                 'ext': 'flv',
  84                 'title': 'Kodu keset linna 398537',
  85                 'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
  86                 'duration': 1257,
  87                 'timestamp': 1292449761,
  88                 'upload_date': '20101215',
  89             },
  90             'params': {
  91                 # rtmp download
  92                 'skip_download': True,
  93             },
  94         },
  95         {
  96             'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
  97             'info_dict': {
  98                 'id': '395385',
  99                 'ext': 'mp4',
 100                 'title': 'Husräddarna S02E07',
 101                 'description': 'md5:f210c6c89f42d4fc39faa551be813777',
 102                 'duration': 2574,
 103                 'timestamp': 1400596321,
 104                 'upload_date': '20140520',
 105             },
 106             'params': {
 107                 'skip_download': True,
 108             },
 109         },
 110         {
 111             'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
 112             'info_dict': {
 113                 'id': '266636',
 114                 'ext': 'mp4',
 115                 'title': 'Den sista dokusåpan S01E08',
 116                 'description': 'md5:295be39c872520221b933830f660b110',
 117                 'duration': 1492,
 118                 'timestamp': 1330522854,
 119                 'upload_date': '20120229',
 120                 'age_limit': 18,
 121             },
 122             'params': {
 123                 'skip_download': True,
 124             },
 125         },
 126         {
 127             'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
 128             'info_dict': {
 129                 'id': '282756',
 130                 'ext': 'mp4',
 131                 'title': 'Antikjakten S01E10',
 132                 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
 133                 'duration': 2646,
 134                 'timestamp': 1348575868,
 135                 'upload_date': '20120925',
 136             },
 137             'params': {
 138                 'skip_download': True,
 139             },
 140         },
 141         {
 142             'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
 143             'info_dict': {
 144                 'id': '230898',
 145                 'ext': 'mp4',
 146                 'title': 'Anna Anka søker assistent - Ep. 8',
 147                 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
 148                 'duration': 2656,
 149                 'timestamp': 1277720005,
 150                 'upload_date': '20100628',
 151             },
 152             'params': {
 153                 'skip_download': True,
 154             },
 155         },
 156         {
 157             'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
 158             'info_dict': {
 159                 'id': '21873',
 160                 'ext': 'mp4',
 161                 'title': 'Budbringerne program 10',
 162                 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
 163                 'duration': 1297,
 164                 'timestamp': 1254205102,
 165                 'upload_date': '20090929',
 166             },
 167             'params': {
 168                 'skip_download': True,
 169             },
 170         },
 171         {
 172             'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
 173             'info_dict': {
 174                 'id': '361883',
 175                 'ext': 'mp4',
 176                 'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
 177                 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
 178                 'duration': 2594,
 179                 'timestamp': 1393236292,
 180                 'upload_date': '20140224',
 181             },
 182             'params': {
 183                 'skip_download': True,
 184             },
 185         },
 186         {
 187             'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
 188             'info_dict': {
 189                 'id': '624952',
 190                 'ext': 'flv',
 191                 'title': 'Здравей, България (12.06.2015 г.) ',
 192                 'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
 193                 'duration': 8838,
 194                 'timestamp': 1434100372,
 195                 'upload_date': '20150612',
 196             },
 197             'params': {
 198                 # rtmp download
 199                 'skip_download': True,
 200             },
 201         },
 202         {
 203             'url': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
 204             'only_matching': True,
 205         },
 206         {
 207             'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
 208             'only_matching': True,
 209         },
 210         {
 211             'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true',
 212             'only_matching': True,
 213         },
 214         {
 215             # views is null
 216             'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
 217             'only_matching': True,
 218         },
 219         {
 220             'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
 221             'only_matching': True,
 222         },
 223         {
 224             'url': 'mtg:418113',
 225             'only_matching': True,
 226         }
 227     ]
 228
 229     def _real_extract(self, url):
 230         video_id = self._match_id(url)
 231         geo_country = self._search_regex(
 232             r'https?://[^/]+\.([a-z]{2})', url,
 233             'geo country', default=None)
 234         if geo_country:
 235             self._initialize_geo_bypass({'countries': [geo_country.upper()]})
 236         video = self._download_json(
 237             'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
 238
 239         title = video['title']
 240
 241         try:
 242             streams = self._download_json(
 243                 'http://playapi.mtgx.tv/v3/videos/stream/%s' % video_id,
 244                 video_id, 'Downloading streams JSON')
 245         except ExtractorError as e:
 246             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 247                 msg = self._parse_json(e.cause.read().decode('utf-8'), video_id)
 248                 raise ExtractorError(msg['msg'], expected=True)
 249             raise
 250
 251         quality = qualities(['hls', 'medium', 'high'])
 252         formats = []
 253         for format_id, video_url in streams.get('streams', {}).items():
 254             video_url = url_or_none(video_url)
 255             if not video_url:
 256                 continue
 257             ext = determine_ext(video_url)
 258             if ext == 'f4m':
 259                 formats.extend(self._extract_f4m_formats(
 260                     update_url_query(video_url, {
 261                         'hdcore': '3.5.0',
 262                         'plugin': 'aasp-3.5.0.151.81'
 263                     }), video_id, f4m_id='hds', fatal=False))
 264             elif ext == 'm3u8':
 265                 formats.extend(self._extract_m3u8_formats(
 266                     video_url, video_id, 'mp4', 'm3u8_native',
 267                     m3u8_id='hls', fatal=False))
 268             else:
 269                 fmt = {
 270                     'format_id': format_id,
 271                     'quality': quality(format_id),
 272                     'ext': ext,
 273                 }
 274                 if video_url.startswith('rtmp'):
 275                     m = re.search(
 276                         r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
 277                     if not m:
 278                         continue
 279                     fmt.update({
 280                         'ext': 'flv',
 281                         'url': m.group('url'),
 282                         'app': m.group('app'),
 283                         'play_path': m.group('playpath'),
 284                         'preference': -1,
 285                     })
 286                 else:
 287                     fmt.update({
 288                         'url': video_url,
 289                     })
 290                 formats.append(fmt)
 291
 292         if not formats and video.get('is_geo_blocked'):
 293             self.raise_geo_restricted(
 294                 'This content might not be available in your country due to copyright reasons',
 295                 metadata_available=True)
 296
 297         # TODO: webvtt in m3u8
 298         subtitles = {}
 299         sami_path = video.get('sami_path')
 300         if sami_path:
 301             lang = self._search_regex(
 302                 r'_([a-z]{2})\.xml', sami_path, 'lang',
 303                 default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
 304             subtitles[lang] = [{
 305                 'url': sami_path,
 306             }]
 307
 308         series = video.get('format_title')
 309         episode_number = int_or_none(video.get('format_position', {}).get('episode'))
 310         season = video.get('_embedded', {}).get('season', {}).get('title')
 311         season_number = int_or_none(video.get('format_position', {}).get('season'))
 312
 313         return {
 314             'id': video_id,
 315             'title': title,
 316             'description': video.get('description'),
 317             'series': series,
 318             'episode_number': episode_number,
 319             'season': season,
 320             'season_number': season_number,
 321             'duration': int_or_none(video.get('duration')),
 322             'timestamp': parse_iso8601(video.get('created_at')),
 323             'view_count': try_get(video, lambda x: x['views']['total'], int),
 324             'age_limit': int_or_none(video.get('age_limit', 0)),
 325             'formats': formats,
 326             'subtitles': subtitles,
 327         }
 328
 329
 330 class ViafreeIE(InfoExtractor):
 331     _VALID_URL = r'''(?x)
 332                     https?://
 333                         (?:www\.)?
 334                         viafree\.(?P<country>dk|no|se|fi)
 335                         /(?P<id>(?:program(?:mer)?|ohjelmat)?/(?:[^/]+/)+[^/?#&]+)
 336                     '''
 337     _TESTS = [{
 338         'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
 339         'info_dict': {
 340             'id': '757786',
 341             'ext': 'mp4',
 342             'title': 'Det beste vorspielet - Sesong 2 - Episode 1',
 343             'description': 'md5:b632cb848331404ccacd8cd03e83b4c3',
 344             'series': 'Det beste vorspielet',
 345             'season_number': 2,
 346             'duration': 1116,
 347             'timestamp': 1471200600,
 348             'upload_date': '20160814',
 349         },
 350         'params': {
 351             'skip_download': True,
 352         },
 353     }, {
 354         'url': 'https://www.viafree.dk/programmer/humor/comedy-central-roast-of-charlie-sheen/film/1047660',
 355         'info_dict': {
 356             'id': '1047660',
 357             'ext': 'mp4',
 358             'title': 'Comedy Central Roast of Charlie Sheen - Comedy Central Roast of Charlie Sheen',
 359             'description': 'md5:ec956d941ae9fd7c65a48fd64951dc6d',
 360             'series': 'Comedy Central Roast of Charlie Sheen',
 361             'season_number': 1,
 362             'duration': 3747,
 363             'timestamp': 1608246060,
 364             'upload_date': '20201217'
 365         },
 366         'params': {
 367             'skip_download': True
 368         }
 369     }, {
 370         # with relatedClips
 371         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
 372         'only_matching': True,
 373     }, {
 374         # Different og:image URL schema
 375         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
 376         'only_matching': True,
 377     }, {
 378         'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
 379         'only_matching': True,
 380     }, {
 381         'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
 382         'only_matching': True,
 383     }, {
 384         'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
 385         'only_matching': True,
 386     }, {
 387         'url': 'https://www.viafree.fi/ohjelmat/entertainment/amazing-makeovers/kausi-7/jakso-2',
 388         'only_matching': True,
 389     }]
 390     _GEO_BYPASS = False
 391
 392     def _real_extract(self, url):
 393         country, path = self._match_valid_url(url).groups()
 394         content = self._download_json(
 395             'https://viafree-content.mtg-api.com/viafree-content/v1/%s/path/%s' % (country, path), path)
 396         program = content['_embedded']['viafreeBlocks'][0]['_embedded']['program']
 397         guid = program['guid']
 398         meta = content['meta']
 399         title = meta['title']
 400
 401         try:
 402             stream_href = self._download_json(
 403                 program['_links']['streamLink']['href'], guid,
 404                 headers=self.geo_verification_headers())['embedded']['prioritizedStreams'][0]['links']['stream']['href']
 405         except ExtractorError as e:
 406             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 407                 self.raise_geo_restricted(countries=[country])
 408             raise
 409
 410         formats, subtitles = self._extract_m3u8_formats_and_subtitles(stream_href, guid, 'mp4')
 411         episode = program.get('episode') or {}
 412         return {
 413             'id': guid,
 414             'title': title,
 415             'thumbnail': meta.get('image'),
 416             'description': meta.get('description'),
 417             'series': episode.get('seriesTitle'),
 418             'subtitles': subtitles,
 419             'episode_number': int_or_none(episode.get('episodeNumber')),
 420             'season_number': int_or_none(episode.get('seasonNumber')),
 421             'duration': int_or_none(try_get(program, lambda x: x['video']['duration']['milliseconds']), 1000),
 422             'timestamp': parse_iso8601(try_get(program, lambda x: x['availability']['start'])),
 423             'formats': formats,
 424         }
 425
 426
 427 class TVPlayHomeIE(InfoExtractor):
 428     _VALID_URL = r'''(?x)
 429             https?://
 430             (?:tv3?)?
 431             play\.(?:tv3|skaties)\.(?P<country>lv|lt|ee)/
 432             (?P<live>lives/)?
 433             [^?#&]+(?:episode|programme|clip)-(?P<id>\d+)
 434     '''
 435     _TESTS = [{
 436         'url': 'https://play.tv3.lt/series/gauju-karai-karveliai,serial-2343791/serija-8,episode-2343828',
 437         'info_dict': {
 438             'id': '2343828',
 439             'ext': 'mp4',
 440             'title': 'Gaujų karai. Karveliai (2021) | S01E08: Serija 8',
 441             'description': 'md5:f6fcfbb236429f05531131640dfa7c81',
 442             'duration': 2710,
 443             'season': 'Gaujų karai. Karveliai',
 444             'season_number': 1,
 445             'release_year': 2021,
 446             'episode': 'Serija 8',
 447             'episode_number': 8,
 448         },
 449         'params': {
 450             'skip_download': 'm3u8',
 451         },
 452     }, {
 453         'url': 'https://play.tv3.lt/series/moterys-meluoja-geriau-n-7,serial-2574652/serija-25,episode-3284937',
 454         'info_dict': {
 455             'id': '3284937',
 456             'ext': 'mp4',
 457             'season': 'Moterys meluoja geriau [N-7]',
 458             'season_number': 14,
 459             'release_year': 2021,
 460             'episode': 'Serija 25',
 461             'episode_number': 25,
 462             'title': 'Moterys meluoja geriau [N-7] (2021) | S14|E25: Serija 25',
 463             'description': 'md5:c6926e9710f1a126f028fbe121eddb79',
 464             'duration': 2440,
 465         },
 466         'skip': '404'
 467     }, {
 468         'url': 'https://play.tv3.lt/lives/tv6-lt,live-2838694/optibet-a-lygos-rungtynes-marijampoles-suduva--vilniaus-riteriai,programme-3422014',
 469         'only_matching': True,
 470     }, {
 471         'url': 'https://tv3play.skaties.lv/series/women-lie-better-lv,serial-1024464/women-lie-better-lv,episode-1038762',
 472         'only_matching': True,
 473     }, {
 474         'url': 'https://play.tv3.ee/series/_,serial-2654462/_,episode-2654474',
 475         'only_matching': True,
 476     }, {
 477         'url': 'https://tv3play.skaties.lv/clips/tv3-zinas-valsti-lidz-15novembrim-bus-majsede,clip-3464509',
 478         'only_matching': True,
 479     }]
 480
 481     def _real_extract(self, url):
 482         country, is_live, video_id = self._match_valid_url(url).groups()
 483
 484         api_path = 'lives/programmes' if is_live else 'vods'
 485         data = self._download_json(
 486             urljoin(url, f'/api/products/{api_path}/{video_id}?platform=BROWSER&lang={country.upper()}'),
 487             video_id)
 488
 489         video_type = 'CATCHUP' if is_live else 'MOVIE'
 490         stream_id = data['programRecordingId'] if is_live else video_id
 491         stream = self._download_json(
 492             urljoin(url, f'/api/products/{stream_id}/videos/playlist?videoType={video_type}&platform=BROWSER'), video_id)
 493         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
 494             stream['sources']['HLS'][0]['src'], video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
 495
 496         thumbnails = set(traverse_obj(
 497             data, (('galary', 'images', 'artworks'), ..., ..., ('miniUrl', 'mainUrl')), expected_type=url_or_none))
 498
 499         return {
 500             'id': video_id,
 501             'title': self._resolve_title(data),
 502             'description': traverse_obj(data, 'description', 'lead'),
 503             'duration': int_or_none(data.get('duration')),
 504             'season': traverse_obj(data, ('season', 'serial', 'title')),
 505             'season_number': int_or_none(traverse_obj(data, ('season', 'number'))),
 506             'episode': data.get('title'),
 507             'episode_number': int_or_none(data.get('episode')),
 508             'release_year': int_or_none(traverse_obj(data, ('season', 'serial', 'year'))),
 509             'thumbnails': [{'url': url, 'ext': 'jpg'} for url in thumbnails],
 510             'formats': formats,
 511             'subtitles': subtitles,
 512         }
 513
 514     @staticmethod
 515     def _resolve_title(data):
 516         return try_get(data, lambda x: (
 517             f'{data["season"]["serial"]["title"]} ({data["season"]["serial"]["year"]}) | '
 518             f'S{data["season"]["number"]:02d}E{data["episode"]:02d}: {data["title"]}'
 519         )) or data.get('title')