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_urlparse,
  10 )
  11 from ..utils import (
  12     determine_ext,
  13     ExtractorError,
  14     int_or_none,
  15     parse_iso8601,
  16     qualities,
  17     try_get,
  18     update_url_query,
  19     url_or_none,
  20 )
  21
  22
  23 class TVPlayIE(InfoExtractor):
  24     IE_NAME = 'mtg'
  25     IE_DESC = 'MTG services'
  26     _VALID_URL = r'''(?x)
  27                     (?:
  28                         mtg:|
  29                         https?://
  30                             (?:www\.)?
  31                             (?:
  32                                 tvplay(?:\.skaties)?\.lv(?:/parraides)?|
  33                                 (?:tv3play|play\.tv3)\.lt(?:/programos)?|
  34                                 tv3play(?:\.tv3)?\.ee/sisu|
  35                                 (?:tv(?:3|6|8|10)play|viafree)\.se/program|
  36                                 (?:(?:tv3play|viasat4play|tv6play|viafree)\.no|(?:tv3play|viafree)\.dk)/programmer|
  37                                 play\.nova(?:tv)?\.bg/programi
  38                             )
  39                             /(?:[^/]+/)+
  40                         )
  41                         (?P<id>\d+)
  42                     '''
  43     _TESTS = [
  44         {
  45             'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
  46             'md5': 'a1612fe0849455423ad8718fe049be21',
  47             'info_dict': {
  48                 'id': '418113',
  49                 'ext': 'mp4',
  50                 'title': 'Kādi ir īri? - Viņas melo labāk',
  51                 'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.',
  52                 'series': 'Viņas melo labāk',
  53                 'season': '2.sezona',
  54                 'season_number': 2,
  55                 'duration': 25,
  56                 'timestamp': 1406097056,
  57                 'upload_date': '20140723',
  58             },
  59         },
  60         {
  61             'url': 'http://play.tv3.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
  62             'info_dict': {
  63                 'id': '409229',
  64                 'ext': 'flv',
  65                 'title': 'Moterys meluoja geriau',
  66                 'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
  67                 'series': 'Moterys meluoja geriau',
  68                 'episode_number': 47,
  69                 'season': '1 sezonas',
  70                 'season_number': 1,
  71                 'duration': 1330,
  72                 'timestamp': 1403769181,
  73                 'upload_date': '20140626',
  74             },
  75             'params': {
  76                 # rtmp download
  77                 'skip_download': True,
  78             },
  79         },
  80         {
  81             'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
  82             'info_dict': {
  83                 'id': '238551',
  84                 'ext': 'flv',
  85                 'title': 'Kodu keset linna 398537',
  86                 'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
  87                 'duration': 1257,
  88                 'timestamp': 1292449761,
  89                 'upload_date': '20101215',
  90             },
  91             'params': {
  92                 # rtmp download
  93                 'skip_download': True,
  94             },
  95         },
  96         {
  97             'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
  98             'info_dict': {
  99                 'id': '395385',
 100                 'ext': 'mp4',
 101                 'title': 'Husräddarna S02E07',
 102                 'description': 'md5:f210c6c89f42d4fc39faa551be813777',
 103                 'duration': 2574,
 104                 'timestamp': 1400596321,
 105                 'upload_date': '20140520',
 106             },
 107             'params': {
 108                 'skip_download': True,
 109             },
 110         },
 111         {
 112             'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
 113             'info_dict': {
 114                 'id': '266636',
 115                 'ext': 'mp4',
 116                 'title': 'Den sista dokusåpan S01E08',
 117                 'description': 'md5:295be39c872520221b933830f660b110',
 118                 'duration': 1492,
 119                 'timestamp': 1330522854,
 120                 'upload_date': '20120229',
 121                 'age_limit': 18,
 122             },
 123             'params': {
 124                 'skip_download': True,
 125             },
 126         },
 127         {
 128             'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
 129             'info_dict': {
 130                 'id': '282756',
 131                 'ext': 'mp4',
 132                 'title': 'Antikjakten S01E10',
 133                 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
 134                 'duration': 2646,
 135                 'timestamp': 1348575868,
 136                 'upload_date': '20120925',
 137             },
 138             'params': {
 139                 'skip_download': True,
 140             },
 141         },
 142         {
 143             'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
 144             'info_dict': {
 145                 'id': '230898',
 146                 'ext': 'mp4',
 147                 'title': 'Anna Anka søker assistent - Ep. 8',
 148                 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
 149                 'duration': 2656,
 150                 'timestamp': 1277720005,
 151                 'upload_date': '20100628',
 152             },
 153             'params': {
 154                 'skip_download': True,
 155             },
 156         },
 157         {
 158             'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
 159             'info_dict': {
 160                 'id': '21873',
 161                 'ext': 'mp4',
 162                 'title': 'Budbringerne program 10',
 163                 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
 164                 'duration': 1297,
 165                 'timestamp': 1254205102,
 166                 'upload_date': '20090929',
 167             },
 168             'params': {
 169                 'skip_download': True,
 170             },
 171         },
 172         {
 173             'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
 174             'info_dict': {
 175                 'id': '361883',
 176                 'ext': 'mp4',
 177                 'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
 178                 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
 179                 'duration': 2594,
 180                 'timestamp': 1393236292,
 181                 'upload_date': '20140224',
 182             },
 183             'params': {
 184                 'skip_download': True,
 185             },
 186         },
 187         {
 188             'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
 189             'info_dict': {
 190                 'id': '624952',
 191                 'ext': 'flv',
 192                 'title': 'Здравей, България (12.06.2015 г.) ',
 193                 'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
 194                 'duration': 8838,
 195                 'timestamp': 1434100372,
 196                 'upload_date': '20150612',
 197             },
 198             'params': {
 199                 # rtmp download
 200                 'skip_download': True,
 201             },
 202         },
 203         {
 204             'url': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
 205             'only_matching': True,
 206         },
 207         {
 208             'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
 209             'only_matching': True,
 210         },
 211         {
 212             'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true',
 213             'only_matching': True,
 214         },
 215         {
 216             # views is null
 217             'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
 218             'only_matching': True,
 219         },
 220         {
 221             'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
 222             'only_matching': True,
 223         },
 224         {
 225             'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
 226             'only_matching': True,
 227         },
 228         {
 229             'url': 'mtg:418113',
 230             'only_matching': True,
 231         }
 232     ]
 233
 234     def _real_extract(self, url):
 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)
 239         if geo_country:
 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')
 243
 244         title = video['title']
 245
 246         try:
 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)
 254             raise
 255
 256         quality = qualities(['hls', 'medium', 'high'])
 257         formats = []
 258         for format_id, video_url in streams.get('streams', {}).items():
 259             video_url = url_or_none(video_url)
 260             if not video_url:
 261                 continue
 262             ext = determine_ext(video_url)
 263             if ext == 'f4m':
 264                 formats.extend(self._extract_f4m_formats(
 265                     update_url_query(video_url, {
 266                         'hdcore': '3.5.0',
 267                         'plugin': 'aasp-3.5.0.151.81'
 268                     }), video_id, f4m_id='hds', fatal=False))
 269             elif ext == 'm3u8':
 270                 formats.extend(self._extract_m3u8_formats(
 271                     video_url, video_id, 'mp4', 'm3u8_native',
 272                     m3u8_id='hls', fatal=False))
 273             else:
 274                 fmt = {
 275                     'format_id': format_id,
 276                     'quality': quality(format_id),
 277                     'ext': ext,
 278                 }
 279                 if video_url.startswith('rtmp'):
 280                     m = re.search(
 281                         r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
 282                     if not m:
 283                         continue
 284                     fmt.update({
 285                         'ext': 'flv',
 286                         'url': m.group('url'),
 287                         'app': m.group('app'),
 288                         'play_path': m.group('playpath'),
 289                         'preference': -1,
 290                     })
 291                 else:
 292                     fmt.update({
 293                         'url': video_url,
 294                     })
 295                 formats.append(fmt)
 296
 297         if not formats and video.get('is_geo_blocked'):
 298             self.raise_geo_restricted(
 299                 'This content might not be available in your country due to copyright reasons')
 300
 301         self._sort_formats(formats)
 302
 303         # TODO: webvtt in m3u8
 304         subtitles = {}
 305         sami_path = video.get('sami_path')
 306         if sami_path:
 307             lang = self._search_regex(
 308                 r'_([a-z]{2})\.xml', sami_path, 'lang',
 309                 default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
 310             subtitles[lang] = [{
 311                 'url': sami_path,
 312             }]
 313
 314         series = video.get('format_title')
 315         episode_number = int_or_none(video.get('format_position', {}).get('episode'))
 316         season = video.get('_embedded', {}).get('season', {}).get('title')
 317         season_number = int_or_none(video.get('format_position', {}).get('season'))
 318
 319         return {
 320             'id': video_id,
 321             'title': title,
 322             'description': video.get('description'),
 323             'series': series,
 324             'episode_number': episode_number,
 325             'season': season,
 326             'season_number': season_number,
 327             'duration': int_or_none(video.get('duration')),
 328             'timestamp': parse_iso8601(video.get('created_at')),
 329             'view_count': try_get(video, lambda x: x['views']['total'], int),
 330             'age_limit': int_or_none(video.get('age_limit', 0)),
 331             'formats': formats,
 332             'subtitles': subtitles,
 333         }
 334
 335
 336 class ViafreeIE(InfoExtractor):
 337     _VALID_URL = r'''(?x)
 338                     https?://
 339                         (?:www\.)?
 340                         viafree\.(?P<country>dk|no|se)
 341                         /(?P<id>program(?:mer)?/(?:[^/]+/)+[^/?#&]+)
 342                     '''
 343     _TESTS = [{
 344         'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
 345         'info_dict': {
 346             'id': '757786',
 347             'ext': 'mp4',
 348             'title': 'Det beste vorspielet - Sesong 2 - Episode 1',
 349             'description': 'md5:b632cb848331404ccacd8cd03e83b4c3',
 350             'series': 'Det beste vorspielet',
 351             'season_number': 2,
 352             'duration': 1116,
 353             'timestamp': 1471200600,
 354             'upload_date': '20160814',
 355         },
 356         'params': {
 357             'skip_download': True,
 358         },
 359     }, {
 360         # with relatedClips
 361         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
 362         'only_matching': True,
 363     }, {
 364         # Different og:image URL schema
 365         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
 366         'only_matching': True,
 367     }, {
 368         'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
 369         'only_matching': True,
 370     }, {
 371         'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
 372         'only_matching': True,
 373     }]
 374     _GEO_BYPASS = False
 375
 376     @classmethod
 377     def suitable(cls, url):
 378         return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
 379
 380     def _real_extract(self, url):
 381         country, path = re.match(self._VALID_URL, url).groups()
 382         content = self._download_json(
 383             'https://viafree-content.mtg-api.com/viafree-content/v1/%s/path/%s' % (country, path), path)
 384         program = content['_embedded']['viafreeBlocks'][0]['_embedded']['program']
 385         guid = program['guid']
 386         meta = content['meta']
 387         title = meta['title']
 388
 389         try:
 390             stream_href = self._download_json(
 391                 program['_links']['streamLink']['href'], guid,
 392                 headers=self.geo_verification_headers())['embedded']['prioritizedStreams'][0]['links']['stream']['href']
 393         except ExtractorError as e:
 394             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 395                 self.raise_geo_restricted(countries=[country])
 396             raise
 397
 398         formats = self._extract_m3u8_formats(stream_href, guid, 'mp4')
 399         self._sort_formats(formats)
 400         episode = program.get('episode') or {}
 401
 402         return {
 403             'id': guid,
 404             'title': title,
 405             'thumbnail': meta.get('image'),
 406             'description': meta.get('description'),
 407             'series': episode.get('seriesTitle'),
 408             'episode_number': int_or_none(episode.get('episodeNumber')),
 409             'season_number': int_or_none(episode.get('seasonNumber')),
 410             'duration': int_or_none(try_get(program, lambda x: x['video']['duration']['milliseconds']), 1000),
 411             'timestamp': parse_iso8601(try_get(program, lambda x: x['availability']['start'])),
 412             'formats': formats,
 413         }
 414
 415
 416 class TVPlayHomeIE(InfoExtractor):
 417     _VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)'
 418     _TESTS = [{
 419         'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
 420         'info_dict': {
 421             'id': '366367',
 422             'ext': 'mp4',
 423             'title': 'Aferistai',
 424             'description': 'Aferistai. Kalėdinė pasaka.',
 425             'series': 'Aferistai [N-7]',
 426             'season': '1 sezonas',
 427             'season_number': 1,
 428             'duration': 464,
 429             'timestamp': 1394209658,
 430             'upload_date': '20140307',
 431             'age_limit': 18,
 432         },
 433         'params': {
 434             'skip_download': True,
 435         },
 436         'add_ie': [TVPlayIE.ie_key()],
 437     }, {
 438         'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
 439         'only_matching': True,
 440     }, {
 441         'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
 442         'only_matching': True,
 443     }]
 444
 445     def _real_extract(self, url):
 446         video_id = self._match_id(url)
 447
 448         webpage = self._download_webpage(url, video_id)
 449
 450         video_id = self._search_regex(
 451             r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id')
 452
 453         if len(video_id) < 8:
 454             return self.url_result(
 455                 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
 456
 457         m3u8_url = self._search_regex(
 458             r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
 459             'm3u8 url', group='url')
 460
 461         formats = self._extract_m3u8_formats(
 462             m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
 463             m3u8_id='hls')
 464         self._sort_formats(formats)
 465
 466         title = self._search_regex(
 467             r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
 468             'title', default=None, group='value') or self._html_search_meta(
 469             'title', webpage, default=None) or self._og_search_title(
 470             webpage)
 471
 472         description = self._html_search_meta(
 473             'description', webpage,
 474             default=None) or self._og_search_description(webpage)
 475
 476         thumbnail = self._search_regex(
 477             r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
 478             'thumbnail', default=None, group='url') or self._html_search_meta(
 479             'thumbnail', webpage, default=None) or self._og_search_thumbnail(
 480             webpage)
 481
 482         duration = int_or_none(self._search_regex(
 483             r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
 484             fatal=False))
 485
 486         season = self._search_regex(
 487             (r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
 488              r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
 489             'season', default=None, group='value')
 490         season_number = int_or_none(self._search_regex(
 491             r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
 492             default=None))
 493         episode = self._search_regex(
 494             (r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
 495              r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
 496             'episode', default=None, group='value')
 497         episode_number = int_or_none(self._search_regex(
 498             r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
 499             default=None))
 500
 501         return {
 502             'id': video_id,
 503             'title': title,
 504             'description': description,
 505             'thumbnail': thumbnail,
 506             'duration': duration,
 507             'season': season,
 508             'season_number': season_number,
 509             'episode': episode,
 510             'episode_number': episode_number,
 511             'formats': formats,
 512         }