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     url_or_none,
  23 )
  24
  25
  26 class TVPlayIE(InfoExtractor):
  27     IE_NAME = 'mtg'
  28     IE_DESC = 'MTG services'
  29     _VALID_URL = r'''(?x)
  30                     (?:
  31                         mtg:|
  32                         https?://
  33                             (?:www\.)?
  34                             (?:
  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
  41                             )
  42                             /(?:[^/]+/)+
  43                         )
  44                         (?P<id>\d+)
  45                     '''
  46     _TESTS = [
  47         {
  48             'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
  49             'md5': 'a1612fe0849455423ad8718fe049be21',
  50             'info_dict': {
  51                 'id': '418113',
  52                 'ext': 'mp4',
  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',
  56                 'season': '2.sezona',
  57                 'season_number': 2,
  58                 'duration': 25,
  59                 'timestamp': 1406097056,
  60                 'upload_date': '20140723',
  61             },
  62         },
  63         {
  64             'url': 'http://play.tv3.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
  65             'info_dict': {
  66                 'id': '409229',
  67                 'ext': 'flv',
  68                 'title': 'Moterys meluoja geriau',
  69                 'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
  70                 'series': 'Moterys meluoja geriau',
  71                 'episode_number': 47,
  72                 'season': '1 sezonas',
  73                 'season_number': 1,
  74                 'duration': 1330,
  75                 'timestamp': 1403769181,
  76                 'upload_date': '20140626',
  77             },
  78             'params': {
  79                 # rtmp download
  80                 'skip_download': True,
  81             },
  82         },
  83         {
  84             'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
  85             'info_dict': {
  86                 'id': '238551',
  87                 'ext': 'flv',
  88                 'title': 'Kodu keset linna 398537',
  89                 'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
  90                 'duration': 1257,
  91                 'timestamp': 1292449761,
  92                 'upload_date': '20101215',
  93             },
  94             'params': {
  95                 # rtmp download
  96                 'skip_download': True,
  97             },
  98         },
  99         {
 100             'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
 101             'info_dict': {
 102                 'id': '395385',
 103                 'ext': 'mp4',
 104                 'title': 'Husräddarna S02E07',
 105                 'description': 'md5:f210c6c89f42d4fc39faa551be813777',
 106                 'duration': 2574,
 107                 'timestamp': 1400596321,
 108                 'upload_date': '20140520',
 109             },
 110             'params': {
 111                 'skip_download': True,
 112             },
 113         },
 114         {
 115             'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
 116             'info_dict': {
 117                 'id': '266636',
 118                 'ext': 'mp4',
 119                 'title': 'Den sista dokusåpan S01E08',
 120                 'description': 'md5:295be39c872520221b933830f660b110',
 121                 'duration': 1492,
 122                 'timestamp': 1330522854,
 123                 'upload_date': '20120229',
 124                 'age_limit': 18,
 125             },
 126             'params': {
 127                 'skip_download': True,
 128             },
 129         },
 130         {
 131             'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
 132             'info_dict': {
 133                 'id': '282756',
 134                 'ext': 'mp4',
 135                 'title': 'Antikjakten S01E10',
 136                 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
 137                 'duration': 2646,
 138                 'timestamp': 1348575868,
 139                 'upload_date': '20120925',
 140             },
 141             'params': {
 142                 'skip_download': True,
 143             },
 144         },
 145         {
 146             'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
 147             'info_dict': {
 148                 'id': '230898',
 149                 'ext': 'mp4',
 150                 'title': 'Anna Anka søker assistent - Ep. 8',
 151                 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
 152                 'duration': 2656,
 153                 'timestamp': 1277720005,
 154                 'upload_date': '20100628',
 155             },
 156             'params': {
 157                 'skip_download': True,
 158             },
 159         },
 160         {
 161             'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
 162             'info_dict': {
 163                 'id': '21873',
 164                 'ext': 'mp4',
 165                 'title': 'Budbringerne program 10',
 166                 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
 167                 'duration': 1297,
 168                 'timestamp': 1254205102,
 169                 'upload_date': '20090929',
 170             },
 171             'params': {
 172                 'skip_download': True,
 173             },
 174         },
 175         {
 176             'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
 177             'info_dict': {
 178                 'id': '361883',
 179                 'ext': 'mp4',
 180                 'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
 181                 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
 182                 'duration': 2594,
 183                 'timestamp': 1393236292,
 184                 'upload_date': '20140224',
 185             },
 186             'params': {
 187                 'skip_download': True,
 188             },
 189         },
 190         {
 191             'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
 192             'info_dict': {
 193                 'id': '624952',
 194                 'ext': 'flv',
 195                 'title': 'Здравей, България (12.06.2015 г.) ',
 196                 'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
 197                 'duration': 8838,
 198                 'timestamp': 1434100372,
 199                 'upload_date': '20150612',
 200             },
 201             'params': {
 202                 # rtmp download
 203                 'skip_download': True,
 204             },
 205         },
 206         {
 207             'url': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
 208             'only_matching': True,
 209         },
 210         {
 211             'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
 212             'only_matching': True,
 213         },
 214         {
 215             'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true',
 216             'only_matching': True,
 217         },
 218         {
 219             # views is null
 220             'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
 221             'only_matching': True,
 222         },
 223         {
 224             'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
 225             'only_matching': True,
 226         },
 227         {
 228             'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
 229             'only_matching': True,
 230         },
 231         {
 232             'url': 'mtg:418113',
 233             'only_matching': True,
 234         }
 235     ]
 236
 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'),
 241         })
 242
 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)
 247         if geo_country:
 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')
 251
 252         title = video['title']
 253
 254         try:
 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)
 262             raise
 263
 264         quality = qualities(['hls', 'medium', 'high'])
 265         formats = []
 266         for format_id, video_url in streams.get('streams', {}).items():
 267             video_url = url_or_none(video_url)
 268             if not video_url:
 269                 continue
 270             ext = determine_ext(video_url)
 271             if ext == 'f4m':
 272                 formats.extend(self._extract_f4m_formats(
 273                     update_url_query(video_url, {
 274                         'hdcore': '3.5.0',
 275                         'plugin': 'aasp-3.5.0.151.81'
 276                     }), video_id, f4m_id='hds', fatal=False))
 277             elif ext == 'm3u8':
 278                 formats.extend(self._extract_m3u8_formats(
 279                     video_url, video_id, 'mp4', 'm3u8_native',
 280                     m3u8_id='hls', fatal=False))
 281             else:
 282                 fmt = {
 283                     'format_id': format_id,
 284                     'quality': quality(format_id),
 285                     'ext': ext,
 286                 }
 287                 if video_url.startswith('rtmp'):
 288                     if smuggled_data.get('skip_rtmp'):
 289                         continue
 290                     m = re.search(
 291                         r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
 292                     if not m:
 293                         continue
 294                     fmt.update({
 295                         'ext': 'flv',
 296                         'url': m.group('url'),
 297                         'app': m.group('app'),
 298                         'play_path': m.group('playpath'),
 299                         'preference': -1,
 300                     })
 301                 else:
 302                     fmt.update({
 303                         'url': video_url,
 304                     })
 305                 formats.append(fmt)
 306
 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')
 310
 311         self._sort_formats(formats)
 312
 313         # TODO: webvtt in m3u8
 314         subtitles = {}
 315         sami_path = video.get('sami_path')
 316         if 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])
 320             subtitles[lang] = [{
 321                 'url': sami_path,
 322             }]
 323
 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'))
 328
 329         return {
 330             'id': video_id,
 331             'title': title,
 332             'description': video.get('description'),
 333             'series': series,
 334             'episode_number': episode_number,
 335             'season': season,
 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)),
 341             'formats': formats,
 342             'subtitles': subtitles,
 343         }
 344
 345
 346 class ViafreeIE(InfoExtractor):
 347     _VALID_URL = r'''(?x)
 348                     https?://
 349                         (?:www\.)?
 350                         viafree\.
 351                         (?:
 352                             (?:dk|no)/programmer|
 353                             se/program
 354                         )
 355                         /(?:[^/]+/)+(?P<id>[^/?#&]+)
 356                     '''
 357     _TESTS = [{
 358         'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
 359         'info_dict': {
 360             'id': '395375',
 361             'ext': 'mp4',
 362             'title': 'Husräddarna S02E02',
 363             'description': 'md5:4db5c933e37db629b5a2f75dfb34829e',
 364             'series': 'Husräddarna',
 365             'season': 'Säsong 2',
 366             'season_number': 2,
 367             'duration': 2576,
 368             'timestamp': 1400596321,
 369             'upload_date': '20140520',
 370         },
 371         'params': {
 372             'skip_download': True,
 373         },
 374         'add_ie': [TVPlayIE.ie_key()],
 375     }, {
 376         # with relatedClips
 377         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
 378         'info_dict': {
 379             'id': '758770',
 380             'ext': 'mp4',
 381             'title': 'Sommaren med YouTube-stjärnorna S01E01',
 382             'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
 383             'series': 'Sommaren med YouTube-stjärnorna',
 384             'season': 'Säsong 1',
 385             'season_number': 1,
 386             'duration': 1326,
 387             'timestamp': 1470905572,
 388             'upload_date': '20160811',
 389         },
 390         'params': {
 391             'skip_download': True,
 392         },
 393         'add_ie': [TVPlayIE.ie_key()],
 394     }, {
 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,
 398     }, {
 399         'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
 400         'only_matching': True,
 401     }, {
 402         'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
 403         'only_matching': True,
 404     }]
 405
 406     @classmethod
 407     def suitable(cls, url):
 408         return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
 409
 410     def _real_extract(self, url):
 411         video_id = self._match_id(url)
 412
 413         webpage = self._download_webpage(url, video_id)
 414
 415         data = self._parse_json(
 416             self._search_regex(
 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)
 422
 423         video_id = None
 424
 425         if data:
 426             video_id = try_get(
 427                 data, lambda x: x['context']['dispatcher']['stores'][
 428                     'ContentPageProgramStore']['currentVideo']['id'],
 429                 compat_str)
 430
 431         # Fallback #1 (extract from og:image URL schema)
 432         if not video_id:
 433             thumbnail = self._og_search_thumbnail(webpage, default=None)
 434             if thumbnail:
 435                 video_id = self._search_regex(
 436                     # Patterns seen:
 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)
 441
 442         # Fallback #2. Extract from raw JSON string.
 443         # May extract wrong video id if relatedClips is present.
 444         if not video_id:
 445             video_id = self._search_regex(
 446                 r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
 447                 webpage, 'video id')
 448
 449         return self.url_result(
 450             smuggle_url(
 451                 'mtg:%s' % video_id,
 452                 {
 453                     'geo_countries': [
 454                         compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]],
 455                     # rtmp host mtgfs.fplive.net for viafree is unresolvable
 456                     'skip_rtmp': True,
 457                 }),
 458             ie=TVPlayIE.ie_key(), video_id=video_id)
 459
 460
 461 class TVPlayHomeIE(InfoExtractor):
 462     _VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)'
 463     _TESTS = [{
 464         'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
 465         'info_dict': {
 466             'id': '366367',
 467             'ext': 'mp4',
 468             'title': 'Aferistai',
 469             'description': 'Aferistai. Kalėdinė pasaka.',
 470             'series': 'Aferistai [N-7]',
 471             'season': '1 sezonas',
 472             'season_number': 1,
 473             'duration': 464,
 474             'timestamp': 1394209658,
 475             'upload_date': '20140307',
 476             'age_limit': 18,
 477         },
 478         'params': {
 479             'skip_download': True,
 480         },
 481         'add_ie': [TVPlayIE.ie_key()],
 482     }, {
 483         'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
 484         'only_matching': True,
 485     }, {
 486         'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
 487         'only_matching': True,
 488     }]
 489
 490     def _real_extract(self, url):
 491         video_id = self._match_id(url)
 492
 493         webpage = self._download_webpage(url, video_id)
 494
 495         video_id = self._search_regex(
 496             r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id')
 497
 498         if len(video_id) < 8:
 499             return self.url_result(
 500                 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
 501
 502         m3u8_url = self._search_regex(
 503             r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
 504             'm3u8 url', group='url')
 505
 506         formats = self._extract_m3u8_formats(
 507             m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
 508             m3u8_id='hls')
 509         self._sort_formats(formats)
 510
 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(
 515             webpage)
 516
 517         description = self._html_search_meta(
 518             'description', webpage,
 519             default=None) or self._og_search_description(webpage)
 520
 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(
 525             webpage)
 526
 527         duration = int_or_none(self._search_regex(
 528             r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
 529             fatal=False))
 530
 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',
 537             default=None))
 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',
 544             default=None))
 545
 546         return {
 547             'id': video_id,
 548             'title': title,
 549             'description': description,
 550             'thumbnail': thumbnail,
 551             'duration': duration,
 552             'season': season,
 553             'season_number': season_number,
 554             'episode': episode,
 555             'episode_number': episode_number,
 556             'formats': formats,
 557         }