Raphaël G. Git Repositories - youtubedl/blob - 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     try_get,
  19     update_url_query,
  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\.novatv\.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': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
 205             'only_matching': True,
 206         },
 207         {
 208             # views is null
 209             'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
 210             'only_matching': True,
 211         },
 212         {
 213             'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
 214             'only_matching': True,
 215         },
 216         {
 217             'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
 218             'only_matching': True,
 219         },
 220         {
 221             'url': 'mtg:418113',
 222             'only_matching': True,
 223         }
 224     ]
 225
 226     def _real_extract(self, url):
 227         video_id = self._match_id(url)
 228
 229         video = self._download_json(
 230             'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
 231
 232         title = video['title']
 233
 234         try:
 235             streams = self._download_json(
 236                 'http://playapi.mtgx.tv/v3/videos/stream/%s' % video_id,
 237                 video_id, 'Downloading streams JSON')
 238         except ExtractorError as e:
 239             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 240                 msg = self._parse_json(e.cause.read().decode('utf-8'), video_id)
 241                 raise ExtractorError(msg['msg'], expected=True)
 242             raise
 243
 244         quality = qualities(['hls', 'medium', 'high'])
 245         formats = []
 246         for format_id, video_url in streams.get('streams', {}).items():
 247             if not video_url or not isinstance(video_url, compat_str):
 248                 continue
 249             ext = determine_ext(video_url)
 250             if ext == 'f4m':
 251                 formats.extend(self._extract_f4m_formats(
 252                     update_url_query(video_url, {
 253                         'hdcore': '3.5.0',
 254                         'plugin': 'aasp-3.5.0.151.81'
 255                     }), video_id, f4m_id='hds', fatal=False))
 256             elif ext == 'm3u8':
 257                 formats.extend(self._extract_m3u8_formats(
 258                     video_url, video_id, 'mp4', 'm3u8_native',
 259                     m3u8_id='hls', fatal=False))
 260             else:
 261                 fmt = {
 262                     'format_id': format_id,
 263                     'quality': quality(format_id),
 264                     'ext': ext,
 265                 }
 266                 if video_url.startswith('rtmp'):
 267                     m = re.search(
 268                         r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
 269                     if not m:
 270                         continue
 271                     fmt.update({
 272                         'ext': 'flv',
 273                         'url': m.group('url'),
 274                         'app': m.group('app'),
 275                         'play_path': m.group('playpath'),
 276                     })
 277                 else:
 278                     fmt.update({
 279                         'url': video_url,
 280                     })
 281                 formats.append(fmt)
 282
 283         if not formats and video.get('is_geo_blocked'):
 284             self.raise_geo_restricted(
 285                 'This content might not be available in your country due to copyright reasons')
 286
 287         self._sort_formats(formats)
 288
 289         # TODO: webvtt in m3u8
 290         subtitles = {}
 291         sami_path = video.get('sami_path')
 292         if sami_path:
 293             lang = self._search_regex(
 294                 r'_([a-z]{2})\.xml', sami_path, 'lang',
 295                 default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
 296             subtitles[lang] = [{
 297                 'url': sami_path,
 298             }]
 299
 300         series = video.get('format_title')
 301         episode_number = int_or_none(video.get('format_position', {}).get('episode'))
 302         season = video.get('_embedded', {}).get('season', {}).get('title')
 303         season_number = int_or_none(video.get('format_position', {}).get('season'))
 304
 305         return {
 306             'id': video_id,
 307             'title': title,
 308             'description': video.get('description'),
 309             'series': series,
 310             'episode_number': episode_number,
 311             'season': season,
 312             'season_number': season_number,
 313             'duration': int_or_none(video.get('duration')),
 314             'timestamp': parse_iso8601(video.get('created_at')),
 315             'view_count': try_get(video, lambda x: x['views']['total'], int),
 316             'age_limit': int_or_none(video.get('age_limit', 0)),
 317             'formats': formats,
 318             'subtitles': subtitles,
 319         }
 320
 321
 322 class ViafreeIE(InfoExtractor):
 323     _VALID_URL = r'''(?x)
 324                     https?://
 325                         (?:www\.)?
 326                         viafree\.
 327                         (?:
 328                             (?:dk|no)/programmer|
 329                             se/program
 330                         )
 331                         /(?:[^/]+/)+(?P<id>[^/?#&]+)
 332                     '''
 333     _TESTS = [{
 334         'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
 335         'info_dict': {
 336             'id': '395375',
 337             'ext': 'mp4',
 338             'title': 'Husräddarna S02E02',
 339             'description': 'md5:4db5c933e37db629b5a2f75dfb34829e',
 340             'series': 'Husräddarna',
 341             'season': 'Säsong 2',
 342             'season_number': 2,
 343             'duration': 2576,
 344             'timestamp': 1400596321,
 345             'upload_date': '20140520',
 346         },
 347         'params': {
 348             'skip_download': True,
 349         },
 350         'add_ie': [TVPlayIE.ie_key()],
 351     }, {
 352         # with relatedClips
 353         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
 354         'info_dict': {
 355             'id': '758770',
 356             'ext': 'mp4',
 357             'title': 'Sommaren med YouTube-stjärnorna S01E01',
 358             'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
 359             'series': 'Sommaren med YouTube-stjärnorna',
 360             'season': 'Säsong 1',
 361             'season_number': 1,
 362             'duration': 1326,
 363             'timestamp': 1470905572,
 364             'upload_date': '20160811',
 365         },
 366         'params': {
 367             'skip_download': True,
 368         },
 369         'add_ie': [TVPlayIE.ie_key()],
 370     }, {
 371         # Different og:image URL schema
 372         'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
 373         'only_matching': True,
 374     }, {
 375         'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
 376         'only_matching': True,
 377     }, {
 378         'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
 379         'only_matching': True,
 380     }]
 381
 382     @classmethod
 383     def suitable(cls, url):
 384         return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
 385
 386     def _real_extract(self, url):
 387         video_id = self._match_id(url)
 388
 389         webpage = self._download_webpage(url, video_id)
 390
 391         data = self._parse_json(
 392             self._search_regex(
 393                 r'(?s)window\.App\s*=\s*({.+?})\s*;\s*</script',
 394                 webpage, 'data', default='{}'),
 395             video_id, transform_source=lambda x: re.sub(
 396                 r'(?s)function\s+[a-zA-Z_][\da-zA-Z_]*\s*\([^)]*\)\s*{[^}]*}\s*',
 397                 'null', x), fatal=False)
 398
 399         video_id = None
 400
 401         if data:
 402             video_id = try_get(
 403                 data, lambda x: x['context']['dispatcher']['stores'][
 404                     'ContentPageProgramStore']['currentVideo']['id'],
 405                 compat_str)
 406
 407         # Fallback #1 (extract from og:image URL schema)
 408         if not video_id:
 409             thumbnail = self._og_search_thumbnail(webpage, default=None)
 410             if thumbnail:
 411                 video_id = self._search_regex(
 412                     # Patterns seen:
 413                     #  http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/inbox/765166/a2e95e5f1d735bab9f309fa345cc3f25.jpg
 414                     #  http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/seasons/15204/758770/4a5ba509ca8bc043e1ebd1a76131cdf2.jpg
 415                     r'https?://[^/]+/imagecache/(?:[^/]+/)+(\d{6,})/',
 416                     thumbnail, 'video id', default=None)
 417
 418         # Fallback #2. Extract from raw JSON string.
 419         # May extract wrong video id if relatedClips is present.
 420         if not video_id:
 421             video_id = self._search_regex(
 422                 r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
 423                 webpage, 'video id')
 424
 425         return self.url_result('mtg:%s' % video_id, TVPlayIE.ie_key())