yt_dlp/extractor/corus.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .theplatform import ThePlatformFeedIE
   6 from ..utils import (
   7     dict_get,
   8     ExtractorError,
   9     float_or_none,
  10     int_or_none,
  11 )
  12
  13
  14 class CorusIE(ThePlatformFeedIE):
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         (?:www\.)?
  18                         (?P<domain>
  19                             (?:
  20                                 globaltv|
  21                                 etcanada|
  22                                 seriesplus|
  23                                 wnetwork|
  24                                 ytv
  25                             )\.com|
  26                             (?:
  27                                 hgtv|
  28                                 foodnetwork|
  29                                 slice|
  30                                 history|
  31                                 showcase|
  32                                 bigbrothercanada|
  33                                 abcspark|
  34                                 disney(?:channel|lachaine)
  35                             )\.ca
  36                         )
  37                         /(?:[^/]+/)*
  38                         (?:
  39                             video\.html\?.*?\bv=|
  40                             videos?/(?:[^/]+/)*(?:[a-z0-9-]+-)?
  41                         )
  42                         (?P<id>
  43                             [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}|
  44                             (?:[A-Z]{4})?\d{12,20}
  45                         )
  46                     '''
  47     _TESTS = [{
  48         'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/',
  49         'info_dict': {
  50             'id': '870923331648',
  51             'ext': 'mp4',
  52             'title': 'Movie Night Popcorn with Bryan',
  53             'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.',
  54             'upload_date': '20170206',
  55             'timestamp': 1486392197,
  56         },
  57         'params': {
  58             'format': 'bestvideo',
  59             'skip_download': True,
  60         },
  61         'expected_warnings': ['Failed to parse JSON'],
  62     }, {
  63         'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753',
  64         'only_matching': True,
  65     }, {
  66         'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/',
  67         'only_matching': True,
  68     }, {
  69         'url': 'http://www.history.ca/the-world-without-canada/video/full-episodes/natural-resources/video.html?v=955054659646#video',
  70         'only_matching': True,
  71     }, {
  72         'url': 'http://www.showcase.ca/eyewitness/video/eyewitness++106/video.html?v=955070531919&p=1&s=da#video',
  73         'only_matching': True,
  74     }, {
  75         'url': 'http://www.bigbrothercanada.ca/video/1457812035894/',
  76         'only_matching': True
  77     }, {
  78         'url': 'https://www.bigbrothercanada.ca/video/big-brother-canada-704/1457812035894/',
  79         'only_matching': True
  80     }, {
  81         'url': 'https://www.seriesplus.com/emissions/dre-mary-mort-sur-ordonnance/videos/deux-coeurs-battant/SERP0055626330000200/',
  82         'only_matching': True
  83     }, {
  84         'url': 'https://www.disneychannel.ca/shows/gabby-duran-the-unsittables/video/crybaby-duran-clip/2f557eec-0588-11ea-ae2b-e2c6776b770e/',
  85         'only_matching': True
  86     }]
  87     _GEO_BYPASS = False
  88     _SITE_MAP = {
  89         'globaltv': 'series',
  90         'etcanada': 'series',
  91         'foodnetwork': 'food',
  92         'bigbrothercanada': 'series',
  93         'disneychannel': 'disneyen',
  94         'disneylachaine': 'disneyfr',
  95     }
  96
  97     def _real_extract(self, url):
  98         domain, video_id = self._match_valid_url(url).groups()
  99         site = domain.split('.')[0]
 100         path = self._SITE_MAP.get(site, site)
 101         if path != 'series':
 102             path = 'migration/' + path
 103         video = self._download_json(
 104             'https://globalcontent.corusappservices.com/templates/%s/playlist/' % path,
 105             video_id, query={'byId': video_id},
 106             headers={'Accept': 'application/json'})[0]
 107         title = video['title']
 108
 109         formats = []
 110         for source in video.get('sources', []):
 111             smil_url = source.get('file')
 112             if not smil_url:
 113                 continue
 114             source_type = source.get('type')
 115             note = 'Downloading%s smil file' % (' ' + source_type if source_type else '')
 116             resp = self._download_webpage(
 117                 smil_url, video_id, note, fatal=False,
 118                 headers=self.geo_verification_headers())
 119             if not resp:
 120                 continue
 121             error = self._parse_json(resp, video_id, fatal=False)
 122             if error:
 123                 if error.get('exception') == 'GeoLocationBlocked':
 124                     self.raise_geo_restricted(countries=['CA'])
 125                 raise ExtractorError(error['description'])
 126             smil = self._parse_xml(resp, video_id, fatal=False)
 127             if smil is None:
 128                 continue
 129             namespace = self._parse_smil_namespace(smil)
 130             formats.extend(self._parse_smil_formats(
 131                 smil, smil_url, video_id, namespace))
 132         if not formats and video.get('drm'):
 133             self.report_drm(video_id)
 134         self._sort_formats(formats)
 135
 136         subtitles = {}
 137         for track in video.get('tracks', []):
 138             track_url = track.get('file')
 139             if not track_url:
 140                 continue
 141             lang = 'fr' if site in ('disneylachaine', 'seriesplus') else 'en'
 142             subtitles.setdefault(lang, []).append({'url': track_url})
 143
 144         metadata = video.get('metadata') or {}
 145         get_number = lambda x: int_or_none(video.get('pl1$' + x) or metadata.get(x + 'Number'))
 146
 147         return {
 148             'id': video_id,
 149             'title': title,
 150             'formats': formats,
 151             'thumbnail': dict_get(video, ('defaultThumbnailUrl', 'thumbnail', 'image')),
 152             'description': video.get('description'),
 153             'timestamp': int_or_none(video.get('availableDate'), 1000),
 154             'subtitles': subtitles,
 155             'duration': float_or_none(metadata.get('duration')),
 156             'series': dict_get(video, ('show', 'pl1$show')),
 157             'season_number': get_number('season'),
 158             'episode_number': get_number('episode'),
 159         }