Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/corus.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .theplatform import ThePlatformFeedIE
   7 from ..utils import (
   8     dict_get,
   9     ExtractorError,
  10     float_or_none,
  11     int_or_none,
  12 )
  13
  14
  15 class CorusIE(ThePlatformFeedIE):
  16     _VALID_URL = r'''(?x)
  17                     https?://
  18                         (?:www\.)?
  19                         (?P<domain>
  20                             (?:
  21                                 globaltv|
  22                                 etcanada|
  23                                 seriesplus|
  24                                 wnetwork|
  25                                 ytv
  26                             )\.com|
  27                             (?:
  28                                 hgtv|
  29                                 foodnetwork|
  30                                 slice|
  31                                 history|
  32                                 showcase|
  33                                 bigbrothercanada|
  34                                 abcspark|
  35                                 disney(?:channel|lachaine)
  36                             )\.ca
  37                         )
  38                         /(?:[^/]+/)*
  39                         (?:
  40                             video\.html\?.*?\bv=|
  41                             videos?/(?:[^/]+/)*(?:[a-z0-9-]+-)?
  42                         )
  43                         (?P<id>
  44                             [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}|
  45                             (?:[A-Z]{4})?\d{12,20}
  46                         )
  47                     '''
  48     _TESTS = [{
  49         'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/',
  50         'info_dict': {
  51             'id': '870923331648',
  52             'ext': 'mp4',
  53             'title': 'Movie Night Popcorn with Bryan',
  54             'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.',
  55             'upload_date': '20170206',
  56             'timestamp': 1486392197,
  57         },
  58         'params': {
  59             'format': 'bestvideo',
  60             'skip_download': True,
  61         },
  62         'expected_warnings': ['Failed to parse JSON'],
  63     }, {
  64         'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753',
  65         'only_matching': True,
  66     }, {
  67         'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/',
  68         'only_matching': True,
  69     }, {
  70         'url': 'http://www.history.ca/the-world-without-canada/video/full-episodes/natural-resources/video.html?v=955054659646#video',
  71         'only_matching': True,
  72     }, {
  73         'url': 'http://www.showcase.ca/eyewitness/video/eyewitness++106/video.html?v=955070531919&p=1&s=da#video',
  74         'only_matching': True,
  75     }, {
  76         'url': 'http://www.bigbrothercanada.ca/video/1457812035894/',
  77         'only_matching': True
  78     }, {
  79         'url': 'https://www.bigbrothercanada.ca/video/big-brother-canada-704/1457812035894/',
  80         'only_matching': True
  81     }, {
  82         'url': 'https://www.seriesplus.com/emissions/dre-mary-mort-sur-ordonnance/videos/deux-coeurs-battant/SERP0055626330000200/',
  83         'only_matching': True
  84     }, {
  85         'url': 'https://www.disneychannel.ca/shows/gabby-duran-the-unsittables/video/crybaby-duran-clip/2f557eec-0588-11ea-ae2b-e2c6776b770e/',
  86         'only_matching': True
  87     }]
  88     _GEO_BYPASS = False
  89     _SITE_MAP = {
  90         'globaltv': 'series',
  91         'etcanada': 'series',
  92         'foodnetwork': 'food',
  93         'bigbrothercanada': 'series',
  94         'disneychannel': 'disneyen',
  95         'disneylachaine': 'disneyfr',
  96     }
  97
  98     def _real_extract(self, url):
  99         domain, video_id = re.match(self._VALID_URL, url).groups()
 100         site = domain.split('.')[0]
 101         path = self._SITE_MAP.get(site, site)
 102         if path != 'series':
 103             path = 'migration/' + path
 104         video = self._download_json(
 105             'https://globalcontent.corusappservices.com/templates/%s/playlist/' % path,
 106             video_id, query={'byId': video_id},
 107             headers={'Accept': 'application/json'})[0]
 108         title = video['title']
 109
 110         formats = []
 111         for source in video.get('sources', []):
 112             smil_url = source.get('file')
 113             if not smil_url:
 114                 continue
 115             source_type = source.get('type')
 116             note = 'Downloading%s smil file' % (' ' + source_type if source_type else '')
 117             resp = self._download_webpage(
 118                 smil_url, video_id, note, fatal=False,
 119                 headers=self.geo_verification_headers())
 120             if not resp:
 121                 continue
 122             error = self._parse_json(resp, video_id, fatal=False)
 123             if error:
 124                 if error.get('exception') == 'GeoLocationBlocked':
 125                     self.raise_geo_restricted(countries=['CA'])
 126                 raise ExtractorError(error['description'])
 127             smil = self._parse_xml(resp, video_id, fatal=False)
 128             if smil is None:
 129                 continue
 130             namespace = self._parse_smil_namespace(smil)
 131             formats.extend(self._parse_smil_formats(
 132                 smil, smil_url, video_id, namespace))
 133         if not formats and video.get('drm'):
 134             raise ExtractorError('This video is DRM protected.', expected=True)
 135         self._sort_formats(formats)
 136
 137         subtitles = {}
 138         for track in video.get('tracks', []):
 139             track_url = track.get('file')
 140             if not track_url:
 141                 continue
 142             lang = 'fr' if site in ('disneylachaine', 'seriesplus') else 'en'
 143             subtitles.setdefault(lang, []).append({'url': track_url})
 144
 145         metadata = video.get('metadata') or {}
 146         get_number = lambda x: int_or_none(video.get('pl1$' + x) or metadata.get(x + 'Number'))
 147
 148         return {
 149             'id': video_id,
 150             'title': title,
 151             'formats': formats,
 152             'thumbnail': dict_get(video, ('defaultThumbnailUrl', 'thumbnail', 'image')),
 153             'description': video.get('description'),
 154             'timestamp': int_or_none(video.get('availableDate'), 1000),
 155             'subtitles': subtitles,
 156             'duration': float_or_none(metadata.get('duration')),
 157             'series': dict_get(video, ('show', 'pl1$show')),
 158             'season_number': get_number('season'),
 159             'episode_number': get_number('episode'),
 160         }