youtube_dl/extractor/nowness.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .brightcove import BrightcoveIE
   5 from .common import InfoExtractor
   6 from ..utils import ExtractorError
   7 from ..compat import compat_urllib_request
   8
   9
  10 class NownessBaseIE(InfoExtractor):
  11     def extract_url_result(self, post):
  12         if post['type'] == 'video':
  13             for media in post['media']:
  14                 if media['type'] == 'video':
  15                     video_id = media['content']
  16                     source = media['source']
  17                     if source == 'brightcove':
  18                         player_code = self._download_webpage(
  19                             'http://www.nowness.com/iframe?id=%s' % video_id, video_id,
  20                             note='Downloading player JavaScript',
  21                             errnote='Player download failed')
  22                         bc_url = BrightcoveIE._extract_brightcove_url(player_code)
  23                         if bc_url is None:
  24                             raise ExtractorError('Could not find player definition')
  25                         return self.url_result(bc_url, 'Brightcove')
  26                     elif source == 'vimeo':
  27                         return self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
  28                     elif source == 'youtube':
  29                         return self.url_result(video_id, 'Youtube')
  30                     elif source == 'cinematique':
  31                         # youtube-dl currently doesn't support cinematique
  32                         # return self.url_result('http://cinematique.com/embed/%s' % video_id, 'Cinematique')
  33                         pass
  34
  35     def api_request(self, url, request_path):
  36         display_id = self._match_id(url)
  37
  38         lang = 'zh-cn' if 'cn.nowness.com' in url else 'en-us'
  39         request = compat_urllib_request.Request('http://api.nowness.com/api/' + request_path % display_id, headers={
  40             'X-Nowness-Language': lang,
  41         })
  42         json_data = self._download_json(request, display_id)
  43         return display_id, json_data
  44
  45
  46 class NownessIE(NownessBaseIE):
  47     IE_NAME = 'nowness'
  48     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/(?:story|(?:series|category)/[^/]+)/(?P<id>[^/]+?)(?:$|[?#])'
  49     _TESTS = [
  50         {
  51             'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation',
  52             'md5': '068bc0202558c2e391924cb8cc470676',
  53             'info_dict': {
  54                 'id': '2520295746001',
  55                 'ext': 'mp4',
  56                 'title': 'Candor: The Art of Gesticulation',
  57                 'description': 'Candor: The Art of Gesticulation',
  58                 'thumbnail': 're:^https?://.*\.jpg',
  59                 'uploader': 'Nowness',
  60             }
  61         },
  62         {
  63             'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr',
  64             'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
  65             'info_dict': {
  66                 'id': '3716354522001',
  67                 'ext': 'mp4',
  68                 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
  69                 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
  70                 'thumbnail': 're:^https?://.*\.jpg',
  71                 'uploader': 'Nowness',
  72             }
  73         },
  74     ]
  75
  76     def _real_extract(self, url):
  77         display_id, post = self.api_request(url, 'post/getBySlug/%s')
  78         return self.extract_url_result(post)
  79
  80
  81 class NownessPlaylistIE(NownessBaseIE):
  82     IE_NAME = 'nowness:playlist'
  83     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P<id>\d+)'
  84     _TEST = {
  85         'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues',
  86         'info_dict':
  87         {
  88             'id': '3286',
  89         },
  90         'playlist_mincount': 8,
  91     }
  92
  93     def _real_extract(self, url):
  94         playlist_id, playlist = self.api_request(url, 'post?PlaylistId=%s')
  95         entries = [self.extract_url_result(item) for item in playlist['items']]
  96         return self.playlist_result(entries, playlist_id)
  97
  98
  99 class NownessSerieIE(NownessBaseIE):
 100     IE_NAME = 'nowness:serie'
 101     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P<id>[^/]+?)(?:$|[?#])'
 102     _TEST = {
 103         'url': 'https://www.nowness.com/series/60-seconds',
 104         'info_dict':
 105         {
 106             'id': '60',
 107         },
 108         'playlist_mincount': 4,
 109     }
 110
 111     def _real_extract(self, url):
 112         display_id, serie = self.api_request(url, 'series/getBySlug/%s')
 113         serie_id = str(serie['id'])
 114         entries = [self.extract_url_result(post) for post in serie['posts']]
 115         return self.playlist_result(entries, serie_id)