yt_dlp/extractor/nowness.py

   1 from .brightcove import (
   2     BrightcoveLegacyIE,
   3     BrightcoveNewIE,
   4 )
   5 from .common import InfoExtractor
   6 from ..networking import Request
   7 from ..utils import ExtractorError
   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                             f'http://www.nowness.com/iframe?id={video_id}', video_id,
  20                             note='Downloading player JavaScript',
  21                             errnote='Unable to download player JavaScript')
  22                         bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code)
  23                         if bc_url:
  24                             return self.url_result(bc_url, BrightcoveLegacyIE.ie_key())
  25                         bc_url = BrightcoveNewIE._extract_url(self, player_code)
  26                         if bc_url:
  27                             return self.url_result(bc_url, BrightcoveNewIE.ie_key())
  28                         raise ExtractorError('Could not find player definition')
  29                     elif source == 'vimeo':
  30                         return self.url_result(f'http://vimeo.com/{video_id}', 'Vimeo')
  31                     elif source == 'youtube':
  32                         return self.url_result(video_id, 'Youtube')
  33                     elif source == 'cinematique':
  34                         # yt-dlp currently doesn't support cinematique
  35                         # return self.url_result('http://cinematique.com/embed/%s' % video_id, 'Cinematique')
  36                         pass
  37
  38     def _api_request(self, url, request_path):
  39         display_id = self._match_id(url)
  40         request = Request(
  41             'http://api.nowness.com/api/' + request_path % display_id,
  42             headers={
  43                 'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us',
  44             })
  45         return display_id, self._download_json(request, display_id)
  46
  47
  48 class NownessIE(NownessBaseIE):
  49     IE_NAME = 'nowness'
  50     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/(?:story|(?:series|category)/[^/]+)/(?P<id>[^/]+?)(?:$|[?#])'
  51     _TESTS = [{
  52         'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation',
  53         'md5': '068bc0202558c2e391924cb8cc470676',
  54         'info_dict': {
  55             'id': '2520295746001',
  56             'ext': 'mp4',
  57             'title': 'Candor: The Art of Gesticulation',
  58             'description': 'Candor: The Art of Gesticulation',
  59             'thumbnail': r're:^https?://.*\.jpg',
  60             'timestamp': 1446745676,
  61             'upload_date': '20151105',
  62             'uploader_id': '2385340575001',
  63         },
  64         'add_ie': ['BrightcoveNew'],
  65     }, {
  66         'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr',
  67         'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
  68         'info_dict': {
  69             'id': '3716354522001',
  70             'ext': 'mp4',
  71             'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
  72             'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
  73             'thumbnail': r're:^https?://.*\.jpg',
  74             'timestamp': 1407315371,
  75             'upload_date': '20140806',
  76             'uploader_id': '2385340575001',
  77         },
  78         'add_ie': ['BrightcoveNew'],
  79     }, {
  80         # vimeo
  81         'url': 'https://www.nowness.com/series/nowness-picks/jean-luc-godard-supercut',
  82         'md5': '9a5a6a8edf806407e411296ab6bc2a49',
  83         'info_dict': {
  84             'id': '130020913',
  85             'ext': 'mp4',
  86             'title': 'Bleu, Blanc, Rouge - A Godard Supercut',
  87             'description': 'md5:f0ea5f1857dffca02dbd37875d742cec',
  88             'thumbnail': r're:^https?://.*\.jpg',
  89             'upload_date': '20150607',
  90             'uploader': 'Cinema Sem Lei',
  91             'uploader_id': 'cinemasemlei',
  92         },
  93         'add_ie': ['Vimeo'],
  94     }]
  95
  96     def _real_extract(self, url):
  97         _, post = self._api_request(url, 'post/getBySlug/%s')
  98         return self._extract_url_result(post)
  99
 100
 101 class NownessPlaylistIE(NownessBaseIE):
 102     IE_NAME = 'nowness:playlist'
 103     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P<id>\d+)'
 104     _TEST = {
 105         'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues',
 106         'info_dict': {
 107             'id': '3286',
 108         },
 109         'playlist_mincount': 8,
 110     }
 111
 112     def _real_extract(self, url):
 113         playlist_id, playlist = self._api_request(url, 'post?PlaylistId=%s')
 114         entries = [self._extract_url_result(item) for item in playlist['items']]
 115         return self.playlist_result(entries, playlist_id)
 116
 117
 118 class NownessSeriesIE(NownessBaseIE):
 119     IE_NAME = 'nowness:series'
 120     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P<id>[^/]+?)(?:$|[?#])'
 121     _TEST = {
 122         'url': 'https://www.nowness.com/series/60-seconds',
 123         'info_dict': {
 124             'id': '60',
 125             'title': '60 Seconds',
 126             'description': 'One-minute wisdom in a new NOWNESS series',
 127         },
 128         'playlist_mincount': 4,
 129     }
 130
 131     def _real_extract(self, url):
 132         display_id, series = self._api_request(url, 'series/getBySlug/%s')
 133         entries = [self._extract_url_result(post) for post in series['posts']]
 134         series_title = None
 135         series_description = None
 136         translations = series.get('translations', [])
 137         if translations:
 138             series_title = translations[0].get('title') or translations[0]['seoTitle']
 139             series_description = translations[0].get('seoDescription')
 140         return self.playlist_result(
 141             entries, str(series['id']), series_title, series_description)