yt_dlp/extractor/nowness.py

   1 from .brightcove import (
   2     BrightcoveLegacyIE,
   3     BrightcoveNewIE,
   4 )
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..networking import Request
   8 from ..utils import ExtractorError
   9
  10
  11 class NownessBaseIE(InfoExtractor):
  12     def _extract_url_result(self, post):
  13         if post['type'] == 'video':
  14             for media in post['media']:
  15                 if media['type'] == 'video':
  16                     video_id = media['content']
  17                     source = media['source']
  18                     if source == 'brightcove':
  19                         player_code = self._download_webpage(
  20                             'http://www.nowness.com/iframe?id=%s' % video_id, video_id,
  21                             note='Downloading player JavaScript',
  22                             errnote='Unable to download player JavaScript')
  23                         bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code)
  24                         if bc_url:
  25                             return self.url_result(bc_url, BrightcoveLegacyIE.ie_key())
  26                         bc_url = BrightcoveNewIE._extract_url(self, player_code)
  27                         if bc_url:
  28                             return self.url_result(bc_url, BrightcoveNewIE.ie_key())
  29                         raise ExtractorError('Could not find player definition')
  30                     elif source == 'vimeo':
  31                         return self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
  32                     elif source == 'youtube':
  33                         return self.url_result(video_id, 'Youtube')
  34                     elif source == 'cinematique':
  35                         # yt-dlp currently doesn't support cinematique
  36                         # return self.url_result('http://cinematique.com/embed/%s' % video_id, 'Cinematique')
  37                         pass
  38
  39     def _api_request(self, url, request_path):
  40         display_id = self._match_id(url)
  41         request = Request(
  42             'http://api.nowness.com/api/' + request_path % display_id,
  43             headers={
  44                 'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us',
  45             })
  46         return display_id, self._download_json(request, display_id)
  47
  48
  49 class NownessIE(NownessBaseIE):
  50     IE_NAME = 'nowness'
  51     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/(?:story|(?:series|category)/[^/]+)/(?P<id>[^/]+?)(?:$|[?#])'
  52     _TESTS = [{
  53         'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation',
  54         'md5': '068bc0202558c2e391924cb8cc470676',
  55         'info_dict': {
  56             'id': '2520295746001',
  57             'ext': 'mp4',
  58             'title': 'Candor: The Art of Gesticulation',
  59             'description': 'Candor: The Art of Gesticulation',
  60             'thumbnail': r're:^https?://.*\.jpg',
  61             'timestamp': 1446745676,
  62             'upload_date': '20151105',
  63             'uploader_id': '2385340575001',
  64         },
  65         'add_ie': ['BrightcoveNew'],
  66     }, {
  67         'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr',
  68         'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
  69         'info_dict': {
  70             'id': '3716354522001',
  71             'ext': 'mp4',
  72             'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
  73             'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
  74             'thumbnail': r're:^https?://.*\.jpg',
  75             'timestamp': 1407315371,
  76             'upload_date': '20140806',
  77             'uploader_id': '2385340575001',
  78         },
  79         'add_ie': ['BrightcoveNew'],
  80     }, {
  81         # vimeo
  82         'url': 'https://www.nowness.com/series/nowness-picks/jean-luc-godard-supercut',
  83         'md5': '9a5a6a8edf806407e411296ab6bc2a49',
  84         'info_dict': {
  85             'id': '130020913',
  86             'ext': 'mp4',
  87             'title': 'Bleu, Blanc, Rouge - A Godard Supercut',
  88             'description': 'md5:f0ea5f1857dffca02dbd37875d742cec',
  89             'thumbnail': r're:^https?://.*\.jpg',
  90             'upload_date': '20150607',
  91             'uploader': 'Cinema Sem Lei',
  92             'uploader_id': 'cinemasemlei',
  93         },
  94         'add_ie': ['Vimeo'],
  95     }]
  96
  97     def _real_extract(self, url):
  98         _, post = self._api_request(url, 'post/getBySlug/%s')
  99         return self._extract_url_result(post)
 100
 101
 102 class NownessPlaylistIE(NownessBaseIE):
 103     IE_NAME = 'nowness:playlist'
 104     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P<id>\d+)'
 105     _TEST = {
 106         'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues',
 107         'info_dict': {
 108             'id': '3286',
 109         },
 110         'playlist_mincount': 8,
 111     }
 112
 113     def _real_extract(self, url):
 114         playlist_id, playlist = self._api_request(url, 'post?PlaylistId=%s')
 115         entries = [self._extract_url_result(item) for item in playlist['items']]
 116         return self.playlist_result(entries, playlist_id)
 117
 118
 119 class NownessSeriesIE(NownessBaseIE):
 120     IE_NAME = 'nowness:series'
 121     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P<id>[^/]+?)(?:$|[?#])'
 122     _TEST = {
 123         'url': 'https://www.nowness.com/series/60-seconds',
 124         'info_dict': {
 125             'id': '60',
 126             'title': '60 Seconds',
 127             'description': 'One-minute wisdom in a new NOWNESS series',
 128         },
 129         'playlist_mincount': 4,
 130     }
 131
 132     def _real_extract(self, url):
 133         display_id, series = self._api_request(url, 'series/getBySlug/%s')
 134         entries = [self._extract_url_result(post) for post in series['posts']]
 135         series_title = None
 136         series_description = None
 137         translations = series.get('translations', [])
 138         if translations:
 139             series_title = translations[0].get('title') or translations[0]['seoTitle']
 140             series_description = translations[0].get('seoDescription')
 141         return self.playlist_result(
 142             entries, compat_str(series['id']), series_title, series_description)