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