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

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