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

   1 # coding: 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             'timestamp': 1446745676,
  67             'upload_date': '20151105',
  68             'uploader_id': '2385340575001',
  69         },
  70         'add_ie': ['BrightcoveNew'],
  71     }, {
  72         'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr',
  73         'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
  74         'info_dict': {
  75             'id': '3716354522001',
  76             'ext': 'mp4',
  77             'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
  78             'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
  79             'thumbnail': 're:^https?://.*\.jpg',
  80             'timestamp': 1407315371,
  81             'upload_date': '20140806',
  82             'uploader_id': '2385340575001',
  83         },
  84         'add_ie': ['BrightcoveNew'],
  85     }, {
  86         # vimeo
  87         'url': 'https://www.nowness.com/series/nowness-picks/jean-luc-godard-supercut',
  88         'md5': '9a5a6a8edf806407e411296ab6bc2a49',
  89         'info_dict': {
  90             'id': '130020913',
  91             'ext': 'mp4',
  92             'title': 'Bleu, Blanc, Rouge - A Godard Supercut',
  93             'description': 'md5:f0ea5f1857dffca02dbd37875d742cec',
  94             'thumbnail': 're:^https?://.*\.jpg',
  95             'upload_date': '20150607',
  96             'uploader': 'Cinema Sem Lei',
  97             'uploader_id': 'cinemasemlei',
  98         },
  99         'add_ie': ['Vimeo'],
 100     }]
 101
 102     def _real_extract(self, url):
 103         _, post = self._api_request(url, 'post/getBySlug/%s')
 104         return self._extract_url_result(post)
 105
 106
 107 class NownessPlaylistIE(NownessBaseIE):
 108     IE_NAME = 'nowness:playlist'
 109     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P<id>\d+)'
 110     _TEST = {
 111         'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues',
 112         'info_dict': {
 113             'id': '3286',
 114         },
 115         'playlist_mincount': 8,
 116     }
 117
 118     def _real_extract(self, url):
 119         playlist_id, playlist = self._api_request(url, 'post?PlaylistId=%s')
 120         entries = [self._extract_url_result(item) for item in playlist['items']]
 121         return self.playlist_result(entries, playlist_id)
 122
 123
 124 class NownessSeriesIE(NownessBaseIE):
 125     IE_NAME = 'nowness:series'
 126     _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P<id>[^/]+?)(?:$|[?#])'
 127     _TEST = {
 128         'url': 'https://www.nowness.com/series/60-seconds',
 129         'info_dict': {
 130             'id': '60',
 131             'title': '60 Seconds',
 132             'description': 'One-minute wisdom in a new NOWNESS series',
 133         },
 134         'playlist_mincount': 4,
 135     }
 136
 137     def _real_extract(self, url):
 138         display_id, series = self._api_request(url, 'series/getBySlug/%s')
 139         entries = [self._extract_url_result(post) for post in series['posts']]
 140         series_title = None
 141         series_description = None
 142         translations = series.get('translations', [])
 143         if translations:
 144             series_title = translations[0].get('title') or translations[0]['seoTitle']
 145             series_description = translations[0].get('seoDescription')
 146         return self.playlist_result(
 147             entries, compat_str(series['id']), series_title, series_description)