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

   1 from __future__ import unicode_literals
   2
   3 from .subtitles import SubtitlesInfoExtractor
   4 from .common import ExtractorError
   5 from ..utils import parse_iso8601
   6
   7
   8 class DRTVIE(SubtitlesInfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
  10
  11     _TEST = {
  12         'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
  13         'md5': '4a7e1dd65cdb2643500a3f753c942f25',
  14         'info_dict': {
  15             'id': 'partiets-mand-7-8',
  16             'ext': 'mp4',
  17             'title': 'Partiets mand (7:8)',
  18             'description': 'md5:a684b90a8f9336cd4aab94b7647d7862',
  19             'timestamp': 1403047940,
  20             'upload_date': '20140617',
  21             'duration': 1299.040,
  22         },
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27
  28         webpage = self._download_webpage(url, video_id)
  29
  30         video_id = self._search_regex(
  31             r'data-(?:material-identifier|episode-slug)="([^"]+)"',
  32             webpage, 'video id')
  33
  34         programcard = self._download_json(
  35             'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
  36             video_id, 'Downloading video JSON')
  37         data = programcard['Data'][0]
  38
  39         title = data['Title']
  40         description = data['Description']
  41         timestamp = parse_iso8601(data['CreatedTime'])
  42
  43         thumbnail = None
  44         duration = None
  45
  46         restricted_to_denmark = False
  47
  48         formats = []
  49         subtitles = {}
  50
  51         for asset in data['Assets']:
  52             if asset['Kind'] == 'Image':
  53                 thumbnail = asset['Uri']
  54             elif asset['Kind'] == 'VideoResource':
  55                 duration = asset['DurationInMilliseconds'] / 1000.0
  56                 restricted_to_denmark = asset['RestrictedToDenmark']
  57                 spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
  58                 for link in asset['Links']:
  59                     target = link['Target']
  60                     uri = link['Uri']
  61                     format_id = target
  62                     preference = -1 if target == 'HDS' else -2
  63                     if spoken_subtitles:
  64                         preference -= 2
  65                         format_id += '-spoken-subtitles'
  66                     formats.append({
  67                         'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
  68                         'format_id': format_id,
  69                         'ext': link['FileFormat'],
  70                         'preference': preference,
  71                     })
  72                 subtitles_list = asset.get('SubtitlesList')
  73                 if isinstance(subtitles_list, list):
  74                     LANGS = {
  75                         'Danish': 'dk',
  76                     }
  77                     for subs in subtitles_list:
  78                         lang = subs['Language']
  79                         subtitles[LANGS.get(lang, lang)] = subs['Uri']
  80
  81         if not formats and restricted_to_denmark:
  82             raise ExtractorError(
  83                 'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
  84
  85         self._sort_formats(formats)
  86
  87         if self._downloader.params.get('listsubtitles', False):
  88             self._list_available_subtitles(video_id, subtitles)
  89             return
  90
  91         return {
  92             'id': video_id,
  93             'title': title,
  94             'description': description,
  95             'thumbnail': thumbnail,
  96             'timestamp': timestamp,
  97             'duration': duration,
  98             'formats': formats,
  99             'subtitles': self.extract_subtitles(video_id, subtitles),
 100         }