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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import int_or_none
   7
   8
   9 class CultureUnpluggedIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/documentary/watch-online/play/(?P<id>\d+)(?:/(?P<display_id>[^/]+))?'
  11     _TESTS = [{
  12         'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662/The-Next--Best-West',
  13         'md5': 'ac6c093b089f7d05e79934dcb3d228fc',
  14         'info_dict': {
  15             'id': '53662',
  16             'display_id': 'The-Next--Best-West',
  17             'ext': 'mp4',
  18             'title': 'The Next, Best West',
  19             'description': 'md5:0423cd00833dea1519cf014e9d0903b1',
  20             'thumbnail': 're:^https?://.*\.jpg$',
  21             'creator': 'Coldstream Creative',
  22             'duration': 2203,
  23             'view_count': int,
  24         }
  25     }, {
  26         'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33         display_id = mobj.group('display_id') or video_id
  34
  35         movie_data = self._download_json(
  36             'http://www.cultureunplugged.com/movie-data/cu-%s.json' % video_id, display_id)
  37
  38         video_url = movie_data['url']
  39         title = movie_data['title']
  40
  41         description = movie_data.get('synopsis')
  42         creator = movie_data.get('producer')
  43         duration = int_or_none(movie_data.get('duration'))
  44         view_count = int_or_none(movie_data.get('views'))
  45
  46         thumbnails = [{
  47             'url': movie_data['%s_thumb' % size],
  48             'id': size,
  49             'preference': preference,
  50         } for preference, size in enumerate((
  51             'small', 'large')) if movie_data.get('%s_thumb' % size)]
  52
  53         return {
  54             'id': video_id,
  55             'display_id': display_id,
  56             'url': video_url,
  57             'title': title,
  58             'description': description,
  59             'creator': creator,
  60             'duration': duration,
  61             'view_count': view_count,
  62             'thumbnails': thumbnails,
  63         }