yt_dlp/extractor/cultureunplugged.py

   1 import time
   2
   3 from .common import InfoExtractor
   4 from ..networking import HEADRequest
   5 from ..utils import int_or_none
   6
   7
   8 class CultureUnpluggedIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/documentary/watch-online/play/(?P<id>\d+)(?:/(?P<display_id>[^/]+))?'
  10     _TESTS = [{
  11         'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662/The-Next--Best-West',
  12         'md5': 'ac6c093b089f7d05e79934dcb3d228fc',
  13         'info_dict': {
  14             'id': '53662',
  15             'display_id': 'The-Next--Best-West',
  16             'ext': 'mp4',
  17             'title': 'The Next, Best West',
  18             'description': 'md5:0423cd00833dea1519cf014e9d0903b1',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'creator': 'Coldstream Creative',
  21             'duration': 2203,
  22             'view_count': int,
  23         },
  24     }, {
  25         'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662',
  26         'only_matching': True,
  27     }]
  28
  29     def _real_extract(self, url):
  30         mobj = self._match_valid_url(url)
  31         video_id = mobj.group('id')
  32         display_id = mobj.group('display_id') or video_id
  33
  34         # request setClientTimezone.php to get PHPSESSID cookie which is need to get valid json data in the next request
  35         self._request_webpage(HEADRequest(
  36             'http://www.cultureunplugged.com/setClientTimezone.php?timeOffset=%d' % -(time.timezone / 3600)), display_id)
  37         movie_data = self._download_json(
  38             f'http://www.cultureunplugged.com/movie-data/cu-{video_id}.json', display_id)
  39
  40         video_url = movie_data['url']
  41         title = movie_data['title']
  42
  43         description = movie_data.get('synopsis')
  44         creator = movie_data.get('producer')
  45         duration = int_or_none(movie_data.get('duration'))
  46         view_count = int_or_none(movie_data.get('views'))
  47
  48         thumbnails = [{
  49             'url': movie_data[f'{size}_thumb'],
  50             'id': size,
  51             'preference': preference,
  52         } for preference, size in enumerate((
  53             'small', 'large')) if movie_data.get(f'{size}_thumb')]
  54
  55         return {
  56             'id': video_id,
  57             'display_id': display_id,
  58             'url': video_url,
  59             'title': title,
  60             'description': description,
  61             'creator': creator,
  62             'duration': duration,
  63             'view_count': view_count,
  64             'thumbnails': thumbnails,
  65         }