yt_dlp/extractor/vimple.py

   1 from .common import InfoExtractor
   2 from ..utils import int_or_none
   3
   4
   5 class SprutoBaseIE(InfoExtractor):
   6     def _extract_spruto(self, spruto, video_id):
   7         playlist = spruto['playlist'][0]
   8         title = playlist['title']
   9         video_id = playlist.get('videoId') or video_id
  10         thumbnail = playlist.get('posterUrl') or playlist.get('thumbnailUrl')
  11         duration = int_or_none(playlist.get('duration'))
  12
  13         formats = [{
  14             'url': f['url'],
  15         } for f in playlist['video']]
  16         self._sort_formats(formats)
  17
  18         return {
  19             'id': video_id,
  20             'title': title,
  21             'thumbnail': thumbnail,
  22             'duration': duration,
  23             'formats': formats,
  24         }
  25
  26
  27 class VimpleIE(SprutoBaseIE):
  28     IE_DESC = 'Vimple - one-click video hosting'
  29     _VALID_URL = r'https?://(?:player\.vimple\.(?:ru|co)/iframe|vimple\.(?:ru|co))/(?P<id>[\da-f-]{32,36})'
  30     _TESTS = [{
  31         'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
  32         'md5': '2e750a330ed211d3fd41821c6ad9a279',
  33         'info_dict': {
  34             'id': 'c0f6b168-7dcd-4000-a97e-be70068039cf',
  35             'ext': 'mp4',
  36             'title': 'Sunset',
  37             'duration': 20,
  38             'thumbnail': r're:https?://.*?\.jpg',
  39         },
  40     }, {
  41         'url': 'http://player.vimple.ru/iframe/52e1beec-1314-4a83-aeac-c61562eadbf9',
  42         'only_matching': True,
  43     }, {
  44         'url': 'http://vimple.co/04506a053f124483b8fb05ed73899f19',
  45         'only_matching': True,
  46     }]
  47
  48     def _real_extract(self, url):
  49         video_id = self._match_id(url)
  50
  51         webpage = self._download_webpage(
  52             'http://player.vimple.ru/iframe/%s' % video_id, video_id)
  53
  54         spruto = self._parse_json(
  55             self._search_regex(
  56                 r'sprutoData\s*:\s*({.+?}),\r\n', webpage, 'spruto data'),
  57             video_id)
  58
  59         return self._extract_spruto(spruto, video_id)