youtube_dl/extractor/vimple.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class SprutoBaseIE(InfoExtractor):
   8     def _extract_spruto(self, spruto, video_id):
   9         playlist = spruto['playlist'][0]
  10         title = playlist['title']
  11         video_id = playlist.get('videoId') or video_id
  12         thumbnail = playlist.get('posterUrl') or playlist.get('thumbnailUrl')
  13         duration = int_or_none(playlist.get('duration'))
  14
  15         formats = [{
  16             'url': f['url'],
  17         } for f in playlist['video']]
  18         self._sort_formats(formats)
  19
  20         return {
  21             'id': video_id,
  22             'title': title,
  23             'thumbnail': thumbnail,
  24             'duration': duration,
  25             'formats': formats,
  26         }
  27
  28
  29 class VimpleIE(SprutoBaseIE):
  30     IE_DESC = 'Vimple - one-click video hosting'
  31     _VALID_URL = r'https?://(?:player\.vimple\.(?:ru|co)/iframe|vimple\.(?:ru|co))/(?P<id>[\da-f-]{32,36})'
  32     _TESTS = [{
  33         'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
  34         'md5': '2e750a330ed211d3fd41821c6ad9a279',
  35         'info_dict': {
  36             'id': 'c0f6b168-7dcd-4000-a97e-be70068039cf',
  37             'ext': 'mp4',
  38             'title': 'Sunset',
  39             'duration': 20,
  40             'thumbnail': r're:https?://.*?\.jpg',
  41         },
  42     }, {
  43         'url': 'http://player.vimple.ru/iframe/52e1beec-1314-4a83-aeac-c61562eadbf9',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://vimple.co/04506a053f124483b8fb05ed73899f19',
  47         'only_matching': True,
  48     }]
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52
  53         webpage = self._download_webpage(
  54             'http://player.vimple.ru/iframe/%s' % video_id, video_id)
  55
  56         spruto = self._parse_json(
  57             self._search_regex(
  58                 r'sprutoData\s*:\s*({.+?}),\r\n', webpage, 'spruto data'),
  59             video_id)
  60
  61         return self._extract_spruto(spruto, video_id)