youtube_dl/extractor/wimp.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from .youtube import YoutubeIE
   5
   6
   7 class WimpIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
   9     _TESTS = [{
  10         'url': 'http://www.wimp.com/maru-is-exhausted/',
  11         'md5': 'ee21217ffd66d058e8b16be340b74883',
  12         'info_dict': {
  13             'id': 'maru-is-exhausted',
  14             'ext': 'mp4',
  15             'title': 'Maru is exhausted.',
  16             'description': 'md5:57e099e857c0a4ea312542b684a869b8',
  17         }
  18     }, {
  19         'url': 'http://www.wimp.com/clowncar/',
  20         'md5': '5c31ad862a90dc5b1f023956faec13fe',
  21         'info_dict': {
  22             'id': 'cG4CEr2aiSg',
  23             'ext': 'webm',
  24             'title': 'Basset hound clown car...incredible!',
  25             'description': '5 of my Bassets crawled in this dog loo! www.bellinghambassets.com\n\nFor licensing/usage please contact: licensing(at)jukinmediadotcom',
  26             'upload_date': '20140303',
  27             'uploader': 'Gretchen Hoey',
  28             'uploader_id': 'gretchenandjeff1',
  29         },
  30         'add_ie': ['Youtube'],
  31     }]
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         webpage = self._download_webpage(url, video_id)
  37
  38         youtube_id = self._search_regex(
  39             (r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']",
  40              r'data-id=["\']([0-9A-Za-z_-]{11})'),
  41             webpage, 'video URL', default=None)
  42         if youtube_id:
  43             return self.url_result(youtube_id, YoutubeIE.ie_key())
  44
  45         info_dict = self._extract_jwplayer_data(
  46             webpage, video_id, require_title=False)
  47
  48         info_dict.update({
  49             'id': video_id,
  50             'title': self._og_search_title(webpage),
  51             'description': self._og_search_description(webpage),
  52         })
  53
  54         return info_dict