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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class GrouponIE(InfoExtractor):
   7     _VALID_URL = r'https?://www\.groupon\.com/deals/(?P<id>[^?#]+)'
   8
   9     _TEST = {
  10         'url': 'https://www.groupon.com/deals/bikram-yoga-huntington-beach-2#ooid=tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
  11         'info_dict': {
  12             'id': 'bikram-yoga-huntington-beach-2',
  13             'title': '$49 for 10 Yoga Classes or One Month of Unlimited Classes at Bikram Yoga Huntington Beach ($180 Value)',
  14             'description': 'Studio kept at 105 degrees and 40% humidity with anti-microbial and anti-slip Flotex flooring; certified instructors',
  15         },
  16         'playlist': [{
  17             'info_dict': {
  18                 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
  19                 'ext': 'mp4',
  20                 'title': 'Bikram Yoga Huntington Beach | Orange County',
  21                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  22                 'duration': 44.961,
  23             },
  24         }],
  25         'params': {
  26             'skip_download': 'HLS',
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         playlist_id = self._match_id(url)
  32         webpage = self._download_webpage(url, playlist_id)
  33
  34         payload = self._parse_json(self._search_regex(
  35             r'var\s+payload\s*=\s*(.*?);\n', webpage, 'payload'), playlist_id)
  36         videos = payload['carousel'].get('dealVideos', [])
  37         entries = []
  38         for v in videos:
  39             if v.get('provider') != 'OOYALA':
  40                 self.report_warning(
  41                     '%s: Unsupported video provider %s, skipping video' %
  42                     (playlist_id, v.get('provider')))
  43                 continue
  44             entries.append(self.url_result('ooyala:%s' % v['media']))
  45
  46         return {
  47             '_type': 'playlist',
  48             'id': playlist_id,
  49             'entries': entries,
  50             'title': self._og_search_title(webpage),
  51             'description': self._og_search_description(webpage),
  52         }