yt_dlp/extractor/gputechconf.py

   1 from .common import InfoExtractor
   2
   3
   4 class GPUTechConfIE(InfoExtractor):
   5     _VALID_URL = r'https?://on-demand\.gputechconf\.com/gtc/2015/video/S(?P<id>\d+)\.html'
   6     _TEST = {
   7         'url': 'http://on-demand.gputechconf.com/gtc/2015/video/S5156.html',
   8         'md5': 'a8862a00a0fd65b8b43acc5b8e33f798',
   9         'info_dict': {
  10             'id': '5156',
  11             'ext': 'mp4',
  12             'title': 'Coordinating More Than 3 Million CUDA Threads for Social Network Analysis',
  13             'duration': 1219,
  14         },
  15     }
  16
  17     def _real_extract(self, url):
  18         video_id = self._match_id(url)
  19         webpage = self._download_webpage(url, video_id)
  20
  21         root_path = self._search_regex(
  22             r'var\s+rootPath\s*=\s*"([^"]+)', webpage, 'root path',
  23             default='http://evt.dispeak.com/nvidia/events/gtc15/')
  24         xml_file_id = self._search_regex(
  25             r'var\s+xmlFileId\s*=\s*"([^"]+)', webpage, 'xml file id')
  26
  27         return {
  28             '_type': 'url_transparent',
  29             'id': video_id,
  30             'url': f'{root_path}xml/{xml_file_id}.xml',
  31             'ie_key': 'DigitallySpeaking',
  32         }