yt_dlp/extractor/howcast.py

   1 from .common import InfoExtractor
   2 from ..utils import parse_iso8601
   3
   4
   5 class HowcastIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
   7     _TEST = {
   8         'url': 'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
   9         'md5': '7d45932269a288149483144f01b99789',
  10         'info_dict': {
  11             'id': '390161',
  12             'ext': 'mp4',
  13             'title': 'How to Tie a Square Knot Properly',
  14             'description': 'md5:dbe792e5f6f1489027027bf2eba188a3',
  15             'timestamp': 1276081287,
  16             'upload_date': '20100609',
  17             'duration': 56.823,
  18         },
  19         'params': {
  20             'skip_download': True,
  21         },
  22         'add_ie': ['Ooyala'],
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27
  28         webpage = self._download_webpage(url, video_id)
  29
  30         embed_code = self._search_regex(
  31             r'<iframe[^>]+src="[^"]+\bembed_code=([^\b]+)\b',
  32             webpage, 'ooyala embed code')
  33
  34         return {
  35             '_type': 'url_transparent',
  36             'ie_key': 'Ooyala',
  37             'url': 'ooyala:%s' % embed_code,
  38             'id': video_id,
  39             'timestamp': parse_iso8601(self._html_search_meta(
  40                 'article:published_time', webpage, 'timestamp')),
  41         }