youtube_dl/extractor/howcast.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import parse_iso8601
   5
   6
   7 class HowcastIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
   9     _TEST = {
  10         'url': 'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
  11         'md5': '7d45932269a288149483144f01b99789',
  12         'info_dict': {
  13             'id': '390161',
  14             'ext': 'mp4',
  15             'title': 'How to Tie a Square Knot Properly',
  16             'description': 'md5:dbe792e5f6f1489027027bf2eba188a3',
  17             'timestamp': 1276081287,
  18             'upload_date': '20100609',
  19             'duration': 56.823,
  20         },
  21         'params': {
  22             'skip_download': True,
  23         },
  24         'add_ie': ['Ooyala'],
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29
  30         webpage = self._download_webpage(url, video_id)
  31
  32         embed_code = self._search_regex(
  33             r'<iframe[^>]+src="[^"]+\bembed_code=([^\b]+)\b',
  34             webpage, 'ooyala embed code')
  35
  36         return {
  37             '_type': 'url_transparent',
  38             'ie_key': 'Ooyala',
  39             'url': 'ooyala:%s' % embed_code,
  40             'id': video_id,
  41             'timestamp': parse_iso8601(self._html_search_meta(
  42                 'article:published_time', webpage, 'timestamp')),
  43         }