yt_dlp/extractor/ehow.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_urllib_parse_unquote
   3
   4
   5 class EHowIE(InfoExtractor):
   6     IE_NAME = 'eHow'
   7     _VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
   8     _TEST = {
   9         'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
  10         'md5': '9809b4e3f115ae2088440bcb4efbf371',
  11         'info_dict': {
  12             'id': '12245069',
  13             'ext': 'flv',
  14             'title': 'Hardwood Flooring Basics',
  15             'description': 'Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...',
  16             'uploader': 'Erick Nathan',
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23         video_url = self._search_regex(
  24             r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
  25         final_url = compat_urllib_parse_unquote(video_url)
  26         uploader = self._html_search_meta('uploader', webpage)
  27         title = self._og_search_title(webpage).replace(' | eHow', '')
  28
  29         return {
  30             'id': video_id,
  31             'url': final_url,
  32             'title': title,
  33             'thumbnail': self._og_search_thumbnail(webpage),
  34             'description': self._og_search_description(webpage),
  35             'uploader': uploader,
  36         }