youtube_dl/extractor/ehow.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_urllib_parse_unquote
   5
   6
   7 class EHowIE(InfoExtractor):
   8     IE_NAME = 'eHow'
   9     _VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
  10     _TEST = {
  11         'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
  12         'md5': '9809b4e3f115ae2088440bcb4efbf371',
  13         'info_dict': {
  14             'id': '12245069',
  15             'ext': 'flv',
  16             'title': 'Hardwood Flooring Basics',
  17             '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...',
  18             'uploader': 'Erick Nathan',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         webpage = self._download_webpage(url, video_id)
  25         video_url = self._search_regex(
  26             r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
  27         final_url = compat_urllib_parse_unquote(video_url)
  28         uploader = self._html_search_meta('uploader', webpage)
  29         title = self._og_search_title(webpage).replace(' | eHow', '')
  30
  31         return {
  32             'id': video_id,
  33             'url': final_url,
  34             'title': title,
  35             'thumbnail': self._og_search_thumbnail(webpage),
  36             'description': self._og_search_description(webpage),
  37             'uploader': uploader,
  38         }