Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ehow.py

   1 from __future__ import unicode_literals
   2
   3 from ..compat import (
   4     compat_urllib_parse,
   5 )
   6 from .common import InfoExtractor
   7
   8
   9 class EHowIE(InfoExtractor):
  10     IE_NAME = 'eHow'
  11     _VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
  12     _TEST = {
  13         'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
  14         'md5': '9809b4e3f115ae2088440bcb4efbf371',
  15         'info_dict': {
  16             'id': '12245069',
  17             'ext': 'flv',
  18             'title': 'Hardwood Flooring Basics',
  19             '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...',
  20             'uploader': 'Erick Nathan',
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27         video_url = self._search_regex(
  28             r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL')
  29         final_url = compat_urllib_parse.unquote(video_url)
  30         uploader = self._html_search_meta('uploader', webpage)
  31         title = self._og_search_title(webpage).replace(' | eHow', '')
  32
  33         return {
  34             'id': video_id,
  35             'url': final_url,
  36             'title': title,
  37             'thumbnail': self._og_search_thumbnail(webpage),
  38             'description': self._og_search_description(webpage),
  39             'uploader': uploader,
  40         }