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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from ..utils import (
   6     compat_urllib_parse,
   7 )
   8 from .common import InfoExtractor
   9
  10
  11 class EHowIE(InfoExtractor):
  12     IE_NAME = 'eHow'
  13     _VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
  14     _TEST = {
  15         'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
  16         'md5': '9809b4e3f115ae2088440bcb4efbf371',
  17         'info_dict': {
  18             'id': '12245069',
  19             'ext': 'flv',
  20             'title': 'Hardwood Flooring Basics',
  21             '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...',
  22             'uploader': 'Erick Nathan',
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('id')
  29         webpage = self._download_webpage(url, video_id)
  30         video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
  31                                        webpage, 'video URL')
  32         final_url = compat_urllib_parse.unquote(video_url)
  33         uploader = self._html_search_meta('uploader', webpage)
  34         title = self._og_search_title(webpage).replace(' | eHow', '')
  35
  36         return {
  37             'id': video_id,
  38             'url': final_url,
  39             'title': title,
  40             'thumbnail': self._og_search_thumbnail(webpage),
  41             'description': self._og_search_description(webpage),
  42             'uploader': uploader,
  43         }