youtube_dl/extractor/ebaumsworld.py

   1 import re
   2 import xml.etree.ElementTree
   3
   4 from .common import InfoExtractor
   5 from ..utils import determine_ext
   6
   7
   8 class EbaumsWorldIE(InfoExtractor):
   9     _VALID_URL = r'https?://www\.ebaumsworld\.com/video/watch/(?P<id>\d+)'
  10
  11     _TEST = {
  12         u'url': u'http://www.ebaumsworld.com/video/watch/83367677/',
  13         u'file': u'83367677.mp4',
  14         u'info_dict': {
  15             u'title': u'A Giant Python Opens The Door',
  16             u'description': u'This is how nightmares start...',
  17             u'uploader': u'jihadpizza',
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group('id')
  24         config_xml = self._download_webpage(
  25             'http://www.ebaumsworld.com/video/player/%s' % video_id, video_id)
  26         config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
  27         video_url = config.find('file').text
  28
  29         return {
  30             'id': video_id,
  31             'title': config.find('title').text,
  32             'url': video_url,
  33             'ext': determine_ext(video_url),
  34             'description': config.find('description').text,
  35             'thumbnail': config.find('image').text,
  36             'uploader': config.find('username').text,
  37         }