youtube_dl/extractor/space.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .brightcove import BrightcoveIE
   7 from ..utils import RegexNotFoundError, ExtractorError
   8
   9
  10 class SpaceIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:(?:www|m)\.)?space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
  12     _TEST = {
  13         'add_ie': ['Brightcove'],
  14         'url': 'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',
  15         'info_dict': {
  16             'id': '2780937028001',
  17             'ext': 'mp4',
  18             'title': 'Huge Martian Landforms\' Detail Revealed By European Probe | Video',
  19             'description': 'md5:db81cf7f3122f95ed234b631a6ea1e61',
  20             'uploader': 'TechMedia Networks',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         title = mobj.group('title')
  27         webpage = self._download_webpage(url, title)
  28         try:
  29             # Some videos require the playerKey field, which isn't define in
  30             # the BrightcoveExperience object
  31             brightcove_url = self._og_search_video_url(webpage)
  32         except RegexNotFoundError:
  33             # Other videos works fine with the info from the object
  34             brightcove_url = BrightcoveIE._extract_brightcove_url(webpage)
  35         if brightcove_url is None:
  36             raise ExtractorError(u'The webpage does not contain a video', expected=True)
  37         return self.url_result(brightcove_url, BrightcoveIE.ie_key())