space.py 1.4 KB

1234567891011121314151617181920212223242526272829303132333435
  1. import re
  2. from .common import InfoExtractor
  3. from .brightcove import BrightcoveIE
  4. from ..utils import RegexNotFoundError, ExtractorError
  5. class SpaceIE(InfoExtractor):
  6. _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
  7. _TEST = {
  8. u'add_ie': ['Brightcove'],
  9. u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',
  10. u'info_dict': {
  11. u'id': u'2780937028001',
  12. u'ext': u'mp4',
  13. u'title': u'Huge Martian Landforms\' Detail Revealed By European Probe | Video',
  14. u'description': u'md5:db81cf7f3122f95ed234b631a6ea1e61',
  15. u'uploader': u'TechMedia Networks',
  16. },
  17. }
  18. def _real_extract(self, url):
  19. mobj = re.match(self._VALID_URL, url)
  20. title = mobj.group('title')
  21. webpage = self._download_webpage(url, title)
  22. try:
  23. # Some videos require the playerKey field, which isn't define in
  24. # the BrightcoveExperience object
  25. brightcove_url = self._og_search_video_url(webpage)
  26. except RegexNotFoundError:
  27. # Other videos works fine with the info from the object
  28. brightcove_url = BrightcoveIE._extract_brightcove_url(webpage)
  29. if brightcove_url is None:
  30. raise ExtractorError(u'The webpage does not contain a video', expected=True)
  31. return self.url_result(brightcove_url, BrightcoveIE.ie_key())