You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

47 lines
2.0 KiB

  1. import re
  2. import xml.etree.ElementTree
  3. from .common import InfoExtractor
  4. from ..utils import determine_ext
  5. class CNNIE(InfoExtractor):
  6. _VALID_URL = r'https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/(?P<path>.+?/(?P<title>[^/]+?)\.cnn)'
  7. _TEST = {
  8. u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
  9. u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
  10. u'md5': u'3e6121ea48df7e2259fe73a0628605c4',
  11. u'info_dict': {
  12. u'title': u'Nadal wins 8th French Open title',
  13. u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
  14. },
  15. }
  16. def _real_extract(self, url):
  17. mobj = re.match(self._VALID_URL, url)
  18. path = mobj.group('path')
  19. page_title = mobj.group('title')
  20. info_xml = self._download_webpage(
  21. 'http://cnn.com/video/data/3.0/%s/index.xml' % path, page_title)
  22. info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
  23. formats = []
  24. for f in info.findall('files/file'):
  25. mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate'])
  26. if mf is not None:
  27. formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text))
  28. formats = sorted(formats)
  29. (_,_,_, video_path) = formats[-1]
  30. video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path
  31. thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
  32. thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
  33. return {'id': info.attrib['id'],
  34. 'title': info.find('headline').text,
  35. 'url': video_url,
  36. 'ext': determine_ext(video_url),
  37. 'thumbnail': thumbnails[-1][1],
  38. 'thumbnails': thumbs_dict,
  39. 'description': info.find('description').text,
  40. }