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.

35 lines
1.5 KiB

  1. # coding: utf-8
  2. import json
  3. import re
  4. from .common import InfoExtractor
  5. class TF1IE(InfoExtractor):
  6. """
  7. TF1 uses the wat.tv player, currently it can only download videos with the
  8. html5 player enabled, it cannot download HD videos.
  9. """
  10. _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
  11. _TEST = {
  12. u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
  13. u'file': u'10635995.mp4',
  14. u'md5': u'66789d3e91278d332f75e1feb7aea327',
  15. u'info_dict': {
  16. u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle',
  17. u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
  18. }
  19. }
  20. def _real_extract(self, url):
  21. mobj = re.match(self._VALID_URL, url)
  22. id = mobj.group(1)
  23. webpage = self._download_webpage(url, id)
  24. embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"',
  25. webpage, 'embed url')
  26. embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page')
  27. wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
  28. wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info')
  29. wat_info = json.loads(wat_info)['media']
  30. wat_url = wat_info['url']
  31. return self.url_result(wat_url, 'Wat')