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.

33 lines
1.4 KiB

  1. # coding: utf-8
  2. import json
  3. import re
  4. from .common import InfoExtractor
  5. class TF1IE(InfoExtractor):
  6. """TF1 uses the wat.tv player."""
  7. _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
  8. _TEST = {
  9. u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
  10. u'file': u'10635995.mp4',
  11. u'md5': u'2e378cc28b9957607d5e88f274e637d8',
  12. u'info_dict': {
  13. u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle',
  14. u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
  15. },
  16. u'skip': u'Sometimes wat serves the whole file with the --test option',
  17. }
  18. def _real_extract(self, url):
  19. mobj = re.match(self._VALID_URL, url)
  20. id = mobj.group(1)
  21. webpage = self._download_webpage(url, id)
  22. embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"',
  23. webpage, 'embed url')
  24. embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page')
  25. wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
  26. wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info')
  27. wat_info = json.loads(wat_info)['media']
  28. wat_url = wat_info['url']
  29. return self.url_result(wat_url, 'Wat')