Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tf1.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class TF1IE(InfoExtractor):
   8     """TF1 uses the wat.tv player."""
   9     _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html'
  10     _TESTS = {
  11         'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
  12         'info_dict': {
  13             'id': '10635995',
  14             'ext': 'mp4',
  15             'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
  16             'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
  17         },
  18         'params': {
  19             # Sometimes wat serves the whole file with the --test option
  20             'skip_download': True,
  21         },
  22     }, {
  23         'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
  24         'info_dict': {
  25             'id': '12043945',
  26             'ext': 'mp4',
  27             'title': 'Le grand Mystérioso - Chuggington',
  28             'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
  29             'upload_date': '20150103',
  30         },
  31         'params': {
  32             # Sometimes wat serves the whole file with the --test option
  33             'skip_download': True,
  34         },
  35     }
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39         webpage = self._download_webpage(url, video_id)
  40         embed_url = self._html_search_regex(
  41             r'["\'](https?://www.wat.tv/embedframe/.*?)["\']', webpage, 'embed url')
  42         embed_page = self._download_webpage(embed_url, video_id,
  43                                             'Downloading embed player page')
  44         wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
  45         wat_info = self._download_json(
  46             'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id)
  47         return self.url_result(wat_info['media']['url'], 'Wat')