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

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