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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     extract_attributes,
   7     smuggle_url,
   8     strip_or_none,
   9     urljoin,
  10 )
  11
  12
  13 class SkySportsIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?skysports\.com/watch/video/(?P<id>[0-9]+)'
  15     _TEST = {
  16         'url': 'http://www.skysports.com/watch/video/10328419/bale-its-our-time-to-shine',
  17         'md5': '77d59166cddc8d3cb7b13e35eaf0f5ec',
  18         'info_dict': {
  19             'id': '10328419',
  20             'ext': 'mp4',
  21             'title': 'Bale: It\'s our time to shine',
  22             'description': 'md5:e88bda94ae15f7720c5cb467e777bb6d',
  23         },
  24         'add_ie': ['Ooyala'],
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30         video_data = extract_attributes(self._search_regex(
  31             r'(<div.+?class="sdc-article-video__media-ooyala"[^>]+>)', webpage, 'video data'))
  32
  33         video_url = 'ooyala:%s' % video_data['data-video-id']
  34         if video_data.get('data-token-required') == 'true':
  35             token_fetch_options = self._parse_json(video_data.get('data-token-fetch-options', '{}'), video_id, fatal=False) or {}
  36             token_fetch_url = token_fetch_options.get('url')
  37             if token_fetch_url:
  38                 embed_token = self._download_webpage(urljoin(url, token_fetch_url), video_id, fatal=False)
  39                 if embed_token:
  40                     video_url = smuggle_url(video_url, {'embed_token': embed_token.strip('"')})
  41
  42         return {
  43             '_type': 'url_transparent',
  44             'id': video_id,
  45             'url': video_url,
  46             'title': self._og_search_title(webpage),
  47             'description': strip_or_none(self._og_search_description(webpage)),
  48             'ie_key': 'Ooyala',
  49         }