_ Git - youtube-dl/blob - youtube_dl/extractor/sbs.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import remove_end
   6
   7
   8 class SBSIE(InfoExtractor):
   9     IE_DESC = 'sbs.com.au'
  10     _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P<id>[0-9]+)'
  11
  12     _TESTS = [{
  13         # Original URL is handled by the generic IE which finds the iframe:
  14         # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation
  15         'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
  16         'md5': '3150cf278965eeabb5b4cea1c963fe0a',
  17         'info_dict': {
  18             'id': '320403011771',
  19             'ext': 'mp4',
  20             'title': 'Dingo Conservation',
  21             'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction',
  22             'thumbnail': 're:http://.*\.jpg',
  23         },
  24         'add_ies': ['generic'],
  25     }, {
  26         'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         # the video is in the following iframe
  34         iframe_url = 'http://www.sbs.com.au/ondemand/video/single/' + video_id + '?context=web'
  35         webpage = self._download_webpage(iframe_url, video_id)
  36
  37         player_params = self._search_regex(
  38             r'(?s)(playerParams.+?releaseUrls.+?\n)',
  39             webpage, 'playerParams')
  40         player_params_js = self._search_regex(
  41             r'({.*})',
  42             player_params, 'player_param_js')
  43
  44         player_params_json = self._parse_json(player_params_js, video_id)
  45
  46         theplatform_url = player_params_json.get('releaseUrls')['progressive'] or player_params_json.get('releaseUrls')['standard']
  47
  48         title = remove_end(self._og_search_title(webpage, default=video_id, fatal=False), ' (The Feed)')
  49         description = self._html_search_meta('description', webpage)
  50         thumbnail = self._og_search_thumbnail(webpage)
  51
  52         return {
  53             '_type': 'url_transparent',
  54             'id': video_id,
  55             'url': theplatform_url,
  56             'title': title,
  57             'description': description,
  58             'thumbnail': thumbnail,
  59         }