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 (
   6     smuggle_url,
   7     ExtractorError,
   8 )
   9
  10
  11 class SBSIE(InfoExtractor):
  12     IE_DESC = 'sbs.com.au'
  13     _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'
  14
  15     _TESTS = [{
  16         # Original URL is handled by the generic IE which finds the iframe:
  17         # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation
  18         'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
  19         'md5': '3150cf278965eeabb5b4cea1c963fe0a',
  20         'info_dict': {
  21             'id': '320403011771',
  22             'ext': 'mp4',
  23             'title': 'Dingo Conservation (The Feed)',
  24             'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
  25             'thumbnail': 're:http://.*\.jpg',
  26             'duration': 308,
  27             'timestamp': 1408613220,
  28             'upload_date': '20140821',
  29             'uploader': 'SBSC',
  30         },
  31     }, {
  32         'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
  33         'only_matching': True,
  34     }, {
  35         'url': 'http://www.sbs.com.au/news/video/471395907773/The-Feed-July-9',
  36         'only_matching': True,
  37     }]
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41         player_params = self._download_json(
  42             'http://www.sbs.com.au/api/video_pdkvars/id/%s?form=json' % video_id, video_id)
  43
  44         error = player_params.get('error')
  45         if error:
  46             error_message = 'Sorry, The video you are looking for does not exist.'
  47             video_data = error.get('results') or {}
  48             error_code = error.get('errorCode')
  49             if error_code == 'ComingSoon':
  50                 error_message = '%s is not yet available.' % video_data.get('title', '')
  51             elif error_code in ('Forbidden', 'intranetAccessOnly'):
  52                 error_message = 'Sorry, This video cannot be accessed via this website'
  53             elif error_code == 'Expired':
  54                 error_message = 'Sorry, %s is no longer available.' % video_data.get('title', '')
  55             raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
  56
  57         urls = player_params['releaseUrls']
  58         theplatform_url = (urls.get('progressive') or urls.get('html') or
  59                            urls.get('standard') or player_params['relatedItemsURL'])
  60
  61         return {
  62             '_type': 'url_transparent',
  63             'ie_key': 'ThePlatform',
  64             'id': video_id,
  65             'url': smuggle_url(self._proto_relative_url(theplatform_url), {'force_smil_url': True}),
  66         }