youtube_dl/extractor/sbs.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     js_to_json,
   9     remove_end,
  10 )
  11
  12
  13 class SBSIE(InfoExtractor):
  14     IE_DESC = 'sbs.com.au'
  15     _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P<id>[0-9]+)'
  16
  17     _TESTS = [{
  18         # Original URL is handled by the generic IE which finds the iframe:
  19         # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation
  20         'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
  21         'md5': '3150cf278965eeabb5b4cea1c963fe0a',
  22         'info_dict': {
  23             'id': '320403011771',
  24             'ext': 'mp4',
  25             'title': 'Dingo Conservation',
  26             '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',
  27             'thumbnail': 're:http://.*\.jpg',
  28         },
  29         'add_ies': ['generic'],
  30     }, {
  31         'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37
  38         webpage = self._download_webpage(url, video_id)
  39
  40         player = self._search_regex(
  41             r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n',
  42             webpage, 'player')
  43         player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player)
  44
  45         release_urls = self._parse_json(js_to_json(player), video_id)
  46
  47         theplatform_url = release_urls.get('progressive') or release_urls['standard']
  48
  49         title = remove_end(self._og_search_title(webpage), ' (The Feed)')
  50         description = self._html_search_meta('description', webpage)
  51         thumbnail = self._og_search_thumbnail(webpage)
  52
  53         return {
  54             '_type': 'url_transparent',
  55             'id': video_id,
  56             'url': theplatform_url,
  57             'title': title,
  58             'description': description,
  59             'thumbnail': thumbnail,
  60         }