]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/sbs.py
Imported Upstream version 2015.11.10
[youtubedl] / youtube_dl / extractor / sbs.py
1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5
6
7 class SBSIE(InfoExtractor):
8 IE_DESC = 'sbs.com.au'
9 _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'
10
11 _TESTS = [{
12 # Original URL is handled by the generic IE which finds the iframe:
13 # http://www.sbs.com.au/thefeed/blog/2014/08/21/dingo-conservation
14 'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
15 'md5': '3150cf278965eeabb5b4cea1c963fe0a',
16 'info_dict': {
17 'id': '320403011771',
18 'ext': 'mp4',
19 'title': 'Dingo Conservation (The Feed)',
20 'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
21 'thumbnail': 're:http://.*\.jpg',
22 'duration': 308,
23 },
24 }, {
25 'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
26 'only_matching': True,
27 }, {
28 'url': 'http://www.sbs.com.au/news/video/471395907773/The-Feed-July-9',
29 'only_matching': True,
30 }]
31
32 def _real_extract(self, url):
33 video_id = self._match_id(url)
34
35 webpage = self._download_webpage(
36 'http://www.sbs.com.au/ondemand/video/single/%s?context=web' % video_id, video_id)
37
38 player_params = self._parse_json(
39 self._search_regex(
40 r'(?s)var\s+playerParams\s*=\s*({.+?});', webpage, 'playerParams'),
41 video_id)
42
43 urls = player_params['releaseUrls']
44 theplatform_url = (urls.get('progressive') or urls.get('standard') or
45 urls.get('html') or player_params['relatedItemsURL'])
46
47 return {
48 '_type': 'url_transparent',
49 'id': video_id,
50 'url': theplatform_url,
51 }