]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/sprout.py
[nova] Fix extraction (closes #17241)
[youtube-dl.git] / youtube_dl / extractor / sprout.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .adobepass import AdobePassIE
5 from ..utils import (
6     extract_attributes,
7     update_url_query,
8     smuggle_url,
9 )
10
11
12 class SproutIE(AdobePassIE):
13     _VALID_URL = r'https?://(?:www\.)?sproutonline\.com/watch/(?P<id>[^/?#]+)'
14     _TEST = {
15         'url': 'http://www.sproutonline.com/watch/cowboy-adventure',
16         'md5': '74bf14128578d1e040c3ebc82088f45f',
17         'info_dict': {
18             'id': '9dexnwtmh8_X',
19             'ext': 'mp4',
20             'title': 'A Cowboy Adventure',
21             'description': 'Ruff-Ruff, Tweet and Dave get to be cowboys for the day at Six Cow Corral.',
22             'timestamp': 1437758640,
23             'upload_date': '20150724',
24             'uploader': 'NBCU-SPROUT-NEW',
25         }
26     }
27
28     def _real_extract(self, url):
29         video_id = self._match_id(url)
30         webpage = self._download_webpage(url, video_id)
31         video_component = self._search_regex(
32             r'(?s)(<div[^>]+data-component="video"[^>]*?>)',
33             webpage, 'video component', default=None)
34         if video_component:
35             options = self._parse_json(extract_attributes(
36                 video_component)['data-options'], video_id)
37             theplatform_url = options['video']
38             query = {
39                 'mbr': 'true',
40                 'manifest': 'm3u',
41             }
42             if options.get('protected'):
43                 query['auth'] = self._extract_mvpd_auth(url, options['pid'], 'sprout', 'sprout')
44             theplatform_url = smuggle_url(update_url_query(
45                 theplatform_url, query), {'force_smil_url': True})
46         else:
47             iframe = self._search_regex(
48                 r'(<iframe[^>]+id="sproutVideoIframe"[^>]*?>)',
49                 webpage, 'iframe')
50             theplatform_url = extract_attributes(iframe)['src']
51
52         return self.url_result(theplatform_url, 'ThePlatform')