Merge remote-tracking branch 'hojel/slutload'
[youtube-dl] / youtube_dl / extractor / nrk.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import ExtractorError
8
9
10 class NRKIE(InfoExtractor):
11     _VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
12
13     _TESTS = [
14         {
15             'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
16             'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
17             'info_dict': {
18                 'id': '150533',
19                 'ext': 'flv',
20                 'title': 'Dompap og andre fugler i Piip-Show',
21                 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
22             }
23         },
24         {
25             'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
26             'md5': '3471f2a51718195164e88f46bf427668',
27             'info_dict': {
28                 'id': '154915',
29                 'ext': 'flv',
30                 'title': 'Slik høres internett ut når du er blind',
31                 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
32             }
33         },
34     ]
35
36     def _real_extract(self, url):
37         mobj = re.match(self._VALID_URL, url)
38         video_id = mobj.group('id')
39
40         page = self._download_webpage(url, video_id)
41
42         video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
43
44         data = self._download_json(
45             'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
46
47         if data['usageRights']['isGeoBlocked']:
48             raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
49
50         video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
51
52         images = data.get('images')
53         if images:
54             thumbnails = images['webImages']
55             thumbnails.sort(key=lambda image: image['pixelWidth'])
56             thumbnail = thumbnails[-1]['imageUrl']
57         else:
58             thumbnail = None
59
60         return {
61             'id': video_id,
62             'url': video_url,
63             'ext': 'flv',
64             'title': data['title'],
65             'description': data['description'],
66             'thumbnail': thumbnail,
67         }