43e8e619f6d0562982097a0e36da5eee58e5c713
[ytdl] / 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 (
8     ExtractorError,
9     float_or_none,
10     unified_strdate,
11 )
12
13
14 class NRKIE(InfoExtractor):
15     _VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
16
17     _TESTS = [
18         {
19             'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
20             'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
21             'info_dict': {
22                 'id': '150533',
23                 'ext': 'flv',
24                 'title': 'Dompap og andre fugler i Piip-Show',
25                 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
26             }
27         },
28         {
29             'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
30             'md5': '3471f2a51718195164e88f46bf427668',
31             'info_dict': {
32                 'id': '154915',
33                 'ext': 'flv',
34                 'title': 'Slik høres internett ut når du er blind',
35                 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
36             }
37         },
38     ]
39
40     def _real_extract(self, url):
41         mobj = re.match(self._VALID_URL, url)
42         video_id = mobj.group('id')
43
44         page = self._download_webpage(url, video_id)
45
46         video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
47
48         data = self._download_json(
49             'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
50
51         if data['usageRights']['isGeoBlocked']:
52             raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
53
54         video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
55
56         images = data.get('images')
57         if images:
58             thumbnails = images['webImages']
59             thumbnails.sort(key=lambda image: image['pixelWidth'])
60             thumbnail = thumbnails[-1]['imageUrl']
61         else:
62             thumbnail = None
63
64         return {
65             'id': video_id,
66             'url': video_url,
67             'ext': 'flv',
68             'title': data['title'],
69             'description': data['description'],
70             'thumbnail': thumbnail,
71         }
72
73
74 class NRKTVIE(InfoExtractor):
75     _VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})'
76
77     _TESTS = [
78         {
79             'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
80             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
81             'info_dict': {
82                 'id': 'MUHH48000314',
83                 'ext': 'flv',
84                 'title': '20 spørsmål',
85                 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
86                 'upload_date': '20140523',
87                 'duration': 1741.52,
88             }
89         },
90         {
91             'url': 'http://tv.nrk.no/program/mdfp15000514',
92             'md5': '383650ece2b25ecec996ad7b5bb2a384',
93             'info_dict': {
94                 'id': 'mdfp15000514',
95                 'ext': 'flv',
96                 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
97                 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
98                 'upload_date': '20140524',
99                 'duration': 4605.0,
100             }
101         },
102     ]
103
104     def _real_extract(self, url):
105         mobj = re.match(self._VALID_URL, url)
106         video_id = mobj.group('id')
107
108         page = self._download_webpage(url, video_id)
109
110         title = self._html_search_meta('title', page, 'title')
111         description = self._html_search_meta('description', page, 'description')
112         thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
113         upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
114         duration = float_or_none(
115             self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False))
116
117         formats = []
118
119         f4m_url = re.search(r'data-media="([^"]+)"', page)
120         if f4m_url:
121             formats.append({
122                 'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
123                 'format_id': 'f4m',
124                 'ext': 'flv',
125             })
126
127         m3u8_url = re.search(r'data-hls-media="([^"]+)"', page)
128         if m3u8_url:
129             formats.append({
130                 'url': m3u8_url.group(1),
131                 'format_id': 'm3u8',
132             })
133
134         self._sort_formats(formats)
135
136         return {
137             'id': video_id,
138             'title': title,
139             'description': description,
140             'thumbnail': thumbnail,
141             'upload_date': upload_date,
142             'duration': duration,
143             'formats': formats,
144         }