]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vgtv.py
Imported Upstream version 2015.02.28
[youtubedl] / youtube_dl / extractor / vgtv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import float_or_none
8
9
10 class VGTVIE(InfoExtractor):
11 _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P<id>[0-9]+)'
12 _TESTS = [
13 {
14 # streamType: vod
15 'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
16 'md5': 'b8be7a234cebb840c0d512c78013e02f',
17 'info_dict': {
18 'id': '84196',
19 'ext': 'mp4',
20 'title': 'Hevnen er søt: Episode 10 - Abu',
21 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
22 'thumbnail': 're:^https?://.*\.jpg',
23 'duration': 648.000,
24 'timestamp': 1404626400,
25 'upload_date': '20140706',
26 'view_count': int,
27 },
28 },
29 {
30 # streamType: wasLive
31 'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
32 'info_dict': {
33 'id': '100764',
34 'ext': 'flv',
35 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
36 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
37 'thumbnail': 're:^https?://.*\.jpg',
38 'duration': 9103.0,
39 'timestamp': 1410113864,
40 'upload_date': '20140907',
41 'view_count': int,
42 },
43 'params': {
44 # m3u8 download
45 'skip_download': True,
46 },
47 },
48 {
49 # streamType: live
50 'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen',
51 'info_dict': {
52 'id': '100015',
53 'ext': 'flv',
54 'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!',
55 'description': 'md5:9a60cc23fa349f761628924e56eeec2d',
56 'thumbnail': 're:^https?://.*\.jpg',
57 'duration': 0,
58 'timestamp': 1407423348,
59 'upload_date': '20140807',
60 'view_count': int,
61 },
62 'params': {
63 # m3u8 download
64 'skip_download': True,
65 },
66 },
67 ]
68
69 def _real_extract(self, url):
70 video_id = self._match_id(url)
71 data = self._download_json(
72 'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id,
73 video_id, 'Downloading media JSON')
74
75 streams = data['streamUrls']
76
77 formats = []
78
79 hls_url = streams.get('hls')
80 if hls_url:
81 formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4'))
82
83 hds_url = streams.get('hds')
84 if hds_url:
85 formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id))
86
87 mp4_url = streams.get('mp4')
88 if mp4_url:
89 _url = hls_url or hds_url
90 MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1])
91 for mp4_format in _url.split(','):
92 m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format)
93 if not m:
94 continue
95 width = int(m.group('width'))
96 height = int(m.group('height'))
97 vbr = int(m.group('vbr'))
98 formats.append({
99 'url': MP4_URL_TEMPLATE % mp4_format,
100 'format_id': 'mp4-%s' % vbr,
101 'width': width,
102 'height': height,
103 'vbr': vbr,
104 'preference': 1,
105 })
106 self._sort_formats(formats)
107
108 return {
109 'id': video_id,
110 'title': data['title'],
111 'description': data['description'],
112 'thumbnail': data['images']['main'] + '?t[]=900x506q80',
113 'timestamp': data['published'],
114 'duration': float_or_none(data['duration'], 1000),
115 'view_count': data['displays'],
116 'formats': formats,
117 }