aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vgtv.py
blob: b0f0b3bc29d14801c608aa3d6a159ca5c257ad74 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import float_or_none


class VGTVIE(InfoExtractor):
    IE_DESC = 'VGTV and BTTV'
    _VALID_URL = r'http://(?:www\.)?(?P<host>vgtv|bt)\.no/(?:(?:tv/)?#!/(?:video|live)/(?P<id>[0-9]+)|(?:[^/]+/)*(?P<path>[^/]+))'
    _TESTS = [
        {
            # streamType: vod
            'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
            'md5': 'b8be7a234cebb840c0d512c78013e02f',
            'info_dict': {
                'id': '84196',
                'ext': 'mp4',
                'title': 'Hevnen er søt: Episode 10 - Abu',
                'description': 'md5:e25e4badb5f544b04341e14abdc72234',
                'thumbnail': 're:^https?://.*\.jpg',
                'duration': 648.000,
                'timestamp': 1404626400,
                'upload_date': '20140706',
                'view_count': int,
            },
        },
        {
            # streamType: wasLive
            'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
            'info_dict': {
                'id': '100764',
                'ext': 'flv',
                'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
                'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
                'thumbnail': 're:^https?://.*\.jpg',
                'duration': 9103.0,
                'timestamp': 1410113864,
                'upload_date': '20140907',
                'view_count': int,
            },
            'params': {
                # m3u8 download
                'skip_download': True,
            },
        },
        {
            # streamType: live
            'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen',
            'info_dict': {
                'id': '100015',
                'ext': 'flv',
                'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!',
                'description': 'md5:9a60cc23fa349f761628924e56eeec2d',
                'thumbnail': 're:^https?://.*\.jpg',
                'duration': 0,
                'timestamp': 1407423348,
                'upload_date': '20140807',
                'view_count': int,
            },
            'params': {
                # m3u8 download
                'skip_download': True,
            },
        },
        {
            'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
            'only_matching': True,
        },
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        host = mobj.group('host')

        HOST_WEBSITES = {
            'vgtv': 'vgtv',
            'bt': 'bttv',
        }

        data = self._download_json(
            'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
            % (host, video_id, HOST_WEBSITES[host]),
            video_id, 'Downloading media JSON')

        streams = data['streamUrls']

        formats = []

        hls_url = streams.get('hls')
        if hls_url:
            formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4'))

        hds_url = streams.get('hds')
        if hds_url:
            formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id))

        mp4_url = streams.get('mp4')
        if mp4_url:
            _url = hls_url or hds_url
            MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1])
            for mp4_format in _url.split(','):
                m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format)
                if not m:
                    continue
                width = int(m.group('width'))
                height = int(m.group('height'))
                vbr = int(m.group('vbr'))
                formats.append({
                    'url': MP4_URL_TEMPLATE % mp4_format,
                    'format_id': 'mp4-%s' % vbr,
                    'width': width,
                    'height': height,
                    'vbr': vbr,
                    'preference': 1,
                })
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': data['title'],
            'description': data['description'],
            'thumbnail': data['images']['main'] + '?t[]=900x506q80',
            'timestamp': data['published'],
            'duration': float_or_none(data['duration'], 1000),
            'view_count': data['displays'],
            'formats': formats,
        }