aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vzaar.py
blob: 6000671c31bc399a405f03a0064996287d46fe3e (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    int_or_none,
    float_or_none,
    unified_timestamp,
    url_or_none,
)


class VzaarIE(InfoExtractor):
    _VALID_URL = r'https?://(?:(?:www|view)\.)?vzaar\.com/(?:videos/)?(?P<id>\d+)'
    _TESTS = [{
        # HTTP and HLS
        'url': 'https://vzaar.com/videos/1152805',
        'md5': 'bde5ddfeb104a6c56a93a06b04901dbf',
        'info_dict': {
            'id': '1152805',
            'ext': 'mp4',
            'title': 'sample video (public)',
        },
    }, {
        'url': 'https://view.vzaar.com/27272/player',
        'md5': '3b50012ac9bbce7f445550d54e0508f2',
        'info_dict': {
            'id': '27272',
            'ext': 'mp3',
            'title': 'MP3',
        },
    }]

    @staticmethod
    def _extract_urls(webpage):
        return re.findall(
            r'<iframe[^>]+src=["\']((?:https?:)?//(?:view\.vzaar\.com)/[0-9]+)',
            webpage)

    def _real_extract(self, url):
        video_id = self._match_id(url)
        video_data = self._download_json(
            'http://view.vzaar.com/v2/%s/video' % video_id, video_id)

        title = video_data['videoTitle']

        formats = []

        source_url = url_or_none(video_data.get('sourceUrl'))
        if source_url:
            f = {
                'url': source_url,
                'format_id': 'http',
            }
            if 'audio' in source_url:
                f.update({
                    'vcodec': 'none',
                    'ext': 'mp3',
                })
            else:
                f.update({
                    'width': int_or_none(video_data.get('width')),
                    'height': int_or_none(video_data.get('height')),
                    'ext': 'mp4',
                    'fps': float_or_none(video_data.get('fps')),
                })
            formats.append(f)

        video_guid = video_data.get('guid')
        usp = video_data.get('usp')
        if isinstance(video_guid, compat_str) and isinstance(usp, dict):
            m3u8_url = ('http://fable.vzaar.com/v4/usp/%s/%s.ism/.m3u8?'
                        % (video_guid, video_id)) + '&'.join(
                '%s=%s' % (k, v) for k, v in usp.items())
            formats.extend(self._extract_m3u8_formats(
                m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
                m3u8_id='hls', fatal=False))

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'thumbnail': self._proto_relative_url(video_data.get('poster')),
            'duration': float_or_none(video_data.get('videoDuration')),
            'timestamp': unified_timestamp(video_data.get('ts')),
            'formats': formats,
        }