aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/go90.py
blob: 3550eca7cba965db7858d9bf33a655544f55b3f1 (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    int_or_none,
    parse_iso8601,
)


class Go90IE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?go90\.com/videos/(?P<id>[0-9a-zA-Z]+)'
    _TEST = {
        'url': 'https://www.go90.com/videos/84BUqjLpf9D',
        'md5': 'efa7670dbbbf21a7b07b360652b24a32',
        'info_dict': {
            'id': '84BUqjLpf9D',
            'ext': 'mp4',
            'title': 'Inside The Utah Coalition Against Pornography Convention',
            'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.',
            'timestamp': 1491868800,
            'upload_date': '20170411',
        }
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)
        video_data = self._download_json(
            'https://www.go90.com/api/view/items/' + video_id,
            video_id, headers={
                'Content-Type': 'application/json; charset=utf-8',
            }, data=b'{"client":"web","device_type":"pc"}')
        title = video_data['title']
        main_video_asset = video_data['main_video_asset']

        thumbnails = []
        formats = []
        for asset in video_data.get('assets'):
            if asset.get('id') == main_video_asset:
                for source in asset.get('sources', []):
                    source_location = source.get('location')
                    if not source_location:
                        continue
                    source_type = source.get('type')
                    if source_type == 'hls':
                        m3u8_formats = self._extract_m3u8_formats(
                            source_location, video_id, 'mp4',
                            'm3u8_native', m3u8_id='hls', fatal=False)
                        for f in m3u8_formats:
                            mobj = re.search(r'/hls-(\d+)-(\d+)K', f['url'])
                            if mobj:
                                height, tbr = mobj.groups()
                                height = int_or_none(height)
                                f.update({
                                    'height': f.get('height') or height,
                                    'width': f.get('width') or int_or_none(height / 9.0 * 16.0 if height else None),
                                    'tbr': f.get('tbr') or int_or_none(tbr),
                                })
                        formats.extend(m3u8_formats)
                    elif source_type == 'dash':
                        formats.extend(self._extract_mpd_formats(
                            source_location, video_id, mpd_id='dash', fatal=False))
                    else:
                        formats.append({
                            'format_id': source.get('name'),
                            'url': source_location,
                            'width': int_or_none(source.get('width')),
                            'height': int_or_none(source.get('height')),
                            'tbr': int_or_none(source.get('bitrate')),
                        })
            elif asset.get('type') == 'image':
                asset_location = asset.get('location')
                if not asset_location:
                    continue
                thumbnails.append({
                    'url': asset_location,
                    'width': int_or_none(asset.get('width')),
                    'height': int_or_none(asset.get('height')),
                })
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
            'thumbnails': thumbnails,
            'description': video_data.get('short_description'),
            'like_count': int_or_none(video_data.get('like_count')),
            'timestamp': parse_iso8601(video_data.get('released_at')),
        }