about summary refs log tree commit diff
path: root/youtube_dl/extractor/beampro.py
blob: 2eaec1ab4981d87281b9580d9798956d1b36ea29 (plain) (blame)
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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    clean_html,
    compat_str,
    float_or_none,
    int_or_none,
    parse_iso8601,
    try_get,
    urljoin,
)


class BeamProBaseIE(InfoExtractor):
    _API_BASE = 'https://mixer.com/api/v1'
    _RATINGS = {'family': 0, 'teen': 13, '18+': 18}

    def _extract_channel_info(self, chan):
        user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
        return {
            'uploader': chan.get('token') or try_get(
                chan, lambda x: x['user']['username'], compat_str),
            'uploader_id': compat_str(user_id) if user_id else None,
            'age_limit': self._RATINGS.get(chan.get('audience')),
        }


class BeamProLiveIE(BeamProBaseIE):
    IE_NAME = 'Mixer:live'
    _VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/(?P<id>[^/?#&]+)'
    _TEST = {
        'url': 'http://mixer.com/niterhayven',
        'info_dict': {
            'id': '261562',
            'ext': 'mp4',
            'title': 'Introducing The Witcher 3 //  The Grind Starts Now!',
            'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
            'thumbnail': r're:https://.*\.jpg$',
            'timestamp': 1483477281,
            'upload_date': '20170103',
            'uploader': 'niterhayven',
            'uploader_id': '373396',
            'age_limit': 18,
            'is_live': True,
            'view_count': int,
        },
        'skip': 'niterhayven is offline',
        'params': {
            'skip_download': True,
        },
    }

    _MANIFEST_URL_TEMPLATE = '%s/channels/%%s/manifest.%%s' % BeamProBaseIE._API_BASE

    @classmethod
    def suitable(cls, url):
        return False if BeamProVodIE.suitable(url) else super(BeamProLiveIE, cls).suitable(url)

    def _real_extract(self, url):
        channel_name = self._match_id(url)

        chan = self._download_json(
            '%s/channels/%s' % (self._API_BASE, channel_name), channel_name)

        if chan.get('online') is False:
            raise ExtractorError(
                '{0} is offline'.format(channel_name), expected=True)

        channel_id = chan['id']

        def manifest_url(kind):
            return self._MANIFEST_URL_TEMPLATE % (channel_id, kind)

        formats = self._extract_m3u8_formats(
            manifest_url('m3u8'), channel_name, ext='mp4', m3u8_id='hls',
            fatal=False)
        formats.extend(self._extract_smil_formats(
            manifest_url('smil'), channel_name, fatal=False))
        self._sort_formats(formats)

        info = {
            'id': compat_str(chan.get('id') or channel_name),
            'title': self._live_title(chan.get('name') or channel_name),
            'description': clean_html(chan.get('description')),
            'thumbnail': try_get(
                chan, lambda x: x['thumbnail']['url'], compat_str),
            'timestamp': parse_iso8601(chan.get('updatedAt')),
            'is_live': True,
            'view_count': int_or_none(chan.get('viewersTotal')),
            'formats': formats,
        }
        info.update(self._extract_channel_info(chan))

        return info


class BeamProVodIE(BeamProBaseIE):
    IE_NAME = 'Mixer:vod'
    _VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>\d+)'
    _TEST = {
        'url': 'https://mixer.com/willow8714?vod=2259830',
        'md5': 'b2431e6e8347dc92ebafb565d368b76b',
        'info_dict': {
            'id': '2259830',
            'ext': 'mp4',
            'title': 'willow8714\'s Channel',
            'duration': 6828.15,
            'thumbnail': r're:https://.*source\.png$',
            'timestamp': 1494046474,
            'upload_date': '20170506',
            'uploader': 'willow8714',
            'uploader_id': '6085379',
            'age_limit': 13,
            'view_count': int,
        },
        'params': {
            'skip_download': True,
        },
    }

    @staticmethod
    def _extract_format(vod, vod_type):
        if not vod.get('baseUrl'):
            return []

        if vod_type == 'hls':
            filename, protocol = 'manifest.m3u8', 'm3u8_native'
        elif vod_type == 'raw':
            filename, protocol = 'source.mp4', 'https'
        else:
            assert False

        data = vod.get('data') if isinstance(vod.get('data'), dict) else {}

        format_id = [vod_type]
        if isinstance(data.get('Height'), compat_str):
            format_id.append('%sp' % data['Height'])

        return [{
            'url': urljoin(vod['baseUrl'], filename),
            'format_id': '-'.join(format_id),
            'ext': 'mp4',
            'protocol': protocol,
            'width': int_or_none(data.get('Width')),
            'height': int_or_none(data.get('Height')),
            'fps': int_or_none(data.get('Fps')),
            'tbr': int_or_none(data.get('Bitrate'), 1000),
        }]

    def _real_extract(self, url):
        vod_id = self._match_id(url)

        vod_info = self._download_json(
            '%s/recordings/%s' % (self._API_BASE, vod_id), vod_id)

        state = vod_info.get('state')
        if state != 'AVAILABLE':
            raise ExtractorError(
                'VOD %s is not available (state: %s)' % (vod_id, state),
                expected=True)

        formats = []
        thumbnail_url = None

        for vod in vod_info['vods']:
            vod_type = vod.get('format')
            if vod_type in ('hls', 'raw'):
                formats.extend(self._extract_format(vod, vod_type))
            elif vod_type == 'thumbnail':
                thumbnail_url = urljoin(vod.get('baseUrl'), 'source.png')

        self._sort_formats(formats)

        info = {
            'id': vod_id,
            'title': vod_info.get('name') or vod_id,
            'duration': float_or_none(vod_info.get('duration')),
            'thumbnail': thumbnail_url,
            'timestamp': parse_iso8601(vod_info.get('createdAt')),
            'view_count': int_or_none(vod_info.get('viewsTotal')),
            'formats': formats,
        }
        info.update(self._extract_channel_info(vod_info.get('channel') or {}))

        return info