aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vlive.py
blob: 1a9f10eb4dc24b17f55dedc163ffbffe8728bde5 (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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    dict_get,
    ExtractorError,
    float_or_none,
    int_or_none,
    remove_start,
)
from ..compat import compat_urllib_parse_urlencode


class VLiveIE(InfoExtractor):
    IE_NAME = 'vlive'
    _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://www.vlive.tv/video/1326',
        'md5': 'cc7314812855ce56de70a06a27314983',
        'info_dict': {
            'id': '1326',
            'ext': 'mp4',
            'title': "[V LIVE] Girl's Day's Broadcast",
            'creator': "Girl's Day",
            'view_count': int,
        },
    }, {
        'url': 'http://www.vlive.tv/video/16937',
        'info_dict': {
            'id': '16937',
            'ext': 'mp4',
            'title': '[V LIVE] 첸백시 걍방',
            'creator': 'EXO',
            'view_count': int,
            'subtitles': 'mincount:12',
        },
        'params': {
            'skip_download': True,
        },
    }]

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

        webpage = self._download_webpage(
            'http://www.vlive.tv/video/%s' % video_id, video_id)

        video_params = self._parse_json(self._search_regex(
            r'\bvlive\.video\.init\(([^)]+)\);',
            webpage, 'video params'), video_id,
            transform_source=lambda s: '[' + s + ']')

        status, long_video_id, key = video_params[2], video_params[5], video_params[6]
        status = remove_start(status, 'PRODUCT_')

        if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR':
            return self._live(video_id, webpage)
        elif status == 'VOD_ON_AIR' or status == 'BIG_EVENT_INTRO':
            if long_video_id and key:
                return self._replay(video_id, webpage, long_video_id, key)
            else:
                status = 'COMING_SOON'

        if status == 'LIVE_END':
            raise ExtractorError('Uploading for replay. Please wait...',
                                 expected=True)
        elif status == 'COMING_SOON':
            raise ExtractorError('Coming soon!', expected=True)
        elif status == 'CANCELED':
            raise ExtractorError('We are sorry, '
                                 'but the live broadcast has been canceled.',
                                 expected=True)
        else:
            raise ExtractorError('Unknown status %s' % status)

    def _get_common_fields(self, webpage):
        title = self._og_search_title(webpage)
        creator = self._html_search_regex(
            r'<div[^>]+class="info_area"[^>]*>\s*<a\s+[^>]*>([^<]+)',
            webpage, 'creator', fatal=False)
        thumbnail = self._og_search_thumbnail(webpage)
        return {
            'title': title,
            'creator': creator,
            'thumbnail': thumbnail,
        }

    def _live(self, video_id, webpage):
        init_page = self._download_webpage(
            'http://www.vlive.tv/video/init/view',
            video_id, data="videoSeq=%s" % video_id, headers={
                'Referer': 'http://www.vlive.tv/video/%s' % video_id,
                'Content-Type': 'application/x-www-form-urlencoded'
            })

        live_params = self._search_regex(
            r'"liveStreamInfo"\s*:\s*(".*"),',
            init_page, 'video params')
        live_params = self._parse_json(live_params, video_id)
        live_params = self._parse_json(live_params, video_id)

        formats = []
        for vid in live_params.get('resolutions', []):
            formats.extend(self._extract_m3u8_formats(
                vid['cdnUrl'], video_id, 'mp4',
                m3u8_id=vid.get('name'),
                fatal=False, live=True))
        self._sort_formats(formats)

        return dict(self._get_common_fields(webpage),
                    id=video_id,
                    formats=formats,
                    is_live=True)

    def _replay(self, video_id, webpage, long_video_id, key):
        playinfo = self._download_json(
            'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s'
            % compat_urllib_parse_urlencode({
                'videoId': long_video_id,
                'key': key,
                'ptc': 'http',
                'doct': 'json',  # document type (xml or json)
                'cpt': 'vtt',  # captions type (vtt or ttml)
            }), video_id)

        formats = [{
            'url': vid['source'],
            'format_id': vid.get('encodingOption', {}).get('name'),
            'abr': float_or_none(vid.get('bitrate', {}).get('audio')),
            'vbr': float_or_none(vid.get('bitrate', {}).get('video')),
            'width': int_or_none(vid.get('encodingOption', {}).get('width')),
            'height': int_or_none(vid.get('encodingOption', {}).get('height')),
            'filesize': int_or_none(vid.get('size')),
        } for vid in playinfo.get('videos', {}).get('list', []) if vid.get('source')]
        self._sort_formats(formats)

        view_count = int_or_none(playinfo.get('meta', {}).get('count'))

        subtitles = {}
        for caption in playinfo.get('captions', {}).get('list', []):
            lang = dict_get(caption, ('locale', 'language', 'country', 'label'))
            if lang and caption.get('source'):
                subtitles[lang] = [{
                    'ext': 'vtt',
                    'url': caption['source']}]

        return dict(self._get_common_fields(webpage),
                    id=video_id,
                    formats=formats,
                    view_count=view_count,
                    subtitles=subtitles)