aboutsummaryrefslogtreecommitdiffstats
path: root/hypervideo_dl/extractor/kakao.py
blob: 483ab712866edb65dd94a60ad300cea9e938b161 (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
155
156
# coding: utf-8

from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
    ExtractorError,
    int_or_none,
    strip_or_none,
    str_or_none,
    traverse_obj,
    unified_timestamp,
)


class KakaoIE(InfoExtractor):
    _VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P<id>\d+|[^?#&]+@my)'
    _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/playmeta/cliplink/%s/'
    _CDN_API = 'https://tv.kakao.com/katz/v1/ft/cliplink/%s/readyNplay?'

    _TESTS = [{
        'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
        'md5': '702b2fbdeb51ad82f5c904e8c0766340',
        'info_dict': {
            'id': '301965083',
            'ext': 'mp4',
            'title': '乃木坂46 バナナマン 「3期生紹介コーナーが始動!顔高低差GPも!」 『乃木坂工事中』',
            'description': '',
            'uploader_id': '2671005',
            'uploader': '그랑그랑이',
            'timestamp': 1488160199,
            'upload_date': '20170227',
            'like_count': int,
            'thumbnail': r're:http://.+/thumb\.png',
            'tags': ['乃木坂'],
            'view_count': int,
            'duration': 1503,
            'comment_count': int,
        }
    }, {
        'url': 'http://tv.kakao.com/channel/2653210/cliplink/300103180',
        'md5': 'a8917742069a4dd442516b86e7d66529',
        'info_dict': {
            'id': '300103180',
            'ext': 'mp4',
            'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
            'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
            'uploader_id': '2653210',
            'uploader': '쇼! 음악중심',
            'timestamp': 1485684628,
            'upload_date': '20170129',
            'like_count': int,
            'thumbnail': r're:http://.+/thumb\.png',
            'tags': 'count:28',
            'view_count': int,
            'duration': 184,
            'comment_count': int,
        }
    }, {
        # geo restricted
        'url': 'https://tv.kakao.com/channel/3643855/cliplink/412069491',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        api_base = self._API_BASE_TMPL % video_id
        cdn_api_base = self._CDN_API % video_id

        query = {
            'player': 'monet_html5',
            'referer': url,
            'uuid': '',
            'service': 'kakao_tv',
            'section': '',
            'dteType': 'PC',
            'fields': ','.join([
                '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
                'description', 'channelId', 'createTime', 'duration', 'playCount',
                'likeCount', 'commentCount', 'tagList', 'channel', 'name',
                'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
                'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
        }

        api_json = self._download_json(
            api_base, video_id, 'Downloading video info')

        clip_link = api_json['clipLink']
        clip = clip_link['clip']

        title = clip.get('title') or clip_link.get('displayTitle')

        formats = []
        for fmt in clip.get('videoOutputList') or []:
            profile_name = fmt.get('profile')
            if not profile_name or profile_name == 'AUDIO':
                continue
            query.update({
                'profile': profile_name,
                'fields': '-*,code,message,url',
            })
            try:
                fmt_url_json = self._download_json(
                    cdn_api_base, video_id, query=query,
                    note='Downloading video URL for profile %s' % profile_name)
            except ExtractorError as e:
                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                    resp = self._parse_json(e.cause.read().decode(), video_id)
                    if resp.get('code') == 'GeoBlocked':
                        self.raise_geo_restricted()

            fmt_url = traverse_obj(fmt_url_json, ('videoLocation', 'url'))
            if not fmt_url:
                continue

            formats.append({
                'url': fmt_url,
                'format_id': profile_name,
                'width': int_or_none(fmt.get('width')),
                'height': int_or_none(fmt.get('height')),
                'format_note': fmt.get('label'),
                'filesize': int_or_none(fmt.get('filesize')),
                'tbr': int_or_none(fmt.get('kbps')),
            })
        self._sort_formats(formats)

        thumbs = []
        for thumb in clip.get('clipChapterThumbnailList') or []:
            thumbs.append({
                'url': thumb.get('thumbnailUrl'),
                'id': str(thumb.get('timeInSec')),
                'preference': -1 if thumb.get('isDefault') else 0
            })
        top_thumbnail = clip.get('thumbnailUrl')
        if top_thumbnail:
            thumbs.append({
                'url': top_thumbnail,
                'preference': 10,
            })

        return {
            'id': video_id,
            'title': title,
            'description': strip_or_none(clip.get('description')),
            'uploader': traverse_obj(clip_link, ('channel', 'name')),
            'uploader_id': str_or_none(clip_link.get('channelId')),
            'thumbnails': thumbs,
            'timestamp': unified_timestamp(clip_link.get('createTime')),
            'duration': int_or_none(clip.get('duration')),
            'view_count': int_or_none(clip.get('playCount')),
            'like_count': int_or_none(clip.get('likeCount')),
            'comment_count': int_or_none(clip.get('commentCount')),
            'formats': formats,
            'tags': clip.get('tagList'),
        }