yt_dlp/extractor/kakao.py

   1 # coding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     int_or_none,
   9     strip_or_none,
  10     traverse_obj,
  11     unified_timestamp,
  12 )
  13
  14
  15 class KakaoIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P<id>\d+|[^?#&]+@my)'
  17     _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/playmeta/cliplink/%s/'
  18     _CDN_API = 'https://tv.kakao.com/katz/v1/ft/cliplink/%s/readyNplay?'
  19
  20     _TESTS = [{
  21         'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
  22         'md5': '702b2fbdeb51ad82f5c904e8c0766340',
  23         'info_dict': {
  24             'id': '301965083',
  25             'ext': 'mp4',
  26             '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』',
  27             'uploader_id': 2671005,
  28             'uploader': '그랑그랑이',
  29             'timestamp': 1488160199,
  30             'upload_date': '20170227',
  31         }
  32     }, {
  33         'url': 'http://tv.kakao.com/channel/2653210/cliplink/300103180',
  34         'md5': 'a8917742069a4dd442516b86e7d66529',
  35         'info_dict': {
  36             'id': '300103180',
  37             'ext': 'mp4',
  38             'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
  39             'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
  40             'uploader_id': 2653210,
  41             'uploader': '쇼! 음악중심',
  42             'timestamp': 1485684628,
  43             'upload_date': '20170129',
  44         }
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         api_base = self._API_BASE_TMPL % video_id
  50         cdn_api_base = self._CDN_API % video_id
  51
  52         query = {
  53             'player': 'monet_html5',
  54             'referer': url,
  55             'uuid': '',
  56             'service': 'kakao_tv',
  57             'section': '',
  58             'dteType': 'PC',
  59             'fields': ','.join([
  60                 '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
  61                 'description', 'channelId', 'createTime', 'duration', 'playCount',
  62                 'likeCount', 'commentCount', 'tagList', 'channel', 'name',
  63                 'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
  64                 'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
  65         }
  66
  67         api_json = self._download_json(
  68             api_base, video_id, 'Downloading video info')
  69
  70         clip_link = api_json['clipLink']
  71         clip = clip_link['clip']
  72
  73         title = clip.get('title') or clip_link.get('displayTitle')
  74
  75         formats = []
  76         for fmt in clip.get('videoOutputList', []):
  77             profile_name = fmt.get('profile')
  78             if not profile_name or profile_name == 'AUDIO':
  79                 continue
  80             query.update({
  81                 'profile': profile_name,
  82                 'fields': '-*,url',
  83             })
  84
  85             fmt_url_json = self._download_json(
  86                 cdn_api_base, video_id,
  87                 'Downloading video URL for profile %s' % profile_name,
  88                 query=query, fatal=False)
  89             fmt_url = traverse_obj(fmt_url_json, ('videoLocation', 'url'))
  90             if not fmt_url:
  91                 continue
  92
  93             formats.append({
  94                 'url': fmt_url,
  95                 'format_id': profile_name,
  96                 'width': int_or_none(fmt.get('width')),
  97                 'height': int_or_none(fmt.get('height')),
  98                 'format_note': fmt.get('label'),
  99                 'filesize': int_or_none(fmt.get('filesize')),
 100                 'tbr': int_or_none(fmt.get('kbps')),
 101             })
 102         self._sort_formats(formats)
 103
 104         thumbs = []
 105         for thumb in clip.get('clipChapterThumbnailList') or []:
 106             thumbs.append({
 107                 'url': thumb.get('thumbnailUrl'),
 108                 'id': compat_str(thumb.get('timeInSec')),
 109                 'preference': -1 if thumb.get('isDefault') else 0
 110             })
 111         top_thumbnail = clip.get('thumbnailUrl')
 112         if top_thumbnail:
 113             thumbs.append({
 114                 'url': top_thumbnail,
 115                 'preference': 10,
 116             })
 117
 118         return {
 119             'id': video_id,
 120             'title': title,
 121             'description': strip_or_none(clip.get('description')),
 122             'uploader': traverse_obj(clip_link, ('channel', 'name')),
 123             'uploader_id': clip_link.get('channelId'),
 124             'thumbnails': thumbs,
 125             'timestamp': unified_timestamp(clip_link.get('createTime')),
 126             'duration': int_or_none(clip.get('duration')),
 127             'view_count': int_or_none(clip.get('playCount')),
 128             'like_count': int_or_none(clip.get('likeCount')),
 129             'comment_count': int_or_none(clip.get('commentCount')),
 130             'formats': formats,
 131             'tags': clip.get('tagList'),
 132         }