youtube_dl/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     unified_timestamp,
  10     update_url_query,
  11 )
  12
  13
  14 class KakaoIE(InfoExtractor):
  15     _VALID_URL = r'https?://tv\.kakao\.com/channel/(?P<channel>\d+)/cliplink/(?P<id>\d+)'
  16     _API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks'
  17
  18     _TESTS = [{
  19         'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
  20         'md5': '702b2fbdeb51ad82f5c904e8c0766340',
  21         'info_dict': {
  22             'id': '301965083',
  23             'ext': 'mp4',
  24             '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』',
  25             'uploader_id': 2671005,
  26             'uploader': '그랑그랑이',
  27             'timestamp': 1488160199,
  28             'upload_date': '20170227',
  29         }
  30     }, {
  31         'url': 'http://tv.kakao.com/channel/2653210/cliplink/300103180',
  32         'md5': 'a8917742069a4dd442516b86e7d66529',
  33         'info_dict': {
  34             'id': '300103180',
  35             'ext': 'mp4',
  36             'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
  37             'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
  38             'uploader_id': 2653210,
  39             'uploader': '쇼 음악중심',
  40             'timestamp': 1485684628,
  41             'upload_date': '20170129',
  42         }
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47
  48         player_header = {
  49             'Referer': update_url_query(
  50                 'http://tv.kakao.com/embed/player/cliplink/%s' % video_id, {
  51                     'service': 'kakao_tv',
  52                     'autoplay': '1',
  53                     'profile': 'HIGH',
  54                     'wmode': 'transparent',
  55                 })
  56         }
  57
  58         QUERY_COMMON = {
  59             'player': 'monet_html5',
  60             'referer': url,
  61             'uuid': '',
  62             'service': 'kakao_tv',
  63             'section': '',
  64             'dteType': 'PC',
  65         }
  66
  67         query = QUERY_COMMON.copy()
  68         query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList'
  69         impress = self._download_json(
  70             '%s/%s/impress' % (self._API_BASE, video_id),
  71             video_id, 'Downloading video info',
  72             query=query, headers=player_header)
  73
  74         clip_link = impress['clipLink']
  75         clip = clip_link['clip']
  76
  77         title = clip.get('title') or clip_link.get('displayTitle')
  78
  79         tid = impress.get('tid', '')
  80
  81         query = QUERY_COMMON.copy()
  82         query.update({
  83             'tid': tid,
  84             'profile': 'HIGH',
  85         })
  86         raw = self._download_json(
  87             '%s/%s/raw' % (self._API_BASE, video_id),
  88             video_id, 'Downloading video formats info',
  89             query=query, headers=player_header)
  90
  91         formats = []
  92         for fmt in raw.get('outputList', []):
  93             try:
  94                 profile_name = fmt['profile']
  95                 fmt_url_json = self._download_json(
  96                     '%s/%s/raw/videolocation' % (self._API_BASE, video_id),
  97                     video_id,
  98                     'Downloading video URL for profile %s' % profile_name,
  99                     query={
 100                         'service': 'kakao_tv',
 101                         'section': '',
 102                         'tid': tid,
 103                         'profile': profile_name
 104                     }, headers=player_header, fatal=False)
 105
 106                 if fmt_url_json is None:
 107                     continue
 108
 109                 fmt_url = fmt_url_json['url']
 110                 formats.append({
 111                     'url': fmt_url,
 112                     'format_id': profile_name,
 113                     'width': int_or_none(fmt.get('width')),
 114                     'height': int_or_none(fmt.get('height')),
 115                     'format_note': fmt.get('label'),
 116                     'filesize': int_or_none(fmt.get('filesize'))
 117                 })
 118             except KeyError:
 119                 pass
 120         self._sort_formats(formats)
 121
 122         thumbs = []
 123         for thumb in clip.get('clipChapterThumbnailList', []):
 124             thumbs.append({
 125                 'url': thumb.get('thumbnailUrl'),
 126                 'id': compat_str(thumb.get('timeInSec')),
 127                 'preference': -1 if thumb.get('isDefault') else 0
 128             })
 129         top_thumbnail = clip.get('thumbnailUrl')
 130         if top_thumbnail:
 131             thumbs.append({
 132                 'url': top_thumbnail,
 133                 'preference': 10,
 134             })
 135
 136         return {
 137             'id': video_id,
 138             'title': title,
 139             'description': clip.get('description'),
 140             'uploader': clip_link.get('channel', {}).get('name'),
 141             'uploader_id': clip_link.get('channelId'),
 142             'thumbnails': thumbs,
 143             'timestamp': unified_timestamp(clip_link.get('createTime')),
 144             'duration': int_or_none(clip.get('duration')),
 145             'view_count': int_or_none(clip.get('playCount')),
 146             'like_count': int_or_none(clip.get('likeCount')),
 147             'comment_count': int_or_none(clip.get('commentCount')),
 148             'formats': formats,
 149         }