yt_dlp/extractor/younow.py

   1 import itertools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     format_field,
   7     int_or_none,
   8     str_or_none,
   9     try_get,
  10 )
  11
  12 CDN_API_BASE = 'https://cdn.younow.com/php/api'
  13 MOMENT_URL_FORMAT = f'{CDN_API_BASE}/moment/fetch/id=%s'
  14
  15
  16 class YouNowLiveIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?younow\.com/(?P<id>[^/?#&]+)'
  18     _TEST = {
  19         'url': 'https://www.younow.com/AmandaPadeezy',
  20         'info_dict': {
  21             'id': 'AmandaPadeezy',
  22             'ext': 'mp4',
  23             'is_live': True,
  24             'title': 'March 26, 2017',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'tags': ['girls'],
  27             'categories': ['girls'],
  28             'uploader': 'AmandaPadeezy',
  29             'uploader_id': '6716501',
  30             'uploader_url': 'https://www.younow.com/AmandaPadeezy',
  31             'creator': 'AmandaPadeezy',
  32         },
  33         'skip': True,
  34     }
  35
  36     @classmethod
  37     def suitable(cls, url):
  38         return (False
  39                 if YouNowChannelIE.suitable(url) or YouNowMomentIE.suitable(url)
  40                 else super().suitable(url))
  41
  42     def _real_extract(self, url):
  43         username = self._match_id(url)
  44
  45         data = self._download_json(
  46             f'https://api.younow.com/php/api/broadcast/info/curId=0/user={username}', username)
  47
  48         if data.get('errorCode') != 0:
  49             raise ExtractorError(data['errorMsg'], expected=True)
  50
  51         uploader = try_get(
  52             data, lambda x: x['user']['profileUrlString'],
  53             str) or username
  54
  55         return {
  56             'id': uploader,
  57             'is_live': True,
  58             'title': uploader,
  59             'thumbnail': data.get('awsUrl'),
  60             'tags': data.get('tags'),
  61             'categories': data.get('tags'),
  62             'uploader': uploader,
  63             'uploader_id': data.get('userId'),
  64             'uploader_url': f'https://www.younow.com/{username}',
  65             'creator': uploader,
  66             'view_count': int_or_none(data.get('viewers')),
  67             'like_count': int_or_none(data.get('likes')),
  68             'formats': [{
  69                 'url': '{}/broadcast/videoPath/hls=1/broadcastId={}/channelId={}'.format(CDN_API_BASE, data['broadcastId'], data['userId']),
  70                 'ext': 'mp4',
  71                 'protocol': 'm3u8',
  72             }],
  73         }
  74
  75
  76 def _extract_moment(item, fatal=True):
  77     moment_id = item.get('momentId')
  78     if not moment_id:
  79         if not fatal:
  80             return
  81         raise ExtractorError('Unable to extract moment id')
  82
  83     moment_id = str(moment_id)
  84
  85     title = item.get('text')
  86     if not title:
  87         title = 'YouNow %s' % (
  88             item.get('momentType') or item.get('titleType') or 'moment')
  89
  90     uploader = try_get(item, lambda x: x['owner']['name'], str)
  91     uploader_id = try_get(item, lambda x: x['owner']['userId'])
  92     uploader_url = format_field(uploader, None, 'https://www.younow.com/%s')
  93
  94     return {
  95         'extractor_key': 'YouNowMoment',
  96         'id': moment_id,
  97         'title': title,
  98         'view_count': int_or_none(item.get('views')),
  99         'like_count': int_or_none(item.get('likes')),
 100         'timestamp': int_or_none(item.get('created')),
 101         'creator': uploader,
 102         'uploader': uploader,
 103         'uploader_id': str_or_none(uploader_id),
 104         'uploader_url': uploader_url,
 105         'formats': [{
 106             'url': f'https://hls.younow.com/momentsplaylists/live/{moment_id}/{moment_id}.m3u8',
 107             'ext': 'mp4',
 108             'protocol': 'm3u8_native',
 109         }],
 110     }
 111
 112
 113 class YouNowChannelIE(InfoExtractor):
 114     _VALID_URL = r'https?://(?:www\.)?younow\.com/(?P<id>[^/]+)/channel'
 115     _TEST = {
 116         'url': 'https://www.younow.com/its_Kateee_/channel',
 117         'info_dict': {
 118             'id': '14629760',
 119             'title': 'its_Kateee_ moments',
 120         },
 121         'playlist_mincount': 8,
 122     }
 123
 124     def _entries(self, username, channel_id):
 125         created_before = 0
 126         for page_num in itertools.count(1):
 127             if created_before is None:
 128                 break
 129             info = self._download_json(
 130                 f'{CDN_API_BASE}/moment/profile/channelId={channel_id}/createdBefore={created_before}/records=20',
 131                 username, note=f'Downloading moments page {page_num}')
 132             items = info.get('items')
 133             if not items or not isinstance(items, list):
 134                 break
 135             for item in items:
 136                 if not isinstance(item, dict):
 137                     continue
 138                 item_type = item.get('type')
 139                 if item_type == 'moment':
 140                     entry = _extract_moment(item, fatal=False)
 141                     if entry:
 142                         yield entry
 143                 elif item_type == 'collection':
 144                     moments = item.get('momentsIds')
 145                     if isinstance(moments, list):
 146                         for moment_id in moments:
 147                             m = self._download_json(
 148                                 MOMENT_URL_FORMAT % moment_id, username,
 149                                 note=f'Downloading {moment_id} moment JSON',
 150                                 fatal=False)
 151                             if m and isinstance(m, dict) and m.get('item'):
 152                                 entry = _extract_moment(m['item'])
 153                                 if entry:
 154                                     yield entry
 155                 created_before = int_or_none(item.get('created'))
 156
 157     def _real_extract(self, url):
 158         username = self._match_id(url)
 159         channel_id = str(self._download_json(
 160             f'https://api.younow.com/php/api/broadcast/info/curId=0/user={username}',
 161             username, note='Downloading user information')['userId'])
 162         return self.playlist_result(
 163             self._entries(username, channel_id), channel_id,
 164             f'{username} moments')
 165
 166
 167 class YouNowMomentIE(InfoExtractor):
 168     _VALID_URL = r'https?://(?:www\.)?younow\.com/[^/]+/(?P<id>[^/?#&]+)'
 169     _TEST = {
 170         'url': 'https://www.younow.com/GABO.../20712117/36319236/3b316doc/m',
 171         'md5': 'a30c70eadb9fb39a1aa3c8c0d22a0807',
 172         'info_dict': {
 173             'id': '20712117',
 174             'ext': 'mp4',
 175             'title': 'YouNow capture',
 176             'view_count': int,
 177             'like_count': int,
 178             'timestamp': 1490432040,
 179             'upload_date': '20170325',
 180             'uploader': 'GABO...',
 181             'uploader_id': '35917228',
 182         },
 183     }
 184
 185     @classmethod
 186     def suitable(cls, url):
 187         return (False
 188                 if YouNowChannelIE.suitable(url)
 189                 else super().suitable(url))
 190
 191     def _real_extract(self, url):
 192         video_id = self._match_id(url)
 193         item = self._download_json(MOMENT_URL_FORMAT % video_id, video_id)
 194         return _extract_moment(item['item'])