yt_dlp/extractor/younow.py

   1 import itertools
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     ExtractorError,
   7     format_field,
   8     int_or_none,
   9     try_get,
  10 )
  11
  12 CDN_API_BASE = 'https://cdn.younow.com/php/api'
  13 MOMENT_URL_FORMAT = '%s/moment/fetch/id=%%s' % CDN_API_BASE
  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(YouNowLiveIE, cls).suitable(url))
  41
  42     def _real_extract(self, url):
  43         username = self._match_id(url)
  44
  45         data = self._download_json(
  46             'https://api.younow.com/php/api/broadcast/info/curId=0/user=%s'
  47             % username, username)
  48
  49         if data.get('errorCode') != 0:
  50             raise ExtractorError(data['errorMsg'], expected=True)
  51
  52         uploader = try_get(
  53             data, lambda x: x['user']['profileUrlString'],
  54             compat_str) or username
  55
  56         return {
  57             'id': uploader,
  58             'is_live': True,
  59             'title': uploader,
  60             'thumbnail': data.get('awsUrl'),
  61             'tags': data.get('tags'),
  62             'categories': data.get('tags'),
  63             'uploader': uploader,
  64             'uploader_id': data.get('userId'),
  65             'uploader_url': 'https://www.younow.com/%s' % username,
  66             'creator': uploader,
  67             'view_count': int_or_none(data.get('viewers')),
  68             'like_count': int_or_none(data.get('likes')),
  69             'formats': [{
  70                 'url': '%s/broadcast/videoPath/hls=1/broadcastId=%s/channelId=%s'
  71                        % (CDN_API_BASE, data['broadcastId'], data['userId']),
  72                 'ext': 'mp4',
  73                 'protocol': 'm3u8',
  74             }],
  75         }
  76
  77
  78 def _extract_moment(item, fatal=True):
  79     moment_id = item.get('momentId')
  80     if not moment_id:
  81         if not fatal:
  82             return
  83         raise ExtractorError('Unable to extract moment id')
  84
  85     moment_id = compat_str(moment_id)
  86
  87     title = item.get('text')
  88     if not title:
  89         title = 'YouNow %s' % (
  90             item.get('momentType') or item.get('titleType') or 'moment')
  91
  92     uploader = try_get(item, lambda x: x['owner']['name'], compat_str)
  93     uploader_id = try_get(item, lambda x: x['owner']['userId'])
  94     uploader_url = format_field(uploader, None, 'https://www.younow.com/%s')
  95
  96     entry = {
  97         'extractor_key': 'YouNowMoment',
  98         'id': moment_id,
  99         'title': title,
 100         'view_count': int_or_none(item.get('views')),
 101         'like_count': int_or_none(item.get('likes')),
 102         'timestamp': int_or_none(item.get('created')),
 103         'creator': uploader,
 104         'uploader': uploader,
 105         'uploader_id': uploader_id,
 106         'uploader_url': uploader_url,
 107         'formats': [{
 108             'url': 'https://hls.younow.com/momentsplaylists/live/%s/%s.m3u8'
 109                    % (moment_id, moment_id),
 110             'ext': 'mp4',
 111             'protocol': 'm3u8_native',
 112         }],
 113     }
 114
 115     return entry
 116
 117
 118 class YouNowChannelIE(InfoExtractor):
 119     _VALID_URL = r'https?://(?:www\.)?younow\.com/(?P<id>[^/]+)/channel'
 120     _TEST = {
 121         'url': 'https://www.younow.com/its_Kateee_/channel',
 122         'info_dict': {
 123             'id': '14629760',
 124             'title': 'its_Kateee_ moments'
 125         },
 126         'playlist_mincount': 8,
 127     }
 128
 129     def _entries(self, username, channel_id):
 130         created_before = 0
 131         for page_num in itertools.count(1):
 132             if created_before is None:
 133                 break
 134             info = self._download_json(
 135                 '%s/moment/profile/channelId=%s/createdBefore=%d/records=20'
 136                 % (CDN_API_BASE, channel_id, created_before), username,
 137                 note='Downloading moments page %d' % page_num)
 138             items = info.get('items')
 139             if not items or not isinstance(items, list):
 140                 break
 141             for item in items:
 142                 if not isinstance(item, dict):
 143                     continue
 144                 item_type = item.get('type')
 145                 if item_type == 'moment':
 146                     entry = _extract_moment(item, fatal=False)
 147                     if entry:
 148                         yield entry
 149                 elif item_type == 'collection':
 150                     moments = item.get('momentsIds')
 151                     if isinstance(moments, list):
 152                         for moment_id in moments:
 153                             m = self._download_json(
 154                                 MOMENT_URL_FORMAT % moment_id, username,
 155                                 note='Downloading %s moment JSON' % moment_id,
 156                                 fatal=False)
 157                             if m and isinstance(m, dict) and m.get('item'):
 158                                 entry = _extract_moment(m['item'])
 159                                 if entry:
 160                                     yield entry
 161                 created_before = int_or_none(item.get('created'))
 162
 163     def _real_extract(self, url):
 164         username = self._match_id(url)
 165         channel_id = compat_str(self._download_json(
 166             'https://api.younow.com/php/api/broadcast/info/curId=0/user=%s'
 167             % username, username, note='Downloading user information')['userId'])
 168         return self.playlist_result(
 169             self._entries(username, channel_id), channel_id,
 170             '%s moments' % username)
 171
 172
 173 class YouNowMomentIE(InfoExtractor):
 174     _VALID_URL = r'https?://(?:www\.)?younow\.com/[^/]+/(?P<id>[^/?#&]+)'
 175     _TEST = {
 176         'url': 'https://www.younow.com/GABO.../20712117/36319236/3b316doc/m',
 177         'md5': 'a30c70eadb9fb39a1aa3c8c0d22a0807',
 178         'info_dict': {
 179             'id': '20712117',
 180             'ext': 'mp4',
 181             'title': 'YouNow capture',
 182             'view_count': int,
 183             'like_count': int,
 184             'timestamp': 1490432040,
 185             'upload_date': '20170325',
 186             'uploader': 'GABO...',
 187             'uploader_id': 35917228,
 188         },
 189     }
 190
 191     @classmethod
 192     def suitable(cls, url):
 193         return (False
 194                 if YouNowChannelIE.suitable(url)
 195                 else super(YouNowMomentIE, cls).suitable(url))
 196
 197     def _real_extract(self, url):
 198         video_id = self._match_id(url)
 199         item = self._download_json(MOMENT_URL_FORMAT % video_id, video_id)
 200         return _extract_moment(item['item'])