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     str_or_none,
  10     try_get,
  11 )
  12
  13 CDN_API_BASE = 'https://cdn.younow.com/php/api'
  14 MOMENT_URL_FORMAT = '%s/moment/fetch/id=%%s' % CDN_API_BASE
  15
  16
  17 class YouNowLiveIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?younow\.com/(?P<id>[^/?#&]+)'
  19     _TEST = {
  20         'url': 'https://www.younow.com/AmandaPadeezy',
  21         'info_dict': {
  22             'id': 'AmandaPadeezy',
  23             'ext': 'mp4',
  24             'is_live': True,
  25             'title': 'March 26, 2017',
  26             'thumbnail': r're:^https?://.*\.jpg$',
  27             'tags': ['girls'],
  28             'categories': ['girls'],
  29             'uploader': 'AmandaPadeezy',
  30             'uploader_id': '6716501',
  31             'uploader_url': 'https://www.younow.com/AmandaPadeezy',
  32             'creator': 'AmandaPadeezy',
  33         },
  34         'skip': True,
  35     }
  36
  37     @classmethod
  38     def suitable(cls, url):
  39         return (False
  40                 if YouNowChannelIE.suitable(url) or YouNowMomentIE.suitable(url)
  41                 else super(YouNowLiveIE, cls).suitable(url))
  42
  43     def _real_extract(self, url):
  44         username = self._match_id(url)
  45
  46         data = self._download_json(
  47             'https://api.younow.com/php/api/broadcast/info/curId=0/user=%s'
  48             % username, username)
  49
  50         if data.get('errorCode') != 0:
  51             raise ExtractorError(data['errorMsg'], expected=True)
  52
  53         uploader = try_get(
  54             data, lambda x: x['user']['profileUrlString'],
  55             compat_str) or username
  56
  57         return {
  58             'id': uploader,
  59             'is_live': True,
  60             'title': uploader,
  61             'thumbnail': data.get('awsUrl'),
  62             'tags': data.get('tags'),
  63             'categories': data.get('tags'),
  64             'uploader': uploader,
  65             'uploader_id': data.get('userId'),
  66             'uploader_url': 'https://www.younow.com/%s' % username,
  67             'creator': uploader,
  68             'view_count': int_or_none(data.get('viewers')),
  69             'like_count': int_or_none(data.get('likes')),
  70             'formats': [{
  71                 'url': '%s/broadcast/videoPath/hls=1/broadcastId=%s/channelId=%s'
  72                        % (CDN_API_BASE, data['broadcastId'], data['userId']),
  73                 'ext': 'mp4',
  74                 'protocol': 'm3u8',
  75             }],
  76         }
  77
  78
  79 def _extract_moment(item, fatal=True):
  80     moment_id = item.get('momentId')
  81     if not moment_id:
  82         if not fatal:
  83             return
  84         raise ExtractorError('Unable to extract moment id')
  85
  86     moment_id = compat_str(moment_id)
  87
  88     title = item.get('text')
  89     if not title:
  90         title = 'YouNow %s' % (
  91             item.get('momentType') or item.get('titleType') or 'moment')
  92
  93     uploader = try_get(item, lambda x: x['owner']['name'], compat_str)
  94     uploader_id = try_get(item, lambda x: x['owner']['userId'])
  95     uploader_url = format_field(uploader, None, 'https://www.younow.com/%s')
  96
  97     entry = {
  98         'extractor_key': 'YouNowMoment',
  99         'id': moment_id,
 100         'title': title,
 101         'view_count': int_or_none(item.get('views')),
 102         'like_count': int_or_none(item.get('likes')),
 103         'timestamp': int_or_none(item.get('created')),
 104         'creator': uploader,
 105         'uploader': uploader,
 106         'uploader_id': str_or_none(uploader_id),
 107         'uploader_url': uploader_url,
 108         'formats': [{
 109             'url': 'https://hls.younow.com/momentsplaylists/live/%s/%s.m3u8'
 110                    % (moment_id, moment_id),
 111             'ext': 'mp4',
 112             'protocol': 'm3u8_native',
 113         }],
 114     }
 115
 116     return entry
 117
 118
 119 class YouNowChannelIE(InfoExtractor):
 120     _VALID_URL = r'https?://(?:www\.)?younow\.com/(?P<id>[^/]+)/channel'
 121     _TEST = {
 122         'url': 'https://www.younow.com/its_Kateee_/channel',
 123         'info_dict': {
 124             'id': '14629760',
 125             'title': 'its_Kateee_ moments'
 126         },
 127         'playlist_mincount': 8,
 128     }
 129
 130     def _entries(self, username, channel_id):
 131         created_before = 0
 132         for page_num in itertools.count(1):
 133             if created_before is None:
 134                 break
 135             info = self._download_json(
 136                 '%s/moment/profile/channelId=%s/createdBefore=%d/records=20'
 137                 % (CDN_API_BASE, channel_id, created_before), username,
 138                 note='Downloading moments page %d' % page_num)
 139             items = info.get('items')
 140             if not items or not isinstance(items, list):
 141                 break
 142             for item in items:
 143                 if not isinstance(item, dict):
 144                     continue
 145                 item_type = item.get('type')
 146                 if item_type == 'moment':
 147                     entry = _extract_moment(item, fatal=False)
 148                     if entry:
 149                         yield entry
 150                 elif item_type == 'collection':
 151                     moments = item.get('momentsIds')
 152                     if isinstance(moments, list):
 153                         for moment_id in moments:
 154                             m = self._download_json(
 155                                 MOMENT_URL_FORMAT % moment_id, username,
 156                                 note='Downloading %s moment JSON' % moment_id,
 157                                 fatal=False)
 158                             if m and isinstance(m, dict) and m.get('item'):
 159                                 entry = _extract_moment(m['item'])
 160                                 if entry:
 161                                     yield entry
 162                 created_before = int_or_none(item.get('created'))
 163
 164     def _real_extract(self, url):
 165         username = self._match_id(url)
 166         channel_id = compat_str(self._download_json(
 167             'https://api.younow.com/php/api/broadcast/info/curId=0/user=%s'
 168             % username, username, note='Downloading user information')['userId'])
 169         return self.playlist_result(
 170             self._entries(username, channel_id), channel_id,
 171             '%s moments' % username)
 172
 173
 174 class YouNowMomentIE(InfoExtractor):
 175     _VALID_URL = r'https?://(?:www\.)?younow\.com/[^/]+/(?P<id>[^/?#&]+)'
 176     _TEST = {
 177         'url': 'https://www.younow.com/GABO.../20712117/36319236/3b316doc/m',
 178         'md5': 'a30c70eadb9fb39a1aa3c8c0d22a0807',
 179         'info_dict': {
 180             'id': '20712117',
 181             'ext': 'mp4',
 182             'title': 'YouNow capture',
 183             'view_count': int,
 184             'like_count': int,
 185             'timestamp': 1490432040,
 186             'upload_date': '20170325',
 187             'uploader': 'GABO...',
 188             'uploader_id': '35917228',
 189         },
 190     }
 191
 192     @classmethod
 193     def suitable(cls, url):
 194         return (False
 195                 if YouNowChannelIE.suitable(url)
 196                 else super(YouNowMomentIE, cls).suitable(url))
 197
 198     def _real_extract(self, url):
 199         video_id = self._match_id(url)
 200         item = self._download_json(MOMENT_URL_FORMAT % video_id, video_id)
 201         return _extract_moment(item['item'])