_ Git - youtube-dl/blob - youtube_dl/extractor/beampro.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     clean_html,
   8     compat_str,
   9     int_or_none,
  10     parse_iso8601,
  11     try_get,
  12 )
  13
  14
  15 class BeamProLiveIE(InfoExtractor):
  16     IE_NAME = 'Beam:live'
  17     _VALID_URL = r'https?://(?:\w+.)?beam.pro/(?P<id>[^?]+)$'
  18     _API_CHANNEL = 'https://beam.pro/api/v1/channels/{0}'
  19     _API_MANIFEST = 'https://beam.pro/api/v1/channels/{0}/manifest.m3u8'
  20     _RATINGS = {'family': 0, 'teen': 13, '18+': 18}
  21
  22     _TEST = {
  23         'url': 'http://www.beam.pro/niterhayven',
  24         'info_dict': {
  25             'id': '261562',
  26             'ext': 'mp4',
  27             'uploader': 'niterhayven',
  28             'timestamp': 1483477281,
  29             'age_limit': 18,
  30             'title': 'Introducing The Witcher 3 //  The Grind Starts Now!',
  31             'thumbnail': r're:https://.*\.jpg$',
  32             'upload_date': '20170103',
  33             'uploader_id': 373396,
  34             'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
  35             'is_live': True,
  36         },
  37         'skip': 'niterhayven is offline',
  38         'params': {
  39             'skip_download': True,
  40         },
  41     }
  42
  43     def _real_extract(self, url):
  44         channel_id = self._match_id(url)
  45         chan_data = self._download_json(self._API_CHANNEL.format(channel_id), channel_id)
  46
  47         if not chan_data.get('online'):
  48             raise ExtractorError('{0} is offline'.format(channel_id), expected=True)
  49
  50         formats = self._extract_m3u8_formats(
  51             self._API_MANIFEST.format(chan_data.get('id')), channel_id, ext='mp4')
  52
  53         self._sort_formats(formats)
  54         info = {}
  55         info['formats'] = formats
  56         if chan_data:
  57             info.update(self._extract_info(chan_data))
  58         if not info.get('title'):
  59             info['title'] = self._live_title(channel_id)
  60         if not info.get('id'):  # barely possible but just in case
  61             info['id'] = compat_str(abs(hash(channel_id)) % (10 ** 8))
  62
  63         return info
  64
  65     def _extract_info(self, info):
  66         thumbnail = try_get(info, lambda x: x['thumbnail']['url'], compat_str)
  67         username = try_get(info, lambda x: x['user']['url'], compat_str)
  68         video_id = compat_str(info['id']) if info.get('id') else None
  69         rating = info.get('audience')
  70
  71         return {
  72             'id': video_id,
  73             'title': info.get('name'),
  74             'description': clean_html(info.get('description')),
  75             'age_limit': self._RATINGS[rating] if rating in self._RATINGS else None,
  76             'is_live': True if info.get('online') else False,
  77             'timestamp': parse_iso8601(info.get('updatedAt')),
  78             'uploader': info.get('token') or username,
  79             'uploader_id': int_or_none(info.get('userId')),
  80             'view_count': int_or_none(info.get('viewersTotal')),
  81             'thumbnail': thumbnail,
  82         }