_ 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     float_or_none,
  10     int_or_none,
  11     parse_iso8601,
  12     try_get,
  13     urljoin,
  14 )
  15
  16
  17 class BeamProBaseIE(InfoExtractor):
  18     _RATINGS = {'family': 0, 'teen': 13, '18+': 18}
  19
  20     def _extract_channel_info(self, chan):
  21         user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
  22         return {
  23             'uploader': chan.get('token') or try_get(
  24                 chan, lambda x: x['user']['username'], compat_str),
  25             'uploader_id': compat_str(user_id) if user_id else None,
  26             'age_limit': self._RATINGS.get(chan.get('audience')),
  27         }
  28
  29
  30 class BeamProLiveIE(BeamProBaseIE):
  31     IE_NAME = 'Beam:live'
  32     _VALID_URL = r'https?://(?:\w+\.)?beam\.pro/(?P<id>[^/?#&]+)'
  33     _TEST = {
  34         'url': 'http://www.beam.pro/niterhayven',
  35         'info_dict': {
  36             'id': '261562',
  37             'ext': 'mp4',
  38             'title': 'Introducing The Witcher 3 //  The Grind Starts Now!',
  39             'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
  40             'thumbnail': r're:https://.*\.jpg$',
  41             'timestamp': 1483477281,
  42             'upload_date': '20170103',
  43             'uploader': 'niterhayven',
  44             'uploader_id': '373396',
  45             'age_limit': 18,
  46             'is_live': True,
  47             'view_count': int,
  48         },
  49         'skip': 'niterhayven is offline',
  50         'params': {
  51             'skip_download': True,
  52         },
  53     }
  54
  55     @classmethod
  56     def suitable(cls, url):
  57         return False if BeamProVodIE.suitable(url) else super(BeamProLiveIE, cls).suitable(url)
  58
  59     def _real_extract(self, url):
  60         channel_name = self._match_id(url)
  61
  62         chan = self._download_json(
  63             'https://beam.pro/api/v1/channels/%s' % channel_name, channel_name)
  64
  65         if chan.get('online') is False:
  66             raise ExtractorError(
  67                 '{0} is offline'.format(channel_name), expected=True)
  68
  69         channel_id = chan['id']
  70
  71         formats = self._extract_m3u8_formats(
  72             'https://beam.pro/api/v1/channels/%s/manifest.m3u8' % channel_id,
  73             channel_name, ext='mp4', m3u8_id='hls', fatal=False)
  74         self._sort_formats(formats)
  75
  76         info = {
  77             'id': compat_str(chan.get('id') or channel_name),
  78             'title': self._live_title(chan.get('name') or channel_name),
  79             'description': clean_html(chan.get('description')),
  80             'thumbnail': try_get(chan, lambda x: x['thumbnail']['url'], compat_str),
  81             'timestamp': parse_iso8601(chan.get('updatedAt')),
  82             'is_live': True,
  83             'view_count': int_or_none(chan.get('viewersTotal')),
  84             'formats': formats,
  85         }
  86         info.update(self._extract_channel_info(chan))
  87
  88         return info
  89
  90
  91 class BeamProVodIE(BeamProBaseIE):
  92     IE_NAME = 'Beam:vod'
  93     _VALID_URL = r'https?://(?:\w+\.)?beam\.pro/[^/?#&]+.*[?&]vod=(?P<id>\d+)'
  94     _TEST = {
  95         'url': 'https://beam.pro/willow8714?vod=2259830',
  96         'md5': 'b2431e6e8347dc92ebafb565d368b76b',
  97         'info_dict': {
  98             'id': '2259830',
  99             'ext': 'mp4',
 100             'title': 'willow8714\'s Channel',
 101             'duration': 6828.15,
 102             'thumbnail': r're:https://.*source\.png$',
 103             'timestamp': 1494046474,
 104             'upload_date': '20170506',
 105             'uploader': 'willow8714',
 106             'uploader_id': '6085379',
 107             'age_limit': 13,
 108             'view_count': int,
 109         },
 110     }
 111
 112     def _extract_format(self, vod, vod_type):
 113         if not vod.get('baseUrl'):
 114             return []
 115
 116         if vod_type == 'hls':
 117             filename, protocol = 'manifest.m3u8', 'm3u8'
 118         elif vod_type == 'raw':
 119             filename, protocol = 'source.mp4', 'https'
 120         else:
 121             return []
 122
 123         data = vod.get('data') or {}
 124
 125         format_id = [vod_type]
 126         if 'Height' in data:
 127             format_id.append('%sp' % data['Height'])
 128
 129         return [{
 130             'url': urljoin(vod['baseUrl'], filename),
 131             'format_id': '-'.join(format_id),
 132             'ext': 'mp4',
 133             'protocol': protocol,
 134             'width': int_or_none(data.get('Width')),
 135             'height': int_or_none(data.get('Height')),
 136             'fps': int_or_none(data.get('Fps')),
 137             'tbr': int_or_none(data.get('Bitrate'), 1000),
 138         }]
 139
 140     def _real_extract(self, url):
 141         vod_id = self._match_id(url)
 142
 143         vod_info = self._download_json(
 144             'https://beam.pro/api/v1/recordings/%s' % vod_id, vod_id)
 145
 146         state = vod_info.get('state')
 147         if state != 'AVAILABLE':
 148             raise ExtractorError(
 149                 'VOD %s is not available (state: %s)' % (vod_id, state), expected=True)
 150
 151         formats = []
 152         thumbnail_url = None
 153
 154         for vod in vod_info['vods']:
 155             vod_type = vod.get('format')
 156             if vod_type in ('hls', 'raw'):
 157                 formats.extend(self._extract_format(vod, vod_type))
 158             elif vod_type == 'thumbnail':
 159                 thumbnail_url = urljoin(vod.get('baseUrl'), 'source.png')
 160
 161         self._sort_formats(formats)
 162
 163         info = {
 164             'id': vod_id,
 165             'title': vod_info.get('name') or vod_id,
 166             'duration': float_or_none(vod_info.get('duration')),
 167             'thumbnail': thumbnail_url,
 168             'timestamp': parse_iso8601(vod_info.get('createdAt')),
 169             'view_count': int_or_none(vod_info.get('viewsTotal')),
 170             'formats': formats,
 171         }
 172
 173         chan = vod_info.get('channel') or {}
 174         info.update(self._extract_channel_info(chan))
 175
 176         return info