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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import ExtractorError, js_to_json, urlencode_postdata
   6
   7
   8 class PicartoIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)[^/]*$'
  10     _TEST = {
  11         'url': 'https://picarto.tv/Setz',
  12         'info_dict': {
  13             'id': 'Setz',
  14             'ext': 'mp4',
  15             'title': 're:^Setz [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  16             'timestamp': int,
  17             'is_live': True
  18         },
  19         'params': {
  20             'skip_download': True
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         channel_id = self._match_id(url)
  26         stream_page = self._download_webpage(url, channel_id)
  27
  28         if 'This channel does not exist.' in stream_page:
  29             raise ExtractorError('Channel does not exist', expected=True)
  30
  31         player_settings_js = self._html_search_regex(
  32             r'(?s)playerSettings\[1\]\s*=\s*(\{.+?\}\n)', stream_page, 'player-settings')
  33         player_settings = self._parse_json(player_settings_js, channel_id,
  34             transform_source=js_to_json)
  35         if not player_settings.get('online'):
  36             raise ExtractorError('Stream is offline', expected=True)
  37
  38         cdn_data = self._download_json('https://picarto.tv/process/channel', channel_id,
  39             data=urlencode_postdata({'loadbalancinginfo': channel_id}),
  40             note='Fetching load balancer info')
  41         edge = [edge['ep'] for edge in cdn_data['edges'] if edge['id'] == cdn_data['preferedEdge']][0]
  42
  43         formats = self._extract_m3u8_formats('https://%s/hls/%s/index.m3u8' % (edge, channel_id),
  44             channel_id, 'mp4')
  45         formats.append({'url': 'https://%s/mp4/%s.mp4' % (edge, channel_id)})
  46         self._sort_formats(formats)
  47
  48         return {
  49             'id': channel_id,
  50             'formats': formats,
  51             'ext': 'mp4',
  52             'title': self._live_title(channel_id),
  53             'is_live': True,
  54             'thumbnail': player_settings.get('vodThumb'),
  55             'age_limit': 18 if player_settings.get('mature') else None,
  56         }
  57
  58
  59 class PicartoVodIE(InfoExtractor):
  60     _VALID_URL = r'https?://(?:www.)?picarto\.tv/videopopout/(?P<id>[a-zA-Z0-9_\-\.]+).flv'
  61     _TEST = {
  62         'url': 'https://picarto.tv/videopopout/Carrot_2018.01.11.07.55.12.flv',
  63         'md5': '80765b67813053ff31d4df2bd5e900ce',
  64         'info_dict': {
  65             'id': 'Carrot_2018.01.11.07.55.12',
  66             'ext': 'mp4',
  67             'title': 'Carrot_2018.01.11.07.55.12',
  68             'thumbnail': r're:^https?://.*\.jpg$'
  69         }
  70     }
  71
  72     def _real_extract(self, url):
  73         video_id = self._match_id(url)
  74         webpage = self._download_webpage(url, video_id)
  75
  76         vod_info_js = self._html_search_regex(r'(?s)"#vod-player",\s*(\{.+?\})\)',
  77             webpage, video_id)
  78         vod_info = self._parse_json(vod_info_js, video_id, transform_source=js_to_json)
  79
  80         return {
  81             'id': video_id,
  82             'title': video_id,
  83             'ext': 'mp4',
  84             'protocol': 'm3u8',
  85             'url': vod_info['vod'],
  86             'thumbnail': vod_info.get('vodThumb'),
  87         }