yt_dlp/extractor/tvplayer.py

   1 from .common import InfoExtractor
   2 from ..networking.exceptions import HTTPError
   3 from ..utils import (
   4     ExtractorError,
   5     extract_attributes,
   6     try_get,
   7     urlencode_postdata,
   8 )
   9
  10
  11 class TVPlayerIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?tvplayer\.com/watch/(?P<id>[^/?#]+)'
  13     _TEST = {
  14         'url': 'http://tvplayer.com/watch/bbcone',
  15         'info_dict': {
  16             'id': '89',
  17             'ext': 'mp4',
  18             'title': r're:^BBC One [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  19         },
  20         'params': {
  21             # m3u8 download
  22             'skip_download': True,
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         display_id = self._match_id(url)
  28         webpage = self._download_webpage(url, display_id)
  29
  30         current_channel = extract_attributes(self._search_regex(
  31             r'(<div[^>]+class="[^"]*current-channel[^"]*"[^>]*>)',
  32             webpage, 'channel element'))
  33         title = current_channel['data-name']
  34
  35         resource_id = current_channel['data-id']
  36
  37         token = self._search_regex(
  38             r'data-token=(["\'])(?P<token>(?!\1).+)\1', webpage,
  39             'token', group='token')
  40
  41         context = self._download_json(
  42             'https://tvplayer.com/watch/context', display_id,
  43             'Downloading JSON context', query={
  44                 'resource': resource_id,
  45                 'gen': token,
  46             })
  47
  48         validate = context['validate']
  49         platform = try_get(
  50             context, lambda x: x['platform']['key'], str) or 'firefox'
  51
  52         try:
  53             response = self._download_json(
  54                 'http://api.tvplayer.com/api/v2/stream/live',
  55                 display_id, 'Downloading JSON stream', headers={
  56                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
  57                 }, data=urlencode_postdata({
  58                     'id': resource_id,
  59                     'service': 1,
  60                     'platform': platform,
  61                     'validate': validate,
  62                 }))['tvplayer']['response']
  63         except ExtractorError as e:
  64             if isinstance(e.cause, HTTPError):
  65                 response = self._parse_json(
  66                     e.cause.response.read().decode(), resource_id)['tvplayer']['response']
  67                 raise ExtractorError(
  68                     '{} said: {}'.format(self.IE_NAME, response['error']), expected=True)
  69             raise
  70
  71         formats = self._extract_m3u8_formats(response['stream'], display_id, 'mp4')
  72
  73         return {
  74             'id': resource_id,
  75             'display_id': display_id,
  76             'title': title,
  77             'formats': formats,
  78             'is_live': True,
  79         }