yt_dlp/extractor/tvplayer.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_HTTPError,
   4     compat_str,
   5 )
   6 from ..utils import (
   7     extract_attributes,
   8     try_get,
   9     urlencode_postdata,
  10     ExtractorError,
  11 )
  12
  13
  14 class TVPlayerIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?tvplayer\.com/watch/(?P<id>[^/?#]+)'
  16     _TEST = {
  17         'url': 'http://tvplayer.com/watch/bbcone',
  18         'info_dict': {
  19             'id': '89',
  20             'ext': 'mp4',
  21             'title': r're:^BBC One [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  22         },
  23         'params': {
  24             # m3u8 download
  25             'skip_download': True,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         display_id = self._match_id(url)
  31         webpage = self._download_webpage(url, display_id)
  32
  33         current_channel = extract_attributes(self._search_regex(
  34             r'(<div[^>]+class="[^"]*current-channel[^"]*"[^>]*>)',
  35             webpage, 'channel element'))
  36         title = current_channel['data-name']
  37
  38         resource_id = current_channel['data-id']
  39
  40         token = self._search_regex(
  41             r'data-token=(["\'])(?P<token>(?!\1).+)\1', webpage,
  42             'token', group='token')
  43
  44         context = self._download_json(
  45             'https://tvplayer.com/watch/context', display_id,
  46             'Downloading JSON context', query={
  47                 'resource': resource_id,
  48                 'gen': token,
  49             })
  50
  51         validate = context['validate']
  52         platform = try_get(
  53             context, lambda x: x['platform']['key'], compat_str) or 'firefox'
  54
  55         try:
  56             response = self._download_json(
  57                 'http://api.tvplayer.com/api/v2/stream/live',
  58                 display_id, 'Downloading JSON stream', headers={
  59                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
  60                 }, data=urlencode_postdata({
  61                     'id': resource_id,
  62                     'service': 1,
  63                     'platform': platform,
  64                     'validate': validate,
  65                 }))['tvplayer']['response']
  66         except ExtractorError as e:
  67             if isinstance(e.cause, compat_HTTPError):
  68                 response = self._parse_json(
  69                     e.cause.read().decode(), resource_id)['tvplayer']['response']
  70                 raise ExtractorError(
  71                     '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
  72             raise
  73
  74         formats = self._extract_m3u8_formats(response['stream'], display_id, 'mp4')
  75
  76         return {
  77             'id': resource_id,
  78             'display_id': display_id,
  79             'title': title,
  80             'formats': formats,
  81             'is_live': True,
  82         }