yt_dlp/extractor/plays.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class PlaysTVIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?plays\.tv/(?:video|embeds)/(?P<id>[0-9a-f]{18})'
   9     _TESTS = [{
  10         'url': 'https://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall',
  11         'md5': 'dfeac1198506652b5257a62762cec7bc',
  12         'info_dict': {
  13             'id': '56af17f56c95335490',
  14             'ext': 'mp4',
  15             'title': 'Bjergsen - When you outplay the Azir wall',
  16             'description': 'Posted by Bjergsen',
  17         }
  18     }, {
  19         'url': 'https://plays.tv/embeds/56af17f56c95335490',
  20         'only_matching': True,
  21     }]
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(
  26             'https://plays.tv/video/%s' % video_id, video_id)
  27
  28         info = self._search_json_ld(webpage, video_id,)
  29
  30         mpd_url, sources = re.search(
  31             r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>',
  32             webpage).groups()
  33         formats = self._extract_mpd_formats(
  34             self._proto_relative_url(mpd_url), video_id, mpd_id='DASH')
  35         for format_id, height, format_url in re.findall(r'<source\s+res="((\d+)h?)"\s+src="([^"]+)"', sources):
  36             formats.append({
  37                 'url': self._proto_relative_url(format_url),
  38                 'format_id': 'http-' + format_id,
  39                 'height': int_or_none(height),
  40             })
  41
  42         info.update({
  43             'id': video_id,
  44             'description': self._og_search_description(webpage),
  45             'thumbnail': info.get('thumbnail') or self._og_search_thumbnail(webpage),
  46             'formats': formats,
  47         })
  48
  49         return info