yt_dlp/extractor/jwplatform.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import unsmuggle_url
   5
   6
   7 class JWPlatformIE(InfoExtractor):
   8     _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
   9     _TESTS = [{
  10         'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
  11         'md5': 'fa8899fa601eb7c83a64e9d568bdf325',
  12         'info_dict': {
  13             'id': 'nPripu9l',
  14             'ext': 'mov',
  15             'title': 'Big Buck Bunny Trailer',
  16             'description': 'Big Buck Bunny is a short animated film by the Blender Institute. It is made using free and open source software.',
  17             'upload_date': '20081127',
  18             'timestamp': 1227796140,
  19         }
  20     }, {
  21         'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js',
  22         'only_matching': True,
  23     }]
  24
  25     @classmethod
  26     def _extract_embed_urls(cls, url, webpage):
  27         for tag, key in ((r'(?:script|iframe)', 'src'), ('input', 'value')):
  28             # <input value=URL> is used by hyland.com
  29             # if we find <iframe>, dont look for <input>
  30             ret = re.findall(
  31                 r'<%s[^>]+?%s=["\']((?:https?:)?//(?:content\.jwplatform|cdn\.jwplayer)\.com/players/[a-zA-Z0-9]{8})' % (tag, key),
  32                 webpage)
  33             if ret:
  34                 return ret
  35         mobj = re.search(r'<div\b[^>]* data-video-jw-id="([a-zA-Z0-9]{8})"', webpage)
  36         if mobj:
  37             return [f'jwplatform:{mobj.group(1)}']
  38
  39     def _real_extract(self, url):
  40         url, smuggled_data = unsmuggle_url(url, {})
  41         self._initialize_geo_bypass({
  42             'countries': smuggled_data.get('geo_countries'),
  43         })
  44         video_id = self._match_id(url)
  45         json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id)
  46         return self._parse_jwplayer_data(json_data, video_id)