yt_dlp/extractor/embedly.py

   1 import re
   2 import urllib.parse
   3 from .common import InfoExtractor
   4 from ..compat import compat_urllib_parse_unquote
   5
   6
   7 class EmbedlyIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www|cdn\.)?embedly\.com/widgets/media\.html\?(?:[^#]*?&)?url=(?P<id>[^#&]+)'
   9     _TESTS = [{
  10         'url': 'https://cdn.embedly.com/widgets/media.html?src=http%3A%2F%2Fwww.youtube.com%2Fembed%2Fvideoseries%3Flist%3DUUGLim4T2loE5rwCMdpCIPVg&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DSU4fj_aEMVw%26list%3DUUGLim4T2loE5rwCMdpCIPVg&image=http%3A%2F%2Fi.ytimg.com%2Fvi%2FSU4fj_aEMVw%2Fhqdefault.jpg&key=8ee8a2e6a8cc47aab1a5ee67f9a178e0&type=text%2Fhtml&schema=youtube&autoplay=1',
  11         'only_matching': True,
  12     }]
  13
  14     @classmethod
  15     def _extract_embed_urls(cls, url, webpage):
  16         # Bypass suitable check
  17         for mobj in re.finditer(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage):
  18             yield mobj.group('url')
  19
  20         for mobj in re.finditer(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage):
  21             yield urllib.parse.unquote(mobj.group('url'))
  22
  23     def _real_extract(self, url):
  24         return self.url_result(compat_urllib_parse_unquote(self._match_id(url)))