yt_dlp/extractor/embedly.py

   1 import re
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5 from .youtube import YoutubeTabIE
   6 from ..utils import parse_qs, smuggle_url, traverse_obj
   7
   8
   9 class EmbedlyIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www|cdn\.)?embedly\.com/widgets/media\.html\?(?:[^#]*?&)?(?:src|url)=(?:[^#&]+)'
  11     _TESTS = [{
  12         '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',
  13         'info_dict': {
  14             'id': 'UUGLim4T2loE5rwCMdpCIPVg',
  15             'modified_date': '20221225',
  16             'view_count': int,
  17             'uploader_url': 'https://www.youtube.com/@TraciHinesMusic',
  18             'channel_id': 'UCGLim4T2loE5rwCMdpCIPVg',
  19             'uploader': 'TraciJHines',
  20             'channel_url': 'https://www.youtube.com/@TraciHinesMusic',
  21             'channel': 'TraciJHines',
  22             'availability': 'public',
  23             'uploader_id': 'UCGLim4T2loE5rwCMdpCIPVg',
  24             'description': '',
  25             'tags': [],
  26             'title': 'Uploads from TraciJHines',
  27         },
  28         'playlist_mincount': 10,
  29     }, {
  30         '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',
  31         'params': {'noplaylist': True},
  32         'info_dict': {
  33             'id': 'SU4fj_aEMVw',
  34             'ext': 'mp4',
  35             'title': 'I\'m on Patreon!',
  36             'age_limit': 0,
  37             'categories': ['Entertainment'],
  38             'thumbnail': 'https://i.ytimg.com/vi_webp/SU4fj_aEMVw/maxresdefault.webp',
  39             'live_status': 'not_live',
  40             'playable_in_embed': True,
  41             'channel': 'TraciJHines',
  42             'uploader_id': 'TraciJHines',
  43             'channel_url': 'https://www.youtube.com/channel/UCGLim4T2loE5rwCMdpCIPVg',
  44             'uploader_url': 'http://www.youtube.com/user/TraciJHines',
  45             'upload_date': '20150211',
  46             'duration': 282,
  47             'availability': 'public',
  48             'channel_follower_count': int,
  49             'tags': 'count:39',
  50             'view_count': int,
  51             'comment_count': int,
  52             'channel_id': 'UCGLim4T2loE5rwCMdpCIPVg',
  53             'like_count': int,
  54             'uploader': 'TraciJHines',
  55             'description': 'md5:8af6425f50bd46fbf29f3db0fc3a8364',
  56             'chapters': list,
  57
  58         },
  59     }, {
  60         'url': 'https://cdn.embedly.com/widgets/media.html?src=https://player.vimeo.com/video/1234567?h=abcdefgh',
  61         'only_matching': True,
  62     }]
  63
  64     @classmethod
  65     def _extract_from_webpage(cls, url, webpage):
  66         # Bypass "ie=cls" and suitable check
  67         for mobj in re.finditer(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage):
  68             yield cls.url_result(mobj.group('url'))
  69
  70         for mobj in re.finditer(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage):
  71             yield cls.url_result(urllib.parse.unquote(mobj.group('url')))
  72
  73     def _real_extract(self, url):
  74         qs = parse_qs(url)
  75         src = urllib.parse.unquote(traverse_obj(qs, ('url', 0)) or '')
  76         if src and YoutubeTabIE.suitable(src):
  77             return self.url_result(src, YoutubeTabIE)
  78         return self.url_result(smuggle_url(
  79             urllib.parse.unquote(traverse_obj(qs, ('src', 0), ('url', 0))),
  80             {'http_headers': {'Referer': url}}))