yt_dlp/extractor/elementorembed.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from .vimeo import VimeoIE
   5 from .youtube import YoutubeIE
   6 from ..utils import unescapeHTML, url_or_none
   7 from ..utils.traversal import traverse_obj
   8
   9
  10 class ElementorEmbedIE(InfoExtractor):
  11     _VALID_URL = False
  12     _WEBPAGE_TESTS = [{
  13         'url': 'https://capitaltv.cy/2023/12/14/υγεια-και-ζωη-14-12-2023-δρ-ξενια-κωσταντινιδο/',
  14         'info_dict': {
  15             'id': 'KgzuxwuQwM4',
  16             'ext': 'mp4',
  17             'title': 'ΥΓΕΙΑ ΚΑΙ ΖΩΗ 14 12 2023 ΔΡ  ΞΕΝΙΑ ΚΩΣΤΑΝΤΙΝΙΔΟΥ',
  18             'thumbnail': 'https://i.ytimg.com/vi/KgzuxwuQwM4/maxresdefault.jpg',
  19             'playable_in_embed': True,
  20             'tags': 'count:16',
  21             'like_count': int,
  22             'channel': 'Capital TV Cyprus',
  23             'channel_id': 'UCR8LwVKTLGEXt4ZAErpCMrg',
  24             'availability': 'public',
  25             'description': 'md5:7a3308a22881aea4612358c4ba121f77',
  26             'duration': 2891,
  27             'upload_date': '20231214',
  28             'uploader_id': '@capitaltvcyprus6389',
  29             'live_status': 'not_live',
  30             'channel_url': 'https://www.youtube.com/channel/UCR8LwVKTLGEXt4ZAErpCMrg',
  31             'uploader_url': 'https://www.youtube.com/@capitaltvcyprus6389',
  32             'uploader': 'Capital TV Cyprus',
  33             'age_limit': 0,
  34             'categories': ['News & Politics'],
  35             'view_count': int,
  36             'channel_follower_count': int,
  37         },
  38     }, {
  39         'url': 'https://elementor.com/academy/theme-builder-collection/?playlist=76011151&video=9e59909',
  40         'info_dict': {
  41             'id': '?playlist=76011151&video=9e59909',
  42             'title': 'Theme Builder Collection - Academy',
  43             'age_limit': 0,
  44             'timestamp': 1702196984.0,
  45             'upload_date': '20231210',
  46             'description': 'md5:7f52c52715ee9e54fd7f82210511673d',
  47             'thumbnail': 'https://elementor.com/academy/wp-content/uploads/2021/07/Theme-Builder-1.png',
  48         },
  49         'playlist_count': 11,
  50         'params': {
  51             'skip_download': True,
  52         },
  53     }]
  54     _WIDGET_REGEX = r'<div[^>]+class="[^"]*elementor-widget-video(?:-playlist)?[^"]*"[^>]*data-settings="([^"]*)"'
  55
  56     def _extract_from_webpage(self, url, webpage):
  57         for data_settings in re.findall(self._WIDGET_REGEX, webpage):
  58             data = self._parse_json(data_settings, None, fatal=False, transform_source=unescapeHTML)
  59             if youtube_url := traverse_obj(data, ('youtube_url', {url_or_none})):
  60                 yield self.url_result(youtube_url, ie=YoutubeIE)
  61
  62             for video in traverse_obj(data, ('tabs', lambda _, v: v['_id'], {dict})):
  63                 if youtube_url := traverse_obj(video, ('youtube_url', {url_or_none})):
  64                     yield self.url_result(youtube_url, ie=YoutubeIE)
  65                 if vimeo_url := traverse_obj(video, ('vimeo_url', {url_or_none})):
  66                     yield self.url_result(vimeo_url, ie=VimeoIE)
  67                 for direct_url in traverse_obj(video, (('hosted_url', 'external_url'), 'url', {url_or_none})):
  68                     yield {
  69                         'id': video['_id'],
  70                         'url': direct_url,
  71                         'title': video.get('title'),
  72                     }