From 4e7f375c949cb152ae953aa834098351f8e5a872 Mon Sep 17 00:00:00 2001
From: Dosychev Peter <dosy4ev@gmail.com>
Date: Mon, 11 Jul 2022 02:18:12 +0300
Subject: [PATCH] [extractor/theholetv] Add extractor (#4325)

Authored by: dosy4ev
---
 yt_dlp/extractor/_extractors.py |  1 +
 yt_dlp/extractor/theholetv.py   | 36 +++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)
 create mode 100644 yt_dlp/extractor/theholetv.py

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index a7a915fa5e..24d066fbe8 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -1718,6 +1718,7 @@ from .tenplay import TenPlayIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .tfo import TFOIE
+from .theholetv import TheHoleTvIE
 from .theintercept import TheInterceptIE
 from .theplatform import (
     ThePlatformIE,
diff --git a/yt_dlp/extractor/theholetv.py b/yt_dlp/extractor/theholetv.py
new file mode 100644
index 0000000000..f0a096d412
--- /dev/null
+++ b/yt_dlp/extractor/theholetv.py
@@ -0,0 +1,36 @@
+from .common import InfoExtractor
+from ..utils import extract_attributes, remove_end
+
+
+class TheHoleTvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?the-hole\.tv/episodes/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://the-hole.tv/episodes/gromkii-vopros-sergey-orlov',
+        'md5': 'fea6682f47786f3ae5a6cbd635ec4bf9',
+        'info_dict': {
+            'id': 'gromkii-vopros-sergey-orlov',
+            'ext': 'mp4',
+            'title': 'Сергей Орлов — Громкий вопрос',
+            'thumbnail': 'https://assets-cdn.the-hole.tv/images/t8gan4n6zn627e7wni11b2uemqts',
+            'description': 'md5:45741a9202331f995d9fb76996759379'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        player_attrs = extract_attributes(self._search_regex(
+            r'(<div[^>]*\bdata-controller="player"[^>]*>)', webpage, 'video player'))
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            player_attrs['data-player-source-value'], video_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': remove_end(self._html_extract_title(webpage), ' — The Hole'),
+            'description': self._og_search_description(webpage),
+            'thumbnail': player_attrs.get('data-player-poster-value'),
+            'formats': formats,
+            'subtitles': subtitles
+        }