From 3a84be9d1660ef798ea28f929a20391bef6afda4 Mon Sep 17 00:00:00 2001
From: Nikolay Fedorov <40500428+swayll@users.noreply.github.com>
Date: Mon, 14 Jul 2025 22:01:53 +0300
Subject: [PATCH] [ie/TheHighWire] Add extractor (#13505)

Closes #13364
Authored by: swayll
---
 yt_dlp/extractor/_extractors.py |  1 +
 yt_dlp/extractor/thehighwire.py | 43 +++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)
 create mode 100644 yt_dlp/extractor/thehighwire.py

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index 0a00db437e..c9172fef78 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -2092,6 +2092,7 @@ from .theguardian import (
     TheGuardianPodcastIE,
     TheGuardianPodcastPlaylistIE,
 )
+from .thehighwire import TheHighWireIE
 from .theholetv import TheHoleTvIE
 from .theintercept import TheInterceptIE
 from .theplatform import (
diff --git a/yt_dlp/extractor/thehighwire.py b/yt_dlp/extractor/thehighwire.py
new file mode 100644
index 0000000000..8b596143f7
--- /dev/null
+++ b/yt_dlp/extractor/thehighwire.py
@@ -0,0 +1,43 @@
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    url_or_none,
+)
+from ..utils.traversal import (
+    find_element,
+    require,
+    traverse_obj,
+)
+
+
+class TheHighWireIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?thehighwire\.com/ark-videos/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://thehighwire.com/ark-videos/the-deposition-of-stanley-plotkin/',
+        'info_dict': {
+            'id': 'the-deposition-of-stanley-plotkin',
+            'ext': 'mp4',
+            'title': 'THE DEPOSITION OF STANLEY PLOTKIN',
+            'description': 'md5:6d0be4f1181daaa10430fd8b945a5e54',
+            'thumbnail': r're:https?://static\.arkengine\.com/video/.+\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        embed_url = traverse_obj(webpage, (
+            {find_element(cls='ark-video-embed', html=True)},
+            {extract_attributes}, 'src', {url_or_none}, {require('embed URL')}))
+        embed_page = self._download_webpage(embed_url, display_id)
+
+        return {
+            'id': display_id,
+            **traverse_obj(webpage, {
+                'title': ({find_element(cls='section-header')}, {clean_html}),
+                'description': ({find_element(cls='episode-description__copy')}, {clean_html}),
+            }),
+            **self._parse_html5_media_entries(embed_url, embed_page, display_id, m3u8_id='hls')[0],
+        }