From c70b57c03e0c25767a5166620798297a2a4878fb Mon Sep 17 00:00:00 2001
From: sepro <sepro@sepr0.com>
Date: Sat, 6 Dec 2025 22:24:03 +0100
Subject: [PATCH] [ie/Alibaba] Add extractor (#15253)

Closes #13774
Authored by: seproDev
---
 yt_dlp/extractor/_extractors.py |  1 +
 yt_dlp/extractor/alibaba.py     | 42 +++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)
 create mode 100644 yt_dlp/extractor/alibaba.py

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index 5a71096c96..9129b5e68f 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -84,6 +84,7 @@ from .agora import (
 )
 from .airtv import AirTVIE
 from .aitube import AitubeKZVideoIE
+from .alibaba import AlibabaIE
 from .aliexpress import AliExpressLiveIE
 from .aljazeera import AlJazeeraIE
 from .allocine import AllocineIE
diff --git a/yt_dlp/extractor/alibaba.py b/yt_dlp/extractor/alibaba.py
new file mode 100644
index 0000000000..0912535266
--- /dev/null
+++ b/yt_dlp/extractor/alibaba.py
@@ -0,0 +1,42 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, str_or_none, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class AlibabaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?alibaba\.com/product-detail/[\w-]+_(?P<id>\d+)\.html'
+    _TESTS = [{
+        'url': 'https://www.alibaba.com/product-detail/Kids-Entertainment-Bouncer-Bouncy-Castle-Waterslide_1601271126969.html',
+        'info_dict': {
+            'id': '6000280444270',
+            'display_id': '1601271126969',
+            'ext': 'mp4',
+            'title': 'Kids Entertainment Bouncer Bouncy Castle Waterslide Juex Gonflables Commercial Inflatable Tropical Water Slide',
+            'duration': 30,
+            'thumbnail': 'https://sc04.alicdn.com/kf/Hc5bb391974454af18c7a4f91cbe4062bg.jpg_120x120.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        product_data = self._search_json(
+            r'window\.detailData\s*=', webpage, 'detail data', display_id)['globalData']['product']
+
+        return {
+            **traverse_obj(product_data, ('mediaItems', lambda _, v: v['type'] == 'video' and v['videoId'], any, {
+                'id': ('videoId', {int}, {str_or_none}),
+                'duration': ('duration', {int_or_none}),
+                'thumbnail': ('videoCoverUrl', {url_or_none}),
+                'formats': ('videoUrl', lambda _, v: url_or_none(v['videoUrl']), {
+                    'url': 'videoUrl',
+                    'format_id': ('definition', {str_or_none}),
+                    'tbr': ('bitrate', {int_or_none}),
+                    'width': ('width', {int_or_none}),
+                    'height': ('height', {int_or_none}),
+                    'filesize': ('length', {int_or_none}),
+                }),
+            })),
+            'title': traverse_obj(product_data, ('subject', {str})),
+            'display_id': display_id,
+        }