From dbf350c12291279c0be56cb82922c2fae1c87eb2 Mon Sep 17 00:00:00 2001
From: Marcel <flashdagger@googlemail.com>
Date: Sun, 27 Nov 2022 16:34:06 +0100
Subject: [PATCH] [parsing] return unclosed matched tags

---
 test/test_parsing.py | 9 +++++----
 yt_dlp/parsing.py    | 4 ++--
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/test/test_parsing.py b/test/test_parsing.py
index 880c41a34..588711518 100644
--- a/test/test_parsing.py
+++ b/test/test_parsing.py
@@ -218,8 +218,9 @@ def test_get_element_text_and_html_by_tag_malformed(self):
             get_element_text_and_html_by_tag('malnested_b', html),
             (f'{inner_text}</malnested_a>',
              f'<malnested_b>{inner_text}</malnested_a></malnested_b>'))
+        self.assertEqual(
+            get_element_text_and_html_by_tag('orphan', f'<orphan>{html}'), ('', '<orphan>'))
         self.assertIsNone(get_element_text_and_html_by_tag('orphan', f'{html}</orphan>'))
-        self.assertIsNone(get_element_text_and_html_by_tag('orphan', f'<orphan>{html}'))
 
     def test_strict_html_parsing(self):
         class StrictTagParser(HTMLTagParser):
@@ -244,13 +245,13 @@ def test_relaxed_html_parsing(self):
         parser = HTMLTagParser()
 
         self.assertEqual(parser.taglist('</p>', reset=True), [])
-        self.assertEqual(parser.taglist('<div><p>', reset=True), [])
+        self.assertEqual(parser.taglist('<div><p>', reset=True), [Tag('div'), Tag('p')])
 
         tags = parser.taglist('<div><p></div></p>', reset=True)
-        self.assertEqual(tags, [Tag('p'), Tag('div')])
+        self.assertEqual(tags, [Tag('div'), Tag('p')])
 
         tags = parser.taglist('<div><p>/p></div>', reset=True)
-        self.assertEqual(tags, [Tag('div')])
+        self.assertEqual(tags, [Tag('div'), Tag('p')])
 
         tags = parser.taglist('<div><p>paragraph</p<ignored></div>', reset=True)
         self.assertEqual(tags, [Tag('div'), Tag('p')])
diff --git a/yt_dlp/parsing.py b/yt_dlp/parsing.py
index 8fbb4db14..5ecd6b75c 100644
--- a/yt_dlp/parsing.py
+++ b/yt_dlp/parsing.py
@@ -190,7 +190,7 @@ def handle_starttag(self, tag, attrs):
             tag_obj = self.Tag(tag, string=self.rawdata, attrs=attrs)
             tag_obj.openrange(self._offset, len(tag_text))
             if tag_is_open:
-                nesting = []
+                nesting = [tag_obj]
                 self._nestedtags[-1].append(nesting)
                 self._nestedtags.append(nesting)
             else:
@@ -218,7 +218,7 @@ def handle_endtag(self, tag):
             if isinstance(tag_obj, self.Tag):
                 close_idx = self.rawdata.find('>', self._offset) + 1
                 tag_obj.closerange(self._offset, close_idx - self._offset)
-                self._nestedtags.pop().insert(0, tag_obj)
+                self._nestedtags.pop()
                 self.callback(tag_obj)
         except ValueError as exc:
             if isinstance(exc, compat_HTMLParseError):