From 65f91148fc6fcbce967d775527edb95b567db0cb Mon Sep 17 00:00:00 2001
From: Marcel <flashdagger@googlemail.com>
Date: Tue, 29 Nov 2022 15:01:18 +0100
Subject: [PATCH] [parsing] search for case-insensitive tag names

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

diff --git a/test/test_parsing.py b/test/test_parsing.py
index 1898ee8ab..8a36beda4 100644
--- a/test/test_parsing.py
+++ b/test/test_parsing.py
@@ -222,6 +222,10 @@ def test_get_element_text_and_html_by_tag_malformed(self):
             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>'))
 
+        # ignore case on tags
+        ci_html = f'<SpAn>{html}</sPaN>'
+        self.assertEqual(get_element_text_and_html_by_tag('span', ci_html), (html, ci_html))
+
     def test_strict_html_parsing(self):
         class StrictTagParser(HTMLTagParser):
             STRICT = True
diff --git a/yt_dlp/parsing.py b/yt_dlp/parsing.py
index 1698591e3..1db6704dd 100644
--- a/yt_dlp/parsing.py
+++ b/yt_dlp/parsing.py
@@ -245,7 +245,7 @@ def matching_tag_regex(tag, attribute, value_regex, escape=True):
             value_regex = re.escape(value_regex)
 
         return rf'''(?x)
-            <(?:{tag})
+            <(?i:{tag})
              (?:\s(?:[^>"'\\]|"[^"\\]*"|'[^'\\]*')*)?
              \s{re.escape(attribute)}\s*=\s*(?P<_q>['"])(?-x:{value_regex})(?P=_q)
             '''
@@ -263,7 +263,7 @@ def tags_by_name(cls, tag, html):
         def matchfunc(tag_str, _attrs):
             return tag_str == tag
 
-        tag_regex = rf'''<\s*{re.escape(tag)}(?:\s(?:[^>"'\\]|"[^"\\]*"|'[^'\\]*')*)?>'''
+        tag_regex = rf'''<\s*(?i:{re.escape(tag)})(?:\s(?:[^>"'\\]|"[^"\\]*"|'[^'\\]*')*)?>'''
         yield from cls.iter_tags(tag_regex, html, matchfunc=matchfunc)
 
     @classmethod