diff --git a/llm_web_kit/main_html_parser/simplify_html/simplify_html.py b/llm_web_kit/main_html_parser/simplify_html/simplify_html.py
index 3c37da8e..05b8352e 100644
--- a/llm_web_kit/main_html_parser/simplify_html/simplify_html.py
+++ b/llm_web_kit/main_html_parser/simplify_html/simplify_html.py
@@ -3,6 +3,7 @@
 import uuid
 from typing import Dict, List, Tuple
 
+from bs4 import BeautifulSoup
 from lxml import etree, html
 from selectolax.parser import HTMLParser
 
@@ -858,8 +859,12 @@ def simplify_html(html_str) -> etree.Element:
        _xpath_mapping: xpath映射
    """
     # 使用selectolax的HTMLParser来修复html
-    soup = HTMLParser(html_str)
-    fixed_html = soup.html
+    try:
+        soup = HTMLParser(html_str)
+        fixed_html = soup.html
+    except Exception:
+        soup = BeautifulSoup(html_str, 'html.parser')
+        fixed_html = str(soup)
 
     preprocessed_html = remove_xml_declaration(fixed_html)
     # 注释通过lxml的HTMLParser的remove_comments参数处理
diff --git a/tests/llm_web_kit/main_html_parser/parser/assets/test_html_data/simplify_cases/unusual_encoding.html b/tests/llm_web_kit/main_html_parser/parser/assets/test_html_data/simplify_cases/unusual_encoding.html
new file mode 100644
index 00000000..969074b3
Binary files /dev/null and b/tests/llm_web_kit/main_html_parser/parser/assets/test_html_data/simplify_cases/unusual_encoding.html differ
diff --git a/tests/llm_web_kit/main_html_parser/parser/test_tag_simplifier.py b/tests/llm_web_kit/main_html_parser/parser/test_tag_simplifier.py
index 45962b1e..e28cc0ce 100644
--- a/tests/llm_web_kit/main_html_parser/parser/test_tag_simplifier.py
+++ b/tests/llm_web_kit/main_html_parser/parser/test_tag_simplifier.py
@@ -472,6 +472,24 @@ def test_tag_simplifier_block_select(self):
         self.assertIsNotNone(p_element.get("_item_id"))
         self.assertIsNotNone(p_element.get("cc-select"))
 
+    def test_tag_simplifier_unusual_encoding(self):
+        file_path = base_dir / 'assets/test_html_data/simplify_cases/unusual_encoding.html'
+        with open(file_path, 'r') as file:
+            raw_html = file.read()
+
+        data_dict = {PreDataJsonKey.TYPICAL_RAW_HTML: raw_html}
+        pre_data = PreDataJson(data_dict)
+
+        pre_data_result = HtmlTagSimplifierParser({}).parse(pre_data)
+
+        simplifier_raw_html = pre_data_result.get(PreDataJsonKey.TYPICAL_SIMPLIFIED_HTML, '')
+        simple_id_count = self.check_and_find_max_item_id(simplifier_raw_html)
+        self.assertEqual(simple_id_count, 102)
+
+        raw_tag_html = pre_data_result.get(PreDataJsonKey.TYPICAL_RAW_TAG_HTML, '')
+        tag_id_count = self.check_and_find_max_item_id(raw_tag_html)
+        self.assertEqual(tag_id_count, simple_id_count)
+
 
 if __name__ == '__main__':
     unittest.main()