From dba0e4773a8704ec9598ef785e6061b09bc29db2 Mon Sep 17 00:00:00 2001
From: higuhigu-lb <higuchi@lightblute-tech.com>
Date: Tue, 3 Dec 2024 11:44:16 +0900
Subject: [PATCH] fix: Skip NavigableString in HTML parsing

---
 docling/backend/html_backend.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/docling/backend/html_backend.py b/docling/backend/html_backend.py
index 9cd1e29b..06f19452 100644
--- a/docling/backend/html_backend.py
+++ b/docling/backend/html_backend.py
@@ -3,7 +3,7 @@
 from pathlib import Path
 from typing import Set, Union
 
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup, NavigableString
 from docling_core.types.doc import (
     DocItemLabel,
     DoclingDocument,
@@ -92,6 +92,8 @@ def walk(self, element, doc):
         try:
             # Iterate over elements in the body of the document
             for idx, element in enumerate(element.children):
+                if isinstance(element, NavigableString):
+                    continue  # Skip over navigable strings
                 try:
                     self.analyse_element(element, idx, doc)
                 except Exception as exc_child: