fix: Skip NavigableString in HTML parsing

DS4SD · Dec 3, 2024 · dba0e47 · dba0e47
1 parent 33cff98
commit dba0e47
Showing 1 changed file with 3 additions and 1 deletion.
diff --git 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: