remove leading and trailing \n for HtmlConverter

microsoft · Jan 6, 2025 · 08a45fa · 08a45fa
1 parent 05b78e7
commit 08a45fa
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
@@ -223,6 +223,9 @@ def _convert(self, html_content: str) -> Union[None, DocumentConverterResult]:
 
         assert isinstance(webpage_text, str)
 
+        # remove leading and trailing \n
+        webpage_text = webpage_text.strip()
+
         return DocumentConverterResult(
             title=None if soup.title is None else soup.title.string,
             text_content=webpage_text,