From 08a45fa4bdb063b92631acaadbea59779ea0b7fb Mon Sep 17 00:00:00 2001
From: ZeyuTeng96 <96521059+ZeyuTeng96@users.noreply.github.com>
Date: Mon, 6 Jan 2025 09:59:46 +0800
Subject: [PATCH] remove leading and trailing \n for HtmlConverter

---
 src/markitdown/_markitdown.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index b6acfe8..3ce0a0b 100644
--- 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,