From 133d19e059a3dc279547d4cea7f0bd04bfcb7737 Mon Sep 17 00:00:00 2001
From: Farruh Sheripov <66794734+Sheripov@users.noreply.github.com>
Date: Fri, 7 Feb 2025 15:55:30 +0100
Subject: [PATCH] Update html_table.py

---
 unstructured/common/html_table.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/unstructured/common/html_table.py b/unstructured/common/html_table.py
index a441e5a57b..a215817991 100644
--- a/unstructured/common/html_table.py
+++ b/unstructured/common/html_table.py
@@ -108,9 +108,8 @@ def iter_rows(self) -> Iterator[HtmlRow]:
     @lazyproperty
     def text(self) -> str:
         """The clean, concatenated, text for this table."""
-        table_text = " ".join(self._table.itertext())
-        # -- blank cells will introduce extra whitespace, so normalize after accumulating --
-        return " ".join(table_text.split())
+        # improve readability of the text
+        return "\n".join([", ".join([j for j in i.iter_cell_texts()]) for i in self.iter_rows()])
 
 
 class HtmlRow: