From eff824f44613bdbc1f8e06bce5e882489da3887b Mon Sep 17 00:00:00 2001
From: shirshasa <katerinagorbac@gmail.com>
Date: Mon, 19 Jul 2021 13:58:28 +0300
Subject: [PATCH] epub converter: change to html.parser

---
 src/epub_postprocessor.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/epub_postprocessor.py b/src/epub_postprocessor.py
index e9ad705..0678032 100644
--- a/src/epub_postprocessor.py
+++ b/src/epub_postprocessor.py
@@ -90,7 +90,8 @@ class EpubPostprocessor:
         nodes = dict()
         for item in self.ebooklib_book.get_items_of_type(ebooklib.ITEM_DOCUMENT):
             html_body_text = item.get_body_content()
-            soup = BeautifulSoup(html_body_text, features='lxml')
+            # html.parser  closes tags if needed
+            soup = BeautifulSoup(html_body_text, features='html.parser')
             nodes[item.file_name] = soup
 
         return nodes