From d03a6b120d63b49eae2af04908645b07fadc910a Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Thu, 27 Jul 2023 18:35:33 +0200
Subject: [PATCH] fix sanitize_fragment('\ufeff')

---
 ox/html.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/ox/html.py b/ox/html.py
index 5fcc6c1..5286116 100644
--- a/ox/html.py
+++ b/ox/html.py
@@ -440,7 +440,12 @@ def sanitize_fragment(html):
     if not html.strip():
         return html
     import lxml.html
-    body = lxml.html.document_fromstring(html).find('body')
+    try:
+        body = lxml.html.document_fromstring(html).find('body')
+    except lxml.etree.ParserError as e:
+        if e.args and e.args[0] == 'Document is empty':
+            return html
+        raise e
     html = lxml.html.tostring(body, encoding='utf-8')[6:-7].decode('utf-8')
     if html.startswith('<p>') and html.endswith('</p>'):
         html = html[3:-4]