From: Oleg Broytman <phd@phdru.name>
Date: Sat, 2 Mar 2024 13:28:46 +0000 (+0300)
Subject: Fix(Robots/bkmk_robot_base): Ignore unknown charset
X-Git-Tag: 5.2.2~5
X-Git-Url: https://git.phdru.name/?a=commitdiff_plain;h=a23c3efc90dd6a038d11f5892510a93e09593a70;p=bookmarks_db.git

Fix(Robots/bkmk_robot_base): Ignore unknown charset

There are sites that provide incorrect
(most probably misspelled) charset.
---

diff --git a/Robots/bkmk_robot_base.py b/Robots/bkmk_robot_base.py
index 7243918..1e511d0 100644
--- a/Robots/bkmk_robot_base.py
+++ b/Robots/bkmk_robot_base.py
@@ -135,8 +135,13 @@ class robot_base(Robot):
                             break
                     content_stripped = content.strip()
                     if content_stripped and charset:
-                        content_stripped = content_stripped.decode(
-                            charset, 'replace')
+                        try:
+                            content_stripped = content_stripped.decode(
+                                charset, 'replace')
+                        except LookupError:
+                            charset = None
+                            self.log("   unknown charset "
+                                     "in Content-Type header")
                     if content_stripped and is_html:
                         parser = parse_html(
                             content_stripped, charset, self.log)