From: Oleg Broytman <phd@phdru.name>
Date: Mon, 20 Nov 2023 01:12:54 +0000 (+0300)
Subject: Fix(parse_html/bkmk_ph_beautifulsoup4): Fix title recombination
X-Git-Tag: 5.0.0~10
X-Git-Url: https://git.phdru.name/?p=bookmarks_db.git;a=commitdiff_plain;h=ea440b7a93009308e8d87351725b600f1929b181

Fix(parse_html/bkmk_ph_beautifulsoup4): Fix title recombination
---

diff --git a/parse_html/bkmk_ph_beautifulsoup4.py b/parse_html/bkmk_ph_beautifulsoup4.py
index d76c05a..7687c75 100644
--- a/parse_html/bkmk_ph_beautifulsoup4.py
+++ b/parse_html/bkmk_ph_beautifulsoup4.py
@@ -71,7 +71,10 @@ def parse_html(html_text, charset=None, log=None):
             for part in title:
                 #if not isinstance(part, string_type):
                 #    part = part.decode()
-                parts.append(part.strip())
+                if part.strip:
+                    parts.append(part.strip())
+                else:
+                    parts.append(' ')  # Skip tags, they're usually `<br>`
             title = ''.join(parts)
 
     meta = head.find(_find_contenttype, recursive=False)