From: Oleg Broytman <phd@phdru.name>
Date: Mon, 25 Feb 2008 02:44:02 +0000 (+0000)
Subject: &nbsp; is an entity that needs to be encoded.
X-Git-Tag: v4.5.3~191
X-Git-Url: https://git.phdru.name/?a=commitdiff_plain;h=3a680d85d6797a14cfed5e6df1d7b75ef1a516ee;p=bookmarks_db.git

&nbsp; is an entity that needs to be encoded.


git-svn-id: file:///home/phd/archive/SVN/bookmarks_db/trunk@185 fdd5c36f-1aea-0310-aeeb-c58d7e2b6c23
---

diff --git a/Robots/parse_html.py b/Robots/parse_html.py
index 680ad55..038cfaf 100755
--- a/Robots/parse_html.py
+++ b/Robots/parse_html.py
@@ -32,7 +32,7 @@ num_entity_re = re.compile("(&#[0-9]+;)")
 def recode_entities(title, charset):
    output = []
    for part in entity_re.split(title):
-      if part not in ("&amp;", "&lt;", "&gt;", "&quote;", "&nbsp;") and \
+      if part not in ("&amp;", "&lt;", "&gt;", "&quote;") and \
             entity_re.match(part):
          part = unichr(name2codepoint.get(part[1:-1], part)).encode(charset)
       output.append(part)