X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fparse_html_beautifulsoup.py;h=47ecbaf459f367a9a80d535af1add172709dcf0d;hb=0e76f1851882b99da63a7c8a9e4cdf0c4a48657f;hp=8f82d249669df7a7d79cc0a203103596f4284936;hpb=5240de604c92063107e41cd00c6b363498d65fa6;p=bookmarks_db.git

diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py
index 8f82d24..47ecbaf 100644
--- a/Robots/parse_html_beautifulsoup.py
+++ b/Robots/parse_html_beautifulsoup.py
@@ -1,7 +1,7 @@
 """
    HTML Parser using BeautifulSoup
 
-   Written by BroytMann. Copyright (C) 2007, 2008 PhiloSoft Design
+   Written by Broytman. Copyright (C) 2007, 2008 PhiloSoft Design
 """
 
 import re
@@ -87,12 +87,16 @@ def parse_html(filename, charset=None, log=None):
       # Lookup TITLE in the root
       title = root.title
 
-   if title is None:
-      title = ''
-   elif title.string:
-      title = title.string.encode(_charset)
-   else:
-      title = str(title)
+   if title is not None:
+      if title.string:
+         title = title.string.encode(_charset)
+      else:
+         parts = []
+         for part in title:
+            if not isinstance(part, basestring):
+               part = unicode(part)
+            parts.append(part.strip())
+         title = ''.join(parts).encode(_charset)
 
    meta = head.find(_find_contenttype, recursive=False)
    if meta: