From fd325219011aaed865f074275b2270112b5e9732 Mon Sep 17 00:00:00 2001 From: Oleg Broytman Date: Fri, 7 Mar 2008 20:56:06 +0000 Subject: [PATCH] Split the title into subparts, reassemble the subparts and recode. git-svn-id: file:///home/phd/archive/SVN/bookmarks_db/trunk@208 fdd5c36f-1aea-0310-aeeb-c58d7e2b6c23 --- Robots/parse_html_beautifulsoup.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py index 8f82d24..db291f9 100644 --- a/Robots/parse_html_beautifulsoup.py +++ b/Robots/parse_html_beautifulsoup.py @@ -92,7 +92,12 @@ def parse_html(filename, charset=None, log=None): elif title.string: title = title.string.encode(_charset) else: - title = str(title) + 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: -- 2.39.2