diff --git a/util/html.py b/util/html.py
new file mode 100644
index 0000000..79bd6ec
--- /dev/null
+++ b/util/html.py
@@ -0,0 +1,63 @@
+#
+# Copyright (c) 2009 Helmut Merz helmutm@cy55.de
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+#
+
+"""
+Strip HTML tags and other HTML-related utilities.
+
+$Id$
+"""
+
+from cybertools.text.lib.BeautifulSoup import BeautifulSoup, Comment
+
+#validTags = 'p i strong b u a h1 h2 h3 img pre br'.split()
+validTags = 'b br div em font h1 h2 h3 i p pre span strong table td tr u'.split()
+
+#validAttrs = 'href src'.split()
+validAttrs = 'class style'.split()
+
+validStyles = 'font-style font-weight'.split()
+
+
+def sanitize(value, validTags=validTags, validAttrs=validAttrs,
+ validStyles=validStyles):
+ soup = BeautifulSoup(value)
+ for comment in soup.findAll(text=lambda text: isinstance(text, Comment)):
+ comment.extract()
+ for tag in soup.findAll(True):
+ if tag.name not in validTags:
+ tag.hidden = True
+ attrs = []
+ for attr, val in tag.attrs:
+ if attr not in validAttrs:
+ continue
+ if attr == 'style':
+ val = sanitizeStyle(val, validStyles)
+ if val:
+ attrs.append((attr, val))
+ tag.attrs = attrs
+ return soup.renderContents().decode('utf8')
+
+
+def sanitizeStyle(value, validStyles=validStyles):
+ result = []
+ for item in value.split(';'):
+ if ':' in item:
+ k, v = item.split(':')
+ if k.strip() in validStyles:
+ result.append(item.strip())
+ return '; '.join(result)
diff --git a/util/html.txt b/util/html.txt
new file mode 100644
index 0000000..4729b41
--- /dev/null
+++ b/util/html.txt
@@ -0,0 +1,20 @@
+==================
+Tweaking HTML text
+==================
+
+$Id$
+
+ >>> from cybertools.util.html import sanitize
+
+ >>> input = """
+ ...
+ ... Text
+ ...
+ ... """
+
+ >>> sanitize(input, validAttrs=['style'])
+ u'\n\nText\n
\n'
+
+ >>> sanitize(input, ['p', 'b'], ['class'])
+ u'\n\nText\n
\n'
+
diff --git a/util/tests.py b/util/tests.py
index 0ac1c0f..a5ef08e 100755
--- a/util/tests.py
+++ b/util/tests.py
@@ -24,6 +24,7 @@ def test_suite():
doctest.DocFileSuite('config.txt', optionflags=flags),
doctest.DocFileSuite('defer.txt', optionflags=flags),
doctest.DocFileSuite('format.txt', optionflags=flags),
+ doctest.DocFileSuite('html.txt', optionflags=flags),
doctest.DocFileSuite('multikey.txt', optionflags=flags),
doctest.DocFileSuite('property.txt', optionflags=flags),
doctest.DocFileSuite('json.txt', optionflags=flags),