summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorscoder <stefan_ml@behnel.de>2013-04-27 05:33:53 -0700
committerscoder <stefan_ml@behnel.de>2013-04-27 05:33:53 -0700
commite6873f0ca287c89ac13d6a54f397bb6f721c5ed5 (patch)
treea8a297664aacb44ea5a971bbb6a59b77bc69e66c
parent7baf99b8232de27923d0a607ac10a2f77f6a66e2 (diff)
parent9d461351349ce5bfa5706cbe6dede4db403cd3a3 (diff)
downloadpython-lxml-e6873f0ca287c89ac13d6a54f397bb6f721c5ed5.tar.gz
Merge pull request #116 from cko/doco2
slightly extended documentation
-rw-r--r--src/lxml/html/clean.py5
1 files changed, 4 insertions, 1 deletions
diff --git a/src/lxml/html/clean.py b/src/lxml/html/clean.py
index 315fc991..dabc1257 100644
--- a/src/lxml/html/clean.py
+++ b/src/lxml/html/clean.py
@@ -97,7 +97,8 @@ class Cleaner(object):
Removes any ``<script>`` tags.
``javascript``:
- Removes any Javascript, like an ``onclick`` attribute.
+ Removes any Javascript, like an ``onclick`` attribute. Also removes stylesheets
+ as they could contain Javascript.
``comments``:
Removes any comments.
@@ -166,6 +167,8 @@ class Cleaner(object):
Note that this parameter might not work as intended if you do not
make the links absolute before doing the cleaning.
+ Note that you may also need to set ``whitelist_tags``.
+
``whitelist_tags``:
A set of tags that can be included with ``host_whitelist``.
The default is ``iframe`` and ``embed``; you may wish to