def strip_tags(text, valid_tags={}):
"""strip tags, remove invalid tag attrs.
example::
>>> strip_tags('this <a href="">xxx</a>')
u'this xxx'
>>> strip_tags('this <a href="">xxx</a>',{'a':'href'})
u'this <a href="">xxx</a>'
"""
from app.BeautifulSoup import BeautifulSoup, Comment
soup = BeautifulSoup(text)
for comment in soup.findAll(text=lambda text: isinstance(text, Comment)):
comment.extract()
for tag in soup.findAll(True):
if tag.name in valid_tags:
valid_attrs = valid_tags[tag.name]
tag.attrs = [(attr, val.replace('javascript:', ''))
for attr, val in tag.attrs if attr in valid_attrs]
else:
tag.hidden = True
return soup.renderContents().decode('utf8')
