Created
May 27, 2013 05:35
-
-
Save FZambia/5655338 to your computer and use it in GitHub Desktop.
lxml html sanitize and autolink
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from lxml.html import clean | |
class Bleacher(clean.Cleaner): | |
safe_attrs_only = True | |
safe_attrs = frozenset([ | |
'abbr', 'accept', 'accept-charset', 'accesskey', 'action', 'align', | |
'alt', 'axis', 'border', 'cellpadding', 'cellspacing', 'char', 'charoff', | |
'charset', 'checked', 'cite', 'class', 'clear', 'cols', 'colspan', | |
'color', 'compact', 'coords', 'datetime', 'dir', 'disabled', 'enctype', | |
'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace', | |
'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method', | |
'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly', | |
'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', | |
'size', 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', | |
'type', 'usemap', 'valign', 'value', 'vspace', 'width' | |
]) | |
_tag_link_attrs = dict( | |
iframe='src', | |
embed='src', | |
a='href' | |
) | |
def clean_html(html, host_whitelist=()): | |
cleaner = Bleacher(host_whitelist=host_whitelist) | |
cleaned_html = cleaner.clean_html('<body>' + html + '</body>') | |
linkified_html = clean.autolink_html(cleaned_html) | |
return linkified_html |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment