diff options
| author | Mike Chen <chagel@gmail.com> | 2009-07-05 10:23:30 +0800 |
|---|---|---|
| committer | Mike Chen <chagel@gmail.com> | 2009-07-05 10:23:30 +0800 |
| commit | 4347c2947834fe7f2edf2b457b2d513454fc6a03 (patch) | |
| tree | 93e9d22d6fb8a6c882e3915a8511a3ac542a1e67 /utils/html.py | |
| download | askbot-4347c2947834fe7f2edf2b457b2d513454fc6a03.tar.gz askbot-4347c2947834fe7f2edf2b457b2d513454fc6a03.tar.bz2 askbot-4347c2947834fe7f2edf2b457b2d513454fc6a03.zip | |
initiliaze git rep
Diffstat (limited to 'utils/html.py')
| -rw-r--r-- | utils/html.py | 51 |
1 files changed, 51 insertions, 0 deletions
diff --git a/utils/html.py b/utils/html.py new file mode 100644 index 00000000..602e1a76 --- /dev/null +++ b/utils/html.py @@ -0,0 +1,51 @@ +"""Utilities for working with HTML."""
+import html5lib
+from html5lib import sanitizer, serializer, tokenizer, treebuilders, treewalkers
+
+class HTMLSanitizerMixin(sanitizer.HTMLSanitizerMixin):
+ acceptable_elements = ('a', 'abbr', 'acronym', 'address', 'b', 'big',
+ 'blockquote', 'br', 'caption', 'center', 'cite', 'code', 'col',
+ 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'font',
+ 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'ins', 'kbd',
+ 'li', 'ol', 'p', 'pre', 'q', 's', 'samp', 'small', 'span', 'strike',
+ 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead',
+ 'tr', 'tt', 'u', 'ul', 'var')
+
+ acceptable_attributes = ('abbr', 'align', 'alt', 'axis', 'border',
+ 'cellpadding', 'cellspacing', 'char', 'charoff', 'charset', 'cite',
+ 'cols', 'colspan', 'datetime', 'dir', 'frame', 'headers', 'height',
+ 'href', 'hreflang', 'hspace', 'lang', 'longdesc', 'name', 'nohref',
+ 'noshade', 'nowrap', 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope',
+ 'span', 'src', 'start', 'summary', 'title', 'type', 'valign', 'vspace',
+ 'width')
+
+ allowed_elements = acceptable_elements
+ allowed_attributes = acceptable_attributes
+ allowed_css_properties = ()
+ allowed_css_keywords = ()
+ allowed_svg_properties = ()
+
+class HTMLSanitizer(tokenizer.HTMLTokenizer, HTMLSanitizerMixin):
+ def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
+ lowercaseElementName=True, lowercaseAttrName=True):
+ tokenizer.HTMLTokenizer.__init__(self, stream, encoding, parseMeta,
+ useChardet, lowercaseElementName,
+ lowercaseAttrName)
+
+ def __iter__(self):
+ for token in tokenizer.HTMLTokenizer.__iter__(self):
+ token = self.sanitize_token(token)
+ if token:
+ yield token
+
+def sanitize_html(html):
+ """Sanitizes an HTML fragment."""
+ p = html5lib.HTMLParser(tokenizer=HTMLSanitizer,
+ tree=treebuilders.getTreeBuilder("dom"))
+ dom_tree = p.parseFragment(html)
+ walker = treewalkers.getTreeWalker("dom")
+ stream = walker(dom_tree)
+ s = serializer.HTMLSerializer(omit_optional_tags=False,
+ quote_attr_values=True)
+ output_generator = s.serialize(stream)
+ return u''.join(output_generator)
|