31 lines
1.2 KiB
Python
31 lines
1.2 KiB
Python
import re
|
|
from typing import Any, Optional
|
|
|
|
|
|
def strip_html(value: Any) -> Optional[str]:
|
|
"""Remove HTML tags from a string, returning plain text for SEO fields."""
|
|
if not value:
|
|
return None
|
|
val_str = str(value).strip()
|
|
if not val_str:
|
|
return None
|
|
return re.sub(r"<[^>]+>", "", val_str).strip()
|
|
|
|
|
|
def sanitize_html(html_content: Optional[str]) -> Optional[str]:
|
|
"""
|
|
Sanitize HTML content by stripping dangerous executable elements
|
|
(script, iframe, object, embed) and inline event handlers (onerror, onload, onclick)
|
|
to prevent Stored XSS attacks in rich text fields.
|
|
"""
|
|
if not html_content:
|
|
return html_content
|
|
# Strip dangerous tags and their contents
|
|
clean = re.sub(r"<(script|iframe|object|embed|applet|meta)[^>]*>.*?</\1>", "", html_content, flags=re.DOTALL | re.IGNORECASE)
|
|
clean = re.sub(r"<(script|iframe|object|embed|applet|meta)[^>]*>", "", clean, flags=re.IGNORECASE)
|
|
# Strip event handler attributes (on*)
|
|
clean = re.sub(r"\s+on[a-zA-Z]+\s*=\s*(?:'[^']*'|\"[^\"]*\"|[^\s>]+)", "", clean, flags=re.IGNORECASE)
|
|
# Neutralize javascript: pseudoprotocol URLs
|
|
clean = re.sub(r"href\s*=\s*['\"]javascript:[^'\"]*['\"]", 'href="#"', clean, flags=re.IGNORECASE)
|
|
return clean
|
|
|