40 lines
1.2 KiB
Python
40 lines
1.2 KiB
Python
"""Backend HTML sanitization for scraped Post.description.
|
|
|
|
Provenance descriptions come from gallery-dl (untrusted third-party HTML).
|
|
We render them via v-html in the UI sub-slice, so they MUST be sanitized
|
|
server-side to a tight allowlist. nh3 (Rust/ammonia bindings) is used;
|
|
bleach is deprecated upstream and intentionally not used.
|
|
"""
|
|
|
|
import nh3
|
|
|
|
ALLOWED_TAGS = {
|
|
"p", "a", "br", "em", "strong", "b", "i", "ul", "ol", "li", "blockquote",
|
|
}
|
|
ALLOWED_ATTRIBUTES = {"a": {"href", "title"}}
|
|
ALLOWED_URL_SCHEMES = {"http", "https"}
|
|
|
|
|
|
def sanitize_post_html(raw: str | None) -> str | None:
|
|
"""Return sanitized HTML, or None for null/empty/whitespace input.
|
|
|
|
- keeps only ALLOWED_TAGS / ALLOWED_ATTRIBUTES
|
|
- only http/https hrefs survive (javascript: etc. dropped)
|
|
- <script> content removed entirely
|
|
- all <a> get rel="noopener noreferrer" (nh3 default link_rel)
|
|
- never raises
|
|
"""
|
|
if raw is None:
|
|
return None
|
|
stripped = raw.strip()
|
|
if not stripped:
|
|
return None
|
|
return nh3.clean(
|
|
stripped,
|
|
tags=ALLOWED_TAGS,
|
|
attributes=ALLOWED_ATTRIBUTES,
|
|
url_schemes=ALLOWED_URL_SCHEMES,
|
|
link_rel="noopener noreferrer",
|
|
clean_content_tags={"script", "style"},
|
|
)
|