cmsmanage/tasks/clean_markdown.py

import nh3
from markdownx.utils import markdownify

# fmt: off
MARKDOWN_TAGS = [
    "h1", "h2", "h3", "h4", "h5", "h6",
    "b", "i", "strong", "em", "tt", "sub", "sup",
    "p", "br", "span", "div",
    "blockquote", "code", "pre",
    "hr",
    "ul", "ol", "li",
    "dl", "dd", "dt",
    "img",
    "a",
    "table", "thead", "tbody", "tr", "th", "td",
]

MARKDOWN_ATTRS = {
    "*": ["id"],
    "img": ["src", "alt", "title"],
    "a": ["href", "alt", "title"],
}


def markdown_to_clean_html(md: str) -> str:
    x = nh3.clean(markdownify(md), tags=MARKDOWN_TAGS, attributes=MARKDOWN_ATTRS)
    return x