preprocess ¤

def autoclean(soup: Soup) -> None:
    """Auto-clean the soup by removing elements.

    Parameters:
        soup: The soup to modify.
    """
    # Remove unwanted elements.
    for element in soup.find_all(_to_remove):
        element.decompose()

    # Unwrap autoref elements.
    for element in soup.find_all("autoref"):
        element.replace_with(NavigableString(element.get_text()))

    # Unwrap mkdocstrings div.doc-md-description.
    for element in soup.find_all("div", attrs={"class": "doc-md-description"}):
        element.replace_with(NavigableString(element.get_text().strip()))

    # Remove mkdocstrings labels.
    for element in soup.find_all("span", attrs={"class": "doc-labels"}):
        element.decompose()

    # Remove line numbers from code blocks.
    for element in soup.find_all("table", attrs={"class": "highlighttable"}):
        element.replace_with(Soup(f"<pre>{element.find('code').get_text()}</pre>", "html.parser"))

def preprocess(soup: Soup, module_path: str, output: str) -> None:
    """Pre-process HTML with user-defined functions.

    Parameters:
        soup: The HTML (soup) to process before conversion to Markdown.
        module_path: The path of a Python module containing a `preprocess` function.
            The function must accept one and only one argument called `soup`.
            The `soup` argument is an instance of [`bs4.BeautifulSoup`][].
        output: The output path of the relevant Markdown file.

    Returns:
        The processed HTML.
    """
    try:
        module = _load_module(module_path)
    except Exception as error:
        raise PluginError(f"Could not load module: {error}") from error
    try:
        module.preprocess(soup, output)
    except Exception as error:
        raise PluginError(f"Could not pre-process HTML: {error}") from error