Function sanitize_html

crawl4ai/utils.py:132–140

(html)

    return parsed_objects, unparsed_segments

def sanitize_html(html):
    # Replace all unwanted and special characters with an empty string
    sanitized_html = html
    # sanitized_html = re.sub(r'[^\w\s.,;:!?=\[\]{}()<>\/\\\-"]', '', html)

    # Escape all double and single quotes
    sanitized_html = sanitized_html.replace('"', '\\"').replace("'", "\\'")

    return sanitized_html

def sanitize_input_encode(text: str) -> str:
    """Sanitize input to handle potential encoding issues."""