INNER CODE UNIT · Python
strip_html
lefterisloukas/edgar-crawler · extract_items.py:202
def strip_html(html_content: str) -> str:
"""
Strip the HTML tags from the HTML content.
Args:
html_content (str): The HTML content.
Returns:
str: The stripped HTML content.
"""
# Replace closing tags of certain elements with two newline characters
html_content = re.sub(r"(<\s*/\s*(div|tr|p|li|)\s*>)", r"\1\n\n", html_content)
# Replace <br> tags with two newline characters
html_content = re.sub(r"(<br\s*>|<br\s*/>)", r"\1\n\n", html_content)
# Replace closing tags of certain elements with a space
html_content = re.sub(r"(<\s*/\s*(th|td)\s*>)", r" \1 ", html_content)
# Use HtmlStripper to strip remaining HTML tags
html_content = HtmlStripper().strip_tags(html_content)