INNER CODE UNIT · Python

extract_title

essamamdani/search-result-scraper-markdown · main.py:139

def extract_title(html_content):
    if html_content:
        soup = BeautifulSoup(html_content, 'html.parser')
        title = soup.find("title")
        return title.string.replace(" - YouTube", "") if title else 'No title'
    return 'No title'

def clean_html(html):
    soup = BeautifulSoup(html, 'html.parser')
    
    # Remove all script, style, and other unnecessary elements
    for script_or_style in soup(["script", "style", "header", "footer", "noscript", "form", "input", "textarea", "select", "option", "button", "svg", "iframe", "object", "embed", "applet", "nav", "navbar"]):
        script_or_style.decompose()

    # remove ids "layers"
    ids = ['layers']
    
    for id_ in ids:

View source record →