Extract Text from HTML by Tag Name

This function extracts text content from HTML content by specifying the tag name.

Technology Stack : lxml

Code Type : Function

Code Difficulty : Intermediate

                
                    
def extract_text_from_html(html_content, tag_name):
    from lxml import etree
    
    parser = etree.HTMLParser()
    tree = etree.fromstring(html_content, parser)
    elements = tree.xpath(f'//{tag_name}')
    text_content = ''.join([element.text for element in elements if element.text])
    
    return text_content