Using html.parser:

class MyHTMLParser(HTMLParser):
    def handle_data(self, data: str):
        line, col = self.getpos()
        previous_lines = ''.join(html_string.splitlines(True)[:line - 1])
        index = len(previous_lines) + col
        print(data, 'at', index)
parser = MyHTMLParser()
parser.feed(html_string)