Primer of html2xml converter in python using html.parser and xml.dom.minidom modules

html2xhtml.py

# python html2htxml.py test.html test.xml

import html.parser
import xml.dom.minidom

class HTMLToMinidom(html.parser.HTMLParser):
    # https://developer.mozilla.org/en-US/docs/Glossary/Void_element
    def __init__(self, void_elements = ('area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', 'track', 'wbr')):
        super().__init__()
        self.doc = xml.dom.minidom.Document()
        self.current_node = self.doc
        self.node_stack = []
        self.shortcode = ''
        self.shortcode_arg = {}
        self.void_elements = void_elements

    def handle_starttag(self, tag, attrs):
        element = self.doc.createElement(tag)
        for name, value in attrs:
            element.setAttribute(name, value)
        self.current_node.appendChild(element)
        if tag.lower() not in self.void_elements:
            self.node_stack.append(self.current_node)
            self.current_node = element

    def handle_endtag(self, tag):
        if tag.lower() in self.void_elements:
            return
        if self.node_stack:
            self.current_node = self.node_stack.pop()

    def handle_data(self, data):
        if data.strip():
            text_node = self.doc.createTextNode(data.strip())
            self.current_node.appendChild(text_node)

    def handle_comment(self, data):
        if data.strip():
            comment_node = self.doc.createComment(data.strip())
            self.current_node.appendChild(comment_node)

    def get_minidom_document(self):
        return self.doc

if __name__ == '__main__':
    import sys
    input_path_html = sys.argv[1]
    output_path_xml = sys.argv[2]

    print(input_path_html)
    parser = HTMLToMinidom()
    with open(input_path_html) as f:
        parser.feed(f.read())
    xmldoc = parser.get_minidom_document()

    print(output_path_xml)
    with open(output_path_xml, 'w') as f:
        xmldoc.writexml(f, addindent = '  ', newl = '\n', encoding = 'utf-8')