python script to count and compare html tags

import re
from xml.sax.saxutils import unescape

html_str = """\
<div class="productdetailcontainer" id="detailtab1"><div class="r nom"><div class="c10"><div class="space ptb"><b>Description</b><br />Tr&egrave;s confortable pour un sommeil r&eacute;parateur. Id&eacute;al pour soulager les tensions : rev&ecirc;tement en mousse confortable et 7 zones de confort constitu&eacute;es de 600 ressorts ensach&eacute;s pour un soutien cibl&eacute; et optimal de l&#39;ensemble du corps. Position de couchage sur&eacute;lev&eacute;e : hauteur totale du matelas : env. 19 cm. R&eacute;gulation optimale de la temp&eacute;rature : la housse surpiqu&eacute;e de fibres respirantes de chaque c&ocirc;t&eacute; et les poches d&#39;air dans les ressorts ensach&eacute;s permettent une a&eacute;ration parfaite du matelas. Facile &agrave; transporter et rapide &agrave; d&eacute;baller. Se d&eacute;place et se retourne facilement gr&acirc;ce aux 4 poign&eacute;es.<p fontsize:1.0em="" style=""><strong>Vous h&eacute;sitez dans votre choix du meilleur matelas? Cliquez <a advies="" frbe="" href="https://www.lidlshop.be/frBE/wonen/slaapkamer/matrassen/advies" https:="" matrassen="" slaapkamer="" wonen="" www.lidlshop.be="">ici</a> pour obtenir plus d&#39;infos.</strong></p></div></div><div><ul class="attributes" id="mattresslist"> <li class="r nom"><strong class="c2 space pr">Noyau</strong><span class="c8">Ressorts ensach&eacute;s</span></li>   <li class="r nom"><strong class="c2 space pr">Housse</strong><span class="c8">100% polyester</span></li>    <li class="r nom"><strong class="c2 space pr">Mesures</strong><span class="c8">140 x 200 cm</span></li> <li class="r nom"><strong class="c2 space pr">Hauteur</strong><span class="c8">19 cm</span></li>    <li class="r nom"><strong class="c2 space pr">Poids</strong><span class="c8">Convient pour un poids corporel de 80100 kg</span></li>    <li class="r nom"><strong class="c2 space pr">Zones de confort</strong><span class="c8">7</span></li>   <li class="r nom"><strong class="c2 space pr">Degr&eacute; de fermet&eacute;</strong><span class="c8">H3</span></li>    <li class="r nom"><strong class="c2 space pr">Antiallergique</strong><span class="c8">Oui</span></li>   <li class="r nom"><strong class="c2 space pr">Housse amovible</strong><span class="c8">Oui</span></li>  <li class="r nom"><strong class="c2 space pr">Fermeture &agrave; glissi&egrave;re</strong><span class="c8">Fermeture zipp&eacute;e sur les 4 c&ocirc;t&eacute;s</span></li> <li class="r nom"><strong class="c2 space pr">Instructions d&#39;entretien</strong><span class="c8">Lavable en machine &agrave; 60 &deg;C sur le programme linge d&eacute;licat</span></li> <li class="r nom"><strong class="c2 space pr">Labels de qualit&eacute;</strong><span class="c8">5</span></li></ul></div></div></div>"""

def check_html(html):

    def remove_space_in_closing_tags(html):
        thtml = unescape(html.replace("'","\"")).replace("&#xa;","")
        while "</ " in thtml:
            thtml = thtml.replace("</ ","</")
        return thtml

    def build_tags(html):
        closing_tag_list = []
        opening_tag_list = []

        # ultimate_regexp = "(?i)<\/?\w+((\s+\w+(\s*=\s*(?:\".*?\"|'.*?'|[^'\">\s]+))?)+\s*|\s*)\/?>" # used to extract htlm tags from html
        ultimate_regexp = "<.+?>"

        for match in re.finditer(ultimate_regexp, html):
            try:
                tag = repr(match.group()).split(" ")[0]
            except:
                tag = repr(match.group())
            tag = tag.replace("<","").replace(">","").replace("'","")
            if tag.startswith("/"):
                closing_tag_list.append(tag.lower())
            else:
                opening_tag_list.append(tag.lower())
        return opening_tag_list, closing_tag_list

    def compare_tags(opening_tag_list, closing_tag_list):
        errors = []
        self_closing = ['area', 'base', 'br', 'col', 'embed', 'hr', 'hr/', 'img','input', 'link', 'meta', 'param', 'source', 'track', 'wbr', 'bgsound']

        unique_opening_tag_list = list(dict.fromkeys(opening_tag_list))
        unique_closing_tag_list = list(dict.fromkeys(closing_tag_list))

        for tag in unique_opening_tag_list:
            opening_tags_count = opening_tag_list.count(tag)
            closing_tags_couunt = closing_tag_list.count("/" + tag)
            if opening_tags_count == closing_tags_couunt or tag in self_closing or '!' in tag or ":" in tag:
                pass
            else:
                errors.append("tag {} - KO - {} opening tags and {} closing tags".format(tag, opening_tags_count, closing_tags_couunt))
        for tag in unique_closing_tag_list:
            opening_tags_count = opening_tag_list.count(tag[1:])
            closing_tags_couunt = closing_tag_list.count(tag)
            if opening_tags_count == closing_tags_couunt or tag in self_closing or tag[1:] in unique_opening_tag_list or '!' in tag or ":" in tag:
                pass
            else:
                errors.append("tag {} - KO - {} opening tags and {} closing tags".format(tag, opening_tags_count, closing_tags_couunt))
        return errors

    opening_tags, closing_tags = build_tags(remove_space_in_closing_tags(html))
    return compare_tags(opening_tags, closing_tags)

if __name__ == '__main__':

    result = check_html(html_str)
    if result :
        print(result)
    else:
        print("OK")