Hoe om werfkaarte Xml te genereer deur Python- en HTML-lêers te gebruik

</urlset>

<?xml version="1.0" encoding="UTF-8"?>
<urlset
     xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xmlns:xhtml="http://www.w3.org/1999/xhtml"
     xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd"
     xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">	  	  
<!-- www.check-domains.com sitemap generator -->

  <url>
   <loc>https://YOUR-WEBSITE.com/example-page.html</loc>
   <lastmod>2021-11-30T17:19:37+00:00</lastmod>
   <changefreq>weekly</changefreq>
   <priority>0.6400</priority>
 </url>

import os
import re
import random
import unidecode
def read_text_from_file(file_path):
   """
    Aceasta functie returneaza continutul unui fisier.
    file_path: calea catre fisierul din care vrei sa citesti
    """
   with open(file_path, encoding='utf8') as f:
       text = f.read()
       return text
def write_to_file(text, file_path):
   """
    Aceasta functie scrie un text intr-un fisier.
    text: textul pe care vrei sa il scrii
    file_path: calea catre fisierul in care vrei sa scrii
    """
   with open(file_path, 'wb') as f:
       f.write(text.encode('utf8', 'ignore'))
def creeaza_fisier_xml():
   lista_nume_fisiere = preia_nume_fisiere_html(
       'e:\\YOUR-FOLDER-WITH-HTML-FILES',
       # files to ignore
       ['404-1.html', '404-2.html', '404-3.html']
   )
   start_xml = read_text_from_file('start_xml.txt')
   final_xml = read_text_from_file('final_xml.txt')
   model_xml = read_text_from_file('model_xml.txt')
   xml_text = start_xml + '\n'
   link_pattern = re.compile('<loc>(.*?)</loc>')
   link = re.findall(link_pattern, model_xml)
   if len(link) != 0:
       link = link[0]
   for nume_fisier in lista_nume_fisiere:
       model = model_xml
       model = model.replace(link, 'https://YOUR-WEBSITE.com/' + nume_fisier)
       xml_text = xml_text + model + '\n'
   xml_text = xml_text + final_xml
   write_to_file(xml_text, 'rss.xml')
   print("Scriere efectuata cu succes.")
def preia_nume_fisiere_html(folder_fisiere_html, lista_fisiere_de_ignorat):
   lista_nume_fisiere_html = list()
   for f in os.listdir(folder_fisiere_html):
           if f.endswith('.html'):
               lista_nume_fisiere_html.append(f)
   lista_finala = list()
   for f in lista_nume_fisiere_html:
       if f not in lista_fisiere_de_ignorat:
           lista_finala.append(f)
   return lista_finala
def main():
   creeaza_fisier_xml()
if __name__ == '__main__':
   main()