Python: заменяет строку ( ) пробелом, а затем удаляет все повторяющиеся пробелы из html-тегов

<!-- ARTICOL START -->
<p class="obisnuit"><em>    Honor &nbsp;your  moral and spiritual      obligations &nbsp;  .</em></p>
<p class="nint">&nbsp;  Bishop  knew how to say the    most meaningful &nbsp;    of things  speech.&nbsp; </p>
<!-- ARTICOL FINAL -->

<!-- ARTICOL START -->
<p class="obisnuit"><em>Honor your moral and spiritual obligations.</em></p>
<p class="nint">Bishop knew how to say the most meaningful of things speech.</p>
<!-- ARTICOL FINAL -->

import re
import os
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 replace_white_spaces(tag_name, file_path):
   """
    Aceasta functie modifica textul dintre un tag dat ca argument.
    """
   text = read_text_from_file(file_path)
   text = str(text)
   articol_pattern = re.compile('<!-- ARTICOL START -->[\s\S]*?<!-- ARTICOL FINAL -->[\s\S]*?')
   text_articol = re.findall(articol_pattern, text)
   if len(text_articol) != 0:
       text_articol = str(text_articol[0])
       pattern = re.compile('<{} class=\".*?\">(.*?)</{}>'.format(tag_name, tag_name))  
      
       tag_texts = re.findall(pattern, text_articol)
      
       new_text_articol = text_articol
       for tag_text in tag_texts:
         
          
          
           new_text = tag_text.strip()
           m = re.findall('<em>(.*?)</em>', new_text)
           if len(m) >= 1:
               text_em = str(m[0])
               text_em_new = text_em
               text_em_new = text_em_new.replace(r'&nbsp;', r' ')
               text_em_new = text_em_new.strip()
               new_text = new_text.replace(text_em, text_em_new)
           
           new_text = new_text.replace(r'&nbsp;', r' ')
           new_text = " ".join(new_text.split())
           
           new_text_articol = new_text_articol.replace(tag_text, new_text)
       
       text = text.replace(text_articol, new_text_articol)
       write_to_file(text, file_path)
       print("Fisierul modificat cu succes este: ", file_path)
   else:
       print("Fisierul nu are structura corecta: ", file_path)
def gaseste_nbsp(file_path):
   text_Reg = f.read()
def replace_white_spaces_only_html_php(tag_name, directory_name):
   for root, dirs, files in os.walk(directory_name):
       for f in files:
           if f.endswith('html'):
               file_path = os.path.join(root, f)
               replace_white_spaces(tag_name, file_path)
           else:
               continue
if __name__ == '__main__':  
   
   
   directory_name = 'c:\\Folder1'
  
   tag_name = 'p'
   
   replace_white_spaces_only_html_php(tag_name, directory_name)