Find double words

-----------------
EXPLANATION"

English: https://neculaifantanaru.com/en/find-all-files-that-contain-a-double-words-string-or-number.html
Romanian: https://neculaifantanaru.com/gaseste-toate-fisierele-care-contin-cuvinte-duble-string-sau-numar.html
-----------------


import os
import re

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', errors='ignore') as f:
        text = f.read()
        return text


def write_to_file(text, file_path, encoding='utf8'):
    """
    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('utf-8', 'ignore'))


def get_duplicates(directory_path, results_file, tag):
    duplicates = dict()
    fisiere_care_nu_au_id = ''
    fisiere_duplicat = ''
    id_pattern = re.compile('\$item_id = (.*?);')
    for f in os.listdir(directory_path):
            if f.endswith('.html') and f != 'termeni-si-conditii.html' and f != "parteneri.html":
                filepath = directory_path + '//' + f
                file_text = read_text_from_file(filepath)
                number = re.findall(id_pattern, file_text)
                if len(number) != 0:
                    number = number[0]
                    number = number.strip()
                    if number in duplicates.keys():
                        duplicates[number].append(f)
                    else:
                        duplicates[number] = [f]
                else:
                    fisiere_care_nu_au_id = fisiere_care_nu_au_id + f + '\n'

    for key in duplicates.keys():
        if len(duplicates[key]) >= 2:
            for f in duplicates[key]:
                fisiere_duplicat = fisiere_duplicat + f + '\n'
            fisiere_duplicat += '\n\n'

    # i-au toate numerele din intervalul 1 - id maxim
    # modificare in numere intregi
    numere_intregi = [int(i) for i in list(duplicates.keys())]
    interval = list()
    if tag == 'ro':
        interval = [i for i in range(1, max(numere_intregi) + 1)]
    elif tag == 'en':
        interval = [i for i in range(5000, max(numere_intregi) + 1)]

    numere_care_lipsesc = list()
    for number in interval:
        if number not in numere_intregi:
            numere_care_lipsesc.append(number)
    print("MAX: ", max(numere_intregi))
    print("NUMERE CARE LIPSESC: ", numere_care_lipsesc)

    fisiere_care_lipsesc_id = ''
    for numar in numere_care_lipsesc:
        fisiere_care_lipsesc_id = fisiere_care_lipsesc_id + str(numar) + '\n'

    result = "FISIERE CARE NU AU ID \n\n" + fisiere_care_nu_au_id + '\n' + "FISIERE DUPLICAT \n\n" + fisiere_duplicat  + '\n' + "NUMERE CARE LIPSESC \n\n" + fisiere_care_lipsesc_id
    write_to_file(result, results_file)

    print("Scriere efectuata cu succes.")

if __name__ == '__main__':
    directory_path = "e:\\Carte\\BB\\17 - Site Leadership\\Principal\\en"   # AICI SCHIMB PATCH cu ro sau cu en
    results_file = "e:\\Carte\\BB\\17 - Site Leadership\\Principal\\ro\\results_duplicates.txt"  # AICI APAR REZULTATELE FINALE

    get_duplicates(directory_path, results_file, "en") # "ro"  # AICI SCHIMB PATCH cu ro sau cu en  (SCHIMBA SI MAI SUS )