ازگر: وہ تمام فائلیں تلاش کریں جن میں ڈبل الفاظ (سٹرنگ یا نمبر) ہوں

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') 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 get_duplicates(directory_path, results_file):
    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)
                        # 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:
            print(key)
            for f in duplicates[key]:
                fisiere_duplicat = fisiere_duplicat + f + '\n'
            fisiere_duplicat += '\n\n'

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

    print("Scriere efectuata cu succes.")

if __name__ == '__main__':
    directory_path = "e:\\Carte\\BB\\17 - Site Leadership\\Principal\\ro"
    results_file = "e:\\Carte\\BB\\17 - Site Leadership\\Principal\\ro\\results_duplicates.txt"
    get_duplicates(directory_path, results_file)