EASvZI/Лекции/plagiat.py

"""
https://www.cyberforum.ru/python-graphics/thread2712141.html
"""
import os
from difflib import SequenceMatcher
from tqdm import tqdm
import datetime

# директория файла
BASE_DIR = os.path.abspath(os.path.dirname(__file__))

# кого проверяем
who = "Савкин"

print()
files_paths = []
exec_files_paths = [] # уже проверенные
remove_files_paths = [] # файлы на удаление

dirs = os.listdir(BASE_DIR)
for dir in dirs:
    dir_path = os.path.join(BASE_DIR, dir)
    if os.path.isdir(dir_path) and (dir != "__pycache__"):
        files = os.listdir(dir_path)
        for file in files:
            file_path = os.path.join(BASE_DIR, dir, file)
            filename, fileext = os.path.splitext(file)

            if os.path.isfile(file_path) and (fileext=='.md'):
                files_paths.append(file_path)

now = datetime.datetime.now().strftime('%d-%m-%Y %H:%M')
out_str = f"Проверка: {who}, время проверки: {now} \n"
print(out_str)


for file_1 in tqdm(files_paths):
    for file_2 in files_paths:
        if (file_1 != file_2):
            small_filename_1 = str(file_1).replace(BASE_DIR, "").strip("\\")
            small_filename_2 = str(file_2).replace(BASE_DIR, "").strip("\\")
            if not (f"{small_filename_2}|{small_filename_1}") in exec_files_paths: # проверка на уже пройденное сравнение

                try:
                    with open(file_1, encoding="utf-8") as f_1:
                        str1 = f_1.read()
                except:
                    with open(file_1, encoding="cp1251") as f_1:
                        str1 = f_1.read()
                        f_1.close()
                    with open(file_1, 'w', encoding="utf-8") as f_1:
                        f_1.write(str1)
                        f_1.close()
                    
                try:
                    with open(file_2, encoding="utf-8") as f_2:
                        str2 = f_2.read()
                except:
                    with open(file_2, encoding="cp1251") as f_2:
                        str2 = f_2.read()
                        f_2.close()
                    with open(file_2, 'w', encoding="utf-8") as f_2:
                        f_2.write(str2)
                        f_2.close()


                ratio = int(SequenceMatcher(None, str1.lower(), str2.lower()).ratio() * 100)
                if (ratio > 70):
                    # время создания файла
                    later_file = small_filename_1
                    early_file = small_filename_2
                    if (os.path.getctime(file_1) < os.path.getctime(file_2)):
                        early_file = small_filename_1
                        later_file = small_filename_2
                    out_str += f"{later_file} позже {early_file}\n"
                    out_str += f"ratio = {ratio}, удален\n"

                    remove_files_paths.append(os.path.join(BASE_DIR, later_file))


                exec_files_paths.append(f"{small_filename_1}|{small_filename_2}")

out_str +="\n\n"
print(out_str)

# запись лога
log_path = os.path.join(BASE_DIR, "log.md")
with open(log_path, "r", encoding="utf-8") as f_log:
    prev_str = f_log.read()

prev_str = out_str + prev_str
with open(log_path, "w", encoding="utf-8") as f_log:
    f_log.write(prev_str)
    f_log.close()

# удаление файлов
for remove_path in remove_files_paths:
    os.remove(remove_path)


print("success")