up/ЭАСвЗИ/Лекции/plagiat_1.py

import os
from difflib import SequenceMatcher
from tqdm import tqdm
import datetime
import requests

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


# ссылка для проверки
url = "http://213.155.192.79:3001/ypv/up/raw/master/%d0%ad%d0%90%d0%a1%d0%b2%d0%97%d0%98/%d0%9b%d0%b5%d0%ba%d1%86%d0%b8%d0%b8/1.3.300_%d0%9a%d1%80%d0%b8%d1%82%d0%b5%d1%80%d0%b8%d0%b8_%d0%ba%d0%bb%d0%b0%d1%81%d1%81%d0%b8%d1%84%d0%b8%d0%ba%d0%b0%d1%86%d0%b8%d0%b8_%d1%83%d0%b3%d1%80%d0%be%d0%b7/Doc.md"

print()

response = requests.get(url)
post_html = response.text

post_list = post_html.split("\n")
print(post_list[0])

exit()
files_paths = []
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)

out_str = ""
max_ratio = 0
max_ratio_file = ""
for file_1 in tqdm(files_paths):
    small_filename_1 = str(file_1).replace(BASE_DIR, "").strip("\\")
    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()
                    


    ratio = int(SequenceMatcher(None, str1.lower(), post_html.lower()).ratio() * 100)
    if (ratio > 70):
        out_str += f"{small_filename_1}\n"
        out_str += f"ratio = {ratio}\n"
    if (ratio > max_ratio):
        max_ratio = ratio
        max_ratio_file = small_filename_1

print(out_str)
print()
print(f"max ratio: {max_ratio}%")
print(f"max ratio file: {max_ratio_file}")
print("success")