up/ЭАСвЗИ/Лекции/plagiat_1.py

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

# download stopwords corpus, you need to run it once
import nltk
#nltk.download("stopwords")
from nltk.corpus import stopwords
import pymorphy2
from string import punctuation

#Create lemmatizer and stopwords list
morph = pymorphy2.MorphAnalyzer()
russian_stopwords = stopwords.words("russian")

#Preprocess function
def preprocess_text(text):
    translator = str.maketrans(punctuation, ' '*len(punctuation))
    words = text.translate(translator)
    words = words.lower().split()
    
    # очистка от прилегающего к слову мусора (слово, "или так")
    clear_words = []
    for word in words:
        clear_word = ""
        for s in word:
            if not s in punctuation:
                clear_word = clear_word + s
        clear_words.append(clear_word)
    tokens = []
    tokens = [morph.parse(token)[0].normal_form for token in clear_words if token not in russian_stopwords\
            and token != " " \
            and token.strip() not in punctuation \
            ]

    text = " ".join(tokens)    
    return tokens, text



# 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")

# проверяем правильность оформления 1й строки
line_1 = post_list[0]
if (line_1[0]) != "#":
    print("Заголовок статьи не найден")

header_text = line_1.replace("# ", "")
header_text = header_text.replace(".", "")
header_text = header_text.strip()

# ищем другие лекции по этой теме
readme_path = os.path.join(BASE_DIR, "README.md")
try:
    with open(readme_path, encoding="utf-8") as f:
        readme_html = f.read()
except:
    with open(readme_path, encoding="cp1251") as f:
        readme_html = f.read()

lection_exist = False
readme_list = readme_html.split("\n")
for readme_str in readme_list:
    readme_str = readme_str.strip()
    readme_str_list = readme_str.split(" ")
    readme_str_list.pop(0)
    name_str = " ".join(readme_str_list)
    name_str = name_str.replace(".", "")

    if (str(name_str) == str(header_text)):
        print("Лекция найдена")
        lection_exist = True

        post_tokens, post_uniq_text = preprocess_text(post_html)
        print(f"количество уникальных слов: {len(set(post_tokens))}")
        print()



    # ищем конец списка вариантов лекций (пустая строка)
    if lection_exist:
        if (readme_str == ""):
            lection_exist = False

    # следующие после названия лекции строки
    if lection_exist and (str(name_str) != str(header_text)):
        variant_name, t = readme_str.split("]")
        variant_name = variant_name.strip("[")
        print(f"проверяю {variant_name}")
        t, variant_uri = readme_str.split("(")
        variant_uri = variant_uri.replace("),", "")
        variant_uri = variant_uri.strip()
        
        variant_path = os.path.join(BASE_DIR, variant_uri)
        try:
            with open(variant_path, encoding="utf-8") as f:
                variant_html = f.read()
        except:
            with open(variant_path, encoding="cp1251") as f:
                variant_html = f.read()

        variant_tokens, variant_uniq_text = preprocess_text(variant_html)
        print(f"количество уникальных слов варианта: {len(set(variant_tokens))}")

        # пересечение множеств 
        c = list(set(post_tokens) & set(variant_tokens))
        ratio = 1 - (len(c) / len(set(post_tokens)))
        print(f"количество совпадающих слов: {len(c)} / {ratio}%")
        print()




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")