логирование plagiat

ЭАСвЗИ/Лекции/plagiat_1.py

@@ -43,11 +43,14 @@ def preprocess_text(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"
+who = "Савкин С."
+
 
-print()
+
+now = datetime.datetime.now().strftime('%d-%m-%Y %H:%M')
+out_str = f"Проверка: {who}, время проверки: {now} \n"
 
 response = requests.get(url)
 post_html = response.text
@@ -57,7 +60,7 @@ 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")
+    out_str += "Заголовок статьи не найден\n"
 
 header_text = line_1.replace("# ", "")
 header_text = header_text.replace(".", "")
@@ -82,12 +85,11 @@ for readme_str in readme_list:
     name_str = name_str.replace(".", "")
 
     if (str(name_str) == str(header_text)):
-        print("Лекция найдена")
+        out_str += "Лекция найдена\n"
         lection_exist = True
 
         post_tokens, post_uniq_text = preprocess_text(post_html)
-        print(f"количество уникальных слов: {len(set(post_tokens))}")
-        print()
+        out_str += f"количество уникальных слов: {len(set(post_tokens))}\n\n"
 
 
 
@@ -100,7 +102,7 @@ for readme_str in readme_list:
     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}")
+        out_str += f"проверяю {variant_name}\n"
         t, variant_uri = readme_str.split("(")
         variant_uri = variant_uri.replace("),", "")
         variant_uri = variant_uri.strip()
@@ -114,60 +116,27 @@ for readme_str in readme_list:
                 variant_html = f.read()
 
         variant_tokens, variant_uniq_text = preprocess_text(variant_html)
-        print(f"количество уникальных слов варианта: {len(set(variant_tokens))}")
+        out_str += f"количество уникальных слов варианта: {len(set(variant_tokens))}\n"
 
         # 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
+        out_str += f"количество совпадающих слов: {len(c)} / {ratio}%\n\n"
+
+if not lection_exist:
+    out_str += "Лекция НЕ найдена\n"    
 
+out_str +="\n\n"
 print(out_str)
-print()
-print(f"max ratio: {max_ratio}%")
-print(f"max ratio file: {max_ratio_file}")
-print("success")
+
+# 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()
+