|
|
@@ -19,7 +19,7 @@ BASE_DIR = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
|
|
|
LECTION_DIR = os.path.join("Лекции", "ПМ3.1")
|
|
|
|
|
|
# ссылка для проверки
|
|
|
-url = "http://213.155.192.79:3001/u20-24dmitrenok/TZI/src/1a57b94f5bc3cf5d529a9e1c7f1b1b9394c9d8c8/%d0%9b%d0%b5%d0%ba%d1%86%d0%b8%d0%b8/%d0%9f%d0%9c3.1/2.2.400_%d0%a5%d0%b0%d1%80%d0%b0%d0%ba%d1%82%d0%b5%d1%80%d0%b8%d1%81%d1%82%d0%b8%d0%ba%d0%b0_%d0%ba%d0%b0%d0%bd%d0%b0%d0%bb%d0%be%d0%b2_%d1%83%d1%82%d0%b5%d1%87%d0%ba%d0%b8_%d0%b8%d0%bd%d1%84%d0%be%d1%80%d0%bc%d0%b0%d1%86%d0%b8%d0%b8_%d0%a7%d0%b5%d1%80%d0%ba%d0%b0%d1%81%d0%be%d0%b2/Dmitrenok.md"
|
|
|
+url = "http://213.155.192.79:3001/u20-24goncharov/TZI/src/72fc17aa4cb299e0ae5cd759c08caa787935e135/%d0%9b%d0%b5%d0%ba%d1%86%d0%b8%d0%b8/%d0%9f%d0%9c3.1/1.2.300_%d0%9a%d0%bb%d0%b0%d1%81%d1%81%d0%b8%d1%84%d0%b8%d0%ba%d0%b0%d1%86%d0%b8%d1%8f_%d1%81%d0%bf%d0%be%d1%81%d0%be%d0%b1%d0%be%d0%b2_%d0%b8_%d1%81%d1%80%d0%b5%d0%b4%d1%81%d1%82%d0%b2_%d0%b7%d0%b0%d1%89%d0%b8%d1%82%d1%8b_%d0%b8%d0%bd%d1%84%d0%be%d1%80%d0%bc%d0%b0%d1%86%d0%b8%d0%b8/Goncharov.md"
|
|
|
|
|
|
# ------------------------------- / НАСТРОЙКИ ------------
|
|
|
url = url.replace("src", "raw")
|
|
|
@@ -175,23 +175,27 @@ for readme_str in readme_list:
|
|
|
variant_uri = variant_uri.replace(")", "")
|
|
|
variant_uri = variant_uri.strip()
|
|
|
|
|
|
- variant_path = os.path.join(BASE_DIR, LECTION_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
|
|
|
- min_tokens_len = min([len(set(post_tokens)), len(set(variant_tokens))])
|
|
|
- c = list(set(post_tokens) & set(variant_tokens))
|
|
|
- ratio = (1 - (len(c) / min_tokens_len)) * 100
|
|
|
- print(f"количество совпадающих слов: {len(c)} / {ratio:.2f}%")
|
|
|
- print()
|
|
|
+ if "youtube" in variant_uri:
|
|
|
+ print(f"youtube in {variant_uri}")
|
|
|
+ print()
|
|
|
+ else:
|
|
|
+ variant_path = os.path.join(BASE_DIR, LECTION_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
|
|
|
+ min_tokens_len = min([len(set(post_tokens)), len(set(variant_tokens))])
|
|
|
+ c = list(set(post_tokens) & set(variant_tokens))
|
|
|
+ ratio = (1 - (len(c) / min_tokens_len)) * 100
|
|
|
+ print(f"количество совпадающих слов: {len(c)} / {ratio:.2f}%")
|
|
|
+ print()
|
|
|
|
|
|
if not(lection_exist):
|
|
|
print("Лекция не найдена в readme")
|
ypv