Economy resources, sorts and latest_changes

links_parser.py

@@ -10,6 +10,11 @@ from bs4 import BeautifulSoup
 BASE_URL = "https://www.vstu.ru/"
 RASP_PREFIX = "https://www.vstu.ru/student/raspisaniya/zanyatiy/index.php?dep="
 
+def sibling_clear_to_date(s: str):
+    if s is None:
+        return "!!!Python None!!!"
+    return s.lower().replace("(последнее изменение:", "").replace(")", "").strip()
+
 # Парсит ссылки на эксель .xls & .xlsx файлы и выдаёт их
 def parse_links(facultets):
     session = requests.Session()
@@ -27,7 +32,7 @@ def parse_links(facultets):
         }
     )
 
-    EXCEL_LINKS = {}
+    EXCEL_LINKS = []
     for facultet in facultets:
         url = RASP_PREFIX + facultet
         print("getting...")
@@ -38,19 +43,23 @@ def parse_links(facultets):
 
         # Ищем все теги <a>, у которых атрибут href соответствует нашему паттерну
         excel_tags = soup.find_all('a', href=excel_pattern)
-        excel_links = [tag.get('href') for tag in excel_tags]
-
-        # Предположим, вы уже получили excel_links из одного из методов выше
-        # excel_links = ['../../../upload/raspisanie/z/ОН_ХТФ_1 курс.xlsx', ...]
-
-        absolute_links = [urljoin(BASE_URL, relative_link) for relative_link in excel_links]
-
-        if facultet not in EXCEL_LINKS.keys():
-            EXCEL_LINKS[facultet] = set()
-
-        for excel_url in absolute_links:
-            EXCEL_LINKS[facultet].add(excel_url)
-            print(f"+url {excel_url}")
+        for a in excel_tags:
+            last_changed = sibling_clear_to_date(a.next_sibling)
+            url = urljoin(BASE_URL, a.get('href'))
+            record = {
+                "facultet": facultet,
+                "url": url,
+                "last_changed": last_changed
+            }
+            print(record)
+            EXCEL_LINKS.append(record)
     
-    return EXCEL_LINKS
+    return sorted(EXCEL_LINKS, key=lambda x: x['url'])
 
+
+def excels_to_diffabledates(excels):
+    dates = []
+    for excel in excels:
+        dates.append(f"{excel['last_changed']} {excel['facultet']} {excel['url']}")
+    
+    return "\n".join(sorted(dates)).strip()