Итоговый проект

main.py

@@ -2,18 +2,39 @@ import requests
 from bs4 import BeautifulSoup
 import re
 
-headers = {
-    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36'
-    }
-response = requests.get(
-    'https://online.top-academy.ru/education/ochno',
-    headers=headers
+url = 'https://msk.top-academy.ru/blog'
+
+class BlogArticle:
+    ls = list()
+    def __init__(self,title,text):
+        self.title = title
+        self.text = text
+        BlogArticle.ls.append(self)
+    @classmethod
+    def count(cls):
+        return len(cls.ls)
+    
+    def to_dict(self):
+        return {'title': self.title, 'text':self.text}
+
+def scan(i):
+    headers = {
+        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36'
+        }
+    response = requests.get(
+        url + (f'?page={i}' if i>1 else ''),
+        headers=headers
     )
-html = response.text
-soup = BeautifulSoup(html,'html.parser')
-result = soup.find_all("a", class_='styles_container__Yf7Qk')
-for el in result:
-    name = el.find("span")
-    name = re.search(r'<span>([^<>]+)</span>',str(name))
-    if name:
-        print(name.group(1))
+    html = response.text
+    soup = BeautifulSoup(html,'html.parser')
+    result = soup.find_all("div", class_='styles_cardBody__qP0jN')
+    for el in result:
+        par = el.find_all("p")
+        BlogArticle(par[0].text,par[1].text)
+
+if __name__ == '__main__':
+    for i in range(3):
+        scan(i)
+    print(BlogArticle.count())
+    for i in range(5):
+        print(BlogArticle.ls[i].to_dict())