добавил from_dict

main.py

@@ -1,79 +1,45 @@
 import requests
 from bs4 import BeautifulSoup
 import re
-import sqlite3
-from datetime import datetime
 
-class Spyder:
+url = 'https://msk.top-academy.ru/blog'
-    def __init__(self):
+
-        self.db_name = 'database.db'
+class BlogArticle:
-        self.conn = sqlite3.connect(self.db_name)
+    ls = list()
-        self.cursor = self.conn.cursor()
+    def __init__(self,title,text):
-    def init_db(self):
+        self.title = title
-        query = '''CREATE TABLE links(
+        self.text = text
-            id INTEGER PRIMARY KEY AUTOINCREMENT,
+        BlogArticle.ls.append(self)
-            link TEXT NOT NULL,
+    @classmethod
-            last_scan INTEGER DEFAULT 0,
+    def count(cls):
-            title TEXT DEFAULT ''
+        return len(cls.ls)
-        )'''
+    
-        self.cursor.execute(query)
+    def to_dict(self):
-    def scan(self,url):
+        return {'title': self.title, 'text':self.text}
-        if url.endswith('.pdf'):
+
-            return
+    @classmethod
+    def from_dict(cls,d):
+        BlogArticle(d['title'],d['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'
         }
-        try:
     response = requests.get(
-                url,
+        url + (f'?page={i}' if i>1 else ''),
-                headers=headers,
+        headers=headers
-                timeout=5
     )
-        except:
-            self.update_url(url,'Scan error')
-            return
     html = response.text
     soup = BeautifulSoup(html,'html.parser')
-        result = soup.find_all("a", href=True)
+    result = soup.find_all("div", class_='styles_cardBody__qP0jN')
-        title = soup.title.text
-        self.update_url(url,title)
     for el in result:
-            if el['href'].endswith('.pdf'):
+        par = el.find_all("p")
-                continue
+        BlogArticle(par[0].text,par[1].text)
-            if not el['href'].startswith('http'):
-                match = re.findall(r'https?://[A-Za-z0-9.-]+',url)
-                link = f"{match[0]}{el['href']}"
-            else:
-                link = el['href']
-            query = f'SELECT id FROM links WHERE link = ?'
-            self.cursor.execute(query,(link,))
-            if self.cursor.fetchone():
-                continue
-            query = f'INSERT INTO links(link) VALUES(?)'
-            self.cursor.execute(query,(link,))
-            self.conn.commit()
-    def update_url(self,url,title):
-        query = "SELECT id FROM links WHERE link = ?"
-        self.cursor.execute(query,(url,))
-        link_id = self.cursor.fetchone()
-        if link_id:
-            query = "UPDATE links SET title=?, last_scan=? WHERE id=?"
-            self.cursor.execute(query,(title,datetime.now().timestamp(),link_id[0]))
-            self.conn.commit()
-    def get_url(self):
-        query = "SELECT link FROM links ORDER BY last_scan LIMIT 1"
-        self.cursor.execute(query)
-        return self.cursor.fetchone()
-    def close(self):
-        self.conn.close()
 
 if __name__ == '__main__':
-    spyder = Spyder()
+    BlogArticle.from_dict({'title':'Заголовок','text':'Текст статьи'})
-    #spyder.init_db()
+    #for i in range(3):
-    #spyder.scan('https://habr.com/ru/news/1046177/')
+        #scan(i)
-    for _ in range(5):
+    print(BlogArticle.count())
-        url = spyder.get_url()
+    for i in range(1):
-        print(url[0])
+        print(BlogArticle.ls[i].to_dict())
-        spyder.scan(url[0])
-    spyder.close()
-