import requests
from bs4 import BeautifulSoup
import re


URL = 'http://www.catalog.update.microsoft.com/ScopedViewInline.aspx?updateid='
UPDATES = {}


def gen(updateid):
    if updateid not in UPDATES:
        kb = KB(updateid)
        kb.get_updates()
        tmp = {updateid: kb}
        UPDATES.update(tmp)
        for updateid in kb.replaced_to:
            new_kb = KB(updateid)
            print('{} replaced to {}'.format(kb, new_kb))
            gen(new_kb.updateid)


class KB:
    def __init__(self, updateid):
        r = requests.get(URL + updateid)
        soup = BeautifulSoup(r.text, 'html.parser')
        self.description = soup.find('div', {'id': 'titleDiv'}).find('span', {'id': 'ScopedViewHandler_titleText'}).text
        self.name = re.findall(r'KB\d+', self.description)[-1]
        self.url = URL + updateid
        self.updateid = updateid
        self.replaced_to = []


    def get_updates(self):
        l = []
        r = requests.get(self.url)
        soup = BeautifulSoup(r.text, 'html.parser')
        for a in soup.find('div', {'id': 'supersededbyInfo'}).find_all('a'):
            l.append(re.findall(r'[\d,\w,\-]+$', a['href'])[-1])
        self.replaced_to = l
        if len(l) == 0:
            self.not_replaced = True
        else:
            self.not_replaced = False


    def __str__(self):
        return self.name


# Обновление для системы безопасности Windows Server 2012 R2 (KB3067505)
# https://www.catalog.update.microsoft.com/ScopedViewInline.aspx?updateid=33cd6b5a-f5a8-4d2d-b163-96e155eed7b9
updateid = '33cd6b5a-f5a8-4d2d-b163-96e155eed7b9'
gen(updateid)
print('\n\nNot replaced updates:')
for kb in UPDATES:
    if UPDATES[kb].not_replaced == True:
        print('{}: {}'.format(UPDATES[kb].name, UPDATES[kb].description))
        print('URL: {}\n'.format(UPDATES[kb].url))