cat_subcat_extractor.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from bs4 import BeautifulSoup
import urllib.request as urllib

def category_parser ():
    checkurl = 'http://www.bazos.sk/'
    checkpage = urllib.urlopen(checkurl)
    checksoup = BeautifulSoup(checkpage.read(), "html.parser")

    categories = {}

    for category in checksoup.select(".nadpisnahlavni a"):
        #print(category.getText())
        #print(category['href'])
        subcat_url = category['href']
        checksub = urllib.urlopen(subcat_url)
        checksubsoup = BeautifulSoup(checksub.read(), "html.parser")
        subcategories = checksubsoup.select(".barvaleva a")
        for subcategory in subcategories:
            subcategory = subcategory.getText()
            #print(subcategory)
            categories[subcategory]=category.getText()

    return categories

#print("\n\n#######")
#print(category_parser())