Bright144

import requests
from bs4 import BeautifulSoup
import re
import os
from urllib.request import urlopen
import json

class Parser:

    def __init__(self, href) -> None:
        self.url = "https://fasie.ru"
        self.href = href
        self.source = self.url + self.href['href']
        self.name = self.href.text
        try:
            r = requests.get(self.source, timeout=20)
        except:
            print(f'err. conn: {self.source} in "def __init__"')
        soup = BeautifulSoup(r.text, "html.parser")
        self.section = soup.find('div',{'class':'tabs'}).find_all('section')

    def get_description(self):
        l = re.findall(r"[^\n\t\r]+", self.section[2].text)
        return '\n'.join(map(str.strip, l))
        
    def get_program(self):
        l = re.findall(r"[^\n\t\r]+", self.section[0].text)
        return '\n'.join(map(str.strip, l))
    
    def get_contact(self):
        l = []
        pattern = r"(\+?[\d\(\) -]+)\s\(?доб\.\s?\d{3}\)?"
        if self.section[-1].find('tr'):
            for i in self.section[-1].find_all('tr'):
                d = {}
                d['name'] = i.find('h4').text.strip().replace('\xa0', ' ')
                d['tel'] = ''
                tmp = re.search(pattern, i.text)
                if tmp:
                    d['tel'] = tmp[1].strip()
                d['email'] = i.find('a').text
                l.append(d)
        elif self.section[-1].find('b'):
            name = [i.text for i in self.section[-1].find_all('b') if i.text.strip()]
            tel = re.findall(pattern, self.section[-1].text)
            email = self.section[-1].find_all('a')
            for i in zip(name, tel, email):
                d = {}
                d['name'] = i[0].strip().replace('\xa0', ' ')
                d['tel'] = i[1].strip()
                d['email'] = i[2].text
                l.append(d)
        else:
            for i in self.section[-1].find_all('p', recursive=False):
                if i.find('a'):
                    d = {}
                    d['name'] = ''
                    d['tel'] = ''
                    tmp = re.search(pattern, i)
                    if tmp:
                        d['tel'] = tmp[1].strip()
                    d['email'] = i.find('a').text
                    l.append(d)
        return l

    def get_documents(self):
        l = []
        for i in self.section[1].find_all('a'):
            d = {}
            d['source'] = self.url + i['href']
            d['path'] = '.'+ self.href['href'] + '/'.join(i['href'].replace('%20', '_').rsplit('/', 2)[-2:])
            d['name'] = d['path'].rsplit('/', 1)[-1]
            d['extension'] = d['name'].rsplit('.', 1)[-1]
            try:
                r = requests.get(d['source'], timeout=20)
            except:
                print(f"err. conn: {d['source']} in 'def get_documents'")
                continue
            os.makedirs(os.path.dirname(d['path']), exist_ok=True)
            with open(d['path'], 'wb') as f:
                f.write(r.content)
            d['size'] = len(r.content)
            l.append(d)
        return l
    
    def run(self):
        d = {
            'source':self.source,
            'name':self.name,
            'description':self.get_description(),
            'programs':self.get_program(),
            'contacts':self.get_contact(),
            'documents':self.get_documents()
        }
        return d


def main():
    url = "https://fasie.ru"
    page = urlopen(url)
    html = page.read().decode("utf-8")
    soup = BeautifulSoup(html, "html.parser")
    div = soup.find_all('div', class_ = 'wrap')
    programms_list = div[1].find('ul', class_='').find_all('ul', class_='')[1]
    hrefs = programms_list.find_all('a')
    data = []
    for i in hrefs:
        p = Parser(i)
        data.append(p.run())

    with open('output.json', 'w', encoding="utf-8") as f:
        f.write(json.dumps(data, indent=2, ensure_ascii=False))

main()