Парсер Циан

import requests
from bs4 import BeautifulSoup
 
floats = []
a = []
 
# url = 'https://saratov.cian.ru/cat.php?currency=2&deal_type=rent&engine_version=2&maxprice=10000&offer_type=flat&p=1&region=5066&room1=1&room2=1&type=4'
# req = requests.get(url)
# print(req.status_code)
 
for i in range(0, 28):
    url = f'https://saratov.cian.ru/cat.php?currency=2&deal_type=rent&engine_version=2&maxprice=10000&offer_type=flat&p={i}&region=5066&room1=1&room2=1&type=4'
 
    q = requests.get(url)
    result = q.content
 
    soup = BeautifulSoup(result, 'lxml')
    div = soup.find_all('div', class_= '_93444fe79c--container--kZeLu _93444fe79c--link--DqDOy')
    
    for a in div:
        classes = div.find_all('a')
        a.append(classes)
  
    for link in a:
        float_page_link = link.get('href')
        floats.append(float_page_link)
    
    print(floats)
    
 
with open('floats.txt', 'a') as file:
    for line in floats:
        file.write(f'{line}\n')

headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36"
}

q = requests.get(url, headers=headers)

result = q.text

import requests
from bs4 import BeautifulSoup
import time
import json
 
floats = []
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.133 Safari/537.36"
}
 
# url = 'https://saratov.cian.ru/cat.php?currency=2&deal_type=rent&engine_version=2&maxprice=10000&offer_type=flat&p=1&region=4969&room1=1&room2=1&type=4'
# req = requests.get(url)
# print(req.status_code)
 
for i in range(0, 16):
    url = f'https://saratov.cian.ru/cat.php?currency=2&deal_type=rent&engine_version=2&maxprice=10000&offer_type=flat&p={i}&region=4969&room1=1&room2=1&type=4'
 
    q = requests.get(url=url, headers=headers)
    result = q.text
 
    soup = BeautifulSoup(result, 'lxml')
    links = soup.find_all(class_= '_93444fe79c--link--eoxce')
 
    for link in links:
        float_page_link = link.get('href')
        floats.append(float_page_link)
    
    print(floats)
    time.sleep(3)
 
sorter = [] 
for link in floats: 
    if link not in sorter: 
        sorter.append(link) 
 
floats = sorter
 
 
with open('floats.txt', 'a') as file:
    for line in floats:
        file.write(f'{line}\n')

PS D:\Python\parsing\cian old> python cian_old.py run
[]
[]
[]
[]
[]
[]
[]
[]
[]
[]
[]
[]
[]
[]
[]
[]

with open('floats.txt') as file:
    lines = [line.strip() for line in file.readlines()]
 
    data_flats = []
    count = 0
    for line in lines:
        print(line)
        q = requests.get(line, headers=headers)
        result = q.text
 
        soup = BeautifulSoup(result, 'lxml')
 
        print(q.status_code)
 
        address = soup.find('meta', property='og:description')
        price = soup.find('span', itemprop='price')
        dop_price = soup.find('p', class_='a10a3f92e9--description--CPyUa').text
        time.sleep(3)
      
        data = {
            'address': address['content'],
            'price': price['content'],
            'dop_price': dop_price,
            'link': line
        }
 
        count += 1
        print(f'#{count}: {line} is done!')
 
        data_flats.append(data)
 
        with open('flats.json', 'w') as json_file:
            json.dump(data_flats, json_file, indent=4, ensure_ascii=False)