Парсер веб - страниц

Вот моя небольшая работа.
Парсер веб сайта - https://auto.ria.com/uk/newauto/marka-mercedes-ben...
Написан он был на Python.

Код проекта :



import requests
from bs4 import BeautifulSoup

import csv
URL = 'https://auto.ria.com/uk/newauto/marka-mercedes-...'
HEADERS = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36'}
HOST = 'https://auto.ria.com'
FILE='cars.csv'

def save_file(items,path):
with open(path,'w',newline='')as file:
writer= csv.writer(file,delimiter=';')
writer.writerow(['Mark','Link','Price','City'])
for item in items:
writer.writerow([item['tilte'],item['link'],item['price'],item['city']])



def get_pages_count(html):
soup = BeautifulSoup(html, 'html.parser')
pagination = soup.find_all('span',class_='mhide')
if pagination:
return int (pagination [-1].get_text())
else:
return 1
print(pagination)

def get_html(url,params=None):
r=requests.get(url,headers =HEADERS,params=params)
return r
def get_content(html):
soup = BeautifulSoup( html,'html.parser')
items = soup.find_all('section', class_='proposition')

cars=[]
for item in items:
cars.append({
'tilte': item.find('div',class_='proposition_title').get_text(strip=True),
'link': HOST+item.find('a', class_='proposition_link').get('href'),
'price': item.find('div',class_='proposition_price').get_text().replace('•',''),
'city': item.find('span',class_='item region').get_text()

})
return cars
def parse():
html=get_html(URL)
if html.status_code==200:
cars =[]
pages_count=get_pages_count(html.text)
for page in range(1,pages_count):
print(f'Парсинг страницы{page} из {pages_count}...')
html=get_html(URL,params={'page':page})
cars.extend(get_content(html.text))
save_file(cars,FILE)
print(f'Получено {len(cars)} атомобилей ')
parse()