Python-сообщество

 import requests
from bs4 import BeautifulSoup
from random import choice, uniform
from time import sleep
import csv
def get_html(url, useragent=None, proxy=None):
    r = requests.get(url, headers=useragent, proxies=proxy)
    return r.text
def write_csv(data):
    with open('cmc.csv', 'a') as f:
        writer = csv.writer(f)
        writer.writerow([data['name'],
                         data['price']])
def get_page_data(html):
    soup = BeautifulSoup(html, 'lxml')
    trs = soup.find('table', id='currencies').find('tbody').find_all('tr')
    for tr in trs:
        tds = tr.find_all('td')
        name = tds[1].find('a', class_='currency-name-container').text
        price = tds[3].find('a',class_='price').text
        data = {'name': name,
                'price': price}
        write_csv(data)
def main():
    url = 'mysite'
    useragent = open('useragent.txt').read().split('\n')
    proxies = open('proxies.txt').read().split('\n')
    for i in range(2):
        sleep(uniform(3, 4))
        proxy = {'http': 'http://' + choice(proxies)}
        useragent = {'User-Agent': choice(useragent)}
        try:
            html = get_html(url, useragent, proxy)
        except:
            continue
        get_page_data(get_html(url))
if __name__ == '__main__':
    main()

 import requests
from bs4 import BeautifulSoup
import csv
import os
URL = 'https:......'
HEADERS = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0', 'accept': '*/*'}
HOST = 'https://zzzzzzz'
FILE = 'zzs.csv'
def get_html(url, params=None):
    r = requests.get(url, headers=HEADERS, params=params)
    return r
def get_pages_count(html):
    soup = BeautifulSoup(html, 'html.parser')
    pagination = soup.find_all('span', class_='hide')
    if pagination:
        return int(pagination[-1].get_text())
    else:
        return 1
def get_content(html):
    soup = BeautifulSoup(html, 'html.parser')
    items = soup.find_all('a', class_='item')
    cars = []
    for item in items:
        uah_price = item.find('span', class_='size15')
        if uah_price:
            uah_price = uah_price_text().replace(' • ', '')
        else:
            uah_price = 'Цену уточняйте'
        cars.append({
            'title': item.find('div', class_='na-card-name').get_text(strip=True),
            'link': HOST + item.find('span', class_='link').get('href'),
            'usd_price': item.find('strong', class_='green').get_text(),
            'uah_price': uah_price,
            'city': item.find('svg', class_='svg_i16_pin').find_next('span').get_text(),
        })
    return cars
def save_file(items, path):
    with open(path, 'w', newline='') as file:
        writer = csv.writer(file, delimiter=';')
        writer.writerow(['Марка', 'Ссылка', 'Цена в $', 'Цена в UAH', 'Город'])
        for item in items:
            writer.writerow([item['title'], item['link'], item['usd_price'], item['uah_price'], item['city']])
def parse():
    URL = input('Введите URL: ')
    URL = URL.strip()
    html = get_html(URL)
    if html.status_code == 200:
        cars = []
        pages_count = get_pages_count(html.text)
        for page in range(1, pages_count + 1):
            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)} автомобилей')
        os.startfile(FILE)
    else:
        print('Error')
parse()