python 3.8
pycharm 2022.3专业版
requests >>> pip install requests
parsel >>> pip install parsel

for page in range(1, 101):
    url = f'https://www.***.com/china/a0_0msdgscncgpi1ltocsp{page}exx0/'
    response = requests.get(url=url, headers=headers, proxies=get_proxies())

html_data = response.text

    select = parsel.Selector(html_data)
    detail_url_list = select.xpath("//ul[@class='viewlist_ul']/li/a[@class='carinfo']/@href").getall()
    # Python学习交流群:872937351
    for detail_url in detail_url_list[:-1]:
        if detail_url[1] == '/':
            detail_url = 'https:' + detail_url
        else:
            detail_url = 'https://www.**.com' + detail_url
        detail_html = requests.get(detail_url, headers=headers, proxies=get_proxies()).text
        detail_select = parsel.Selector(detail_html)
        title = detail_select.xpath("string(//h3[@class='car-brand-name'])").get("").strip()
        licheng = detail_select.xpath("//ul[@class='brand-unit-item fn-clear']/li[1]/h4/text()").get("").strip()
        shangpai = detail_select.xpath("//ul[@class='brand-unit-item fn-clear']/li[2]/h4/text()").get("").strip()
        pailiang = detail_select.xpath("//ul[@class='brand-unit-item fn-clear']/li[3]/h4/text()").get("").strip()
        suozaidi = detail_select.xpath("//ul[@class='brand-unit-item fn-clear']/li[4]/h4/text()").get("").strip()
        guobiao = detail_select.xpath("//ul[@class='brand-unit-item fn-clear']/li[5]/h4/text()").get("").strip()
        price = detail_select.xpath("string(//span[@id='overlayPrice'])").get("").strip()
        print(title, licheng, shangpai, pailiang, suozaidi, guobiao, price, detail_url)

with open('汽车之家.csv', mode='a', encoding='utf-8', newline='') as f:
    csv_writer = csv.writer(f)
    csv_writer.writerow([card_name, cards_unit, price, img_url])