import csv
import fake_useragent
import requests
from bs4 import BeautifulSoup as bs
def get_html(url):
    user_agent = fake_useragent.UserAgent()
    user = user_agent.random
    headers = {'User-Agent': str(user)}
    r = requests.get(url, headers=headers, params='')
    return r.text
def get_page_links(html):
    soup = bs(html, 'lxml')
    ads = soup.find('div', class_='col-md-12 search-result').find_all('div', class_='search-result_item')
    all_links = []
    for ad in ads:
        link = 'https://tourism.gov.ru' + ad.find('a', class_='search-result_item_link').get('href')
        all_links.append(link)
    return all_links
def get_page_data(html):
    soup = bs(html, 'lxml')
    try:
        title = soup.find('div', class_='col-sm-9 col-xs-12 content').find('h1').text
    except Exception:
        title = ''
    try:
        inn = soup.select('div.col-sm-9.col-xs-12.content > div:nth-child(8) > div:nth-child(2)')
    except Exception:
        inn = ''
    data = {'Название': title,
            'ИНН': inn, }
    return data
def write_csv(data):
    with open('any.csv', 'a') as f:
        writer = csv.writer(f)
        writer.writerow((data["Название"], data["ИНН"]))
def main():
    url = 'https://tourism.gov.ru/operators/'
    all_links = get_page_links(get_html(url))
    for link in all_links:
        html = get_html(link,)
        data = get_page_data(html)
        write_csv(data)
      
if __name__ == '__main__':
    main()

 urls = []
for i in range(430):
    url = 'https://tourism.gov.ru/operators/' + f'?PAGEN_1={i}'
    links = get_page_links(get_html(url))
    urls.append(links)

 for url in urls:
    data = get_page_data(get_html(url))

 def main():
    urls = []
    for i in range(100):
        url = 'https://tourism.gov.ru/operators/' + f'?PAGEN_1={i}'
        links = get_page_links(get_html(url))
        urls.append(links)
    for url in urls:
        data = get_page_data(get_html(url))
        print(data)

 urls_list = []
    for i in range(1, 430):
        url = 'https://tourism.gov.ru/operators/' + f'?PAGEN_1={i}'
        links = get_page_links(get_html(url))
        urls_list.append(links)
        print(f'{i}')  # для наглядности работы парсера
    for urls in urls_list:
        for url in urls:
            data = get_page_data(get_html(url))

 inn = soup.select('div.col-sm-9.col-xs-12.content > div:nth-child(8) > div:nth-child(2)')[0].text.strip()

 import requests
import re
url = 'https://tourism.gov.ru/operators/'
headers = {
'User-Agent': 'Mozilla/5.0',
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Accept-Language': 'ru-RU,ru;q=0.8,en-US;q=0.5,en;q=0.3',
'Accept-Encoding': 'gzip, deflate, br',
'X-Requested-With': 'XMLHttpRequest',
'Connection': 'keep-alive',
}
response =requests.get(url,headers = headers,params='PAGEN_1=429')
print(response.status_code)
data_json = response.json()
print(data_json)
data_html = data_json['html']
target = re.findall(r'id=\d+',data_html)
print(target)