A one-article guide on how Python can create your own IP pools

proxies_dict = {
    "http": "http://" + ip:port,
    "https": "http://" + ip:port,
}

# Import data request module
import requests  # Data request module Third-party module pip install requests
# Import the regular expression module
import re  # Built-in modules
# Import data parsing module
import parsel  # Data parsing module Third-party module pip install parsel >>> This is a core component of the scrapy framework.


lis = []
lis_1 = []

# 1. Send a request, for the destination URL send a request for /free/.
for page in range(11, 21):
    url = f'/free/inha/{page}/'  # Determine the request url address
    """
    headers Request headers that disguise python code.
    """
    # Use the get method of the requests module to send a request to a url address, and then use the response variable to receive the returned data.
    response = (url)
    # <Response [200]> return response object after the request, 200 status code means the request was successful
    # 2. get data, get server response data (web page source code) get response body text data
    # print()
    # 3. Parsing the data, extracting what we want.
    """
    Parsing data methods.
        Regular: You can extract the content of the string data directly.
    Need to get down html string data for conversion
        xpath: according to the label node to extract data content
        css selector: according to the label attributes to extract data content

        Which aspect to use that, that is preferred to use that
    """
    # Regular expressions to extract data content
    """
    # Regular Extract Data () calls a method inside the module
    # ♪ The positive is indecisive. ♪ *? matches any character (except the newline character \n).
    
    ip_list = ('<td data-title="IP">(.*?)</td>', , )
    port_list = ('<td data-title="PORT">(.*?)</td>', , )
    print(ip_list)
    print(port_list)
    """
    # css selector.
    """
    # css selector extract data need to get down html string data() for conversion
    # I don't know css or xpath what to do #
    # #list > table > tbody > tr > td:nth-child(1)
    # //*[@]/table/tbody/tr/td[1]
    selector = () # Convert html string data to selector object
    ip_list = ('#list tbody tr td:nth-child(1)::text').getall()
    port_list = ('#list tbody tr td:nth-child(2)::text').getall()
    print(ip_list)
    print(port_list)
    """
    # xpath extract data
    selector = () # Convert html string data to selector object
    ip_list = ('//*[@]/table/tbody/tr/td[1]/text()').getall()
    port_list = ('//*[@]/table/tbody/tr/td[2]/text()').getall()
    # print(ip_list)
    # print(port_list)
    for ip, port in zip(ip_list, port_list):
        # print(ip, port)
        proxy = ip + ':' + port
        proxies_dict = {
            "http": "http://" + proxy,
            "https": "http://" + proxy,
        }
        # print(proxies_dict)
        (proxies_dict)
        # 4. Detecting IP quality
        try:
            response = (url=url, proxies=proxies_dict, timeout=1)
            if response.status_code == 200:
                print('Current proxy IP: ', proxies_dict,  'Can be used')
                lis_1.append(proxies_dict)
        except:
            print('Current proxy IP: ', proxies_dict,  'Request timed out, test failed')



print('Number of proxy IPs acquired: ', len(lis))
print('Get the number of available IP proxies: ', len(lis_1))
print('Get available IP proxies: ', lis_1)

dit = {
    'http': 'http://110.189.152.86:40698',
    'https': 'http://110.189.152.86:40698'
}