host : port is accessable from china

host_port_accessable_from_china.py

from time import sleep
from bs4 import BeautifulSoup
from requests_html import HTMLSession

def host_port_accessable_from_china(host: str, port: int, delay: bool) -> bool:
    """
    test if the host:port is accessable from China
    """
    
    url = "https://tool.chinaz.com/port?host={}&port={}".format(host, port)

    # initialize the session
    session = HTMLSession()

    r = session.get(url)

    # for javascript driven websites
    r.html.render()

    if delay:
        sleep(1)

    soup = BeautifulSoup(r.html.html, 'html.parser')

    title = soup.title.text
    if title != "{}网站端口扫描结果".format(host):
        print("{} is not a accessable website".format(host))
        return False

    # get all spans with class "portitem"
    spans = soup.find_all("span", class_="portitem")
    if len(spans) != 1:
        print("{} is not a accessable website".format(host))
        return False
    port_span = spans[0]
    target_port = port_span.text
    if target_port != str(port):
        print("{} is not a accessable website".format(host))
        return False
    spans2 = port_span.find_next_siblings("span")
    if len(spans2) == 0:
        print("{} is not a accessable website".format(host))
        return False
    status_span = spans2[0]
    status = status_span.text
    if status != "开启":
        print("{} is not a accessable website".format(host))
        return False
    return True

if __name__ == "__main__":
    host = "sina.com.cn"
    port = 443

    result = host_port_accessable_from_china(host, port, False)
    r_txt =  "accessable" if result else "unaccessable"
    print("{}:{} is {} from China".format(host, port, r_txt))

requirements.txt

beautifulsoup4>=4.11.1
requests-html>=0.10.0

pip3 install -r requirements.txt