'''fplproxies.py
scrapes 600 http(s) proxies to ip:port

https://www.sslproxies.org 100
https://www.us-proxy.org 200
https://free-proxy-list.net 300
'''

def z(fpl):

    from requests_html import HTMLSession

    session = HTMLSession()  # session appears to be currently required for a single get request with this library?

    cells = session.get(fpl).html.find('td')  # table cells

    s = ''  # string as data stream to then parse

    for cell in cells:
        c = cell.text
        if not c.lower().islower():  # lowercase all letters and then check if islower to determine if the cell contains letters (only ip and port cells will remain)
            if '.' in c: c = 'proxy' + c + ':'  # ip's will have .
            s += c  # string together to be parsed

    p = s.replace('proxy', '\n')  # proxyip:portproxyip:portproxyip:port -> ip:port\nip:port\n...

    print(p)

z('https://www.sslproxies.org')
z('https://www.us-proxy.org')
z('https://free-proxy-list.net')
#z('https://www.socks-proxy.net')  # socks