Notes

from urllib.request import Request, urlopen
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
import random
import urllib
from threading import Thread

ua = UserAgent() # From here we generate a random user agent
proxies = [] # Will contain proxies [ip, port]
proxy_check_thread_list = list()

def is_bad_proxy(pip):
try:
proxy_handler = urllib.request.ProxyHandler({'https': pip})
opener = urllib.request.build_opener(proxy_handler)
urllib.request.install_opener(opener)
sock=urllib.request.urlopen('https://ipinfo.io/ip') # change the url address here
#sock=urllib.urlopen(req)
except urllib.error.HTTPError as e:
print('Error code: ', e.code)
return 1, e.code
except Exception as detail:
return 1, detail
return 0, sock.read().decode("UTF-8")


# Main function
def proxy_check():
# Retrieve latest proxies
proxies_req = Request('https://www.sslproxies.org/')
proxies_req.add_header('User-Agent', ua.random)
proxies_doc = urlopen(proxies_req).read().decode('utf8')

soup = BeautifulSoup(proxies_doc, 'html.parser')
proxies_table = soup.find(id='proxylisttable')

# Save proxies in the array
for row in proxies_table.tbody.find_all('tr'):
proxies.append({
'ip': row.find_all('td')[0].string,
'port': row.find_all('td')[1].string
})

# Choose a random proxy

for proxy in proxies:
item = proxy['ip'] + ':' + proxy['port']
proxy_status, proxy_ip = is_bad_proxy(item)
if proxy_status:
pass
else:
print(item)
# Retrieve a random index proxy (we need the index to delete it if not working)
def random_proxy():
return random.randint(0, len(proxies) - 1)


def main():
proxies = proxy_check()
pip = random_proxy()

proxy_thread_list = list()
for counter in range(1, 10):
proxy_thread = Thread(target=is_bad_proxy, args=(pip))
proxy_thread.start()
pip = random_proxy()
proxy_thread_list.append(proxy_thread)

main()