Итак, я нашел этот код на GitHub, он предназначен для сбора IP-адресов с: https://free -proxy-list.net / и их поворота.Но у меня появляется сообщение об ошибке при попытке его запустить.
Я пытался отладить его, но не смог найти решение.Я обнаружил, что новая версия моего Chrome Web Driver создает проблему?
Это код:
from selenium import webdriver
from selenium.webdriver.chrome.options import DesiredCapabilities
from selenium.webdriver.common.proxy import Proxy, ProxyType
import time
co = webdriver.ChromeOptions()
co.add_argument("log-level=3")
co.add_argument("--headless")
def get_proxies(co=co):
driver = webdriver.Chrome(chrome_options=co)
driver.get("https://free-proxy-list.net/")
PROXIES = []
proxies = driver.find_elements_by_css_selector("tr[role='row']")
for p in proxies:
result = p.text.split(" ")
if result[-1] == "yes":
PROXIES.append(result[0]+":"+result[1])
driver.close()
return PROXIES
ALL_PROXIES = get_proxies()
def proxy_driver(PROXIES, co=co):
prox = Proxy()
if PROXIES:
pxy = PROXIES[-1]
else:
print("--- Proxies used up (%s)" % len(PROXIES))
PROXIES = get_proxies()
prox.proxy_type = ProxyType.MANUAL
prox.http_proxy = pxy
prox.socks_proxy = pxy
prox.ssl_proxy = pxy
capabilities = webdriver.DesiredCapabilities.CHROME
prox.add_to_capabilities(capabilities)
driver = webdriver.Chrome(chrome_options=co, desired_capabilities=capabilities)
return driver
# --- YOU ONLY NEED TO CARE FROM THIS LINE ---
# creating new driver to use proxy
pd = proxy_driver(ALL_PROXIES)
# code must be in a while loop with a try to keep trying with different proxies
running = True
while running:
try:
mycodehere()
# if statement to terminate loop if code working properly
something()
# you
except:
new = ALL_PROXIES.pop()
# reassign driver if fail to switch proxy
pd = proxy_driver(ALL_PROXIES)
print("--- Switched proxy to: %s" % new)
time.sleep(1)
Это ошибка, которую я получаю:
Traceback (most recent call last):
File "test_v1.py", line 53, in <module>
pd = proxy_driver(ALL_PROXIES)
File "test_v1.py", line 47, in proxy_driver
driver = webdriver.Chrome('/home/djurovic/Desktop/Linux ChromeDriver/chromedriver', chrome_options=co, desired_capabilities=capabilities)
File "/usr/local/lib/python3.6/dist-packages/selenium/webdriver/chrome/webdriver.py", line 81, in __init__
desired_capabilities=desired_capabilities)
File "/usr/local/lib/python3.6/dist-packages/selenium/webdriver/remote/webdriver.py", line 157, in __init__
self.start_session(capabilities, browser_profile)
File "/usr/local/lib/python3.6/dist-packages/selenium/webdriver/remote/webdriver.py", line 252, in start_session
response = self.execute(Command.NEW_SESSION, parameters)
File "/usr/local/lib/python3.6/dist-packages/selenium/webdriver/remote/webdriver.py", line 321, in execute
self.error_handler.check_response(response)
File "/usr/local/lib/python3.6/dist-packages/selenium/webdriver/remote/errorhandler.py", line 242, in check_response
raise exception_class(message, screen, stacktrace)
selenium.common.exceptions.InvalidArgumentException: Message: invalid argument: cannot parse capability: proxy
from invalid argument: Specifying 'socksProxy' requires an integer for 'socksVersion'
(Driver info: chromedriver=2.45.615279 (12b89733300bd268cff3b78fc76cb8f3a7cc44e5),platform=Linux 4.15.0-43-generic x86_64)