Reputation: 647
I have followed a tutorial to put all required modules for a modified selenium webdriver into one single class. However, as I implemented the codes, the following errors keeps happening:
Traceback (most recent call last):
File "c:\Users\s1982\Documents\GitHub\Preventing-Selenium-from-being-detected\master.py", line 149, in <module>
main()
File "c:\Users\s1982\Documents\GitHub\Preventing-Selenium-from-being-detected\master.py", line 140, in main
driverinstance.get("https://bot.sannysoft.com")
File "C:\Python311\Lib\site-packages\selenium\webdriver\remote\webdriver.py", line 455, in get
self.execute(Command.GET, {"url": url})
File "C:\Python311\Lib\site-packages\selenium\webdriver\remote\webdriver.py", line 444, in execute
self.error_handler.check_response(response)
File "C:\Python311\Lib\site-packages\selenium\webdriver\remote\errorhandler.py", line 249, in check_response
raise exception_class(message, screen, stacktrace)
selenium.common.exceptions.WebDriverException: Message: unknown error: net::ERR_TUNNEL_CONNECTION_FAILED
(Session info: chrome=109.0.5414.75)
Stacktrace:
Backtrace:
(No symbol) [0x007F6643]
(No symbol) [0x0078BE21]
(No symbol) [0x0068DA9D]
(No symbol) [0x00689E22]
(No symbol) [0x0067FCFD]
(No symbol) [0x00681101]
(No symbol) [0x0067FFDD]
(No symbol) [0x0067F3BC]
(No symbol) [0x0067F2D8]
(No symbol) [0x0067DC68]
(No symbol) [0x0067E512]
(No symbol) [0x0068F75B]
(No symbol) [0x006F7727]
(No symbol) [0x006DFD7C]
(No symbol) [0x006F6B09]
(No symbol) [0x006DFB76]
(No symbol) [0x006B49C1]
(No symbol) [0x006B5E5D]
GetHandleVerifier [0x00A6A142+2497106]
GetHandleVerifier [0x00A985D3+2686691]
GetHandleVerifier [0x00A9BB9C+2700460]
GetHandleVerifier [0x008A3B10+635936]
(No symbol) [0x00794A1F]
(No symbol) [0x0079A418]
(No symbol) [0x0079A505]
(No symbol) [0x007A508B]
BaseThreadInitThunk [0x751E7D69+25]
RtlInitializeExceptionChain [0x76F1BB9B+107]
RtlClearBits [0x76F1BB1F+191]
The code is provided whole as below, as though I suspect the problem comes from the free-proxy
class, I am unsure of the actual problem. However, I believe it is at least reproducible.
try:
import sys
import os
from fp.fp import FreeProxy
from fake_useragent import UserAgent
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver import Chrome
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
import time
print('all module are loaded ')
except Exception as e:
print("Error ->>>: {} ".format(e))
class Spoofer(object):
def __init__(self, country_id=['US'], rand=True, anonym=True):
self.country_id = country_id
self.rand = rand
self.anonym = anonym
self.userAgent, self.ip = self.get()
def get(self):
ua = UserAgent()
proxy = FreeProxy(country_id=self.country_id,
rand=self.rand, anonym=self.anonym).get()
ip = proxy.split("://")[1]
return ua.random, ip
class DriverOptions(object):
def __init__(self):
self.options = Options()
self.options.add_argument('--no-sandbox')
self.options.add_argument('--start-maximized')
self.options.add_argument('--disable-dev-shm-usage')
self.options.add_argument("--incognito")
self.options.add_argument('--disable-blink-features')
self.options.add_argument(
'--disable-blink-features=AutomationControlled')
self.options.add_experimental_option(
"excludeSwitches", ["enable-automation"])
self.options.add_experimental_option('useAutomationExtension', False)
self.options.add_argument('disable-infobars')
self.options.add_experimental_option(
"excludeSwitches", ["enable-logging"])
self.helperSpoofer = Spoofer()
self.options.add_argument(
'user-agent={}'.format(self.helperSpoofer.userAgent))
self.options.add_argument('--proxy-server=%s' % self.helperSpoofer.ip)
class WebDriver(DriverOptions):
def __init__(self, path=''):
DriverOptions.__init__(self)
self.driver_instance = self.get_driver()
def get_driver(self):
print("""
IP:{}
UserAgent: {}
""".format(self.helperSpoofer.ip, self.helperSpoofer.userAgent))
PROXY = self.helperSpoofer.ip
webdriver.DesiredCapabilities.CHROME['proxy'] = {
"httpProxy": PROXY,
"ftpProxy": PROXY,
"sslProxy": PROXY,
"noProxy": None,
"proxyType": "MANUAL",
"autodetect": False,
}
webdriver.DesiredCapabilities.CHROME['acceptSslCerts'] = True
os.environ['PATH'] += r"C:\Program Files (x86)"
driver = webdriver.Chrome(service=Service(), options=self.options)
driver.execute_script(
"Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
"source":
"const newProto = navigator.__proto__;"
"delete newProto.webdriver;"
"navigator.__proto__ = newProto;"
})
return driver
def main():
driver = WebDriver()
driverinstance = driver.driver_instance
driverinstance.get("https://www.expressvpn.com/what-is-my-ip")
time.sleep(5)
user_agent_check = driverinstance.execute_script(
"return navigator.userAgent;")
print(user_agent_check)
print("done")
if __name__ == "__main__":
main()
I have also checked this two questions on StackOverFlow, but both answers fail to solve the problem in my scenario: Error with Proxy Selenium Webdriver Python : ERR_TUNNEL_CONNECTION_FAILED and Selenium proxy server argument - unknown error: net::ERR_TUNNEL_CONNECTION_FAILED.
Thank you for all the help, and please let me know what I could have corrected in the code.
Upvotes: 1
Views: 2695
Reputation: 647
I have tried different options to validate the problem. After proofing by exhaustion, the issue is clarified as the problem between proxy
and self.options.add_argument('--proxy-server=%s' % self.helperSpoofer.ip)
.
Even though removing the latter argument can solve the net::ERR_TUNNEL_CONNECTION_FAILED
problem, the code itself is essential to block the tracking of actual IP Address
examined in www.expressvpn.com/what-is-my-ip
.
Therefore, I have drawn out a minimal reproducible code example for the next step:
from selenium import webdriver
from fp.fp import FreeProxy
import os
proxy = FreeProxy(country_id='US',
rand=True, anonym=True).get() # IP:PORT or HOST:PORT
ip = proxy.split("://")[1]
print(ip)
webdriver.DesiredCapabilities.CHROME['proxy'] = {
"httpProxy": ip,
"ftpProxy": ip,
"sslProxy": ip,
"noProxy": None,
"proxyType": "MANUAL",
"autodetect": False,
}
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--proxy-server=https://%s' % ip)
chrome_options.add_experimental_option('detach', True)
chrome = webdriver.Chrome(options=chrome_options)
chrome.get("https://www.expressvpn.com/what-is-my-ip")
And even though I can still ping every single proxy server in cmd
, the above code still results in either Cloudfront 403
or ERR_TUNNEL_CONNECTION_FAILED
. Therefore, the problem could be further concluded as issues with proxy servers.
After that, I tried different methods to eliminate the problem while encountering errors not limited to net::ERR_TIMED_OUT
, net::ERR_EMPTY_RESPONSE
, net::ERR_CONNECTION_RESET
.
Multiple StackOverflow answers have provided essential guidelines for such a problem, including Getting 403 when using Selenium to automate checkout process and Error ERR_TUNNEL_CONNECTION_FAILED Selenium. Yet, the problem hasn't been fixed, but I think it does lower the opportunities of the issue.
After reviewing all methods, it appears that manually inserting some specific proxy
can overcome the issue; in my case, for example, both 54.208.22.128:8080
and 129.226.100.188:8080
did the work perfectly well.
As a result, inspired by an answer of @PDHide (unfortunately, I cannot find the exact solution), a valid way would be to search for a random proxy
once, then switch to ensured well-performed proxy
:
from selenium import webdriver
from selenium.common.exceptions import WebDriverException
from fp.fp import FreeProxy
import os
is_valid = False
is_failed = False
while not is_valid:
try:
if not is_failed:
proxy = FreeProxy(country_id='US',
rand=True, anonym=True).get()
ip = proxy.split("://")[1]
print(ip)
else:
# Get a random proxy server from a stored list (for example, a txt document).
continue
webdriver.DesiredCapabilities.CHROME['proxy'] = {
"httpProxy": ip,
"ftpProxy": ip,
"sslProxy": ip,
"noProxy": None,
"proxyType": "MANUAL",
"autodetect": False,
}
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--proxy-server=https://%s' % ip)
chrome_options.add_argument('--disable-blink-features')
chrome_options.add_argument('--disable-blink-features=AutomationControlled')
chrome_options.add_argument("--disable-extensions")
chrome_options.add_experimental_option('useAutomationExtension', False)
chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option('detach', True)
os.environ['PATH'] += r"C:\Program Files (x86)\Chromedriver.exe"
chrome = webdriver.Chrome(options=chrome_options)
chrome.execute_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
chrome.get("https://www.expressvpn.com/what-is-my-ip")
# Check if the pre-stored list has the valid proxy server stored, if not, store the new valid proxy server.
except WebDriverException:
continue
Or to just keep rotating until a valid proxy
is found.
Upvotes: 1
Reputation: 514
Here is a bare minimal version of your code. I have used webdriver_manager to initialize chrome driver.
from fp.fp import FreeProxy
from fake_useragent import UserAgent
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
import time
from webdriver_manager.chrome import ChromeDriverManager
class Spoofer(object):
def __init__(self, country_id=['US'], rand=True, anonym=True):
self.country_id = country_id
self.rand = rand
self.anonym = anonym
self.userAgent, self.ip = self.get()
def get(self):
ua = UserAgent()
proxy = FreeProxy(country_id=self.country_id, rand=self.rand, anonym=self.anonym).get()
print(proxy)
ip = proxy.split("://")[1]
print(ip)
return ua.random, ip
def main():
ser = Service(ChromeDriverManager().install())
options = Options()
options.add_argument('--no-sandbox')
options.add_argument('--start-maximized')
options.add_argument('--disable-dev-shm-usage')
options.add_argument("--incognito")
options.add_argument('--disable-blink-features')
options.add_argument('--disable-blink-features=AutomationControlled')
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)
options.add_argument('disable-infobars')
options.add_experimental_option("excludeSwitches", ["enable-logging"])
helperSpoofer = Spoofer()
webdriver.DesiredCapabilities.CHROME['proxy'] = {
"httpProxy": helperSpoofer.ip,
"ftpProxy": helperSpoofer.ip,
"sslProxy": helperSpoofer.ip,
"proxyType": "MANUAL",
}
webdriver.DesiredCapabilities.CHROME['acceptSslCerts'] = True
options.add_argument("user-agent=" + helperSpoofer.userAgent)
print(webdriver.DesiredCapabilities.CHROME)
driver = webdriver.Chrome(options=options, service=ser)
driver.get("https://www.expressvpn.com/what-is-my-ip")
time.sleep(25)
user_agent_check = driver.execute_script(
"return navigator.userAgent;")
print(user_agent_check)
print("done")
if __name__ == "__main__":
main()
Upvotes: 2