首页 > 解决方案 > 无法在 Selenium 中为 chrome 设置代理服务器(Python 3.7)

问题描述

我正在尝试构建一个使用代理来抓取某个网站的程序。我已经正确设置了我的随机代理生成器,但是在运行以下代码时:

from selenium import webdriver
from selenium.webdriver.common.proxy import Proxy, ProxyType
import random
from string import ascii_lowercase

PATH = r"C:\Users\...\PythonProject\chromedriver.exe"


def proxy_update():
    global driver
    proxies = []
    driver.get('https://free-proxy-list.net/')
    proxy_search = driver.find_element_by_xpath("""//*[@id="proxylisttable"]/tbody""").text.split('ago\n')
    for pr in proxy_search:
        proxies.append(pr.split(' '))
    for lst in proxies:
        for pr in lst:
            if pr == "elite":
                proxies.append(lst[0] + ':' + lst[1])
            else:
                pass
    if len(proxies) > 10:
        driver.quit()
        return random.sample(proxies, k=1)
    else:
        proxy_update()


driver = webdriver.Chrome(PATH)
PROXY = proxy_update()
webdriver.DesiredCapabilities.CHROME['proxy'] = {
    "httpProxy": PROXY,
    "ftpProxy": PROXY,
    "sslProxy": PROXY,
    "proxyType": "MANUAL",
}
webdriver.DesiredCapabilities.CHROME['acceptSslCerts'] = True


proxy_update()


尝试连接到维基百科时出现错误:

driver.get("https://www.wikipedia.org/wiki/Rotterdam")

结果是:

Traceback (most recent call last):
  File "C:\Users\...\venv\lib\site-packages\urllib3\connection.py", line 170, in _new_conn
    (self._dns_host, self.port), self.timeout, **extra_kw
  File "C:\Users\...\venv\lib\site-packages\urllib3\util\connection.py", line 96, in create_connection
    raise err
  File "C:\Users\...\venv\lib\site-packages\urllib3\util\connection.py", line 86, in create_connection
    sock.connect(sa)
ConnectionRefusedError: [WinError 10061] No connection could be made because the target machine actively refused it

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\...\venv\lib\site-packages\urllib3\connectionpool.py", line 706, in urlopen
    chunked=chunked,
  File "C:\Users\...\venv\lib\site-packages\urllib3\connectionpool.py", line 394, in _make_request
    conn.request(method, url, **httplib_request_kw)
  File "C:\Users\...\venv\lib\site-packages\urllib3\connection.py", line 234, in request
    super(HTTPConnection, self).request(method, url, body=body, headers=headers)
  File "C:\Users\...\AppData\Local\Programs\Python\Python37\lib\http\client.py", line 1262, in request
    self._send_request(method, url, body, headers, encode_chunked)
  File "C:\Users\...\AppData\Local\Programs\Python\Python37\lib\http\client.py", line 1308, in _send_request
    self.endheaders(body, encode_chunked=encode_chunked)
  File "C:\Users\...\AppData\Local\Programs\Python\Python37\lib\http\client.py", line 1257, in endheaders
    self._send_output(message_body, encode_chunked=encode_chunked)
  File "C:\Users\...\AppData\Local\Programs\Python\Python37\lib\http\client.py", line 1028, in _send_output
    self.send(msg)
  File "C:\Users\...\AppData\Local\Programs\Python\Python37\lib\http\client.py", line 968, in send
    self.connect()
  File "C:\Users\...\venv\lib\site-packages\urllib3\connection.py", line 200, in connect
    conn = self._new_conn()
  File "C:\Users\...\venv\lib\site-packages\urllib3\connection.py", line 182, in _new_conn
    self, "Failed to establish a new connection: %s" % e
urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPConnection object at 0x000001F755EC47C8>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:/Users/.../PythonProject.py", line 46, in <module>
    proxy_update()
  File "C:/Users/.../PythonProject.py", line 15, in proxy_update
    driver.get('https://free-proxy-list.net/')
  File "C:\Users\...\venv\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 333, in get
    self.execute(Command.GET, {'url': url})
  File "C:\Users\...\venv\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 319, in execute
    response = self.command_executor.execute(driver_command, params)
  File "C:\Users\...\venv\lib\site-packages\selenium\webdriver\remote\remote_connection.py", line 374, in execute
    return self._request(command_info[0], url, body=data)
  File "C:\Users\...\venv\lib\site-packages\selenium\webdriver\remote\remote_connection.py", line 397, in _request
    resp = self._conn.request(method, url, body=body, headers=headers)
  File "C:\Users\...\venv\lib\site-packages\urllib3\request.py", line 79, in request
    method, url, fields=fields, headers=headers, **urlopen_kw
  File "C:\Users\...\venv\lib\site-packages\urllib3\request.py", line 170, in request_encode_body
    return self.urlopen(method, url, **extra_kw)
  File "C:\Users\...\venv\lib\site-packages\urllib3\poolmanager.py", line 375, in urlopen
    response = conn.urlopen(method, u.request_uri, **kw)
  File "C:\Users\...\venv\lib\site-packages\urllib3\connectionpool.py", line 796, in urlopen
    **response_kw
  File "C:\Users\...\venv\lib\site-packages\urllib3\connectionpool.py", line 796, in urlopen
    **response_kw
  File "C:\Users\...\venv\lib\site-packages\urllib3\connectionpool.py", line 796, in urlopen
    **response_kw
  File "C:\Users\...\venv\lib\site-packages\urllib3\connectionpool.py", line 756, in urlopen
    method, url, error=e, _pool=self, _stacktrace=sys.exc_info()[2]
  File "C:\Users\...\venv\lib\site-packages\urllib3\util\retry.py", line 573, in increment
    raise MaxRetryError(_pool, url, error or ResponseError(cause))

urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host='127.0.0.1', port=62467): 
Max retries exceeded with url: /session/8d08a1391f64979088c1e0a83cb674b6/url 
(Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x0000011EF27F48C8>: 
Failed to establish a new connection: [WinError 10061] 
No connection could be made because the target machine actively refused it')) 

这是否意味着维基百科拒绝来自公共、免费代理服务器的请求?因为我的代理只是从一个免费的代理网站上刮下来的。我听说这些代理非常有名,并被谷歌等网站积极阻止。

标签: pythonseleniumproxywebdriverselenium-chromedriver

解决方案


推荐阅读