Selenium 如何使用代理 IP 进行 Web 爬虫（无认证实现、有账号密码认证实现）

from selenium import webdriver
from selenium.webdriver.common.proxy import Proxy, ProxyType

# 设置代理IP
proxy_ip = "your_proxy_ip"
proxy_port = "your_proxy_port"

# 设置代理
proxy = Proxy()
proxy.proxy_type = ProxyType.MANUAL
proxy.http_proxy = f"{proxy_ip}:{proxy_port}"
proxy.ssl_proxy = f"{proxy_ip}:{proxy_port}"

# 配置浏览器选项
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--proxy-server=http://{}:{}'.format(proxy_ip, proxy_port))

# 启动浏览器
driver = webdriver.Chrome(executable_path='path/to/chromedriver', options=chrome_options)

# 访问百度官网
driver.get('https://www.baidu.com')

# 在这里执行你的操作，比如查找元素、输入搜索关键词等

# 关闭浏览器
driver.quit()

import time

from selenium import webdriver
from selenium.webdriver.chrome.service import Service

# 设置代理IP
proxy_ip = "127.0.0.1"
proxy_port = "1080"

# 配置浏览器选项
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--proxy-server=http://{}:{}'.format(proxy_ip, proxy_port))

# 启动浏览器
chrome_service = Service("./chromedriver.exe")
driver = webdriver.Chrome(service=chrome_service, options=chrome_options)

# 访问百度官网
driver.get('https://www.baidu.com')

# 在这里执行你的操作，比如查找元素、输入搜索关键词等
time.sleep(30)

# 关闭浏览器
driver.quit()

import time

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.proxy import Proxy, ProxyType

# 设置代理IP
proxy_ip = "your_proxy_ip"
proxy_port = "your_proxy_port"
proxy_username = "your_proxy_username"
proxy_password = "your_proxy_password"

# 设置代理
proxy = Proxy()
proxy.proxy_type = ProxyType.MANUAL
proxy.http_proxy = f"{proxy_ip}:{proxy_port}"

# 配置代理的认证信息
capabilities = webdriver.DesiredCapabilities.CHROME.copy()
proxy_auth = f"{proxy_username}:{proxy_password}"
capabilities['proxy'] = {
    'httpProxy': proxy.http_proxy,
    'ftpProxy': proxy.http_proxy,
    'sslProxy': proxy.http_proxy,
    'proxyType': 'MANUAL',
    'socksUsername': proxy_username,
    'socksPassword': proxy_password
}

# 配置浏览器选项
chrome_options = webdriver.ChromeOptions()
chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
chrome_options.add_argument('--proxy-server=http://{}:{}'.format(proxy_ip, proxy_port))

# 启动浏览器
chrome_service = Service("./chromedriver.exe")
driver = webdriver.Chrome(service=chrome_service, options=chrome_options)

# 访问百度官网
driver.get('https://www.baidu.com')

# 在这里执行你的操作，比如查找元素、输入搜索关键词等
time.sleep(30)

# 关闭浏览器
driver.quit()

import time

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service


def create_proxyauth_extension(proxy_host, proxy_port,
                               proxy_username, proxy_password,
                               scheme='http', plugin_path=None):
    """Proxy Auth Extension

    args:
        proxy_host (str): domain or ip address, ie proxy.domain.com
        proxy_port (int): port
        proxy_username (str): auth username
        proxy_password (str): auth password
    kwargs:
        scheme (str): proxy scheme, default http
        plugin_path (str): absolute path of the extension

    return str -> plugin_path
    """
    import string
    import zipfile

    if plugin_path is None:
        plugin_path = 'Selenium-Chrome-HTTP-Private-Proxy.zip'

    manifest_json = """
    {
        "version": "1.0.0",
        "manifest_version": 2,
        "name": "Chrome Proxy",
        "permissions": [
            "proxy",
            "tabs",
            "unlimitedStorage",
            "storage",
            "<all_urls>",
            "webRequest",
            "webRequestBlocking"
        ],
        "background": {
            "scripts": ["background.js"]
        },
        "minimum_chrome_version":"22.0.0"
    }
    """

    background_js = string.Template(
        """
        var config = {
                mode: "fixed_servers",
                rules: {
                  singleProxy: {
                    scheme: "${scheme}",
                    host: "${host}",
                    port: parseInt(${port})
                  },
                  bypassList: ["foobar.com"]
                }
              };

        chrome.proxy.settings.set({value: config, scope: "regular"}, function() {});

        function callbackFn(details) {
            return {
                authCredentials: {
                    username: "${username}",
                    password: "${password}"
                }
            };
        }

        chrome.webRequest.onAuthRequired.addListener(
                    callbackFn,
                    {urls: ["<all_urls>"]},
                    ['blocking']
        );
        """
    ).substitute(
        host=proxy_host,
        port=proxy_port,
        username=proxy_username,
        password=proxy_password,
        scheme=scheme,
    )
    with zipfile.ZipFile(plugin_path, 'w') as zp:
        zp.writestr("manifest.json", manifest_json)
        zp.writestr("background.js", background_js)

    return plugin_path


def configure_headless_browser(proxy_config):
    chrome_options = Options()
    chrome_options.add_argument("--start-maximized")
    proxyauth_plugin_path = create_proxyauth_extension(
        proxy_host=proxy_config[0],
        proxy_port=proxy_config[1],
        proxy_username=proxy_config[2],
        proxy_password=proxy_config[3]
    )
    chrome_options.add_extension(proxyauth_plugin_path)
    # chrome_options.add_argument('--headless')
    # chrome_options.add_argument(
    #     "user-agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'")
    chrome_service = Service("./chromedriver.exe")
    return webdriver.Chrome(service=chrome_service, options=chrome_options)


# 设置代理IP
proxy_config = ["175.153.142.127""", "10033", "9ER62CtIr", "fGGVvqedX"]

# 启动浏览器
driver = configure_headless_browser(proxy_config)

# 访问百度官网
driver.get('https://www.baidu.com')

# 在这里执行你的操作，比如查找元素、输入搜索关键词等
time.sleep(30)

# 关闭浏览器
driver.quit()