selenium+chromedriver常用基礎設置

一、常用基礎設置

from selenium import webdriver # 導入webdriver
from auth_proxy import  proxyauth_plugin_path

options = webdriver.ChromeOptions() #設置谷歌瀏覽器的一些配置選項
options.add_argument('--incognito') #隱身模式(無痕模式)
# options.add_argument('--headless') # 無頭模式
options.add_argument('--proxy-server=http://host:port')  #設置無賬號密碼代理
# options.add_extension(proxyauth_plugin_path) #設置私密代理

# 屏蔽谷歌瀏覽器正在接收自動化軟件控制提示，加上以下兩行
options.add_experimental_option('useAutomationExtension',False)
options.add_experimental_option('excludeSwitches', ['enable-automation'])

options.add_argument("disable-blink-features=AutomationControlled")#去掉webdriver痕跡
options.add_argument('--disable-gpu')  #規避bug
options.add_argument('--no-sandbox')  #取消沙盒模式，解決DevToolsActivePort文件不存在的報錯

prefs = {'profile.managed_default_content_settings.images': 2} #不加載圖片, 提升速度
prefs.update({"credentials_enable_service":False,"profile.password_manager_enabled":False}) #登錄時關閉彈出的密碼保存提示框
prefs.update({'profile.default_content_setting_values':{'notifications' :2}}) # 禁用瀏覽器彈窗
options.add_experimental_option('prefs',prefs)

driver = webdriver.Chrome(executable_path="xxx/chromedriver.exe", options=options)
driver.maximize_window() # 瀏覽器啟動后最大化
# 規避webdriver檢測
driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
    "source": """
        Object.defineProperty(navigator,'webdriver',{
            get: () => undefined
        })
    """
})

二、用於設置上述私密代理的插件代碼（auth_proxy.py）

from selenium import webdriver


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 = 'vimm_chrome_proxyauth_plugin.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


proxyauth_plugin_path = create_proxyauth_extension(
    proxy_host="http-xxxxxxxx.com",  ##代理服務器
    proxy_port=端口號,                   ##代理端口
    proxy_username="用戶名", ##認證用戶名
    proxy_password="密碼"  ##認證密碼
)

注意：代理服務器域名、端口號、用戶名和密碼記得設置