Python Selenium全栈指南：从自动化入门到企业级实战

graph TD
    A[Selenium WebDriver] --> B[浏览器驱动]
    A --> C[编程语言绑定]
    A --> D[Grid分布式]
    C --> E[Python]
    C --> F[Java]
    B --> G[ChromeDriver]
    B --> H[GeckoDriver]
    D --> I[多节点并发]

# 安装Python库
pip install selenium
 
# 浏览器驱动管理工具
pip install webdriver-manager

from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
 
# 自动下载并配置Chrome驱动
service = webdriver.ChromeService(ChromeDriverManager().install())
driver = webdriver.Chrome(service=service)

# ID定位
driver.find_element(By.ID, "username")
 
# CSS选择器
driver.find_element(By.CSS_SELECTOR, ".login-form input[type='password']")

# 文本内容定位
//button[contains(text(),'提交')]
 
# 层级关系定位
//div[@id='header']/ul/li[position()>2]

# 传统input标签
file_input = driver.find_element(By.XPATH, "//input[@type='file']")
file_input.send_keys("/path/to/file.pdf")
 
# 复杂控件处理（需AutoIT或PyWin32）

from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
 
wait = WebDriverWait(driver, 10)
element = wait.until(
    EC.element_to_be_clickable((By.ID, "dynamicButton"))
)

class element_has_css_class(object):
    def __init__(self, locator, css_class):
        self.locator = locator
        self.css_class = css_class
 
    def __call__(self, driver):
        element = driver.find_element(*self.locator)
        if self.css_class in element.get_attribute("class"):
            return element
        return False
 
# 使用自定义等待
wait.until(element_has_css_class((By.ID, "status"), "active"))

class LoginPage:
    def __init__(self, driver):
        self.driver = driver
        self.username_field = (By.ID, "username")
        self.password_field = (By.ID, "password")
        self.submit_btn = (By.XPATH, "//button[@type='submit']")
 
    def login(self, username, password):
        self.driver.find_element(*self.username_field).send_keys(username)
        self.driver.find_element(*self.password_field).send_keys(password)
        self.driver.find_element(*self.submit_btn).click()

import pytest
 
@pytest.mark.parametrize("username,password,expected", [
    ("admin", "123456", "Dashboard"),
    ("test", "wrongpass", "Invalid Credentials")
])
def test_login(driver, username, password, expected):
    login_page = LoginPage(driver)
    login_page.login(username, password)
    assert expected in driver.title

# 启动Hub
java -jar selenium-server.jar hub
 
# 注册Node
java -jar selenium-server.jar node --hub http://hub-host:4444

from selenium.webdriver import Remote
 
caps = {
    "browserName": "chrome",
    "version": "latest",
    "platform": "WINDOWS",
    "cloud:options": {
        "screenResolution": "1920x1080"
    }
}
 
driver = Remote(
    command_executor="CLOUD_PROVIDER_URL",
    desired_capabilities=caps
)

# 人工介入模式
input("请在浏览器完成验证码后按回车继续...")
 
# 第三方服务集成
from anticaptchaofficial.recaptchav2proxyless import *
 
solver = recaptchaV2Proxyless()
solver.set_verbose(1)
solver.set_key("API_KEY")
result = solver.solve_and_return_solution("SITE_KEY", "PAGE_URL")

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("--headless")  # 无头模式
chrome_options.add_argument("--disable-gpu")  # 禁用GPU加速
chrome_options.add_argument("--no-sandbox")  # 容器环境必备

from selenium.webdriver import Chrome
from selenium.webdriver.common.proxy import Proxy
 
dev_tools = driver.get_devtools()
dev_tools.send("Network.enable")
dev_tools.send("Network.setRequestInterception", {"patterns": [{"urlPattern": "*"}]})
 
def intercept_request(request):
    if "ad.jpg" in request.url:
        dev_tools.send("Network.continueInterceptedRequest", {
            "interceptionId": request.interception_id,
            "errorReason": "BlockedByClient"
        })
 
dev_tools.add_listener("Network.requestIntercepted", intercept_request)

from appium import webdriver
 
desired_caps = {
    "platformName": "Android",
    "deviceName": "emulator-5554",
    "appPackage": "com.example.app",
    "appActivity": ".MainActivity"
}
 
driver = webdriver.Remote("http://localhost:4723/wd/hub", desired_caps)

# 使用CV识别元素
from selenium_ai import SmartDriver
 
smart_driver = SmartDriver(driver)
element = smart_driver.find_element_by_image("submit_button.png")

graph LR
A[基础语法] --> B[元素定位]
B --> C[框架设计]
C --> D[分布式测试]
D --> E[移动端扩展]
E --> F[AI整合]

# 自动下载学习资源
import requests
 
url = "https://selenium-resources.com/download"
params = {
    "type": "fullpack",
    "license": "education"
}
response = requests.get(url, params=params)
with open("selenium_master.zip", "wb") as f:
    f.write(response.content)