Playwright

Playwright 是微软开发的现代浏览器自动化工具，比 Selenium 更快、更稳定、功能更强大。

安装

pip install playwright
playwright install  # 安装浏览器驱动

基本使用

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    # 启动浏览器
    browser = p.chromium.launch(headless=False)
    page = browser.new_page()

    # 访问网页
    page.goto('https://example.com')

    # 获取标题
    print(f"标题: {page.title()}")

    # 截图
    page.screenshot(path='example.png')

    # 关闭浏览器
    browser.close()

元素定位和操作

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=False)
    page = browser.new_page()
    page.goto('https://example.com')

    # 点击元素
    page.click('button#submit')

    # 输入文本
    page.fill('input#username', '张三')

    # 获取文本
    text = page.text_content('div.content')

    # 获取属性
    href = page.get_attribute('a.link', 'href')

    # 等待元素
    page.wait_for_selector('.dynamic-content')

    # 等待导航
    page.wait_for_load_state('networkidle')

    # 执行 JavaScript
    result = page.evaluate('() => document.title')

    browser.close()

表单操作

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=False)
    page = browser.new_page()
    page.goto('https://example.com/login')

    # 填写表单
    page.fill('input[name="username"]', 'admin')
    page.fill('input[name="password"]', 'password123')

    # 选择下拉框
    page.select_option('select#country', 'China')

    # 勾选复选框
    page.check('input[type="checkbox"]')

    # 点击单选按钮
    page.click('input[type="radio"][value="male"]')

    # 提交表单
    page.click('button[type="submit"]')

    # 等待跳转
    page.wait_for_url('**/dashboard')

    browser.close()

网络拦截

from playwright.sync_api import sync_playwright

def handle_route(route):
    # 修改请求
    headers = route.request.headers
    headers['X-Custom-Header'] = 'test'
    route.continue_(headers=headers)

with sync_playwright() as p:
    browser = p.chromium.launch(headless=False)
    page = browser.new_page()

    # 拦截请求
    page.route('**/*.{png,jpg,jpeg}', lambda route: route.abort())
    page.route('**/api/**', handle_route)

    # 监听响应
    def handle_response(response):
        if 'api' in response.url:
            print(f"API 响应: {response.status}")

    page.on('response', handle_response)

    page.goto('https://example.com')
    browser.close()

多页面和上下文

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=False)

    # 创建多个上下文（类似隐身模式）
    context1 = browser.new_context()
    context2 = browser.new_context()

    # 在不同上下文中创建页面
    page1 = context1.new_page()
    page2 = context2.new_page()

    page1.goto('https://example.com')
    page2.goto('https://test.com')

    # 处理新标签页
    with page.expect_popup() as popup_info:
        page.click('a[target="_blank"]')
    new_page = popup_info.value

    browser.close()

异步模式

import asyncio
from playwright.async_api import async_playwright

async def main():
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=False)
        page = await browser.new_page()

        await page.goto('https://example.com')
        print(f"标题: {await page.title()}")

        await browser.close()

asyncio.run(main())

爬虫示例

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()

    # 访问网页
    page.goto('https://quotes.toscrape.com/js/')

    # 等待内容加载
    page.wait_for_selector('.quote')

    # 获取所有名言
    quotes = page.locator('.quote')
    count = quotes.count()

    for i in range(count):
        text = quotes.nth(i).locator('.text').text_content()
        author = quotes.nth(i).locator('.author').text_content()
        print(f"{author}: {text}")

    browser.close()