python中Playwright 数据提取和验证

import { test, expect } from '@playwright/test';

// 页面标题
await expect(page).toHaveTitle('Playwright - 首页');
await expect(page).toHaveTitle(/Playwright/);  // 正则匹配

// URL
await expect(page).toHaveURL('https://playwright.dev/');
await expect(page).toHaveURL(/docs/);

// 元素可见/隐藏
await expect(page.getByText('加载成功')).toBeVisible();
await expect(page.getByText('加载中')).toBeHidden();

// 元素文本
await expect(page.getByRole('heading')).toHaveText('欢迎使用');
await expect(page.getByTestId('status')).toContainText('成功');  // 包含

// 元素属性
await expect(page.getByRole('link')).toHaveAttribute('href', '/docs');
await expect(page.getByRole('img')).toHaveAttribute('src', /logo/);

// 输入框值
await expect(page.getByLabel('搜索')).toHaveValue('Playwright');

// 元素数量
await expect(page.getByRole('listitem')).toHaveCount(5);

// Checkbox/Radio 状态
await expect(page.getByRole('checkbox')).toBeChecked();
await expect(page.getByRole('radio', { name: '男' })).toBeChecked();

// 元素启用/禁用
await expect(page.getByRole('button')).toBeEnabled();
await expect(page.getByRole('button')).toBeDisabled();

// 软断言（不立即失败，继续执行）
expect.soft(page.getByText('错误提示')).toBeHidden();

// 自定义超时
await expect(page.getByText('加载完成'), { timeout: 10000 }).toBeVisible();

// 轮询断言（复杂条件）
await expect(async () => {
  const count = await page.getByRole('listitem').count();
  expect(count).toBeGreaterThan(0);
}).toPass({ timeout: 15000 });

// 截图断言（视觉回归）
await expect(page).toHaveScreenshot('homepage.png', { maxDiffPixels: 100 });

// 全页面截图比较（像素级）
await expect(page).toHaveScreenshot({ fullPage: true });

test('百度搜索 Playwright 并验证结果', async ({ page }) => {
  await page.goto('https://www.baidu.com');
  await page.getByLabel('搜索输入框').fill('Playwright');
  await page.getByRole('button', { name: '百度一下' }).click();

  // 等待结果加载
  await page.waitForLoadState('networkidle');

  // 提取第一个结果标题
  const firstTitle = await page.getByRole('heading').first().textContent();
  console.log('第一个结果标题：', firstTitle);

  // 验证结果包含关键词
  await expect(page.getByRole('heading').first()).toContainText('Playwright');
  await expect(page.getByRole('heading')).toHaveCount(10);  // 通常一页 10 条

  // 提取所有结果链接
  const links = await page.getByRole('link', { name: /Playwright/ }).all();
  console.log(`找到 ${links.length} 个相关链接`);
});

from playwright.sync_api import sync_playwright, expect

with sync_playwright() as p:
    browser = p.chromium.launch(headless=False)
    page = browser.new_page()
    page.goto("https://playwright.dev")

    # 提取
    title = page.title()
    heading = page.get_by_role("heading", name="Fast and reliable").text_content()
    print(f"标题: {title}, 副标题: {heading}")

    # 验证
    expect(page).to_have_title("Playwright")
    expect(page.get_by_role("link", name="Get started")).to_be_visible()
    expect(page.get_by_text("Playwright is a")).to_contain_text("reliable")

    browser.close()