tydata-webview-v2/server/test-seo.js

/**
 * SEO 端到端检测脚本
 * 模拟爬虫与普通用户请求，验证是否返回正确的页面
 *
 * 使用前请先启动服务器: npm run start
 * 然后运行: npm run test  或  node test-seo.js
 */

const http = require('http')
const https = require('https')

const BASE_URL = process.env.SEO_TEST_URL || 'http://localhost:3000'

// 要检测的路由及期望的 SEO 标题关键词（与 useSEO.js 一致，天远数据）
const ROUTES = [
    { path: '/', titleKeyword: '天远数据' },
    { path: '/agent', titleKeyword: '天远数据代理' },
    { path: '/help', titleKeyword: '天远数据帮助中心' },
    { path: '/inquire/personalData', titleKeyword: '个人综合风险报告' },
    { path: '/agent/promote', titleKeyword: '推广码' },
    { path: '/historyQuery', titleKeyword: '我的报告' }
]

function request(url, userAgent) {
    return new Promise((resolve, reject) => {
        const lib = url.startsWith('https') ? https : http
        const req = lib.get(url, {
            headers: { 'User-Agent': userAgent },
            timeout: 10000
        }, res => {
            const chunks = []
            res.on('data', chunk => chunks.push(chunk))
            res.on('end', () => {
                resolve({
                    statusCode: res.statusCode,
                    headers: res.headers,
                    body: Buffer.concat(chunks).toString('utf-8')
                })
            })
        })
        req.on('error', reject)
        req.on('timeout', () => {
            req.destroy()
            reject(new Error('请求超时'))
        })
    })
}

function extractTitle(html) {
    const match = html.match(/<title[^>]*>([^<]+)<\/title>/i)
    return match ? match[1].trim() : null
}

function hasMetaDescription(html) {
    return /<meta\s+name=["']description["']\s+content=["']/i.test(html)
}

function isSEOTemplate(html) {
    return (
        /<meta\s+name=["']description["']/i.test(html) &&
        /<meta\s+name=["']keywords["']/i.test(html) &&
        /<link\s+rel=["']canonical["']/i.test(html)
    )
}

async function runTest(route, titleKeyword) {
    const url = BASE_URL + route
    const results = { route, crawler: null, normal: null }

    // 1. 爬虫请求
    try {
        const crawlerRes = await request(url, 'Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)')
        const title = extractTitle(crawlerRes.body)
        const seoHeader = crawlerRes.headers['x-seomiddleware']

        results.crawler = {
            status: crawlerRes.statusCode,
            title,
            hasSEOMeta: hasMetaDescription(crawlerRes.body),
            isSEOTemplate: isSEOTemplate(crawlerRes.body),
            seoHeader: seoHeader || '(无)'
        }

        if (crawlerRes.statusCode !== 200) {
            results.crawler.error = `HTTP ${crawlerRes.statusCode}`
        } else if (!title || !title.includes(titleKeyword)) {
            results.crawler.error = `标题不匹配，期望含「${titleKeyword}」，实际: ${title || '未找到'}`
        } else if (!results.crawler.isSEOTemplate) {
            results.crawler.error = '响应中缺少完整 SEO 标签（description/keywords/canonical）'
        }
    } catch (e) {
        results.crawler = { error: e.message || String(e) }
    }

    // 2. 普通用户请求（仅验证能正常返回）
    try {
        const normalRes = await request(url, 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36')
        results.normal = {
            status: normalRes.statusCode,
            bodyLength: normalRes.body.length
        }
        if (normalRes.statusCode !== 200) {
            results.normal.error = `HTTP ${normalRes.statusCode}`
        }
    } catch (e) {
        results.normal = { error: e.message || String(e) }
    }

    return results
}

function printResult(results) {
    const { route, crawler, normal } = results

    console.log(`\n📍 路由: ${route}`)
    console.log('─'.repeat(60))

    const crawlerOk = crawler && !crawler.error && crawler.status === 200 && crawler.isSEOTemplate
    if (crawlerOk) {
        console.log('  爬虫请求: ✓ 通过')
        console.log(`    标题: ${crawler.title}`)
        console.log(`    响应头: X-SEOMiddleware = ${crawler.seoHeader}`)
    } else {
        console.log('  爬虫请求: ✗ 未通过')
        if (crawler && crawler.error) console.log(`    原因: ${crawler.error}`)
        else if (crawler) console.log(`    状态: ${crawler.status}, 标题: ${crawler.title || '无'}`)
        else console.log('    请求失败')
    }

    const normalOk = normal && !normal.error && normal.status === 200
    if (normalOk) {
        console.log('  普通用户: ✓ 正常 (SPA)')
    } else {
        console.log('  普通用户: ✗ 异常')
        if (normal && normal.error) console.log(`    原因: ${normal.error}`)
    }
}

async function main() {
    console.log('='.repeat(60))
    console.log('SEO 端到端检测')
    console.log('='.repeat(60))
    console.log(`目标地址: ${BASE_URL}`)
    console.log('若服务器未启动，请先执行: npm run start')
    console.log('')

    let allPass = true

    for (const r of ROUTES) {
        try {
            const results = await runTest(r.path, r.titleKeyword)
            printResult(results)

            const crawlerOk = results.crawler && !results.crawler.error && results.crawler.isSEOTemplate
            const normalOk = results.normal && !results.normal.error && results.normal.status === 200
            if (!crawlerOk || !normalOk) allPass = false
        } catch (e) {
            console.log(`\n📍 路由: ${r.path}`)
            console.log('  错误:', e.message)
            allPass = false
        }
    }

    console.log('\n' + '='.repeat(60))
    if (allPass) {
        console.log('✓ 全部检测通过：爬虫获得 SEO 模板，普通用户获得 SPA')
    } else {
        console.log('✗ 部分检测未通过，请检查服务器与模板配置')
    }
    console.log('='.repeat(60))

    process.exit(allPass ? 0 : 1)
}

main().catch(err => {
    console.error('检测失败:', err)
    process.exit(1)
})