当前位置：首页 > news >正文

【SEO】SEO研究一

news 2026/6/7 14:02:49

自我测试与工具

参考目录

nginx里转发一下

if ($http_user_agent ~* "bot|spider|crawl|slurp|bing|baidu") { proxy_pass http://localhost:26666/renderHtml?url=$request_uri; }

自我测试与工具

10.30.2.7： /docker/puppeteer

const express = require('express'); const puppeteer = require('puppeteer'); const fs = require('fs'); const app = express(); // 通用浏览器启动配置 const launchOptions = { headless: 'new', args: ['--no-sandbox', '--disable-setuid-sandbox'] }; // ========================== // 1. SEO 页面检测 (GET /seoCheck?url=xxx) // ========================== app.get('/seoCheck', async (req, res) => { const { url } = req.query; if (!url) return res.send({ error: '请传入 url 参数' }); try { const browser = await puppeteer.launch(launchOptions); const page = await browser.newPage(); await page.setUserAgent('Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'); await page.goto(url, { waitUntil: 'networkidle2', timeout: 30000 }); const data = await page.evaluate(() => { const title = document.title || ''; const metaDesc = document.querySelector('meta[name="description"]')?.content || ''; const h1Count = document.querySelectorAll('h1').length; const h1Text = document.querySelector('h1')?.innerText || ''; const imgsNoAlt = document.querySelectorAll('img:not([alt])').length; const textLength = document.body.innerText.length; const canonical = document.querySelector('link[rel="canonical"]')?.href || ''; return { title, metaDesc, h1Count, h1Text, imgsNoAlt, textLength, canonical }; }); await browser.close(); res.json({ success: true, url, seo: data }); } catch (err) { res.json({ success: false, error: err.message }); } }); // ========================== // 2. 渲染完整 HTML (GET /renderHtml?url=xxx) // ========================== app.get('/renderHtml', async (req, res) => { const { url } = req.query; if (!url) return res.send('请传入 url 参数'); try { const browser = await puppeteer.launch(launchOptions); const page = await browser.newPage(); await page.goto(url, { waitUntil: 'networkidle2' }); const html = await page.content(); await browser.close(); res.setHeader('Content-Type', 'text/html; charset=utf-8'); res.send(html); } catch (err) { res.send('渲染失败：' + err.message); } }); // ========================== // 3. 生成 sitemap.xml (GET /sitemap?url=xxx) // ========================== app.get('/sitemap', async (req, res) => { const { url } = req.query; if (!url) return res.send('请传入 url 参数'); try { const browser = await puppeteer.launch(launchOptions); const page = await browser.newPage(); await page.goto(url, { waitUntil: 'networkidle2' }); const links = await page.evaluate(() => { return Array.from(document.querySelectorAll('a')) .map(a => a.href) .filter(href => href.startsWith(location.origin)); }); const uniqueLinks = [...new Set(links)]; await browser.close(); let sitemap = `<?xml version="1.0" encoding="UTF-8"?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n`; uniqueLinks.forEach(link => { sitemap += ` <url><loc>${link}</loc></url>\n`; }); sitemap += `</urlset>`; res.setHeader('Content-Type', 'application/xml'); res.send(sitemap); } catch (err) { res.send('生成失败：' + err.message); } }); // 启动服务 const PORT = 26666; app.listen(PORT, () => { console.log('SEO 服务已启动：http://localhost:' + PORT); console.log('使用方式：'); console.log('1. SEO检测： /seoCheck?url=网址'); console.log('2. 渲染HTML： /renderHtml?url=网址'); console.log('3. 生成地图： /sitemap?url=网址'); });

http://localhost:26666/seoCheck?url=https://你的网址.com http://localhost:26666/renderHtml?url=https://你的网址.com http://localhost:26666/sitemap?url=https://你的网址.com

10.30.2.7:35105/seoCheck?url=https://www.gbcom.com.cn

上海寰创通信科技股份有限公司