当应用 Vue,React 等开发前端页面时,如果采纳前端渲染模式,则对搜索引擎不太敌对。能够利用 chrome 将渲染好的页面内容输入给搜索引擎,以此达到动态化页面的目标。将其残缺封装到 Docker,更便于部署。
以下为 Dockerfile 及服务程序。
Dockerfile
FROM node:10
EXPOSE 3000
VOLUME /var/www
WORKDIR /var/www
ADD package.js /var/www
ADD package.json /var/www
ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD=1
RUN apt-get update \
&& apt-get install -y wget gnupg ca-certificates \
&& wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - \
&& echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google.list \
&& apt-get update \
&& apt-get install -y google-chrome-stable \
&& npm install
CMD ["npm", "start"]
package.js
const puppeteer = require('puppeteer');
const path = require('path');
const koa = require('koa');
const app = new koa();
const ref = "http://www.xxx.com"; // 理论网站网址
let browser;
app.use(async ctx=>{if(!browser){
browser = await puppeteer.launch({args: ['--no-sandbox', '--disable-setuid-sandbox'],
ignoreHTTPSErrors: true, // 疏忽 https 谬误
headless: true, // 不显示浏览器
devtools: false // 不关上控制台
});
}
const page = await browser.newPage();
await page.goto(ref + ctx.request.url, {waitUntil: ['load', 'networkidle0'] // 加载实现, 无新申请, 则页面渲染结束
});
const html = await page.content();
page.close();
ctx.response.body = html;
})
app.listen(3000);
package.json
{
"name": "spa-seo",
"author": "Hongs",
"license": "MIT",
"version": "1.0.0",
"keywords": ["SPA","SEO"],
"description": "SPA SEO",
"main": "package.js",
"scripts": {"start": "node package.js"},
"dependencies": {
"koa": "^2.7.0",
"mime": "^2.4.5",
"mkdirp": "^1.0.4",
"rimraf": "^3.0.2",
"hotnode": "0.0.8",
"puppeteer": "^1.18.1",
"extract-zip": "^2.0.0"
}
}
构建及执行:
docker build -t xxx/seo .
docker run -m 256m -p 3000:3000 --read-only --name xxx/seo xxx/seo
nginx server 内配置:
location /path/to/spa {if ($http_user_agent ~* "Baiduspider|Googlebot|Googlebot-Mobile|Googlebot-Image|Mediapartners-Google|Adsbot-Google|Feedfetcher-Google|Yahoo! Slurp|Yahoo! Slurp China|YoudaoBot|Sosospider|Sogou spider|Sogou web spider|MSNBot|ia_archiver|Tomato Bot|FeedDemon|JikeSpider|Indy Library|Alexa Toolbar|AskTbFXTV|AhrefsBot|CrawlDaddy|CoolpadWebkit|Java|Feedly|UniversalFeedParser|ApacheBench|Microsoft URL Control|Swiftbot|ZmEu|oBot|jaunty|Python-urllib|lightDeckReports Bot|YYSpider|DigExt|YisouSpider|HttpClient|MJ12bot|EasouSpider|Ezooms|heritrix|qihoobot|^$")
{
proxy_pass http://127.0.0.1:3000;
break;
}
# ...
}