start

首先npm install koa --save
我的packjson目录如下

{
  "name": "tuku",
  "scripts": {
    "test": "echo \"Error: no test specified\" && exit 1",
    "start": "node koa.js"
  },
  "engines": {
    "node": "7.10.0"
  },
  "author": "silentsvv",
  "license": "ISC",
  "devDependencies": {
  },
  "dependencies": {
    "koa": "^2.3.0",
    "cheerio": "^0.22.0",
    "chromedriver": "^2.29.0",
    "selenium-webdriver": "^3.4.0"
  }
}

新建一个koa.js文件，进行简单的测试

const Koa = require('koa');
const app = new Koa();

app.use(async (ctx) => {
  ctx.body = 'hello world'
});

app.listen(3000);

输入node koa.js 然后打开http://localhost:3000来查看是否显示成功。

输出成功

输出成功！

接下来，我们要试着返回我们刚刚获取的爬虫信息。

index.js

将原来的内容，变成promise函数导出

function Spider() {
  return new Promise((resolve) => {
    require('chromedriver'); //chrome浏览器驱动
    let webdriver = require('selenium-webdriver'); //浏览器自动操作
    let cheerio = require('cheerio'); //获取页面数据
    let fs = require('fs');

    let driver = new webdriver.Builder().forBrowser('chrome').build()

    let data = new Map()
    driver.get('http://tu.duowan.com/tu')
    let PageSource = driver.getPageSource().then((val) => {
      const $ = cheerio.load(val);  //解析网站
      let result = $('.masonry-brick:not(.tags) a').find('img') //寻找有图片的节点
      let parent,textNode,title,link,imgSrc;
      result.each((i,elem) => {
        let obj = {};
        parent = $(elem).closest('li') //图片所在li父节点
        textNode = parent.find('em a')
        title = textNode.text()
        link = textNode.attr('href')
        imgSrc = $(elem).attr('src')

        obj = {
          imgSrc,
          link
        }
        data.set(title,obj)
      })

      driver.close(); // 关闭浏览器
      resolve(data); //返回data
      return data;
    })
  })
}


module.exports = Spider;

koa.js

返回信息

const Koa = require('koa');
const app = new Koa();
const Spider = require('./index.js')  //引用spider函数

app.use(async (ctx) => {
  let data = await Spider();
  let text = [...data] //将返回的map对象转成数组
  ctx.body = JSON.stringify(text) //将数组转成文本
});

app.listen(3000);

接下来试一下运行node koa.js，打开http://localhost:3000地址，待爬虫完毕后会出现以下数据。