学习 node爬虫丁香园疫情

前提准备：

你需要 : cnpm i 安装这些包

package.json

{
  "name": "test",
  "version": "1.0.0",
  "description": "",
  "main": "index.js",
  "scripts": {
    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "keywords": [],
  "author": "",
  "license": "ISC",
  "dependencies": {
    "cheerio": "^1.0.0-rc.3",
    "express": "^4.17.1",
    "requests": "^0.3.0"
  }
}

index.js

• 执行命令：node index.js
• 得到html

let requests = require('requests');
let fs = require('fs') //fs模块
let path = require('path') //path模块

requests('https://ncov.dxy.cn/ncovh5/view/pneumonia?from=timeline&isappinstalled=0')
    .on('data', function(chunk) {
        fs.writeFile(path.resolve(__dirname, 'data.html'), chunk, () => { //得到html字符串
            console.log('保存成功');
        })
    })

data.html

---

---

index.js

• 执行命令：node index.js
• 得到html结构，再得到里面的省份信息

let requests = require('requests');
let fs = require('fs') //fs模块
let path = require('path') //path模块


const cheerio = require('cheerio')

requests('https://ncov.dxy.cn/ncovh5/view/pneumonia?from=timeline&isappinstalled=0')
    .on('data', function(chunk) {
        let window = {};
        const $ = cheerio.load(chunk) // cheerio 解析html结构
        
        // cheerio 解析html结构，得到json格式字符串，再用eval转化成省份信息
        eval($("#getAreaStat").html())

        // 得到html里面的getAreaStat对象，转化成josn格式字符串
        var jsons = JSON.stringify(eval($("#getAreaStat").html()))
        fs.writeFile(path.resolve(__dirname, 'data.json'), jsons, () => {
            // 把字符串写入到dada.json里面去
            console.log('保存成功');
        })
    })

data.json