Node.js爬虫如何获取天气和每日问候详解

安装依赖

安装node.js,同时安装好依赖：

npm install request --save // http请求库
npm install cheerio --save // 分析html工具
npm install express --save // nodejs web框架

获取墨迹天气

地址示例：

东莞 tianqi.moji.com/weather/chi…

广州 tianqi.moji.com/weather/chi…

深圳 tianqi.moji.com/weather/chi…

可打开墨迹天气网站找到女朋友对应城市修改url地址拼音即可。

查看网页结构：

下面开始提取网页天气信息：

const request = require("request")
const cheerio = require("cheerio")
const weatherURL = 'https://tianqi.moji.com/weather/china/Guangdong/dongguan'

// 获取墨迹天气提示信息
function getWeatherTips(url) {
 return new Promise((resolve,reject)=>{
 	request(weatherURL,(error,res,body)=>{
 	 if (!error) {
 	 let html = res.body || "";
 	let $ =cheerio.load(html)
 	let temp = $('.wea_weather em').text().trim()+'℃'
 	let desc = $('.wea_weather b').text().trim()
 	let water = $('.wea_about span').text().trim()
 	let win = $('.wea_about em').text().trim()
 	let tips = $('.wea_tips em').text().trim()
 	let words=`今日${city}天气\n${desc}\n温度：${temp}\n湿度：${water}\n风力：${win}\n${tips}`
 	resolve(words)
 	} else {
 	reject(error)
 	} 
 })
 }) 
}

获取每日一句

地址：wufazhuce.com/

const greetingURL = 'http://wufazhuce.com/'
// 获取wufazhuce.com每日一句
function getDailyGreeting() {
 return new Promise((resolve,reject)=>{
 	request(greetingURL,(error,res,body)=>{
 	let everyDayWordsList = [];
 	if(!error && res.statusCode==200) {
 	let $ = cheerio.load(res.body.toString())
 	$('div .fp-one-cita a').each(function(item){
 	if($(this).text()){
 	everyDayWordsList.push($(this).text().trim())
 	} 
 	})
 	let result = everyDayWordsList[0] || '网络错误，获取每日问候失败！'
 	resolve(result) 
 	} else {
 	reject(error)	
 	}
 	})
 })
}

计算在一起天数

// 计算在一起的日子
function getDiffDate(targetDate) {
 let date1 = new Date(targetDate);
 let date2 = new Date();
 date1 = new Date(date1.getFullYear(), date1.getMonth(), date1.getDate());
 date2 = new Date(date2.getFullYear(), date2.getMonth(), date2.getDate());
 const diff = date2.getTime() - date1.getTime();
 const diffDate = diff / (24 * 60 * 60 * 1000);
 return `宝贝，这是我们在一起的${diffDate}天`
}

接口调用

var express=require('express');
var app=express();
const api = require('./crawer.js')
app.get('/words',async function(req,res){
 let dateTips = api.getDiffDate()
 let weather = await api.getWeatherTips()
 let words = await api.getDailyGreeting()
 let str =`${dateTips}\n${weather}\n${words}`
 res.writeHead(200, {'Content-Type': 'application/json; charset=utf-8'})
 res.end(str)
})
var server = app.listen(8083, function () { // 启动ip和端口
 var port = server.address().port
 console.log("应用实例，访问地址为 http://%s:%s", port)
})

总结