node crawling resources on the returned data - Music

Crawling music website

页面源代码无数据,数据在返回的资源中

在返回数据中,找到所要资源,在Headers中找到请求的地址

爬取音乐步骤:
获取音乐src等信息->按流的方式请求src地址,再流写入文件

Code Example:

const axios=require('axios')
const fs=require('fs')
const path=require('path')

//获取单个页面数据
async function getPage(num){
	let httpUrl='http://www.app-echo.com/api/recommend/sound-day?page='+num;
	let res= await axios.get(httpUrl)
	//循环音乐列表,获取音乐数据
	res.data.list.forEach(function(item,index){
		let title=item.sound.name;
		let mp3Url=item.sound.source;
		let filename=path.parse(mp3Url).name;

		let info=`${title},${mp3Url},${filename}`
		fs.writeFile('C:/Users/10853/Desktop/爬虫music.txt',info,{flag:'a'},function(err){
			console.log('ok');
		})
		console.log('歌名:'+filename);
		console.log('歌曲:'+mp3Url);
		download(mp3Url,filename);
	})
}

//下载音乐资源,流的形式
async function download(url,filename){
	let res=await axios.get(url,{responseType:'stream'})
	let extname=path.extname(url);
	let ws=fs.createWriteStream('C:/Users/10853/Desktop/爬虫music/'+filename+'.mp3');
	res.data.pipe(ws)
	res.data.on('close',function(){
		ws.end();
	})
}

getPage(2);