关于node请求数据爬取网易云数据

在用node爬取网易云音乐信息时候在很多地方是不如python简单方便

但是下面的这个案例会报错

再读文档时候源码有些地方出错要改源码 (不建议更改源码)

const fs = require("fs")

const cheerio = require("cheerio")

const Nightmare = require('nightmare')

const nightmare = Nightmare({ show: true, openDevTools: { mode: 'detach' } })

let home_url = "https://music.163.com/#/discover/artist/cat?id=1002"

nightmare

.goto(home_url)

.click(".m-cvrlst li:nth-child(2) a", () => { // 这个地方要想不报错只能从源码更改

console.log("点击完了......")

setTimeout(() => {

console.log("新界面....")

nightmare.goto("https://music.163.com/#/artist?id=8103")

.evaluate(() => {

return document.querySelector(".g-iframe").contentWindow.document.querySelector("body").innerHTML

})

.then((data) => {

console.log("开始查询.,,....")

let $ = cheerio.load(data)

let songs = []

$(".m-table tr .txt a").each((i, item) => {

let song_id = $(item).attr("href")

let song_name = $(item).find("b").attr("title")

let tmp_dic = {

"song_id": song_id,

"song_name": song_name

}

songs.push(tmp_dic)

})

let songs_string = JSON.stringify(songs)

let file_name = "./test" + $(".sname-max").text() + ".json"

fs.writeFile(file_name, songs_string, () => {

})

}, 2000);

})

.then(() => {

})

//------------------------------------------------------

//下面是源码

从源码做了一些更改

xports.click = function(selector, done) {

debug('.click() on ' + selector)

this.evaluate_now(

function(selector) {

document.activeElement.blur()

// var element = document.querySelector(selector)

var element = ""

if(document.querySelector(".g-iframe").contentWindow.document) {

element = document.querySelector(".g-iframe").contentWindow.document.querySelector(selector)

}else{

var element = document.querySelector(selector)

}

if (!element) {

throw new Error('Unable to find element by selector: ' + selector)

}

原文地址：https://www.cnblogs.com/bl11-07/p/11396727.html

关于node请求数据 爬取网易云数据

关于node请求数据爬取网易云数据