npm i puppeteer

const puppeteer = require('puppeteer');

(async () => { "external nofollow" target="_blank" href="https://peter.sh/experiments/chromium-command-line-switches/">点此查看

使用示例如下：


const browser = await puppeteer.launch({headless:false, args: ["--no-sandbox",]}) //打开浏览器


打开新的窗口：


const page = await browser.newPage();


设置窗口大小


await page.setViewport({
 width: 1920,
 height: 1080
})


过滤不需要的请求：


await page.setRequestInterception(true);
page.on('request', interceptedRequest => {
 if (interceptedRequest.url().endsWith('.png') || interceptedRequest.url().endsWith('.jpg'))
  interceptedRequest.abort();
 else
  interceptedRequest.continue();
});


为浏览器设置userAgent：


await page.setUserAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299")


设置cookie，


const data = {
 name: "smidB2", 
 domain: ".csdn.net", 
 value: "201806051502283cf43902aa8991a248f9c605204f92530032f23ef22c16270"
}
await page.setCookie(data)


示例中只是演示，真实的cookie是一个列表形式的，需要循环添加才可以


for(let data of cookies){
 await page.setCookie(data)
}


请求url：


const url = "http://www.baidu.com"
await page.goto(url, { waitUntil: "networkidle2" });


设置页面等待时间：


await page.waitFor(1000); // 单位是毫秒


等待页面某个元素加载完成


await page.waitForSelector("input[class='usrname']")


点击某个元素


await page.click("input[class='submit']")


利用page.evaluate()函数拖动鼠标至页面底部，原理就是在页面注入js代码。


let scrollEnable = false;
let scrollStep = 500; //每次滚动的步长
while (scrollEnable) {
	scrollEnable = await page.evaluate((scrollStep) => {
		let scrollTop = document.scrollingElement.scrollTop;
		document.scrollingElement.scrollTop = scrollTop + scrollStep;
		return document.body.clientHeight > scrollTop + 1080 "htmlcode">

const frame = await page.mainFrame()
const bodyHandle = await frame.$('html');
const html = await frame.evaluate(body => body.innerHTML, bodyHandle);
await bodyHandle.dispose(); //销毁 
console.log(html)  


这是爬虫能用到的大致操作，以下是爬取豆瓣热门电影的基本信息和评分的代码，写这个程序时对node也是一知半解，如有不对，欢迎留言
basePupp.js


const puppeteer = require("puppeteer")

class BasePuppeteer{
 puppConfig(){
  const config = {
   headless: false
  }
  return config
 }
 async openBrower(setting){
  const browser = puppeteer.launch(setting)
  return browser
 }
 async openPage(browser){
  const page = await browser.newPage()
  return page
 }
 async closeBrower(browser){
  await browser.close()
 }
 async closePage(page){
  await page.close()
 }
}

const pupp = new BasePuppeteer()
module.exports = pupp


douban.js


const pupp = require("./basePupp.js")
const cheerio = require("cheerio")
const mongo = require("mongodb")
const assert = require("assert")

const MongoClient = mongo.MongoClient
const Urls = "mongodb://10.4.251.129:27017/douban"

MongoClient.connect(Urls, function (err, db) {
 if (err) throw err;
  console.log('数据库已创建');
 var dbase = db.db("runoob");
 dbase.createCollection('detail', function (err, res) {
  if (err) throw err;
  console.log("创建集合!");
  db.close();
 });
});

async function getList(){
 const brower = await pupp.openBrower()
 const page = await pupp.openPage( brower)
 const url = "https://movie.douban.com/explore#!type=movie&tag=%E7%83%AD%E9%97%A8&sort=recommend&page_limit=20&page_start=0"
 await page.goto(url);
 while(true){           // 循环点击, 直到获取不到该元素
  try{
   await page.waitFor(1000); 
   await page.waitForSelector('a[class=more]'); // 等待元素加载完成，超时时间30000ms
   await page.click("a[class=more]")
   // break
  }catch(err){
   console.log(err)
   console.log("stop click !!!")
   break
  }
 } 
 await page.waitFor(1000);        // 等待页面一秒
 const links = await page.evaluate(() => {    // 获取电影详情url
  let movies = [...document.querySelectorAll('.list a[class=item]')];
  return movies.map((movie) =>{
   return {
    href: movie.href.trim(),
   }
  });
 });
 console.log(links.length)
 for (var i = 0; i < links.length; i++) {
  const a = links[i];
  await page.waitFor(2000); 
  await getDetail(brower, a.href)
  // break
 }
 await pupp.closePage(page)
 await pupp.closeBrower(brower)
 
}

async function getDetail(brower, url){
 const page = await pupp.openPage(brower)
 await page.goto(url);
 await page.waitFor(1000); 
 try{
  await page.click(".more-actor", {delay: 20})
 }catch(err){
  console.log(err)
 }
 const frame = await page.mainFrame()
 const bodyHandle = await frame.$('html');
 const html = await frame.evaluate(body => body.innerHTML, bodyHandle);
 await bodyHandle.dispose();      // 销毁      
 const $ = cheerio.load(html)
 const title = $("h1 span").text().trim()
 const rating_num = $(".rating_num").text().trim()
 const data = {}
 data["title"] = title
 data["rating_num"] = rating_num
 let info = $("#info").text()
 const keyword = ["director", "screenplay", "lead", "type", "website", "location", "language", "playdate", "playtime", "byname", "imdb"]
 if (info.indexOf("www.") > 0){
  info = info.replace(/https:\/\/|http:\/\//g, "").replace(/\t/g," ").replace(/\r/g, " ").split(":")
  for(var i = 1; i < info.length; i++){
   data[keyword[i-1]] = info[i].split(/\n/g)[0].replace(/ \/ /g, ",").trim()
  }

 }else{
  info = info.replace(/\t/g," ").replace(/\r/g, " ").split(":")
  keyword.splice(4,1)
  for(var i = 1; i < info.length-1; i++){
   data[keyword[i-1]] = info[i].split(/\n/g)[0].replace(/ \/ /g, ",").trim()
  }
  data["website"] = ""
 }
 // console.log(data)
 MongoClient.connect(Urls,function(err,db){       //获取连接
  assert.equal(null,err);           //使用断言模块代替以前的 if判断
  var dbo = db.db("douban");
  dbo.collection("detail").insert(data, function(err,result){  //连接到数据库上面，并使用参数传入集合
   assert.equal(null,err);
   console.log(result);
   db.close();
  });
 });
 await pupp.closePage(page)
}

getList()


以上的代码完成了对豆瓣热门电影的全部抓取，有以下几个步骤：
1， 循环点击加载更多，直到没有此元素可操作而抛出异常
2，加载完全部热门电影列表时解析出每个电影详情页的url并逐一请求
3， 解析详情页的所需数据，
4，对所抓取数据进行入库，这里使用MongoDB
入库后的数据如下所示：



对以上的浏览器实例化做了优化，写成了单例模式
config.js


module.exports = {
 browserOptions:{
 headless: false,
 // args: ['--no-sandbox', '--proxy-server=http://proxy:abc100@cp.test.com:8995'],
 args: ['--no-sandbox'],
 }
};


brower.js


const puppeteer = require("puppeteer");
const config = require('./config');//
const deasync = require('deasync');
const BROWSER_KEY = Symbol.for('browser');
const BROWSER_STATUS_KEY = Symbol.for('browser_status');

launch(config.browserOptions)
wait4Lunch();

/**
 * 启动并获取浏览器实例
 * @param {*} options
 * param options is puppeteer.launch function's options
 */
function launch(options = {}) {
 if (!global[BROWSER_STATUS_KEY]) {
 global[BROWSER_STATUS_KEY] = 'lunching';
 puppeteer.launch(options)
  .then((browser) => {
  global[BROWSER_KEY] = browser;
  global[BROWSER_STATUS_KEY] = 'lunched';
  })
  .catch((err) => {
  global[BROWSER_STATUS_KEY] = 'error';
  throw err;
  });
 }
}

function wait4Lunch(){
 while (!global[BROWSER_KEY] && global[BROWSER_STATUS_KEY] == 'lunching') {
 // wait for lunch
 deasync.runLoopOnce();
 }
}
module.exports = global[BROWSER_KEY];


以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。