第二章 puppeteer

1-1 简单实用

const puppeteer = require("puppeteer");
const url = "http://www.kuwo.cn/search/list?key=你";
(async ()=>{
    const browser = await puppeteer.launch({
        headless:false,  //模拟浏览器行为
        defaultViewport:null, //可视区域最大化
          args: ['--start-maximized'], //浏览器窗口最大化
        ignoreDefaultArgs:['--enable-automation--'] //忽略验证
    });
    const page = await browser.newPage();
    await page.goto(url)
    await page.waitFor(9000) //页面等待9s
    await page.screenshot({
        path:"douban.png"
    })
    await browser.close()
})();

1-2 爬虫 puppeteer+cheerio爬取酷我

const puppeteer = require("puppeteer");
const cheerio = require("cheerio")
const url = "http://www.kuwo.cn/search/list?key=浪子闲话";
(async () => {
    const browser = await puppeteer.launch({
        headless: false,
        args: ['--start-maximized'],
        defaultViewport: null
    });
    const page = await browser.newPage();
    await page.goto(url, {
        waitUntil: 'networkidle2'
    })
    await page.waitForTimeout(3000)
    await page.hover(".search_list")
    var content  = await page.content();
    var $ = cheerio.load(content,{
        decodeEntities:false
    })
    var title = $(".song_name").find(".name").html()
    console.log(title)
    await browser.close()
})();

1-3 evaluate

const puppeteer = require('puppeteer');
(async () => {
    /* 1.新建一个浏览器的实例 */
  const browser = await puppeteer.launch({
      headless:false,
      defaultViewport:null
  });
  /* 2.新建一个页面 */
  const page = await browser.newPage();
  /* 3.到达某个页面 */
  await page.goto('https://movie.douban.com/top250');
  /* 4.在页面停顿3s */
  await page.waitForTimeout(1000)
  /* 5.evaluate可以获取页面内容 */
  var res = await page.evaluate(()=>{
    var $ = window.jQuery;
    var content  = $("#content h1").html();
    return content
  })
  console.log(res)
  await browser.close();
})();