puppeteer 小项目初体验

puppeteer是谷歌推出的无头浏览器框架，提供了完备的api用于控制浏览器
以爬取某资源网站为例，简单使用puppeteer

这里使用页面获取的代码需要实现两部分，即打开网页，然后点击获取地址的按钮，最后获取链接地址和提取密码并返回。打开网页部分可以通过暴力枚举数字即可。

const puppeteer = require('puppeteer-core')
const cheerio = require('cheerio')
const sleep = () => new Promise((res, rej) => setTimeout(res, 2000));

async function crawlXXX(url){
    var brower = puppeteer.launch({
        headless:true,
        executablePath:'你的chrome.exe地址'
    });
    var page = await (await brower).newPage();
    try{
        page.setDefaultTimeout(2 * 60 * 1000);
        page.setUserAgent('Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.130 Safari/537.36');
        page.setJavaScriptEnabled(true);
        page.setCacheEnabled(true);
        await page.goto(url);
        await page.waitForSelector('html');   
        let button = await page.$('.data_details > div > .btn-primary'); // 获取按钮
        button.click();
        let title = await page.title();
        let link = await page.$eval('.bs-example-modal-sm > .modal-sm > .modal-content > a > font',el=>el.innerHTML); 
        let pass = await page.$eval('.bs-example-modal-sm > .modal-sm > .modal-content > font',el=>el.innerHTML);
        return {link,pass,title};
    }catch(err){
        console.error(err);
    }
    finally{
        (await brower).close();
    }
}

class crawlSiteController{
    static async getSite(ctx){
        let req = ctx.request.body;
        var type = req.type;
        if(type === 1){
            let num = req.num;
           let url = 'http://xxxx.xxxxxx.xxxx/article/';
            let res = await crawlXXX(url+num);
            ctx.response.status = 200;
            ctx.response.body = res
        }
    }
}

module.exports = crawlSiteController;