使用 puppeteer 绕过 Headless Chrome 的验证码

Question

google 发现我的浏览器正在被软件 manipulated/controlled/automated，因此我得到 reCaptcha。当我手动启动铬并执行相同的步骤时，reCaptcha 不会出现。

Question 1)

在使用 puppeteer 时是否可以通过编程方式解决验证码或摆脱它？有什么办法可以解决这个问题？

Question 2)

只有在没有 headless 选项时才会发生这种情况 i.e

const browser = await puppeteer.launch({
  headless: false
})

或者这是我们必须接受并继续前进的事实？

Answer 1

您试过设置浏览器代理吗？

await page.setUserAgent('5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36');

Answer 2

尝试使用此 npm package 生成随机用户代理。这通常解决了基于用户代理的保护。

在 puppeteer 页面中可以使用 page.setUserAgent

覆盖浏览器用户代理

var userAgent = require('user-agents');
...
await page.setUserAgent(userAgent.toString())

此外，您可以添加这两个额外的插件，

puppeteer-extra-plugin-recaptcha - 使用单行代码自动解决 reCAPTCHA：page.solveRecaptchas()

注意：puppeteer-extra-plugin-recaptcha 使用付费服务 2captcha

puppeteer-extra-plugin-stealth - 应用各种规避技术使无头木偶操纵者的检测更加困难。

Answer 3

以下是我为绕过验证码和类似阻止所做的事情的列表：

启用隐身模式（通过puppeteer-extra-plugin-stealth）
随机化 User-agent 或设置一个有效的（通过 random-useragent）
随机化视口大小
跳过 images/styles/fonts 加载以获得更好的性能
通过“WebDriver 检查”
通过“Chrome检查”
通过“通知检查”
通过“插件检查”
通过“语言检查”

    const randomUseragent = require('random-useragent');

    //Enable stealth mode
    const puppeteer = require('puppeteer-extra')
    const StealthPlugin = require('puppeteer-extra-plugin-stealth')
    puppeteer.use(StealthPlugin())
    
    const USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.75 Safari/537.36';
    
    async function createPage (browser,url) {

        //Randomize User agent or Set a valid one
        const userAgent = randomUseragent.getRandom();
        const UA = userAgent || USER_AGENT;
        const page = await browser.newPage();

        //Randomize viewport size
        await page.setViewport({
            width: 1920 + Math.floor(Math.random() * 100),
            height: 3000 + Math.floor(Math.random() * 100),
            deviceScaleFactor: 1,
            hasTouch: false,
            isLandscape: false,
            isMobile: false,
        });

        await page.setUserAgent(UA);
        await page.setJavaScriptEnabled(true);
        await page.setDefaultNavigationTimeout(0);

        //Skip images/styles/fonts loading for performance
        await page.setRequestInterception(true);
        page.on('request', (req) => {
            if(req.resourceType() == 'stylesheet' || req.resourceType() == 'font' || req.resourceType() == 'image'){
                req.abort();
            } else {
                req.continue();
            }
        });

        await page.evaluateOnNewDocument(() => {
            // Pass webdriver check
            Object.defineProperty(navigator, 'webdriver', {
                get: () => false,
            });
        });

        await page.evaluateOnNewDocument(() => {
            // Pass chrome check
            window.chrome = {
                runtime: {},
                // etc.
            };
        });

        await page.evaluateOnNewDocument(() => {
            //Pass notifications check
            const originalQuery = window.navigator.permissions.query;
            return window.navigator.permissions.query = (parameters) => (
                parameters.name === 'notifications' ?
                    Promise.resolve({ state: Notification.permission }) :
                    originalQuery(parameters)
            );
        });

        await page.evaluateOnNewDocument(() => {
            // Overwrite the `plugins` property to use a custom getter.
            Object.defineProperty(navigator, 'plugins', {
                // This just needs to have `length > 0` for the current test,
                // but we could mock the plugins too if necessary.
                get: () => [1, 2, 3, 4, 5],
            });
        });

        await page.evaluateOnNewDocument(() => {
            // Overwrite the `languages` property to use a custom getter.
            Object.defineProperty(navigator, 'languages', {
                get: () => ['en-US', 'en'],
            });
        });

        await page.goto(url, { waitUntil: 'networkidle2',timeout: 0 } );
        return page;
    }

Answer 4

经过几次测试，有几个软件包帮助我避免了重新验证：

//const puppeteer = require('puppeteer');
const puppeteerExtra = require('puppeteer-extra');
const pluginStealth = require('puppeteer-extra-plugin-stealth');
const randomUseragent = require('random-useragent');

class PuppeteerService {

    constructor() {
        this.browser = null;
        this.page = null;
        this.pageOptions = null;
        this.waitForFunction = null;
        this.isLinkCrawlTest = null;
    }

    async initiate(countsLimitsData, isLinkCrawlTest) {
        this.pageOptions = {
            waitUntil: 'networkidle2',
            timeout: countsLimitsData.millisecondsTimeoutSourceRequestCount
        };
        this.waitForFunction = 'document.querySelector("body")';
        puppeteerExtra.use(pluginStealth());
        //const browser = await puppeteerExtra.launch({ headless: false });
        this.browser = await puppeteerExtra.launch({ headless: false });
        this.page = await this.browser.newPage();
        await this.page.setRequestInterception(true);
        this.page.on('request', (request) => {
            if (['image', 'stylesheet', 'font', 'script'].indexOf(request.resourceType()) !== -1) {
                request.abort();
            } else {
                request.continue();
            }
        });
        this.isLinkCrawlTest = isLinkCrawlTest;
    }

    async crawl(link) {
        const userAgent = randomUseragent.getRandom();
        const crawlResults = { isValidPage: true, pageSource: null };
        try {
            await this.page.setUserAgent(userAgent);
            await this.page.goto(link, this.pageOptions);
            await this.page.waitForFunction(this.waitForFunction);
            crawlResults.pageSource = await this.page.content();
        }
        catch (error) {
            crawlResults.isValidPage = false;
        }
        if (this.isLinkCrawlTest) {
            this.close();
        }
        return crawlResults;
    }

    close() {
        if (!this.browser) {
            this.browser.close();
        }
    }
}

const puppeteerService = new PuppeteerService();
module.exports = puppeteerService;

使用 puppeteer 绕过 Headless Chrome 的验证码

Bypassing CAPTCHAs with Headless Chrome using puppeteer

javascript

node.js

puppeteer