webdriver反爬

'''
webdriver反爬虫
通过selenum操作会被浏览器识别是否为webdriver=true
识别出来即判断为爬虫
案例一：http://www.porters.vip/features/webdriver.html
案例二：淘宝登录中https://login.taobao.com/member/login.jhtml
index.js中存在如下验证：
function r() {
            return "$cdc_asdjflasutopfhvcZLmcfl_"in u || f.webdriver
        }
解决方法：
方法一、修改navigator.webdriver里的js
script = 'Object.defineProperty(navigator,"webdriver",{get:() => false,})'
browser.execute_script(script)
方法二、通过mitmproxy代理绕过
'''
import asyncio
import time

from pyppeteer import launch
from selenium.webdriver import Chrome


class WebdriverSpider:
    @classmethod
    def get_webdriver_spider(cls):
        return cls()

    def chrome_driver(self):
        browser = Chrome(r'E:\tool\chromedriver_win32\chromedriver.exe')
        browser.get('http://www.porters.vip/features/webdriver.html')
        # 执行一段js，设置navigator的webdriver
        script = 'Object.defineProperty(navigator,"webdriver",{get:() => false,})'
        browser.execute_script(script)
        browser.find_element_by_xpath("//button[@class='btn btn-primary btn-lg']").click()
        elements = browser.find_element_by_xpath("//div[@class='modal-content']")
        print(elements.text)
        time.sleep(10)
        browser.close()

    def run(self):
        self.chrome_driver()


async def main():
    browser = await launch()
    page = await browser.newPage()
    await page.goto('http://www.porters.vip/features/webdriver.html')
    await page.click('.btn.btn-primary.btn-lg')
    await asyncio.sleep(1)
    await page.screenshot({'path': 'webdriver.png'})
    await browser.close()


if __name__ == '__main__':
    WebdriverSpider.get_webdriver_spider().run()
    # asyncio.get_event_loop().run_until_complete(main())

--反爬虫原理与绕过