Playwright反爬虫

官方文档

使用默认方式控制浏览器

安装chromium浏览器

cmd执行如下代码

python -m playwright install

生成文件stealth.min.js

安装nodejs，执行如下代码，则会在环境根目录下生成stealth.min.js文件

npx extract-stealth-evasions

执行代码

import time
from playwright.sync_api import sync_playwright
from playwright.sync_api import Page
playwright = sync_playwright().start()
# 过检测方法1：--disable-blink-features=AutomationControlled
browser = playwright.chromium.launch(
    headless=False, 
    args=['--disable-blink-features=AutomationControlled'],
    # 指定浏览器
    # executable_path=r"C:\Program Files (x86)\Microsoft\Edge\Application\msedge.exe",
)
# 过检测方法2：stealth.min.js
context = browser.new_context(viewport={'width': 1920, 'height': 1080})
context.add_init_script(path=r'c:\Users\zghmvp\Desktop\stealth.min.js')
# 测试
page = context.new_page()
page.goto('https://bot.sannysoft.com/')
time.sleep(5)
page.evaluate('''window.open("https://bot.sannysoft.com/")''')
browser.close()

使用cdp链接已打开的浏览器

import time
from playwright.sync_api import sync_playwright
from playwright.sync_api import Page
from playwright.sync_api import Response
playwright = sync_playwright().start()
# 浏览器快捷方式：C:\xxx\chrome.exe --remote-debugging-port=9222
browser = playwright.chromium.connect_over_cdp('http://localhost:9222')
context = browser.contexts[0] # 获取默认的上下文
# context.add_init_script(path=r'c:\Users\zghmvp\Desktop\stealth.min.js')
# 添加监听
def on_response(response: Response):
    print(response.url)
    # print(response.json())
    # print(response.text())
    # print(response.body())
context.on('response', on_response)
# 测试
page = context.new_page()
page.goto('https://bot.sannysoft.com/')
time.sleep(10)
page.close()