pyppeteer 在debugging状态下驱动chrome浏览器

1.以命令窗口启动chrome浏览器，选择远程连接的端口为9222

chrome.exe --disable-infobars --remote-debugging-port=9222 --user-data-dir="设置路径"

 --disable-infobars 表示关闭提示

2. 启动之后chromium通过http://localhost:9222/json得到调试信息，chrome通过http://127.0.0.1:9222/json/version  得到调试信息，

其中webSocketDebuggerUrl为pyppeteer连接的ws地址。

页面显示为

{
   "Browser": "Chrome/78.0.3904.70",
   "Protocol-Version": "1.3",
   "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36",
   "V8-Version": "7.8.279.17",
   "WebKit-Version": "537.36 (@edb9c9f3de0247fd912a77b7f6cae7447f6d3ad5)",
   "webSocketDebuggerUrl": "ws://127.0.0.1:9222/devtools/browser/8fc97fd6-a7dd-4ff2-b760-3f6b25b7419b"
}

3.案例

import asyncio
import random
from pyppeteer.launcher import connect


useragents=['Mozilla/5.0 (Windows NT 6.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36','Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36','Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36','Mozilla/5.0 (Windows NT 6.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36','Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36']

async def main(url):
    connect_params={
        'browserWSEndpoint': 'ws://127.0.0.1:9222/devtools/browser/8fc97fd6-a7dd-4ff2-b760-3f6b25b7419b',
'logLevel':3,
    }
    browser = await connect(connect_params)
    page = await browser.newPage()   # 启动个新的浏览器页面
    await page.setUserAgent(random.choice(useragents))
    #设置页面超时时间
    page.setDefaultNavigationTimeout(1000*60) #60s
    #启用js
    await page.setJavaScriptEnabled(True)
    await page.setViewport({'width':1300,'height':750}) #设置界面
    try:
        await page.goto(url)    # 访问登录页面
    except Exception as e1:
        print('e1:',e1)
        await page.close()
        await browser.close()
        return
  

if __name__ == '__main__':
    loop = asyncio.get_event_loop()
    url = 'https://www.baidu.com'
    m = main(url)
    loop.run_until_complete(m)

 #方式2

from anti_useragent import UserAgent
ua=UserAgent(platform='windows',min_version=80)
import asyncio
from pyppeteer.launcher import connect
import json
async def main():
    port=9222
    options = {'browserURL': f'http://127.0.0.1:{port}/json/version'}
    browser = await connect(options=options)
    page = await browser.newPage()  # 启动个新的浏览器页面
    page.setDefaultNavigationTimeout(1000 * 60)  # 60s
    await page.setUserAgent(ua.chrome)
    await page.goto('https://www.baidu.com')

loop = asyncio.get_event_loop()
loop.run_until_complete(main())