如何重用 selenium 浏览器会话

Question

我正在尝试从单独的 python 进程访问现有的 selenium 浏览器会话。我能够在同一个 python 脚本中实现它，但是当我将重用逻辑分解为一个单独的脚本时，它失败并显示错误消息：

Traceback (most recent call last):
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py", line 1318, in do_open
    encode_chunked=req.has_header('Transfer-encoding'))
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1239, in request
    self._send_request(method, url, body, headers, encode_chunked)
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1285, in _send_request
    self.endheaders(body, encode_chunked=encode_chunked)
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1234, in endheaders
    self._send_output(message_body, encode_chunked=encode_chunked)
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1026, in _send_output
    self.send(msg)
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 964, in send
    self.connect()
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 936, in connect
    (self.host,self.port), self.timeout, self.source_address)
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/socket.py", line 722, in create_connection
    raise err
  File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/socket.py", line 713, in create_connection
    sock.connect(sa)
ConnectionRefusedError: [Errno 61] Connection refused

这是尝试从单独的脚本访问现有会话的代码（这是生成错误的代码）。现在我每次都手动更新 session_id 和 executor 值：

""" module docstring """
import time
from selenium import webdriver

def main():
  """ reuse window in different scripts """
  # driver = webdriver.Chrome()
  session_id = '7b10acc2c99d90a68fecb71e5e481c0f'
  # executor_url = 'http://127.0.0.1:9515'
  executor_url = 'http://127.0.0.1:54467'

  print(session_id)
  print(executor_url)

  driver2 = webdriver.Remote(command_executor=executor_url,
                             desired_capabilities={})

  print('driver instance created')
  driver2.session_id = session_id
  print(driver2.current_url)
  driver2.get('http://www.yahoo.com')

  time.sleep(10)

if __name__ == '__main__':
  main()

这是设置初始浏览器会话的代码：

""" module docstring """
import time
from selenium import webdriver

def main():
  """ reuse window in different scripts """
  driver = webdriver.Chrome()
  executor_url = driver.command_executor._url # pylint: disable=W0212
  session_id = driver.session_id
  driver.get("http://tarunlalwani.com")

  print(session_id)
  print(executor_url)

  time.sleep(300)

if __name__ == '__main__':
  main()

这是成功改变现有浏览器 window 的脚本，但它来自同一个 python 脚本：

""" module docstring """
import time
from selenium import webdriver

def main():
  """ reuse window in same script """
  driver = webdriver.Chrome()
  executor_url = driver.command_executor._url # pylint: disable=W0212
  session_id = driver.session_id
  driver.get("http://tarunlalwani.com")

  print(session_id)
  print(executor_url)

  driver2 = webdriver.Remote(command_executor=executor_url,
                             desired_capabilities={})
  driver2.session_id = session_id
  print(driver2.current_url)
  driver2.get('http://www.yahoo.com')

  time.sleep(300)

if __name__ == '__main__':
  main()

Answer 1

这是一个使用单文件解决方案的示例，但它也适用于双文件解决方案。

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from multiprocessing import Process
import time

# The main process calls this function to create the driver instance.
def createDriverInstance():
    options = Options()
    options.add_argument('--disable-infobars')
    driver = webdriver.Chrome(chrome_options=options, port=9515)
    return driver

# Called by the second process only.
def secondProcess(executor_url, session_id):
    options = Options()
    options.add_argument("--disable-infobars")
    options.add_argument("--enable-file-cookies")
    capabilities = options.to_capabilities()
    same_driver = webdriver.Remote(command_executor=executor_url, desired_capabilities=capabilities)
    same_driver.close()
    same_driver.session_id = session_id
    same_driver.get("https://www.wikipedia.org")
    time.sleep(4)
    same_driver.quit()

if __name__ == '__main__':
    driver = createDriverInstance()
    driver.get("https://google.com")
    time.sleep(2)

    # Pass the driver session and command_executor to the second process.
    p = Process(target=secondProcess, args=(driver.command_executor._url,driver.session_id))
    p.start()

Answer 2

如果你想要终极性能，你可以让Selenium作为一个HTTP服务器来接收命令。示例：

# Created by BaiJiFeiLong@gmail.com at 2022/1/29 11:58

import threading

import flask
import requests
import selenium.webdriver

app = flask.Flask(__name__)


@app.post("/")
def home():
    return str(driver.execute_script(flask.request.data.decode()))


threading.Thread(target=lambda: app.run(host="127.0.0.1", port=5000)).start()
driver = selenium.webdriver.Chrome()

print("1+1=", requests.post("http://localhost:5000", "return 1+1").text)
print("userAgent=", requests.post("http://localhost:5000", "return navigator.userAgent").text)

如何重用 selenium 浏览器会话

How to reuse a selenium browser session

python

python-3.x

selenium

selenium-chromedriver

selenium-rc