在通过Python使用硒进行多处理时，Chrome会在几个小时后崩溃

Question

The process started from chrome location /usr/bin/google-chrome is no longer running, so ChromeDriver is assuming that Chrome has crashed.

#scrape.py
from selenium.common.exceptions import *
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.chrome.options import Options

def run_scrape(link):
    chrome_options = Options()
    chrome_options.add_argument('--no-sandbox')
    chrome_options.add_argument("--headless")
    chrome_options.add_argument('--disable-dev-shm-usage')
    chrome_options.add_argument("--lang=en")
    chrome_options.add_argument("--start-maximized")
    chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
    chrome_options.add_experimental_option('useAutomationExtension', False)
    chrome_options.add_argument("user-agent=Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36")
    chrome_options.binary_location = "/usr/bin/google-chrome"
    browser = webdriver.Chrome(executable_path=r'/usr/local/bin/chromedriver', options=chrome_options)
    browser.get(<link passed here>)
    try:
        #scrape process
    except:
        #other stuffs
    browser.quit()

#multiprocess.py
import time,
from multiprocessing import Pool
from scrape import *

if __name__ == '__main__':
    start_time = time.time()
    #links = list of links to be scraped
    pool = Pool(20)
    results = pool.map(run_scrape, links)
    pool.close()
    print("Total Time Processed: "+"--- %s seconds ---" % (time.time() - start_time))

ChromeDriver 79.0.3945.36 (3582db32b33893869b8c1339e8f4d9ed1816f143-refs/branch-heads/3945@{#614})
Google Chrome 79.0.3945.79
Selenium Version: 4.0.0a3

我想知道为什么chrome正在关闭，而其他进程正在工作？

Answer 1

我使用了您的代码，对其进行了一些修改以适应我的测试环境，下面是执行结果：

>

代码块：

>

multiprocess.py:

import time
from multiprocessing import Pool
from multiprocessingPool.scrape import run_scrape

if __name__ == '__main__':
    start_time = time.time()
    links = ["https://selenium.dev/downloads/", "https://selenium.dev/documentation/en/"] 
    pool = Pool(2)
    results = pool.map(run_scrape, links)
    pool.close()
    print("Total Time Processed: "+"--- %s seconds ---" % (time.time() - start_time)) 

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException, TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options

def run_scrape(link):
    chrome_options = Options()
    chrome_options.add_argument('--no-sandbox')
    chrome_options.add_argument("--headless")
    chrome_options.add_argument('--disable-dev-shm-usage')
    chrome_options.add_argument("--lang=en")
    chrome_options.add_argument("--start-maximized")
    chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
    chrome_options.add_experimental_option('useAutomationExtension', False)
    chrome_options.add_argument("user-agent=Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36")
    chrome_options.binary_location=r'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe'
    browser = webdriver.Chrome(executable_path=r'C:\Utility\BrowserDrivers\chromedriver.exe', options=chrome_options)
    browser.get(link)
    try:
        print(browser.title)
    except (NoSuchElementException, TimeoutException):
        print("Error")
    browser.quit()

Downloads
The Selenium Browser Automation Project :: Documentation for Selenium
Total Time Processed: --- 10.248600006103516 seconds ---