selenium 切换标签页解决 get 超时问题

从 gif 直观地感受一下效果

我有大量 url 需要访问，但是有些 url 会超时

为了避免超时，设置driver.set_page_load_timeout(3)限时3秒，一旦超时就会产生 TimeoutException

而且超时后标签页就卡柱了，只能通过 driver.close()关闭

如果你只有一个标签页，关闭就直接退出了，还得重启

自然想到先保留一个备用的标签，原标签超时需要关闭的时候就切换过来，然后再关闭，并打开新标签，保证任何时候都有两个标签页可用！！

def visit(urls, timeout=3):
    driver.implicitly_wait(timeout) # 操作、获取元素时的隐式等待时间
    driver.set_page_load_timeout(timeout) # 页面加载超时等待时间
    
    main_win = driver.current_window_handle
    
    for url in urls:
        all_win = driver.window_handles
        try:
            if len(all_win) == 1:
                driver.execute_script('window.open();')
            driver.get(url)
            # 页面处理
            pass
            
        except Exception:
            for win in all_win:
                if main_win != win:
                    driver.close()  # 关闭卡住的标签
                    driver.switch_to.window(win)  # 切换到备用标签
                    main_win = win  # 切换到备用标签
                    break

完整代码

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.chrome.options import Options
import time
import requests
import zipfile
import os

def un_zip(file_name, to_dir='./'):
    """unzip zip file"""
    zip_file = zipfile.ZipFile(file_name)
    if os.path.isdir(to_dir):
        pass
    else:
        os.mkdir(to_dir)
    for names in zip_file.namelist():
        zip_file.extract(names, to_dir)
    zip_file.close()

    
def download_driver(to_dir='./', version=''):
    print('install chrome-driver first')
    url = 'http://npm.taobao.org/mirrors/chromedriver/LATEST_RELEASE'
    if len(version)>0:
        url = 'http://npm.taobao.org/mirrors/chromedriver/LATEST_RELEASE_'+version
        
    version = requests.get(url).content.decode('utf8')
    driver_file = 'http://npm.taobao.org/mirrors/chromedriver/' + version + '/chromedriver_win32.zip'
    r = requests.get(driver_file)
    download_zip = "chromedriver_win32.zip"
    with open(download_zip, "wb") as code:
        code.write(r.content)
    un_zip(download_zip,  to_dir)
    os.remove(download_zip)


try:
    driver = webdriver.Chrome()
except Exception as e:
    download_driver(to_dir='./', version='76')
    driver = webdriver.Chrome()

with open("url.txt", 'r') as file:
    urls = [ line.strip('\n') for line in file.readlines()]

visit(urls)

for i in driver.window_handles:
    driver.switch_to.window(i)
    driver.close()