当前位置：首页 > news >正文

python selenium 打开网页

news 来源：原创 2024/7/4 13:18:56

selenium工具类 - 文件名 seleniumkit.py

代码如下

# -*- coding:utf-8 _*-from selenium import webdriverimport os
import timefrom selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import Byfrom selenium.webdriver.chrome.service import Service# 打开网页,会呼出浏览器
def seleniumOpenUrl(initUrl):chrome_options = webdriver.ChromeOptions()chrome_options.add_argument('---ignore-certificate-errors-spki-list')chrome_options.add_argument('--ignore-ssl-errors')chrome_options.add_argument('--ignore-ssl-error')chrome_options.add_argument('log-level=2')# 解决谷歌堆栈溢出问题chrome_options.add_experimental_option('useAutomationExtension', False)# https://blog.csdn.net/huashao0602/article/details/124322123# 解决遇到反爬虫 获取不到数据问题 Selenium绕过检测 & 隐藏特征chrome_options.add_argument("--disable-blink-features=AutomationControlled")# chromedriver.exe 放在根目录下path = os.path.join(os.getcwd(), 'chromedriver.exe')print('chromePath:', path)service = Service(executable_path=path)driver = webdriver.Chrome(options=chrome_options,service=service)driver.get(initUrl)driver.maximize_window()return driver# 打开网页，无浏览器模式
def seleniumOpenUrlHeadless(initUrl):chrome_options = webdriver.ChromeOptions()chrome_options.add_argument('---ignore-certificate-errors-spki-list')chrome_options.add_argument('--ignore-ssl-errors')chrome_options.add_argument('--ignore-ssl-error')chrome_options.add_argument('log-level=2')# 解决谷歌堆栈溢出问题chrome_options.add_experimental_option('useAutomationExtension', False)# https://blog.csdn.net/huashao0602/article/details/124322123# 解决遇到反爬虫 获取不到数据问题 Selenium绕过检测 & 隐藏特征chrome_options.add_argument("--disable-blink-features=AutomationControlled")# chromedriver.exe 放在根目录下path = os.path.join(os.getcwd(), 'chromedriver.exe')print('chromePath:', path)browser_locale = 'fr'chrome_options.add_argument("--lang={}".format(browser_locale))chrome_options.add_argument("--headless")chrome_options.add_argument('headless')service = Service(executable_path=path)driver = webdriver.Chrome(options=chrome_options, service=service)driver.get(initUrl)driver.maximize_window()return driver

测试打开百度 - test.py

# -*- coding:utf-8 _*-from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from seleniumkit import *def openBaiDu():initUrl = "https://www.baidu.com/"driver = seleniumOpenUrl(initUrl)return driverif __name__ == "__main__":openBaiDu()time.sleep(10)