python保存网页截图

executable_path是谷歌浏览器驱动的地址

win chromedriver.exe

linux

wget https://dl.google.com/linux/direct/google-chrome-stable_current_x86_64.rpm

sudo rpm -ivh google-chrome-stable_current_x86_64.rpm
google-chrome -v

报错时需要安装依赖

sudo yum install -y vulkan-1.0.61.1-2.amzn2.x86_64

python3 selenium安装

pip3 install selenium

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
def save_image(url,executable_path,save_path):
 
    chrome_options = Options()
    chrome_options.add_argument('--headless')
    chrome_options.add_argument('--disable-gpu')
    # 创建浏览器对象
    # driver = webdriver.Chrome(ChromeDriverManager().install())
    driver = webdriver.Chrome(executable_path=executable_path, chrome_options=chrome_options)

    # 打开网页
    driver.get(url)
    driver.maximize_window()
    # 加延时 防止未加载完就截图
    time.sleep(10)

    # 用js获取页面的宽高，如果有其他需要用js的部分也可以用这个方法
    width = driver.execute_script("return document.documentElement.scrollWidth")

    height = driver.execute_script("return document.documentElement.scrollHeight")

    # # 获取页面宽度及其宽度
    # print(width,height)

    # 将浏览器的宽高设置成刚刚获取的宽高
    driver.set_window_size(1920, 1080)

    time.sleep(2)

 
    driver.get_screenshot_as_file(save_path)

    driver.quit()