Python+Selenium实现无头浏览器网页截图

#1、安装google-chrome-stable的依赖
yum install -y atk at-spi2-atk libdrm mesa-libgbm gtk3 vulkan xdg-utils
#安装中文字体
yum install -y wqy-microhei-fonts
 
#2、下载rpm安装包
https://mirrors.aliyun.com/google-chrome/google-chrome/google-chrome-stable-110.0.5481.77-1.x86_64.rpm
 
#3、安装
 
rpm -ivh google-chrome-stable-110.0.5481.77-1.x86_64.rpm
 
#4、查看版本信息
google-chrome-stable --version

# 下载安装包
wget "https://registry.npmmirror.com/-/binary/chromedriver/110.0.5481.77/chromedriver_linux64.zip"
 
# 解压
unzip chromedriver_linux64.zip -d /usr/local/chromedriver
 
# 设置环境变量
 
export CHROME_DRIVER=/usr/local/chromedriver
export PATH=$PATH:$CHROME_DRIVER
 
# 验证chromedriver版本是否与google-chrome-stable版本完全一致,否则会出现兼容性问题
chromedriver --version

pip3 install selenium
 
pip3 install pillow

from selenium.webdriver import Chrome
from selenium.webdriver.chrome.options import Options
import time
import os.path
from PIL import Image
 
def mergeImage(output_path):
    images = [Image.open(os.path.join(output_path, f"screenshot_{i}.png")) for i in range(scrolls)]
    widths, heights = zip(*(i.size for i in images))
 
    total_width = max(widths)
    total_height = sum(heights)
 
    new_image = Image.new('RGB', (total_width, total_height))
    y_offset = 0
    for img in images:
        new_image.paste(img, (0, y_offset))
        y_offset += img.height
 
    final_screenshot_path = os.path.join(output_path, "final_screenshot.png")
    new_image.save(final_screenshot_path)
    print(f"Final screenshot saved to {final_screenshot_path}")
 
 
if __name__ == "__main__":
    # 设置浏览器
    options = Options()
    options.add_argument('--no-sandbox')
    options.add_argument('--disable-gpu')
    options.add_argument('--headless')  # 无头参数
 
    output_path = "./screenshots"
    # 启动浏览器
    driver = Chrome(options=options)
    driver.maximize_window()
    try:
        # 访问页面
        url = 'https://qq.com'
        driver.get(url)
        time.sleep(1)
        # 设置截屏整个网页的宽度以及高度
        scroll_width = 2500
        scroll_height = 9500
        driver.set_window_size(scroll_width, scroll_height)
 
        # 获取页面高度
        total_height = driver.execute_script("return document.body.scrollHeight")
        viewport_height = driver.execute_script("return window.innerHeight")
        scrolls = int(total_height / viewport_height) + 1
 
        # 创建输出目录
        if not os.path.exists(output_path):
            os.makedirs(output_path)
 
        # 滚动并截屏
        for i in range(scrolls):
            y_offset = i * viewport_height
            driver.execute_script(f"window.scrollTo(0, {y_offset});")
            time.sleep(1)  # 等待内容加载
            screenshot_path = os.path.join(output_path, f"screenshot_{i}.png")
            driver.get_screenshot_as_file(screenshot_path)
            print(f"Saved {screenshot_path}")
 
        # 合并图片
        mergeImage(output_path)
 
        # 关闭浏览器
        driver.close()
        driver.quit()
 
    except Exception as e:
        print(e)