Python 및 WebDriver를 사용하여 웹 페이지를 캡처하고 PDF 파일로 저장

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.chrome.options import Options
from selenium.common.exceptions import WebDriverException

# 设置Chrome浏览器选项
chrome_options = Options()
chrome_options.add_argument("--headless") # 无界面模式
chrome_options.add_argument("--disable-gpu") 

def save_webpage_as_pdf(url, save_path):
    try:
        # 创建浏览器实例
        driver = webdriver.Chrome(options=chrome_options)
        
        # 调整窗口大小以适应网页
        driver.set_window_size(1280, 800)
        
        # 访问网页
        driver.get(url)
        
        # 等待页面加载完成
        driver.implicitly_wait(5)
        
        # 获取网页高度
        total_height = driver.execute_script("return document.body.scrollHeight")
        
        # 将页面切成多个视口，每个视口高度为800
        viewports = int(total_height / 800) + 1
        
        # 初始化PDF打印选项
        driver.execute_script("document.body.style.webkitPrintColorAdjust='exact'")
        driver.execute_script("document.body.style.background='white'")
        driver.execute_script("window.scrollTo(0, 0)")
        
        # 逐个截取每个视口并保存为PDF
        for i in range(viewports):
            # 设置视口位置，每次向下滚动800像素
            driver.execute_script(f"window.scrollTo(0, {i * 800})")
            
            # 截图并保存为图片文件
            driver.save_screenshot(f"{save_path}_{i}.png")
        
        # 关闭浏览器
        driver.quit()
        
        # 使用Python库将截图合并为PDF
        from PIL import Image
        image_files = [f"{save_path}_{i}.png" for i in range(viewports)]
        images = [Image.open(img) for img in image_files]
        images[0].save(f"{save_path}.pdf", "PDF", save_all=True, append_images=images[1:])
        
        # 删除临时图片文件
        import os
        for img in image_files:
            os.remove(img)
            
        print(f"截图成功，并保存为PDF文件：{save_path}.pdf")
    
    except WebDriverException as e:
        print(f"截图失败：{e}")

# 调用截图函数
save_webpage_as_pdf("https://www.example.com", "example_webpage")