Springboot使用Selenium+ChormeDriver在服务器端将网页保存为图片或PDF

sudo yum update -y

sudo yum install -y python3 python3-pip

python3 --version
pip3 --version

pip3 install selenium

sudo tee /etc/yum.repos.d/google-chrome.repo <<EOF
[google-chrome]
name=google-chrome
baseurl=http://dl.google.com/linux/chrome/rpm/stable/x86_64
enabled=1
gpgcheck=1
gpgkey=https://dl.google.com/linux/linux_signing_key.pub
EOF

sudo yum install -y google-chrome-stable

google-chrome --version

sudo chmod +x /usr/local/bin/chromedriver

chromedriver --version

<dependency>
	<groupId>org.seleniumhq.selenium</groupId>
	<artifactId>selenium-java</artifactId>
	<version>4.16.0</version>
</dependency>
<dependency>
	<groupId>org.seleniumhq.selenium</groupId>
	<artifactId>selenium-chrome-driver</artifactId>
	<version>4.16.0</version>
</dependency>

/**
 * 将网页地址保存
 * @param response
 * @param url
 * @return
 */
@GetMapping("/urlToPdf")
@ResponseBody
public Result<String> urlToPdf(HttpServletResponse response, @RequestParam(value = "url", required = false) String url) {
	if (url == null || url.isEmpty()) {
		return Result.error("抱歉，url不能为空！");
	}
	if (!isValidUrl(url)) {
		return Result.error("抱歉，url格式错误！");
	}

	// 设置 ChromeDriver 的路径
	//Linux 系统
	System.setProperty("webdriver.chrome.driver", "/usr/local/bin/chromedriver");
	//Windows系统
	//System.setProperty("webdriver.chrome.driver", "D:\\chromedriver-win64\\chromedriver.exe");

	// 设置Chrome选项
	ChromeOptions options = new ChromeOptions();
	Map<String, Object> prefs = new HashMap<>();
	prefs.put("profile.default_content_setting_values.images", 1); // 1:允许加载图片，2:阻止加载图片
	options.setExperimentalOption("prefs", prefs);
	options.addArguments("--incognito");
	options.setAcceptInsecureCerts(true);
	options.addArguments("--headless=new");// 无头模式
	options.addArguments("--disable-gpu");
	options.addArguments("--no-sandbox");
	options.addArguments("--disable-dev-shm-usage");
	options.addArguments("--window-size=1920,1080");

	// 创建 WebDriver 实例
	ChromeDriver driver = new ChromeDriver(options);
	try {

		// 打开目标网页
		driver.get(url);

		// 设置打印选项
		PrintOptions printOptions = new PrintOptions();
		printOptions.setPageRanges("1-500"); // 打印页码范围
		printOptions.setOrientation(PrintOptions.Orientation.PORTRAIT); // 纵向
		//printOptions.setScale(0.79); // 缩放比例
		printOptions.setBackground(true); // 打印背景
		// 执行打印并获取 PDF（Base64 编码）
		String pdfBase64 = ((PrintsPage) driver).print(printOptions).getContent();
		byte[] pdfBytes = Base64.getDecoder().decode(pdfBase64);
		//2.文件流
		OutputStream os = response.getOutputStream();
		//3.输出文件
		response.setContentType("application/pdf");
		response.setCharacterEncoding(StandardCharsets.UTF_8.name());
		String fileName = URLEncoder.encode(System.currentTimeMillis() + ".pdf", StandardCharsets.UTF_8); // 这里URLEncoder.encode可以防止中文乱码
		response.setHeader("Content-disposition", "attachment;filename*=utf-8''" + fileName);
		os.write(pdfBytes);
		os.flush();
		os.close();
	} catch (Exception e) {
		return Result.error(e.getMessage());
	} finally {
		driver.quit(); // 关闭浏览器
	}
	return Result.success("success");
}