java的pdf处理方式

最新推荐文章于 2024-07-20 16:46:26 发布

谁是我的程序媛？

最新推荐文章于 2024-07-20 16:46:26 发布

阅读量617

点赞数

分类专栏： Utils 文章标签： java html

本文链接：https://blog.csdn.net/qq_40572200/article/details/120698431

版权

Utils 专栏收录该内容

24 篇文章 0 订阅

订阅专栏

java的pdf处理方式

html转图片
图片转pdf
pdf转图片
pdf转base64和base64转pdf

引入包依赖

<dependency>
    <groupId>com.itextpdf</groupId>
    <artifactId>itextpdf</artifactId>
    <version>5.5.13.2</version>
</dependency>
<dependency>
    <groupId>com.itextpdf.tool</groupId>
    <artifactId>xmlworker</artifactId>
    <version>5.5.13.2</version>
</dependency>
// 下面的好像也可以不用
 <dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>itext-asian</artifactId>
            <version>5.2.0</version>
 </dependency>
 <dependency>
     <groupId>org.xhtmlrenderer</groupId>
     <artifactId>flying-saucer-pdf-itext5</artifactId>
     <version>9.0.3</version>
 </dependency>
// 如果不使用freemarker模板可以不加这个
<dependency>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-freemarker</artifactId>
</dependency>

html转图片

创建模板

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8"/>
    <title>Title</title>
    <style>
        body{font-family:SimSun;}
        .title{align-content: center;text-align: center;}
        .signature{float:right }
    </style>
</head>
<body>
<div>
    <h1 class="title">标题</h1>
    <h4 class="title">副标题</h4>
    <span>当前时间: ${date_time} </span>
    <div class="signature">日期：${date}</div>
</div>
</body>
</html>

获取html内容
html存放在系统文件夹

String templateDirectory = "D:\\";  // 系统文件夹路径 如: D:\

当HTML模板存放在项目resources/templates目录

ClassLoader classLoader = PdfUtilTest.class.getClassLoader();
URL resource = classLoader.getResource("templates");
String templateDirectory = resource.toURI().getPath();

示例代码

import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.PdfWriter;
import com.itextpdf.tool.xml.XMLWorkerHelper;
import freemarker.template.Configuration;
import freemarker.template.Template;

import java.io.*;
import java.net.URL;
import java.nio.charset.Charset;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.HashMap;
import java.util.Map;

public class PdfUtilTest {
    /**
     * 获取模板内容
     * @param templateDirectory 模板文件夹
     * @param templateName      模板文件名
     * @param paramMap          模板参数
     * @return
     * @throws Exception
     */
    private static String getTemplateContent(String templateDirectory, String templateName, Map<String, Object> paramMap) throws Exception {
        Configuration configuration = new Configuration(Configuration.DEFAULT_INCOMPATIBLE_IMPROVEMENTS);
        try {
            configuration.setDirectoryForTemplateLoading(new File(templateDirectory));
        } catch (Exception e) {
            System.out.println("-- exception --");
        }

        Writer out = new StringWriter();
        Template template = configuration.getTemplate(templateName,"UTF-8");
        template.process(paramMap, out);
        out.flush();
        out.close();
        return out.toString();
    }
    public static void main(String[] args) throws Exception {
        Map<String, Object> paramMap = new HashMap<>();
        DateTimeFormatter dateTimeFormatter = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
        paramMap.put("date_time", dateTimeFormatter.format(LocalDateTime.now()));
        paramMap.put("date", dateTimeFormatter.format(LocalDateTime.now()).substring(0, 10));
        ClassLoader classLoader = PdfUtilTest.class.getClassLoader();
        URL resource = classLoader.getResource("templates");
        String templateDirectory  =resource.toURI().getPath();
        String templateContent = PdfUtilTest.getTemplateContent(templateDirectory, "test_template.html", paramMap);
        System.out.println(templateContent);
    }
    
}

生成PDF文档
示例代码

/**
 * HTML 转 PDF
 * @param content html内容
 * @param outPath           输出pdf路径
 * @return 是否创建成功
 */
public static boolean html2Pdf(String content, String outPath) {
    try {
        Document document = new Document();
        PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream(outPath));
        document.open();
        XMLWorkerHelper.getInstance().parseXHtml(writer, document,
                new ByteArrayInputStream(content.getBytes()), null, Charset.forName("UTF-8"));
        document.close();
    } catch (Exception e) {
        System.out.println("生成模板内容失败"+e.fillInStackTrace());
        return false;
    }
    return true;
}
/**
 * HTML 转 PDF
 * @param content html内容
 * @return PDF字节数组
 */
public static byte[] html2Pdf(String content) {
    ByteArrayOutputStream outputStream = null;
    try {
        Document document = new Document();
        outputStream = new ByteArrayOutputStream();
        PdfWriter writer = PdfWriter.getInstance(document, outputStream);
        document.open();
        XMLWorkerHelper.getInstance().parseXHtml(writer, document,
                new ByteArrayInputStream(content.getBytes()), null, Charset.forName("UTF-8"));
        document.close();
    } catch (Exception e) {
        System.out.println("------生成pdf失败-------");
    }
    return outputStream.toByteArray();
}
public static void main(String[] args) throws Exception {
    Map<String, Object> paramMap = new HashMap<>();
    DateTimeFormatter dateTimeFormatter = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
    paramMap.put("date_time", dateTimeFormatter.format(LocalDateTime.now()));
    paramMap.put("date", dateTimeFormatter.format(LocalDateTime.now()).substring(0, 10));
    String outPath = "D:\\A.pdf";
    String templateDirectory = "D:\\";
    String templateContent = PdfUtilTest.getTemplateContent(templateDirectory, "test_template.html", paramMap);
    PdfUtilTest.html2Pdf(templateContent, outPath);
    
}

注：转pdf会影响有些样式不能使用，如果有解决样式问题的可以交流下

图片转pdf

以上引入依赖
导入工具类

package com.hrp.util;

import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.Image;
import com.itextpdf.text.PageSize;
import com.itextpdf.text.pdf.PdfWriter;
import org.springframework.stereotype.Component;
import org.springframework.web.multipart.MultipartFile;

import javax.servlet.http.HttpServletResponse;
import java.io.*;
import java.net.URLEncoder;


/**
 * @description: pdf相关的工具类
 */
@Component
public class PdfUtils {

    /**
     * 图片转换PDF的公共接口
     *
     * @param file     SpringMVC获取的图片文件
     * @param response HttpServletResponse
     * @throws IOException       IO异常
     * @throws DocumentException PDF文档异常
     */
    public static void imageToPdf(MultipartFile file, HttpServletResponse response) throws IOException, DocumentException {
        File pdfFile = generatePdfFile(file);
        downloadPdfFile(pdfFile, response);
    }

    /**
     * 将图片转换为PDF文件
     *
     * @param file SpringMVC获取的图片文件
     * @return PDF文件
     * @throws IOException       IO异常
     * @throws DocumentException PDF文档异常
     */
    private static File generatePdfFile(MultipartFile file) throws IOException, DocumentException {
        String fileName = file.getOriginalFilename();
        String pdfFileName = fileName.substring(0, fileName.lastIndexOf(".")) + ".pdf";
        Document doc = new Document(PageSize.A4, 20, 20, 20, 20);
        PdfWriter.getInstance(doc, new FileOutputStream(pdfFileName));
        doc.open();
        doc.newPage();
        Image image = Image.getInstance(file.getBytes());
        float height = image.getHeight();
        float width = image.getWidth();
        int percent = getPercent(height, width);
        image.setAlignment(Image.MIDDLE);
        image.scalePercent(percent);
        doc.add(image);
        doc.close();
        File pdfFile = new File(pdfFileName);
        return pdfFile;
    }

    /**
     *
     * 用于下载PDF文件
     *
     * @param pdfFile  PDF文件
     * @param response HttpServletResponse
     * @throws IOException IO异常
     */
    private static void downloadPdfFile(File pdfFile, HttpServletResponse response) throws IOException {
        FileInputStream fis = new FileInputStream(pdfFile);
        byte[] bytes = new byte[fis.available()];
        fis.read(bytes);
        fis.close();

        response.reset();
        response.setHeader("Content-Type", "application/pdf");
        response.setHeader("Content-Disposition", "attachment; filename=" + URLEncoder.encode(pdfFile.getName(), "UTF-8"));
        OutputStream out = response.getOutputStream();
        out.write(bytes);
        out.flush();
        out.close();
    }


    /**
     * 等比压缩，获取压缩百分比
     *
     * @param height 图片的高度
     * @param weight 图片的宽度
     * @return 压缩百分比
     */
    private static int getPercent(float height, float weight) {
        float percent = 0.0F;
        if (height > weight) {
            percent = PageSize.A4.getHeight() / height * 100;
        } else {
            percent = PageSize.A4.getWidth() / weight * 100;
        }
        return Math.round(percent);
    }
}

pdf转图片

引入依赖

// PDF转图片的必要依赖
<dependency>
	<groupId>org.apache.pdfbox</groupId>
	<artifactId>pdfbox</artifactId>
	<version>2.0.20</version>
</dependency>
// 如果要处理字体的话，需要引入这个依赖
<dependency>
	<groupId>org.apache.pdfbox</groupId>
	<artifactId>fontbox</artifactId>
	<version>2.0.9</version>
</dependency>

PDF转图片工具类

public class PdfToImageUtil {
    /**
     * dpi越大转换后越清晰，相对转换速度越慢
     */
    private static final Integer DPI = 100;

    /**
     * 转换后的图片类型
     */
    private static final String IMG_TYPE = "png";

    /**
     * PDF转图片
     *
     * @param fileContent PDF文件的二进制流
     * @return 图片文件的二进制流
     */
    public static List<byte[]> pdfToImage(byte[] fileContent) throws IOException {
        List<byte[]> result = new ArrayList<>();
        try (PDDocument document = PDDocument.load(fileContent)) {
            PDFRenderer renderer = new PDFRenderer(document);
            for (int i = 0; i < document.getNumberOfPages(); ++i) {
                BufferedImage bufferedImage = renderer.renderImageWithDPI(i, DPI);
                ByteArrayOutputStream out = new ByteArrayOutputStream();
                ImageIO.write(bufferedImage, IMG_TYPE, out);
                result.add(out.toByteArray());
            }
        }
        return result;
    }
}

对以上代码进行优化
可参考链接：https://www.cnblogs.com/Marydon20170307/p/14759048.html

pdf转base64和base64转pdf

 /**
     *  将base64编码转换成PDF
     *  @param base64String
     *  1.使用BASE64Decoder对编码的字符串解码成字节数组
     *  2.使用底层输入流ByteArrayInputStream对象从字节数组中获取数据；
     *  3.建立从底层输入流中读取数据的BufferedInputStream缓冲输出流对象；
     *  4.使用BufferedOutputStream和FileOutputSteam输出数据到指定的文件中
     */
    public static void base64StringToPDF(String base64String, File file){
        BASE64Decoder decoder = new BASE64Decoder();
        BufferedInputStream bin = null;
        FileOutputStream fout = null;
        BufferedOutputStream bout = null;
        try {
            //将base64编码的字符串解码成字节数组
            byte[] bytes = decoder.decodeBuffer(base64String);
            //创建一个将bytes作为其缓冲区的ByteArrayInputStream对象
            ByteArrayInputStream bais = new ByteArrayInputStream(bytes);
            //创建从底层输入流中读取数据的缓冲输入流对象
            bin = new BufferedInputStream(bais);
            //创建到指定文件的输出流
            fout  = new FileOutputStream(file);
            //为文件输出流对接缓冲输出流对象
            bout = new BufferedOutputStream(fout);

            byte[] buffers = new byte[1024];
            int len = bin.read(buffers);
            while(len != -1){
                bout.write(buffers, 0, len);
                len = bin.read(buffers);
            }
            //刷新此输出流并强制写出所有缓冲的输出字节，必须这行代码，否则有可能有问题
            bout.flush();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                bout.close();
                fout.close();
                bin.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

    /**
     * PDF转换为Base64编码
     *
     * @param file
     * @return
     */
    public static String pdfToBase64(File file) {
        BASE64Encoder encoder = new BASE64Encoder();
        FileInputStream fin = null;
        BufferedInputStream bin = null;
        ByteArrayOutputStream baos = null;
        BufferedOutputStream bout = null;
        try {
            fin = new FileInputStream(file);
            bin = new BufferedInputStream(fin);
            baos = new ByteArrayOutputStream();
            bout = new BufferedOutputStream(baos);
            byte[] buffer = new byte[1024];
            int len = bin.read(buffer);
            while (len != -1) {
                bout.write(buffer, 0, len);
                len = bin.read(buffer);
            }
            //刷新此输出流并强制写出所有缓冲的输出字节
            bout.flush();
            byte[] bytes = baos.toByteArray();
            return encoder.encodeBuffer(bytes).trim();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                fin.close();
                bin.close();
                baos.close();
                bout.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return null;
    }