JAVA实现PDF转HTML文档

本文是将PDF文档转PNG图片,然后进行图片拼接，拼接后的图片转为base64字符串，然后拼接html文档（再写入html文件）。

引入maven依赖

<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.12</version>
        </dependency>

工具实现类

package cn.yueworld.pms.web.util;

import cn.yueworld.framework.tools.exception.LogicException;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import sun.misc.BASE64Encoder;

import javax.imageio.ImageIO;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.*;
import java.net.URL;

/**
 * PDF文档转HTML文档
 *
 * @author zkg
 * @since 2024/6/11 16:45
 */
public class PdfConvertHtmlUtil {
   
   
    /**
     * 日志对象
     */
    private static Logger logger = LoggerFactory.getLogger(PdfConvertHtmlUtil.class);

    /**
     * pdf转图片
     *
     * @param pdfUrl pdf路径
     * @return BufferedImage 图片
     */
    public static BufferedImage pdfToImage(String pdfUrl) {
   
   

        PDDocument doc = null;
        try {
   
   
            // 本地文件
            // File file = new File("C:\\Users\\Dell\\Downloads\\测试.pdf");
            // inputStream = new FileInputStream(file);

            logger.info("解析pdf+pdfUrl：" + pdfUrl);
            URL url = new URL(pdfUrl);

            InputStream inputStream = url.openStream();
            doc = PDDocument.load(inputStream);
            PDFRenderer renderer = new PDFRenderer(doc);

            int pageCount = doc.getNumberOfPages()