JAVA实现PDF转HTML文档

本文是基于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文档写入html文件实现PDF文档转HTML文档。

引入Maven依赖

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

工具实现类

package com.frame.utils;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import sun.misc.BASE64Decoder;
import sun.misc.BASE64Encoder;

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

/**
 * PDF文档转HTML文档
 * @author LXW
 * @date 2020/6/17 16:45
 */
public class PdfConvertHtmlUtil {
    /**
     * 日志对象
     */
    private static Logger logger = LoggerFactory.getLogger(PdfConvertHtmlUtil.class);

    /**
     * PDF文档流转Png
     * @param pdfFileInputStream
     * @return BufferedImage
     */
    public static BufferedImage pdfStreamToPng(InputStream pdfFileInputStream){
        PDDocument doc = null;
        PDFRenderer renderer = null;
        try {
            doc = PDDocument.load(pdfFileInputStream);
            renderer = new PDFRenderer(doc);
            int pageCount = doc.getNumberOfPages();
            BufferedImage image = null;
            for (int i = 0; i < pageCount; i++) {
                if (image != null) {
                    image = combineBufferedImages(image, renderer.renderImageWithDPI(i, 144));
                }

                if (i == 0) {
                    image = renderer.renderImageWithDPI(i, 144); // Windows native DPI
                }
                // BufferedImage srcImage = resize(image, 240, 240);//产生缩略图

            }
            return combineBufferedImages(image);
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            try {
                if(doc != null){doc.close();}
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return null;
    }

    /**
     *BufferedImage拼接处理，添加分割线
     * @param images
     * @return BufferedImage
     */
    public static BufferedImage combineBufferedImages(BufferedImage... images) {
        int height = 0;
        int width = 0;
        for (BufferedImage image : images) {
			//height += Math.max(height, image.getHeight());
            height += image.getHeight();
            width = image.getWidth();
        }
        BufferedImage combo = new BufferedImage(width, height, BufferedImage.TYPE_INT_ARGB);
        Graphics2D g2 = combo.createGraphics();
        int x = 0;
        int y = 0;
        for (BufferedImage image : images) {
			//int y = (height - image.getHeight()) / 2;
            g2.setStroke(new BasicStroke(2.0f));// 线条粗细
            g2.setColor(new Color(193, 193, 193));// 线条颜色
            g2.drawLine(x, y, width, y);// 线条起点及终点位置

            g2.drawImage(image, x, y, null);
			//x += image.getWidth();
            y += image.getHeight();

        }
        return combo;
    }
    /**
     * 通过Base64创建HTML文件并输出html文件
     * @param base64
     * @param htmlPath html保存路径
     */
    public static void createHtmlByBase64(String base64,String htmlPath) {
        StringBuilder stringHtml = new StringBuilder();
        PrintStream printStream = null;
        try {
            // 打开文件
            printStream = new PrintStream(new FileOutputStream(htmlPath));
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
        // 输入HTML文件内容
        stringHtml.append("");
        stringHtml.append("");
        stringHtml.append("");
        stringHtml.append("");
        stringHtml.append(
                " + "    text-align: center;\r\n" + "    background-color: #C1C1C1;\r\n" + "\">");
        stringHtml.append(" + base64 + "\" />");
        stringHtml.append("");
		//添加锚点用于返回首页
        stringHtml.append("回到首页");
        stringHtml.append("");
try {
// 将HTML文件内容写入文件中
printStream.println(stringHtml.toString());
} catch (Exception e) {
e.printStackTrace();
}finally {
if(printStream != null){printStream.close();}
}
}
/**
* bufferedImage 转为 base64编码
* @param bufferedImage
* @return
*/
public static String bufferedImageToBase64(BufferedImage bufferedImage) {
ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
String png_base64 = "";
try {
ImageIO.write(bufferedImage, "png", byteArrayOutputStream);// 写入流中
byte[] bytes = byteArrayOutputStream.toByteArray();// 转换成字节
BASE64Encoder encoder = new BASE64Encoder();
// 转换成base64串 删除 \r\n
png_base64 = encoder.encodeBuffer(bytes).trim()
.replaceAll("\n", "")
.replaceAll("\r", "");
} catch (IOException e) {
e.printStackTrace();
}
return png_base64;
}
}

测试Demo

public static void main(String[] args) {
        File file = new File("F:\\111\\Files\\MySQL查询语句大全集锦(经典珍藏).pdf");
        String htmlPath = "F:\\111\\Files\\MySQL查询语句大全集锦(经典珍藏).html";
        InputStream inputStream = null;
        BufferedImage bufferedImage = null;
        try {
            inputStream = new FileInputStream(file);
            bufferedImage = pdfStreamToPng(inputStream);
            String base64_png = bufferedImageToBase64(bufferedImage);
            createHtmlByBase64(base64_png,htmlPath);

        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }finally {
            try {
                if(inputStream != null){inputStream.close();}
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

最终结果

转换后文件

转换后的文件内容

文件预览效果