JAVA實現PDF轉HTML文檔的示例代碼

Posted on by

本文是基於PDF文檔轉PNG圖片,然後進行圖片拼接，拼接後的圖片轉為base64字符串，然後拼接html文檔寫入html文件實現PDF文檔轉HTML文檔。

引入Maven依賴

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

工具實現類

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文檔轉HTML文檔
 * @author LXW
 * @date 2020/6/17 16:45
 */
public class PdfConvertHtmlUtil {
    /**
     * 日志對象
     */
    private static Logger logger = LoggerFactory.getLogger(PdfConvertHtmlUtil.class);

    /**
     * PDF文檔流轉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);//產生縮略圖

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

    /**
     *BufferedImage拼接處理，添加分割線
     * @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));// 線條粗細
            g2.setColor(new Color(193, 193, 193));// 線條顏色
            g2.drawLine(x, y, width, y);// 線條起點及終點位置

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

        }
        return combo;
    }
    /**
     * 通過Base64創建HTML文件並輸出html文件
     * @param base64
     * @param htmlPath html保存路徑
     */
    public static void createHtmlByBase64(String base64,String htmlPath) {
        StringBuilder stringHtml = new StringBuilder();
        PrintStream printStream = null;
        try {
            // 打開文件
            printStream = new PrintStream(new FileOutputStream(htmlPath));
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
        // 輸入HTML文件內容
        stringHtml.append("<html><head>");
        stringHtml.append("<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\">");
        stringHtml.append("<title></title>");
        stringHtml.append("</head>");
        stringHtml.append(
                "<body style=\"\r\n" + "    text-align: center;\r\n" + "    background-color: #C1C1C1;\r\n" + "\">");
        stringHtml.append("<img src=\"data:image/png;base64," + base64 + "\" />");
        stringHtml.append("<a name=\"head\" style=\"position:absolute;top:0px;\"></a>");
		//添加錨點用於返回首頁
        stringHtml.append("<a style=\"position:fixed;bottom:10px;right:10px\" href=\"#head\">回到首頁</a>");
        stringHtml.append("</body></html>");
        try {
            // 將HTML文件內容寫入文件中
            printStream.println(stringHtml.toString());
        } catch (Exception e) {
            e.printStackTrace();
        }finally {
            if(printStream != null){printStream.close();}
        }

    }

    /**
     * bufferedImage 轉為 base64編碼
     * @param bufferedImage
     * @return
     */
    public static String bufferedImageToBase64(BufferedImage bufferedImage) {
        ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
        String png_base64 = "";
        try {
            ImageIO.write(bufferedImage, "png", byteArrayOutputStream);// 寫入流中
            byte[] bytes = byteArrayOutputStream.toByteArray();// 轉換成字節
            BASE64Encoder encoder = new BASE64Encoder();
            // 轉換成base64串 刪除 \r\n
            png_base64 = encoder.encodeBuffer(bytes).trim()
                    .replaceAll("\n", "")
                    .replaceAll("\r", "");
        } catch (IOException e) {
            e.printStackTrace();
        }
        return png_base64;
    }
}

測試Demo

public static void main(String[] args) {
        File file = new File("F:\\111\\Files\\MySQL查詢語句大全集錦(經典珍藏).pdf");
        String htmlPath = "F:\\111\\Files\\MySQL查詢語句大全集錦(經典珍藏).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();
            }
        }
    }

最終結果 轉換後文件

轉換後的文件

轉換後的文件內容

文件內容

文件預覽效果

預覽效果

到此這篇關於JAVA實現PDF轉HTML文檔的示例代碼的文章就介紹到這瞭,更多相關JAVA PDF轉HTML 內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet！

推薦閱讀：