DOC,PDF,PPT文件转换为HTML代码记录

pom文件引入

<repositories>
	<repository>
		<id>com.e-iceblue</id>
		<url>http://repo.e-iceblue.cn/repository/maven-public/</url>
	</repository>
</repositories>

<dependency>
	<groupId>e-iceblue</groupId>
	<artifactId>spire.presentation.free</artifactId>
	<version>3.9.0</version>
</dependency>

<dependency>
	<groupId>org.apache.tika</groupId>
	<artifactId>tika-parsers</artifactId>
	<version>1.23</version>
</dependency>

工具类

package com.soft.mpms.zframe.common;

import com.aspose.words.Document;
import com.aspose.words.HtmlSaveOptions;
import com.aspose.words.SaveFormat;
import com.soft.mpms.basebean.mima.JwtUserObject;
import com.soft.mpms.minio.bean.FileObject;
import com.soft.mpms.minio.common.FileTypeConstant;
import com.soft.mpms.minio.service.SsoFileCommand;
import com.soft.mpms.zframe.config.FilePathConfig;
import com.soft.mpms.zframe.config.PdfConvertHtmlUtil;
import com.spire.presentation.*;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.FilenameUtils;
import org.apache.tika.Tika;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.springframework.mock.web.MockMultipartFile;
import org.springframework.util.ObjectUtils;
import org.springframework.web.multipart.MultipartFile;

import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.*;
import java.util.Base64;
import java.util.HashMap;
import java.util.UUID;

/**
 * @ClassName ChangeFileToHtml
 * @description: TODO
 * @author: hhs
 * @Date 2022/11/14 0014 上午 8:48
 **/
public class ChangeFileToHtml {

    private static SsoFileCommand sso = new SsoFileCommand();

    /**
     * *methodName: pdfSaveHtml
     *
     * @return
     * @Author: hhs
     * @Description: pdf转换为html(均为图片格式)并提取第一张pdf的文字
     * @Date: 2022/11/14 上午 8:54
     * @Param: * @param null
     **/
    public static HashMap<String, String> pdfSaveHtml(MultipartFile multipartFile, String zjId, JwtUserObject jwtUserObject) {
        HashMap<String, String> map = new HashMap<>();
        String context = "";
        try {
            String htmlPath = FilePathConfig.gettempfilepath() + zjId + ".html";
            BufferedImage bufferedImage = null;
            //保存图片
            bufferedImage = PdfConvertHtmlUtil.pdfStreamToPng(multipartFile.getInputStream(),zjId);
            //转换
            String base64_png = PdfConvertHtmlUtil.bufferedImageToBase64(bufferedImage);
            //保存html文件
            String html = PdfConvertHtmlUtil.createHtmlByBase64(base64_png, htmlPath, "pdf");
            map.put("html", html);
            File file = new File(FilePathConfig.gettempfilepath() + zjId + ".jpeg");
            File pdffile = new File(FilePathConfig.gettempfilepath() + zjId + ".pdf");

            FileUtils.copyInputStreamToFile(multipartFile.getInputStream(), pdffile);
            //取摘要
            Tika tika = new Tika();
            context = tika.parseToString(pdffile);
            context = context.replaceAll("\n", "");
            context = context.replaceAll(" ", "");
            if (context.length() >= 200) {
                context = context.substring(0, 200);
            }
            if(file.exists()){
                //上传第一张图片
                uploadImgs(file,zjId,jwtUserObject);
            }
            //删除pdf文件
            if (pdffile.exists()){pdffile.delete();}
            //删除html文件
            File htmlFile = new File(htmlPath);
            if (htmlFile.exists()){ htmlFile.delete(); }
        } catch (Exception e) {
            e.printStackTrace();
        }
        map.put("remark", context);
        return map;
    }

    /**
     * *methodName: pptToHtml
     *
     * @return
     * @Author: hhs
     * @Description: ppt转换为html，上传第一张ppt，并提取文字
     * @Date: 2022/11/14 上午 8:55
     * @Param: * @param null
     **/
    public static HashMap<String, String> pptToHtml(MultipartFile file, JwtUserObject jwtUserObject, String zjId) {
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        HashMap<String, String> map = new HashMap<>();
        String remark = "";
        try {
            // 将文件保存在服务器目录中
            // 新生成的文件名称
            String uuid = UUID.randomUUID().toString().replaceAll("-", "");
            // 得到上传文件后缀
            String originalName = file.getOriginalFilename();
            String ext = "." + FilenameUtils.getExtension(originalName);
            // 新生成的文件名称
            String fileName = uuid + ext;
            // 得到新的文件File对象
            File targetFile = new File(FilePathConfig.gettempfilepath(), fileName);
            // 开始复制文件
            FileUtils.writeByteArrayToFile(targetFile, file.getBytes());

            ////加载幻灯片文档,创建Presentation类的对象
            Presentation ppt = new Presentation();
            ppt.loadFromFile(FilePathConfig.gettempfilepath() + fileName);
            //转换为html
            baos = new ByteArrayOutputStream();
            ppt.saveToFile(baos, FileFormat.HTML);
            org.jsoup.nodes.Document htmlDoc = Jsoup.parse(baos.toString());

            //取第一张幻灯片上传到服务器
            BufferedImage image = ppt.getSlides().get(0).saveAsImage();
            File imgFile = new File(uuid + ".jpeg");
            ImageIO.write(image, "jpeg", imgFile);

            //转换为MultipartFile
            MultipartFile multipartFile = new MockMultipartFile(imgFile.getName(), imgFile.getName(), "", new FileInputStream(imgFile));
            //上传到服务器

            //上传图片
            if (!ObjectUtils.isEmpty(multipartFile) && multipartFile.getSize() > 0) {
                //上传第一张
                sso.uploadFileCommond(multipartFile, jwtUserObject.getUSERID(), jwtUserObject.getUSERNAME(),
                        jwtUserObject.getITEMCODE(), jwtUserObject.getORGCODE(), "10036", jwtUserObject.getUSERIDENTITY(),
                        zjId, jwtUserObject.getITEMCODE().toLowerCase(), FileTypeConstant.COMP_10 + "/" + "10036" + "/", "");
            }

            map.put("html", htmlDoc.toString());
            //处理摘要
            StringBuilder buffer = new StringBuilder();
            for (Object slide : ppt.getSlides()) {
                for (Object shape : ((ISlide) slide).getShapes()) {
                    if (shape instanceof IAutoShape) {
                        for (Object tp : ((IAutoShape) shape).getTextFrame().getParagraphs()) {
                            buffer.append(((ParagraphEx) tp).getText());
                        }
                    }
                }
            }
            if (buffer.length() >= 200) {
                remark = buffer.substring(0, 200);
            } else {
                remark = buffer.toString();
            }
            map.put("remark", remark);
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                baos.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return map;
    }

    /**
     * *methodName: docSaveHtml
     *
     * @return
     * @Author: hhs
     * @Description: word转换为html，上传全部图片并提取文字
     * @Date: 2022/11/14 上午 8:55
     * @Param: * @param null
     **/
    public static String docSaveHtml(String zjId, JwtUserObject jwtUserObject, Document doc) {
        org.jsoup.nodes.Document htmlDoc = null;
        ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
        try {
            // 2.设置doc转html配置
            HtmlSaveOptions saveOptions = new HtmlSaveOptions(SaveFormat.HTML);
            saveOptions.setExportTextInputFormFieldAsText(false);
            saveOptions.setExportImagesAsBase64(true);
            saveOptions.setPrettyFormat(true);
            //高质量渲染
            saveOptions.setUseHighQualityRendering(true);
            // 3.内存流保存
            doc.save(outputStream, saveOptions);
            htmlDoc = Jsoup.parse(outputStream.toString());
            if (htmlDoc != null) {
                Elements elements = htmlDoc.getElementsByTag("img");
                for (Element element : elements) {
                    String oldSrc = element.attr("src");
                    File file = base64ToFile(oldSrc);
                    String newSrc = uploadImgs(file, zjId, jwtUserObject);
                    //上传
                    element.attr("src", newSrc);
                }
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                if (outputStream != null) {
                    outputStream.close();
                }
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return htmlDoc.toString();
    }

    /*
     * base64图片转换为本地图片
     */
    private static File base64ToFile(String base64) throws Exception {
        if (base64.contains("data:image")) {
            base64 = base64.substring(base64.indexOf(",") + 1);
        }
        base64 = base64.toString().replace("\r\n", "");
        //创建文件目录
        String prefix = ".jpeg";
        File file1 = new File(FilePathConfig.gettempfilepath());
        String uid = UUID.randomUUID().toString().replaceAll("-", "");
        System.out.println(uid);
        File file = File.createTempFile(uid, prefix, file1);
        BufferedOutputStream bos = null;
        FileOutputStream fos = null;
        try {
            Base64.Decoder decoder = Base64.getDecoder();
            byte[] bytes = decoder.decode(base64);
            fos = new FileOutputStream(file);
            bos = new BufferedOutputStream(fos);
            bos.write(bytes);
        } finally {
            if (bos != null) {
                try {
                    bos.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (fos != null) {
                try {
                    fos.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
        return file;
    }

    /*
     * 上传附件
     */
    private static String uploadImgs(File file, String zjId, JwtUserObject jwtUserObject) {
        String imgPath = "";
        try {
            MultipartFile multipartFile = new MockMultipartFile(file.getName(), file.getName(), "", new FileInputStream(file));
            //上传正文附件
            FileObject fileObject = sso.uploadFileCommond(multipartFile, jwtUserObject.getUSERID(), jwtUserObject.getUSERNAME(),
                    jwtUserObject.getITEMCODE(), jwtUserObject.getORGCODE(), "10036", jwtUserObject.getUSERIDENTITY(),
                    zjId, jwtUserObject.getITEMCODE().toLowerCase(), FileTypeConstant.COMP_10 + "/" + "10036" + "/", "");
            //返回路径
            imgPath = sso.queryFileTempFilePathFileByid(fileObject.getFileid());

            //删除文件
            file.delete();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return imgPath;
    }
}

pdf处理

package com.soft.mpms.zframe.config;

import cn.hutool.core.lang.UUID;
import lombok.extern.slf4j.Slf4j;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import sun.misc.BASE64Encoder;

import javax.imageio.ImageIO;
import java.awt.*;
import java.awt.geom.AffineTransform;
import java.awt.image.BufferedImage;
import java.awt.image.ColorModel;
import java.awt.image.WritableRaster;
import java.io.*;

/**
 * PDF文档转HTML文档工具类
 */
@Slf4j
public class PdfConvertHtmlUtil {

    /**
     * PDF文档流转Png
     *
     * @param input
     * @return BufferedImage
     */
    public static BufferedImage pdfStreamToPng(byte[] input,String uid) {
        PDDocument doc = null;
        PDFRenderer renderer = null;
        try {
            doc = PDDocument.load(input);
            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.renderImage(i));
                }

                if (i == 0) {
                    // 设置图片的分辨率
                    image = renderer.renderImage(i); // Windows native DPI
                    // 如果是PNG图片想要背景透明的话使用下面这个
                    // BufferedImage image = render.renderImageWithDPI(i, 296, ImageType.ARGB);
                }
            }
            // 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;
    }

    /**
     * PDF文档流转Png
     *
     * @param pdfFileInputStream
     * @return BufferedImage
     */
    public static BufferedImage pdfStreamToPng(InputStream pdfFileInputStream,String uid) {
        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
                    //保存第一张
                    String img = FilePathConfig.gettempfilepath()+uid+ ".jpeg";
                    ImageIO.write(image, "jpeg", new File(img));
                }
                // 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;
    }

    /**
     * 压缩图片
     *
     * @param source
     * @param targetW
     * @param targetH
     * @return
     */
    private static BufferedImage resize(BufferedImage source, int targetW, int targetH) {
        int type = source.getType();
        BufferedImage target = null;
        double sx = (double) targetW / source.getWidth();
        double sy = (double) targetH / source.getHeight();
        if (sx > sy) {
            sx = sy;
            targetW = (int) (sx * source.getWidth());
        } else {
            sy = sx;
            targetH = (int) (sy * source.getHeight());
        }
        if (type == BufferedImage.TYPE_CUSTOM) {
            ColorModel cm = source.getColorModel();
            WritableRaster raster = cm.createCompatibleWritableRaster(targetW, targetH);
            boolean alphaPremultiplied = cm.isAlphaPremultiplied();
            target = new BufferedImage(cm, raster, alphaPremultiplied, null);
        } else {
            target = new BufferedImage(targetW, targetH, type);
        }
        Graphics2D g = target.createGraphics();
        g.setRenderingHint(RenderingHints.KEY_RENDERING, RenderingHints.VALUE_RENDER_QUALITY);
        g.drawRenderedImage(source, AffineTransform.getScaleInstance(sx, sy));
        g.dispose();
        return target;
    }

    /**
     * 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
     * @param title    html标题
     */
    public static String createHtmlByBase64(String base64, String htmlPath, String title) {
        PrintStream printStream = null;
        try {
            // 打开文件
            printStream = new PrintStream(new FileOutputStream(htmlPath));
        } catch (FileNotFoundException e) {
            log.error("create file error!", e);
            return "";
        }
        try {
            // 将HTML文件内容写入文件中
            String htmlString = getHtmlString(base64, title);
            printStream.println(htmlString);
            return htmlString;
        } catch (Exception e) {
            log.error("createHtmlByBase64 error!", e);
        } finally {
            printStream.close();
        }
        return "";
    }

    /**
     * 通过Base64创建HTML文件并输出html文件
     *
     * @param base64
     */
    public static String getHtmlString(String base64, String title) {
        StringBuilder stringHtml = new StringBuilder();
        // 输入HTML文件内容
        stringHtml.append("<html><head>");
        stringHtml.append("<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\">");
        stringHtml.append("<title>").append(title).append("</title>");
        stringHtml.append("</head>");
        stringHtml.append("<body style=\"" + "text-align: center;\">");
        stringHtml.append("<img style=\""+"width: 100%;\""+ "src=\"data:image/png;base64,").append(base64).append("\"/>");
        stringHtml.append("</body></html>");
        return stringHtml.toString();
    }

    /**
     * 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
    public static void main(String[] args) {
        File file = new File("E:\\aaa.pdf");
        String htmlPath = "E:\\aaaa.html";
        InputStream inputStream = null;
        BufferedImage bufferedImage = null;
        try {
            inputStream = new FileInputStream(file);
            bufferedImage = pdfStreamToPng(inputStream,"");
            String base64_png = bufferedImageToBase64(bufferedImage);
            createHtmlByBase64(base64_png, htmlPath, "授权书");

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

    }

}

html转换

package com.soft.mpms.zframe.common;

import org.apache.commons.lang.StringUtils;

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * @ClassName 富文本编辑器提取image路径和文字
 * @description: TODO
 * @author: hhs
 * @Date 2022/4/26 0026 下午 13:43
 **/
public class HtmlToText {

    private static Pattern p_image= Pattern.compile("<img.*src\\s*=\\s*(.*?)[^>]*?>",Pattern.CASE_INSENSITIVE);
    private static Pattern r_image=Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)");

    /**
     * 提取富文本中纯文本
     */
    public static String getText(String richText) {
        if (StringUtils.isEmpty(richText)){
            return "";
        }
        String regx = "(<.+?>)|(</.+?>)";
        Matcher matcher = Pattern.compile(regx).matcher(richText);
        while (matcher.find()) {
            // 替换图片
            richText = matcher.replaceAll("").replace(" ", "");
        }
        richText = richText.replaceAll("\\s*|\t|\r|\n", "");
        //去除html的&nbsp;标签
        if (richText.contains("&nbsp;")) {
            richText= richText.replaceAll("&nbsp;", "");
        }
        //取200字
        richText = richText.length() > 200?richText.substring(0, 200):richText;
        return richText;
    }

    /**
     * 提取富文本中图片地址
     */
    public static List<String> getImgStr(String richText) {
        List<String> list = new ArrayList<>();
        if (StringUtils.isNotEmpty(richText)){
            if(richText.contains("<") && richText.contains(">")){
                Matcher pMatcher = p_image.matcher(richText);
                while (pMatcher.find()) {
                    // 得到<img />数据
                    String img = pMatcher.group();
                    // 匹配<img>中的src数据
                    Matcher rMatcher = r_image.matcher(img);
                    while (rMatcher.find()) {
                        list.add(rMatcher.group(1));
                    }
                }
            }else {
                return list;
            }
        }
        return list;
    }
}

该工具类可能会有缺陷或者性能问题，欢迎提出指正