文档转图片整理归纳

文档转图片整理归纳

如下文档都可转换：

• excel（.xls、.xlsx）
• word（.doc、.docx）
• pdf
• ppt

适用于文档预览 图片生成等需求

代码及maven jar包下载地址：下载地址
所有转换都整理归纳到了一块，无水印。
有问题联系QQ：2331202797
如下是生成部分的代码：

package com.lxf.utils;

import com.aspose.cells.*;
import com.aspose.words.Document;
import com.aspose.words.ImageSaveOptions;
import com.aspose.words.SaveFormat;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.poi.hslf.usermodel.*;
import org.apache.poi.xslf.usermodel.*;
import javax.imageio.ImageIO;
import java.awt.*;
import java.awt.Color;
import java.awt.geom.Rectangle2D;
import java.awt.image.BufferedImage;
import java.io.*;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.UUID;

/**
 * word、excel、ppt、pdf 转图片
 * @QQ
 * @Author lxf
 * @Date 2021/3/11
 **/
public class AsposeUtils {

    private final static String XLS = ".xls";
    private final static String XLSX = ".xlsx";
    private final static String DOC = ".doc";
    private final static String DOCX = ".docx";
    private final static String PDF = ".pdf";
    private final static String PPT = ".ppt";
    private final static String PPTX = ".pptx";
	//生成图片时临时存放缓存地址
	private final static String TEMP = System.getProperty("user.dir") + File.separator + "media" + File.separator + "temp" + File.separator;

    public static List<BufferedImage> toImages(String fileType,InputStream inputStream){
        List<BufferedImage> list = new ArrayList<>();
        switch (fileType){
            case XLS:
                list = excelToImages(inputStream);
                break;
            case XLSX:
                list = excelToImages(inputStream);
                break;
            case DOC:
                list = wordToImages(inputStream);
                break;
            case DOCX:
                list = wordToImages(inputStream);
                break;
            case PPT:
                list = pptToImages(inputStream);
                break;
            case PPTX:
                list = pptxToImages(inputStream);
                break;
            case PDF:
                list = pdfToImages(inputStream);
                break;
        }
        return list;
    }

    /**
     * excel所有sheet转成多个图片
     * @param excelInputStream excel文件流
     * @return 多个图片
     */
    public static List<BufferedImage> excelToImages(InputStream excelInputStream){
        List<BufferedImage> images = new ArrayList<>();
        try {
            Workbook workbook = new Workbook(excelInputStream);
            excelInputStream.close();
            WorksheetCollection worksheets = workbook.getWorksheets();
            Iterator<Worksheet> iterator = worksheets.iterator();
            while(iterator.hasNext()) {
                Worksheet worksheet = iterator.next();
                worksheet.getPageSetup().setLeftMargin(0);
                worksheet.getPageSetup().setRightMargin(0);
                worksheet.getPageSetup().setTopMargin(0);
                worksheet.getPageSetup().setBottomMargin(0);
                ImageOrPrintOptions imgOptions = new ImageOrPrintOptions();
                imgOptions.setImageFormat(ImageFormat.getJpeg());
                imgOptions.setOnePagePerSheet(true);
                imgOptions.setPrintingPage(PrintingPageType.IGNORE_BLANK);
                SheetRender sr = new SheetRender(worksheet, imgOptions);
                for (int i = 0; i < sr.getPageCount(); i++) {
                    File file = new File(TEMP + getUUID() + ".jpg");
                    FileOutputStream fileOutputStream = new FileOutputStream(file);
                    sr.toImage(i,fileOutputStream);
                    images.add(ImageIO.read(file));

                    fileOutputStream.close();
                    file.delete();
                }
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return images;
    }

    /**
     * word转成多个图片
     * @param wordInputStream excel文件流
     * @return 多个图片
     */
    public static List<BufferedImage> wordToImages(InputStream wordInputStream){
        List<BufferedImage> images = new ArrayList<>();
        try {
            Document document = new Document(wordInputStream);
            wordInputStream.close();
            ImageSaveOptions iso = new ImageSaveOptions(SaveFormat.JPEG);
            iso.setResolution(128);
            iso.setPrettyFormat(true);
            iso.setUseAntiAliasing(true);
            for (int i = 0; i < document.getPageCount(); i++) {
                iso.setPageIndex(i);
                File file = new File(TEMP + getUUID() + ".jpg");
                FileOutputStream fileOutputStream = new FileOutputStream(file);
                document.save(fileOutputStream,iso);
                images.add(ImageIO.read(file));
                fileOutputStream.close();
                file.delete();
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return images;
    }


    /**
     * pdf转成多个图片
     * @param pdfInputStream
     * @return
     */
    public static List<BufferedImage> pdfToImages(InputStream pdfInputStream) {
        List<BufferedImage> list = new ArrayList<>();

        try {
            PDDocument doc = PDDocument.load(pdfInputStream);
            pdfInputStream.close();
            PDFRenderer renderer = new PDFRenderer(doc);
            int pageCount = doc.getNumberOfPages();
            for (int i = 0; i < pageCount; i++) {
                // 方式1,第二个参数是设置缩放比(即像素)
//                 BufferedImage image = renderer.renderImageWithDPI(i, 296);
                // 方式2,第二个参数是设置缩放比(即像素)
                BufferedImage image = renderer.renderImage(i, 1.25f); // 第二个参数越大生成图片分辨率越高，转换时间也就越长
                list.add(image);
            }
            doc.close(); // 关闭文件,不然该pdf文件会一直被占用。
        } catch (IOException e) {
            e.printStackTrace();
        }
        return list;
    }

    /**
     * pptx 转成多个图片
     * @param pptxInputStream
     * @return
     */
    public static List<BufferedImage> pptxToImages(InputStream pptxInputStream) {
        List<BufferedImage> list = new ArrayList<>();
        try {
            XMLSlideShow ppt = new XMLSlideShow(pptxInputStream);
            pptxInputStream.close();
            Dimension pgsize = ppt.getPageSize();
            for (XSLFSlide slide : ppt.getSlides()) {
                //设置字体
                for (XSLFShape shape : slide.getShapes()){
                    if (shape instanceof XSLFTextShape){
                        XSLFTextShape sh = (XSLFTextShape) shape;
                        List<XSLFTextParagraph> textParagraphs = sh.getTextParagraphs();
                        for (XSLFTextParagraph xslfTextParagraph : textParagraphs) {
                            List<XSLFTextRun> textRuns = xslfTextParagraph.getTextRuns();
                            for (XSLFTextRun xslfTextRun : textRuns) {
                                xslfTextRun.setFontFamily("宋体");
                            }
                        }
                    }
                }
                BufferedImage img = new BufferedImage(pgsize.width, pgsize.height, BufferedImage.TYPE_INT_RGB);
                Graphics2D graphics = img.createGraphics();
                // clear the drawing area
                graphics.setPaint(Color.white);
                graphics.fill(new Rectangle2D.Float(0, 0, pgsize.width, pgsize.height));
                // render
                slide.draw(graphics);
                list.add(img);
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        return list;
    }
    /**
     * ppt 转成多个图片
     * @param pptInputStream
     * @return
     */
    public static List<BufferedImage> pptToImages(InputStream pptInputStream) {
        List<BufferedImage> list = new ArrayList<>();
        try {
            HSLFSlideShow ppt = new HSLFSlideShow(pptInputStream);
            pptInputStream.close();
            Dimension pgsize = ppt.getPageSize();
            for (HSLFSlide slide : ppt.getSlides()) {
                //设置字体
                for (HSLFShape shape : slide.getShapes()) {
                    if (shape instanceof HSLFTextShape) {
                        HSLFTextShape sh = (HSLFTextShape) shape;
                        List<HSLFTextParagraph> textParagraphs = sh.getTextParagraphs();
                        for (HSLFTextParagraph hslfTextParagraph : textParagraphs) {
                            List<HSLFTextRun> textRuns = hslfTextParagraph.getTextRuns();
                            for (HSLFTextRun hslfTextRun : textRuns) {
                                hslfTextRun.setFontFamily("宋体");
                                hslfTextRun.setFontIndex(1);
                            }
                        }
                    }
                }
                BufferedImage img = new BufferedImage(pgsize.width, pgsize.height, BufferedImage.TYPE_INT_RGB);
                Graphics2D graphics = img.createGraphics();
                // clear the drawing area
                graphics.setPaint(Color.white);
                graphics.fill(new Rectangle2D.Float(0, 0, pgsize.width, pgsize.height));
                // render
                slide.draw(graphics);
                list.add(img);
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        return list;
    }
    private static String getUUID(){
        return UUID.randomUUID().toString().replaceAll("-","");
    }
    public static void main(String[] args) throws IOException {
        String filePath = System.getProperty("user.dir") + File.separator + "media" + File.separator;
        //excel转换 需要初始化license，不加license或有水印。springboot或web服务 启动时初始化一次即可
        License aposeLic = new License();
        aposeLic.setLicense(new FileInputStream(System.getProperty("user.dir") + File.separator + "AsposeLicense" + File.separator + "license.xml"));

        List<BufferedImage> images = toImages(".xlsx", new FileInputStream(filePath + "test.xlsx"));
        for (int i = 0; i < images.size(); i++) {
            ImageIO.write(images.get(i),"jpeg",new FileOutputStream(filePath + "test"+(i+1)+".jpeg"));
        }
    }

}