【Java】使用Apache POI识别PPT中的图片和文字，以及对应的大小、坐标、颜色、字体等

逃离我推掉我的手 2023-10-14 21:31 3阅读 0赞

本文介绍如何使用Apache POI识别PPT中的图片和文字，获取图片的数据、大小、尺寸、坐标，以及获取文字的字体、大小、颜色、坐标。

官方文档：https://poi.apache.org/components/slideshow/xslf-cookbook.html

官方文档和网上的资料介绍的很少，很多元素，需要一点点尝试才能获取到。

注意：本篇文章针对.pptx结尾的PPT文件

引入依赖：

<dependency>
                <groupId>org.apache.poi</groupId>
                <artifactId>poi</artifactId>
                <version>5.0.0</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.poi</groupId>
                <artifactId>poi-ooxml</artifactId>
                <version>5.0.0</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.poi</groupId>
                <artifactId>poi-scratchpad</artifactId>
                <version>5.0.0</version>
            </dependency>

核心代码：

private static final String FILE_PATH = "/Temp/PPT/test.pptx";
        private static final String OUTPUT_PATH = "/Temp/PPT/output/";
        private static final String RGBA_TEMPLATE = "rgba(%d,%d,%d,1)";
    
        public static void main(String[] args) {
        
            analysisPpt(FILE_PATH);
        }
    
        public static void analysisPpt(String filePath) {
        
            try {
        
                InputStream input = new FileInputStream(filePath);
                XMLSlideShow xss = new XMLSlideShow(input);
                //getSlides(); 返回幻灯片中找到的所有普通幻灯片
                List<XSLFSlide> xslfSlideList = xss.getSlides();
                for (XSLFSlide xslfSlide : xslfSlideList) {
        
                    //HSLFShape表示工作表中包含的所有形状（幻灯片或注释）
                    List<XSLFShape> shapes = xslfSlide.getShapes();
                    handleShapes(shapes);
                }
            } catch (Exception e) {
        
                e.printStackTrace();
            }
        }
    
        private static void handleShapes(final List<XSLFShape> shapes) throws Exception {
        
            for (XSLFShape shape : shapes) {
        
                if (shape instanceof XSLFGroupShape) {
        
                    XSLFGroupShape groupShape = ((XSLFGroupShape) shape);
                    // 对XSLFGroupShape进行递归处理
                    handleShapes(groupShape.getShapes());
                } else if (shape instanceof XSLFTextShape) {
        
                    XSLFTextShape xslfTextShape = ((XSLFTextShape) shape);
                    List<XSLFTextParagraph> textParagraphs = xslfTextShape.getTextParagraphs();
                    XSLFTextRun textRun = textParagraphs.get(0).getTextRuns().get(0);
                    Rectangle2D anchor = xslfTextShape.getAnchor();
                    PaintStyle fontColor = textRun.getFontColor();
                    Color color = null;
                    if (Objects.nonNull(fontColor)) {
        
                        if (fontColor instanceof PaintStyle.SolidPaint) {
        
                            PaintStyle.SolidPaint solidPaint = (PaintStyle.SolidPaint) fontColor;
                            color = solidPaint.getSolidColor().getColor();
                        } else if (fontColor instanceof XSLFTexturePaint) {
        
                            // 一些大标题是该类型，暂无法获取大标题文字颜色
                            XSLFTexturePaint texturePaint = (XSLFTexturePaint) fontColor;
                            System.out.println("todo: XSLFTexturePaint ");
                        } else {
        
                            System.out.println("not match: " + fontColor.getClass());
                        }
                    }
                    String fill = "";
                    if (Objects.nonNull(color)) {
        
                        fill = String.format(RGBA_TEMPLATE, color.getRed(), color.getGreen(), color.getBlue());
                    }
                    System.out.printf("[text]: %s \n[font]: %s [size]: %s [x,y]: (%s,%s) [color]: %s \n", xslfTextShape.getText(),
                            textRun.getFontFamily(), textRun.getFontSize(), anchor.getX(), anchor.getY(), fill);
                    System.out.println("----------------------------");
                } else if (shape instanceof XSLFPictureShape) {
        
                    XSLFPictureShape xslfPictureShape = ((XSLFPictureShape) shape);
                    XSLFPictureData pictureData = xslfPictureShape.getPictureData();
                    // 图片数据
                    byte[] data = pictureData.getData();
                    savePicture(data, pictureData.getFileName());
                    Dimension dimensionInPixels = pictureData.getImageDimensionInPixels();
                    Rectangle2D anchor = xslfPictureShape.getAnchor();
                    System.out.printf("[picture name]: %s: [size]: %s * %s [X,Y]: (%s,%s) \n", pictureData.getFileName(), dimensionInPixels.getWidth(),
                            dimensionInPixels.getHeight(), anchor.getX(), anchor.getY());
                } else {
        
                    System.out.println("unknown shape：" + shape.getClass());
                }
            }
        }
    
        private static void savePicture(final byte[] data, final String fileName) throws IOException {
        
            FileOutputStream out = new FileOutputStream(OUTPUT_PATH + fileName);
            out.write(data);
            out.close();
        }