使用Itext操作PDF,修改文本内容及指定位置插入图片

客官°小女子只卖身不卖艺 2022-11-21 15:12 1486阅读 0赞

参考博客：[修改文本的][Link 1]  
参考博客：[插入图片的][Link 2]

这里基于修改文本的博客编写的，主要解决了几个问题：  
1、文件乱码  
2、设置区域背景色  
3、设置文字字体颜色  
4、插入图片空指针  
5、指定位置插入偏移  
等等问题

准备工作  
1、创建一个或者自己找一个pdf。使用编辑器，编辑PDF（你也可以使用word，然后转PDF），在你期望的位置打上标记，比如我的是：$\{userName\} 这个标记后面会被替换成文本，也是插入图片的相对位置  
2、准备一个图片。 再想好操作完PDF后要输出PDF的路径

## 添加依赖 ##

pom文件添加：

<dependency>
                <groupId>com.itextpdf</groupId>
                <artifactId>itextpdf</artifactId>
                <version>5.4.3</version>
            </dependency>
    
            <dependency>
                <groupId>com.itextpdf</groupId>
                <artifactId>itext-asian</artifactId>
                <version>5.2.0</version>
            </dependency>

## 工具类 ##

我命名为：ItextPDFUtil 。下面代码可直接粘贴

public static final float defaultHeight = 16;
        public static final float fixHeight = 10;
    
    
    
    
        /**
         * @description: 查找插入签名图片的最终位置，因为是插入签名图片，所以之前的关键字应只会出现一次
         * 这里直接使用了第一次查找到关键字的位置，并返回该关键字之后的坐标位置
         * @return: float[0]:页码，float[1]:最后一个字的x坐标，float[2]:最后一个字的y坐标
         */
        public static float[] getAddImagePositionXY(String pdfName, String keyword) throws IOException { 
            float[] temp = new float[3];
            List<float[]> positions = findKeywordPostions(pdfName, keyword);
            temp[0] = positions.get(0)[0];
            temp[1] = positions.get(0)[1] + positions.get(0)[3];
            temp[2] = positions.get(0)[2] - (positions.get(0)[3] / 2);
    
            return temp;
        }
    
        /**
         * findKeywordPostions
         *  返回查找到关键字的首个文字的左上角坐标值
         *
         * @param pdfName
         * @param keyword
         * @return List<float [ ]> : float[0]:pageNum float[1]:x float[2]:y
         * @throws IOException
         */
        public static List<float[]> findKeywordPostions(String pdfName, String keyword) throws IOException { 
            File pdfFile = new File(pdfName);
            byte[] pdfData = new byte[(int) pdfFile.length()];
            FileInputStream inputStream = new FileInputStream(pdfFile);
            //从输入流中读取pdfData.length个字节到字节数组中，返回读入缓冲区的总字节数，若到达文件末尾，则返回-1
            inputStream.read(pdfData);
            inputStream.close();
    
            List<float[]> result = new ArrayList<>();
            List<PdfPageContentPositions> pdfPageContentPositions = getPdfContentPostionsList(pdfData);
    
    
            for (PdfPageContentPositions pdfPageContentPosition : pdfPageContentPositions) { 
                List<float[]> charPositions = findPositions(keyword, pdfPageContentPosition);
                if (charPositions == null || charPositions.size() < 1) { 
                    continue;
                }
                result.addAll(charPositions);
            }
            return result;
        }
    
    
    
        /**
         * findKeywordPostions
         *
         * @param pdfData 通过IO流 PDF文件转化的byte数组
         * @param keyword 关键字
         * @return List<float [ ]> : float[0]:pageNum float[1]:x float[2]:y
         * @throws IOException
         */
        public static List<float[]> findKeywordPostions(byte[] pdfData, String keyword) throws IOException { 
            List<float[]> result = new ArrayList<float[]>();
            List<PdfPageContentPositions> pdfPageContentPositions = getPdfContentPostionsList(pdfData);
    
    
            for (PdfPageContentPositions pdfPageContentPosition : pdfPageContentPositions) { 
                List<float[]> charPositions = findPositions(keyword, pdfPageContentPosition);
                if (charPositions == null || charPositions.size() < 1) { 
                    continue;
                }
                result.addAll(charPositions);
            }
            return result;
        }
    
    
        private static List<PdfPageContentPositions> getPdfContentPostionsList(byte[] pdfData) throws IOException { 
            PdfReader reader = new PdfReader(pdfData);
    
            List<PdfPageContentPositions> result = new ArrayList<PdfPageContentPositions>();
    
            int pages = reader.getNumberOfPages();
            for (int pageNum = 1; pageNum <= pages; pageNum++) { 
                float width = reader.getPageSize(pageNum).getWidth();
                float height = reader.getPageSize(pageNum).getHeight();
    
    
                PdfRenderListener pdfRenderListener = new PdfRenderListener(pageNum, width, height);
    
    
                //解析pdf，定位位置
                PdfContentStreamProcessor processor = new PdfContentStreamProcessor(pdfRenderListener);
                PdfDictionary pageDic = reader.getPageN(pageNum);
                PdfDictionary resourcesDic = pageDic.getAsDict(PdfName.RESOURCES);
                try { 
                    processor.processContent(ContentByteUtils.getContentBytesForPage(reader, pageNum), resourcesDic);
                } catch (IOException e) { 
                    reader.close();
                    throw e;
                }
    
    
                String content = pdfRenderListener.getContent();
                List<CharPosition> charPositions = pdfRenderListener.getcharPositions();
    
    
                List<float[]> positionsList = new ArrayList<float[]>();
                for (CharPosition charPosition : charPositions) { 
                    float[] positions = new float[]{ charPosition.getPageNum(), charPosition.getX(), charPosition.getY(), charPosition.getWidth(), charPosition.getHeight()};
                    positionsList.add(positions);
                }
    
    
                PdfPageContentPositions pdfPageContentPositions = new PdfPageContentPositions();
                pdfPageContentPositions.setContent(content);
                pdfPageContentPositions.setPostions(positionsList);
    
    
                result.add(pdfPageContentPositions);
            }
            reader.close();
            return result;
        }
    
    
        private static List<float[]> findPositions(String keyword, PdfPageContentPositions pdfPageContentPositions) { 
    
    
            List<float[]> result = new ArrayList<float[]>();
    
    
            String content = pdfPageContentPositions.getContent();
            List<float[]> charPositions = pdfPageContentPositions.getPositions();
    
    
            for (int pos = 0; pos < content.length(); ) { 
                int positionIndex = content.indexOf(keyword, pos);
                if (positionIndex == -1) { 
                    break;
                }
                float[] postions = charPositions.get(positionIndex);
                //此处较为关键通过第一个关键字计算出整个关键字的宽度
                for (int i = 1; i < keyword.length(); i++) { 
                    float[] postionsNew = charPositions.get(positionIndex + i);
                    postions[3] = postions[3] + postionsNew[3];
                }
                result.add(postions);
                pos = positionIndex + 1;
            }
            return result;
        }
    
    
        private static class PdfPageContentPositions { 
            private String content;
            private List<float[]> positions;
    
    
            public String getContent() { 
                return content;
            }
    
    
            public void setContent(String content) { 
                this.content = content;
            }
    
    
            public List<float[]> getPositions() { 
                return positions;
            }
    
    
            public void setPostions(List<float[]> positions) { 
                this.positions = positions;
            }
        }
    
    
        private static class PdfRenderListener implements RenderListener { 
            private int pageNum;
            private float pageWidth;
            private float pageHeight;
            private StringBuilder contentBuilder = new StringBuilder();
            private List<CharPosition> charPositions = new ArrayList<CharPosition>();
    
    
            public PdfRenderListener(int pageNum, float pageWidth, float pageHeight) { 
                this.pageNum = pageNum;
                this.pageWidth = pageWidth;
                this.pageHeight = pageHeight;
            }
    
    
            public void beginTextBlock() { 
            }
    
    
            public void renderText(TextRenderInfo renderInfo) { 
                List<TextRenderInfo> characterRenderInfos = renderInfo.getCharacterRenderInfos();
                for (TextRenderInfo textRenderInfo : characterRenderInfos) { 
                    String word = textRenderInfo.getText();
                    if (word.length() > 1) { 
                        word = word.substring(word.length() - 1, word.length());
                    }
                    Rectangle2D.Float rectangle = textRenderInfo.getAscentLine().getBoundingRectange();
    
                    float x = (float) rectangle.getX();
                    float y = (float) rectangle.getY();
    //                float x = (float)rectangle.getCenterX();
    //                float y = (float)rectangle.getCenterY();
    //                double x = rectangle.getMinX();
    //                double y = rectangle.getMaxY();
    
    
                    //这两个是关键字在所在页面的XY轴的百分比
                    float xPercent = Math.round(x / pageWidth * 10000) / 10000f;
                    float yPercent = Math.round((1 - y / pageHeight) * 10000) / 10000f; // CharPosition charPosition = new CharPosition(pageNum, xPercent, yPercent); CharPosition charPosition = new CharPosition(pageNum, x, y - fixHeight, (float) rectangle.getWidth(), (float) (rectangle.getHeight() == 0 ? defaultHeight : rectangle.getHeight()));
                    charPositions.add(charPosition);
                    contentBuilder.append(word);
                }
            }
    
    
            public void endTextBlock() { 
            }
    
    
            public void renderImage(ImageRenderInfo renderInfo) { 
            }
    
    
            public String getContent() { 
                return contentBuilder.toString();
            }
    
    
            public List<CharPosition> getcharPositions() { 
                return charPositions;
            }
        }
    
    
        private static class CharPosition { 
            private int pageNum = 0;
            private float x = 0;
            private float y = 0;
            private float width;
            private float height;
    
    
            public CharPosition(int pageNum, float x, float y, float width, float height) { 
                this.pageNum = pageNum;
                this.x = x;
                this.y = y;
                this.width = width;
                this.height = height;
            }
    
    
            public int getPageNum() { 
                return pageNum;
            }
    
    
            public float getX() { 
                return x;
            }
    
    
            public float getY() { 
                return y;
            }
    
            public float getWidth() { 
                return width;
            }
    
            public float getHeight() { 
                return height;
            }
    
            @Override
            public String toString() { 
                return "CharPosition{" +
                        "pageNum=" + pageNum +
                        ", x=" + x +
                        ", y=" + y +
                        ", width=" + width +
                        ", height=" + height +
                        '}';
            }
        }

## 调用的示例代码 ##

改一下main方法的命名就可以直接测试了

public class ItextPDFUtilDemo { 
        //输入的模版路径
        public static String inputFilePath = "C:\\Users\\Administrator\\Desktop\\TEST.pdf";
        //插入的文件路径
        public static String imgFilePath = "C:\\Users\\Administrator\\Desktop\\test图.png";
        //输出路径
        public static String out = "C:\\Users\\Administrator\\Desktop\\3.pdf";
        public static String keyword = "${userName}";//测试标记
    
       //插入图片的例子
        public static void main(String[] args) throws IOException, DocumentException { 
            //查找位置
            float[] position= ItextPDFUtil.getAddImagePositionXY(inputFilePath,keyword);
            //Read file using PdfReader
            PdfReader pdfReader = new PdfReader(inputFilePath);
            System.out.println("x:"+position[1]+" y:"+position[2]);
    
            //Modify file using PdfReader
            PdfStamper pdfStamper = new PdfStamper(pdfReader, new FileOutputStream(out));
    
            Image image = Image.getInstance(imgFilePath);
            //Fixed Positioning
    //        image.scaleToFit(100, 50);
            image.scaleAbsolute(100, 50);
            //Scale to new height and new width of image
            image.setAbsolutePosition(position[1], position[2]);
    
            System.out.println("pages:"+pdfReader.getNumberOfPages());
    
            PdfContentByte content = pdfStamper.getUnderContent((int) position[0]);
            content.addImage(image);
            pdfStamper.close();
    
        }
    
        //修改文字的示例
        public static void main1(String[] args) { 
            //1.给定文件
            File pdfFile = new File(inputFilePath);
            File imgFile = new File(imgFilePath);
    
            //2.定义一个byte数组，长度为文件的长度
            byte[] pdfData = new byte[(int) pdfFile.length()];
    
            //3.IO流读取文件内容到byte数组
            FileInputStream inputStream = null;
            try { 
                inputStream = new FileInputStream(pdfFile);
                inputStream.read(pdfData);
            } catch (IOException e) { 
                e.printStackTrace();
            } finally { 
                if (inputStream != null) { 
                    try { 
                        inputStream.close();
                    } catch (IOException e) { 
                    }
                }
            }
    
            //4.指定关键字
    
    
            String replace = " 王文博 先生";
    
            //5.调用方法，给定关键字和文件
            List<float[]> positions = null;
            try { 
                positions = ItextPDFUtil.findKeywordPostions(pdfData, keyword);
            } catch (IOException e) { 
                e.printStackTrace();
            }
    
            PdfReader pdfReader = null;
            PdfStamper stamper = null;
            try { 
                pdfReader = new PdfReader(pdfData);
                stamper = new PdfStamper(pdfReader, new FileOutputStream(out));
    
                if (positions != null) { 
                    for (int i = 0; i < positions.size(); i++) { 
                        float[] position = positions.get(i);
    
                        PdfContentByte canvas = stamper.getOverContent((int) position[0]); //修改背景色 canvas.saveState(); BaseColor baseColor = new BaseColor(23,71,158); // canvas.setColorFill(BaseColor.WHITE); canvas.setColorFill(baseColor); // canvas.setColorFill(BaseColor.BLUE); // 以左下点为原点，x轴的值，y轴的值，总宽度，总高度： // canvas.rectangle(mode.getX() - 1, mode.getY(), // mode.getWidth() + 2, mode.getHeight());
                        canvas.rectangle(position[1]-1, position[2]-1, position[3]+1, position[4]+4);
    
                       /* PdfGState gs = new PdfGState();
                        gs.setFillOpacity(0.3f);// 设置透明度为0.8
                        canvas.setGState(gs);*/
    
                        canvas.fill();
                        canvas.restoreState();
                        //替换关键字
                       canvas.beginText();
    
                        BaseFont bf = BaseFont.createFont("STSong-Light", "UniGB-UCS2-H", BaseFont.NOT_EMBEDDED);
                        canvas.setFontAndSize(bf, 13);
                        canvas.setTextMatrix(position[1]+3, position[2]);/*修正背景与文本的相对位置*/
                        //下面两行代码再次设置，设设置的字体的颜色
                        BaseColor baseColor1 = new BaseColor(255,255,255);
                        canvas.setColorFill(baseColor1);
    
                        canvas.showText(replace);
                        canvas.endText();
                    }
                }
            } catch (IOException e) { 
                e.printStackTrace();
            } catch (DocumentException e) { 
                e.printStackTrace();
            } finally { 
                if (stamper != null)
                    try { 
                        stamper.close();
                    } catch (DocumentException e) { 
                        e.printStackTrace();
                    } catch (IOException e) { 
                        e.printStackTrace();
                    }
                if (pdfReader != null) { 
                    pdfReader.close();
                }
            }
    
            //6.返回值类型是  List<float[]> 每个list元素代表一个匹配的位置，分别为 float[0]所在页码  float[1]所在x轴 float[2]所在y轴 float[3]关键字宽度 floatt[4]关键字高度
            System.out.println("total:" + positions.size());
            if (positions != null && positions.size() > 0)
    
            { 
                for (float[] position : positions) { 
                    System.out.print("pageNum: " + (int) position[0]);
                    System.out.print("\tx: " + position[1]);
                    System.out.println("\ty: " + position[2]);
                    System.out.println("\tw: " + position[3]);
                    System.out.println("\th: " + position[4]);
                }
            }
        }
    
    }

[Link 1]: https://blog.csdn.net/u011110982/article/details/99679149?utm_medium=distribute.pc_aggpage_search_result.none-task-blog-2~all~first_rank_v2~rank_v28-11-99679149.nonecase&utm_term=java%20%E6%9B%BF%E6%8D%A2pdf%E4%B8%AD%E7%9A%84%E6%96%87%E5%AD%97&spm=1000.2123.3001.4430
[Link 2]: https://blog.csdn.net/SOME___ONE/article/details/52562740?utm_medium=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_param&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_param