java读取pdf文档

╰半橙微兮° 2022-11-03 11:17 207阅读 0赞

使用maven引入pdfbox依赖

<dependency>
                <groupId>org.apache.pdfbox</groupId>
                <artifactId>pdfbox</artifactId>
                <version>2.0.1</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.pdfbox</groupId>
                <artifactId>fontbox</artifactId>
                <version>2.0.0</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.pdfbox</groupId>
                <artifactId>jempbox</artifactId>
                <version>1.8.11</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.pdfbox</groupId>
                <artifactId>xmpbox</artifactId>
                <version>2.0.0</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.pdfbox</groupId>
                <artifactId>preflight</artifactId>
                <version>2.0.0</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.pdfbox</groupId>
                <artifactId>pdfbox-tools</artifactId>
                <version>2.0.0</version>
            </dependency>

public static void main(String[] args) { 
    //要读取的pdf文档位置
            String path = "C:/Users/Administrator/Desktop/123.pdf";
            //File file = new File(path);
            try { 
                //XSSFWorkbook workbook = new XSSFWorkbook();
                //XSSFSheet sheet =workbook.createSheet();
                //加载pdf文件，创建PDDocument对象
                PDDocument document = PDDocument.load(file);
                //创建pdf文本获取对象PDFTextStripper 
                PDFTextStripper pdfStripper = new PDFTextStripper();
                //获取pdf中所有信息，text中包含的就是当前pdf文档中所有信息
                String text = pdfStripper.getText(document);
                //根据自己的业务需求处理text中的信息
                //String data =text.replaceAll("([\\u4e00-\\u9fa5]|[\\uff0c]|[\\u3001]|[\\u3002])\\s+([\\u4e00-\\u9fa5])","$1$2");
                //String [] str=data.split("\\n");
                /**for(int i=0;i< str.length;i++){ XSSFRow row=sheet.createRow(i); String string1=str[i].replaceAll(" ",""); String[] str2=string1.split(" "); if(str2.length>1){ for(int j=0;j<str2.length;j++){ if(str2[j].equals(null)||str2[j].equals("")){ continue; } XSSFCell cell=row.createCell(j); String data1=str2[j].replaceAll("\\r\\n|\\r|\\n",""); cell.setCellValue(data1); } }else { XSSFCell cell=row.createCell(0); cell.setCellValue(string1); } } FileOutputStream fileOutputStream=new FileOutputStream("C:/Users/Administrator/Desktop/ccs.xlsx"); workbook.write(fileOutputStream); fileOutputStream.close();*/
            } catch (Exception e) { 
    
            }
        }

**注释的内容是将pdf文件中的信息读取到excel表格，实际操作可按照自己业务需求进行**