文档解析

    解析常见的word,excle,ppt,pdf等文档转换成字符串输出。

word解析:

    word解析采用apche的开源poi技术,用的时候把里面所有的jar包都需装上

    public static void main(String[] args) {

// TODO Auto-generated method stub

//读取word文件，指定文件路径

File file=new File("D:/软件/qq消息/2846227347/FileRecv/qq.doc");    

//封装到流中

InputStream fileInputStream = null;

try {

fileInputStream = new FileInputStream(file);

} catch (FileNotFoundException e1) {

// TODO Auto-generated catch block

e1.printStackTrace();

}

try {//微软的解析

XWPFDocument xwpfDocument=new XWPFDocument(fileInputStream);

XWPFWordExtractor xwpfWordExtractor=new XWPFWordExtractor(xwpfDocument);

//WordExtractor wordExtractor=new WordExtractor(fileInputStream);

String text = xwpfWordExtractor.getText();

//wordExtractor.getParagraphText();

System.out.println(text);

} catch (Exception e) {

// TODO Auto-generated catch block

e.printStackTrace();

try {//金山的解析

fileInputStream=new FileInputStream(file);

WordExtractor wordExtractor=new WordExtractor(fileInputStream);

String text = wordExtractor.getText();//获取文本内容直接打印输出

System.out.println(text);

String textFromPieces = wordExtractor.getTextFromPieces();

System.out.println(textFromPieces);

String[] commentsText = wordExtractor.getCommentsText();

for (String string : commentsText) {

System.out.println(string);

}

System.out.println(textFromPieces);

} catch (Exception e2) {

// TODO: handle exception

}

}

     excle解析:

    还是采用poi技术

       public static void main(String[] args) {

// TODO Auto-generated method stub

//作为两个实例用，过程一样

String fileAddr="C:/Users/kaitao/Desktop/打印/请问.xls";

String file2Addr="D:/新建 Microsoft Excel 工作表.xlsx";

File file=new File(fileAddr);

File file2=new File(file2Addr);

FileInputStream fileInputStream=null;

try {

fileInputStream = new FileInputStream(file2);

} catch (FileNotFoundException e2) {

// TODO Auto-generated catch block

e2.printStackTrace();

}

//程序按理说也可以向worder的方式运行，但是程序表示流以关闭，之后试着用了很多方式，都不行，最后只能进行判断了

if (file2Addr.substring(file2Addr.lastIndexOf(".")).equals(".xls")) {

try {//解析xls

HSSFWorkbook wb=new HSSFWorkbook(fileInputStream);

ExcelExtractor excelExtractor=new ExcelExtractor(wb);

String text = excelExtractor.getText();

System.out.println(text);

excelExtractor.close();

wb.close();

} catch (Exception e1) {

// TODO Auto-generated catch block

e1.printStackTrace();

}

}else if (file2Addr.substring(file2Addr.lastIndexOf(".")).equals(".xlsx")) {

try {

XSSFWorkbook xssfWorkbook=new XSSFWorkbook(fileInputStream);

for (Sheet sheet : xssfWorkbook) {

for (Row row : sheet) {

for (Cell cell : row) {

System.out.println(cell);

}

}

}

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

    pdf解析:

    采用的pdfbox这个开源技术，同样把所有的jar包导进去，映射版的pdf文件不能解析，大家可以试着用itext7试试看

        public static void main(String[] args) {

// TODO Auto-generated method stub

File file=new File("C://Users//kaitao//Desktop//打印//we.pdf");

InputStream inputStream= null;

try {

inputStream=new FileInputStream(file);

} catch (FileNotFoundException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

DataInputStream dataInputStream=new DataInputStream(inputStream);

try {

PDDocument load = PDDocument.load(fileInputStream);

PDFTextStripper pdfTextStripper=new PDFTextStripper();

String text = pdfTextStripper.getText(load);

System.out.println(text);

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

    ppt解析:

    采用的还是poi的开源技术,只能解析ppt形式的pptx形式的解析不了。

        public static void main(String[] args) {

        InputStream inputStream = null;

try {

inputStream = new FileInputStream("C:/Users/kaitao/Desktop/打印/请问.ppt");

} catch (FileNotFoundException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

          try {

PowerPointExtractor extractor = new PowerPointExtractor(inputStream);

String text = extractor.getText();

  System.out.println(text);

       } catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}