java poi读取word内容

1.添加jar包

    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi</artifactId>
      <version>4.1.0</version>
    </dependency>

    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi-ooxml</artifactId>
      <version>4.1.0</version>
    </dependency>

      <dependency>
          <groupId>org.apache.poi</groupId>
          <artifactId>poi-ooxml-schemas</artifactId>
          <version>4.1.0</version>
      </dependency>
      <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-scratchpad -->
      <dependency>
          <groupId>org.apache.poi</groupId>
          <artifactId>poi-scratchpad</artifactId>
          <version>4.1.0</version>
      </dependency>

2.读取所有内容（非表格）

public static String readDoc(String path) {
	String resullt = "";
	//首先判断文件中的是doc/docx
	try {
	   if (path.endsWith(".doc")) {
	       InputStream is = new FileInputStream(new File(path));
	       WordExtractor extractor = new WordExtractor(is);
	       resullt = extractor.getText();
	
	       //输出word文档所有的文本
	       System.out.println(extractor.getText());
	       System.out.println("=================1=================");
	       System.out.println("==================2================");
	//                //输出页脚的内容
	       System.out.println("页脚：" + extractor.getDocument());
	//                System.out.println("===============4===================");
	//                //输出当前word文档的元数据信息，包括作者、文档的修改时间等。
	       System.out.println(extractor.getMetadataTextExtractor().getText());
	       System.out.println("===============5===================");
	       //获取各个段落的文本
	       String paraTexts[] = extractor.getParagraphText();
	       for (int i=0; i<paraTexts.length; i++) {
	           System.out.println("Paragraph " + (i+1) + " : " + paraTexts[i]);
	       }
	       //输出当前word的一些信息
	       System.out.println(extractor.getTextFromPieces());
	       System.out.println("=============6=====================");
	       //输出当前word的一些信息
	       System.out.println(extractor.getMetadataTextExtractor());
	       System.out.println("===============7===================");
	       System.out.println(extractor.getEndnoteText());
	       System.out.println("===============8===================");
	
	
	
	       extractor.close();
	   } else if (path.endsWith(".docx")) {
	       OPCPackage opcPackage = POIXMLDocument.openPackage(path);
	       POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
	       resullt = extractor.getText();
	
	       extractor.close();
	   } else {
	       System.out.println("此文件不是word文件");
	   }
	} catch(Exception e){
	   e.printStackTrace();
	}
	return resullt;
}

3.读取表格内容

以下代码包含读取段落内容、表格内容

    public static void readTableData(String path){
        try {
            InputStream is = new FileInputStream(path);
            XWPFDocument doc = new XWPFDocument(is);
            List<XWPFParagraph> paras = doc.getParagraphs();
            for (XWPFParagraph para : paras) {
                //当前段落的属性
                //CTPPr pr = para.getCTP().getPPr();
                System.out.println(para.getText());
            }

            //获取文档中所有的表格
            List<XWPFTable> tables = doc.getTables();
            List<XWPFTableRow> rows;
            List<XWPFTableCell> cells;
            for (XWPFTable table : tables) {
                //表格属性
                //CTTblPr pr = table.getCTTbl().getTblPr();

                //获取表格对应的行
                rows = table.getRows();
                for (XWPFTableRow row : rows) {
                    //获取行对应的单元格
                    cells = row.getTableCells();
                    for (XWPFTableCell cell : cells) {
                        System.out.println(cell.getText());
                    }
                }
            }
            is.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

参考文章：java poi word 表格_java 使用POI 读写word 表格 https://blog.csdn.net/weixin_33045961/article/details/114433011