POI读取word文件，（支持HSSF和XSSF两种方式）

POI读取word文件，（支持HSSF和XSSF两种方式）

参考：HSSF，XSSF，SXSSF三种方式

1.引用maven（版本必须一致）

   <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi</artifactId>
      <version>4.1.1</version>
    </dependency>
    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi-ooxml</artifactId>
      <version>4.1.1</version>
    </dependency>
    <dependency>
      <groupId>org.apache.poi</groupId>
      <artifactId>poi-scratchpad</artifactId>
      <version>4.1.1</version>
    </dependency>

2.读取word

public class POIUtil {

  /**
   * @Description: POI 读取  word
   * @create: 2019-07-27 9:48
   * @update logs
   */
  public static String readWord(String path) throws Exception {

//    WordExtractor extractor = new WordExtractor(is);

    String content = null;
    File file = new File(path);
    if (file.exists() && file.isFile()) {
      InputStream is = null;
      XWPFDocument xwpfDocument = null;
      POIXMLTextExtractor extractor = null;
      HWPFDocument hwpfDocument = null;
      WordExtractor wordExtractor = null;
      try {
        is = new FileInputStream(file);
        xwpfDocument = new XWPFDocument(is);
        extractor = new XWPFWordExtractor(xwpfDocument);
        // 文档文本内容
        content = extractor.getText();
//          // 文档图片内容
//          List<XWPFPictureData> pictures = docx.getAllPictures();
//          for (XWPFPictureData picture : pictures) {
//            byte[] bytev = picture.getData();
//            // 输出图片到磁盘
//            FileOutputStream out = new FileOutputStream(
//                "D:\\temp\\temp\\" + UUID.randomUUID() + picture.getFileName());
//            out.write(bytev);
//            out.close();
//          }
      } catch (FileNotFoundException e) {
      } catch (IOException e) {
      } catch (OLE2NotOfficeXmlFileException e) {//较低版本的word文件
        is = new FileInputStream(file);
        hwpfDocument = new HWPFDocument(is);
        wordExtractor = new WordExtractor(hwpfDocument);
        // 文档文本内容
        content = wordExtractor.getText();
      } finally {
        try {
          if (extractor != null) {
            extractor.close();
          }
          if (xwpfDocument != null) {
            xwpfDocument.close();
          }
          if (wordExtractor != null) {
            wordExtractor.close();
          }
          if (hwpfDocument != null) {
            hwpfDocument.close();
          }
          if (is != null) {
            is.close();
          }
        } catch (IOException e) {
        }
      }
    }
    return content;
  }

  public static void main(String[] args) {
    String path = "/Users/jj/Desktop/胜多负少的范德萨.doc";
//    String path = "/Users/jj/Desktop/测试1 2.doc";
//    String path = "/Users/jj/Desktop/测试1.docx";

    try {
      System.out.println(readWord(path));
    } catch (Exception e) {
      e.printStackTrace();
    }
  }


}