Java中使用ApachePOI读取word文件简单示例

import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;

import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;

public class Test {
  public static void main(String[] args) {
    try {
      InputStream is = new FileInputStream(new File("2003.doc"));
      WordExtractor ex = new WordExtractor(is);
      String text2003 = ex.getText();
      System.out.println(text2003);

      OPCPackage opcPackage = POIXMLDocument.openPackage("2007.docx");
      POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
      String text2007 = extractor.getText();
      System.out.println(text2007);
      
    } catch (Exception e) {
      e.printStackTrace();
    }
  }
}