用java读取word2003和word2007的内容

需要使用apache的poi开源项目包；下载地址：http://poi.apache.org/download.html

引入其中的6个包poi-3.8-20120326.jar；poi-ooxml-3.8-20120326.jar；poi-ooxml-schemas-3.8-20120326.jar；poi-scratchpad-3.8-20120326.jar；xmlbeans-2.3.0.jar；dom4j-1.6.1.jar。

 

java的函数代码如下：

private void readWord2007() {
try {
OPCPackage oPCPackage = POIXMLDocument.openPackage("e:/test.docx");
XWPFDocument xwpf = new XWPFDocument(oPCPackage);
POIXMLTextExtractor ex = new XWPFWordExtractor(xwpf);
System.out.print(ex.getText());

oPCPackage.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}

private void readWord2003() {
try {
FileInputStream fis = new FileInputStream("e:/test.doc");
WordExtractor wordExtractor = new WordExtractor(fis);
System.out.println(wordExtractor.getText());
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}