标签:
暂时只写读取word内容的方法。
依赖的jar:
poi-3.9-20121203.jar
poi-ooxml-3.9-20121203.jar
xmlbeans-2.3.0.jar
package com.word; 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; /** * @author QiaoJiafei * @version 创建时间:2016年2月22日 上午11:30:04 * 类说明 */ public class OptionWord { public static void main(String[] args) { // TODO Auto-generated method stub } public static StringBuffer readWord(String path) { String s = ""; try { if(path.endsWith(".doc")) { InputStream is = new FileInputStream(new File(path)); WordExtractor ex = new WordExtractor(is); s = ex.getText(); }else if (path.endsWith("docx")) { OPCPackage opcPackage = POIXMLDocument.openPackage(path); POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage); s = extractor.getText(); }else { System.out.println("传入的word文件不正确:"+path); } } catch (Exception e) { e.printStackTrace(); } StringBuffer bf = new StringBuffer(s); return bf; } }
标签:
原文地址:http://www.cnblogs.com/qiaoyeye/p/5206626.html