POI简单读取word(把word读取成txt格式)

  /**
     * 段落读取
     *
     * @param in 文件输入流
     * @throws IOException IO流异常
     */
    public void read(FileInputStream in) throws IOException {
        WordExtractor we = new WordExtractor(in);
        String[] strArray = we.getParagraphText();//按段落读取word
        for (; i < strArray.length; i++) {
            System.out.print("第" + (i + 1) + "段 is " + strArray[i]);
           
            }

        }
    }



 /**
     * 读取word全部内容
     * @param in 
     */
    public void readWord(FileInputStream in) {
        try {
            //读取word文档   
            HWPFDocument doc = new HWPFDocument(in);
            Range rang = doc.getRange();//
            int num = rang.numParagraphs();//获取段
            String text = rang.text();//获取文本内容(文件稍微大点就无法读取)  
            System.out.println("该文档共" + num + "段");//空行也算一段
            System.out.println("word content is" + text);
            in.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

 

posted @ 2015-05-08 15:21  悠悠天不老  阅读(272)  评论(0)    收藏  举报