import org.apache.poi.POITextExtractor; 

import org.apache.poi.hwpf.extractor.WordExtractor; 

//得到.doc文件提取器 

org.apache.poi.hwpf.extractor.WordExtractor doc = new WordExtractor(new FileInputStream(filePath)); 

//提取.doc正文文本 

String text = doc.getText(); 

//提取.doc批注 

String[] comments = doc. getCommentsText(); 



2007 



import org.apache.poi.POITextExtractor; 

import org.apache.poi.xwpf.extractor.XWPFWordExtractor; 

import org.apache.poi.xwpf.usermodel.XWPFComment; 

import org.apache.poi.xwpf.usermodel.XWPFDocument; 

//得到.docx文件提取器 

org.apache.poi.xwpf.extractor.XWPFWordExtractor docx = new XWPFWordExtractor(POIXMLDocument.openPackage(filePath)); 

//提取.docx正文文本 

String text = docx.getText(); 

//提取.docx批注 

org.apache.poi.xwpf.usermodel.XWPFComment[] comments = docx.getDocument()).getComments(); 

for(XWPFComment comment:comments){ 

comment.getId();//提取批注Id 

comment.getAuthor();//提取批注修改人 

comment.getText();//提取批注內(nèi)容 

} 

五：利用POI提取Word總頁(yè)數(shù)、總字符數(shù)... 

97-2003 

WordExtractor doc = new WordExtractor(new FileInputStream(filePath));//.doc格式Word文件提取器 

int pages = doc.getSummaryInformation().getPageCount();//總頁(yè)數(shù) 

int wordCount = doc.getSummaryInformation().getWordCount();//總字符數(shù) 

2007: 



XWPFDocument docx = nnew XWPFDocument(POIXMLDocument.openPackage(filePath)); 



int pages = docx.getProperties().getExtendedProperties().getUnderlyingProperties().getPages();//總頁(yè)數(shù) 

int characters = docx.getProperties().getExtendedProperties().getUnderlyingProperties().getCharacters();// 忽略空格的總字符數(shù) 另外還有g(shù)etCharactersWithSpaces()方法獲取帶空格的總字?jǐn)?shù)。 
    

      package org.shirdrn.word; 



import java.io.File; 

import java.io.FileInputStream; 

import java.io.FileNotFoundException; 

import java.io.IOException; 



import org.apache.poi.hwpf.extractor.WordExtractor; 



public class MyWordExtractor { 



public static void main(String[] args) { 

   File file = new File("E:\\POI\\word\\JBoss3.0 下配置和部署EJB簡(jiǎn)介.doc"); 

   try { 

    FileInputStream fis = new FileInputStream(file); 

    WordExtractor wordExtractor = new WordExtractor(fis); 

    System.out.println("【 使用getText()方法提取的Word文件的內(nèi)容如下所示：】"); 

    System.out.println(wordExtractor.getText()); 

   } catch (FileNotFoundException e) { 

    e.printStackTrace(); 

   } catch (IOException e) { 

   e.printStackTrace(); 

} 

} 

} 
    

      package org.shirdrn.word; 



import java.io.File; 

import java.io.FileInputStream; 

import java.io.FileNotFoundException; 

import java.io.IOException; 



import org.apache.poi.hwpf.extractor.WordExtractor; 



public class MyWordExtractor { 



public static void main(String[] args) { 

   File file = new File("E:\\POI\\word\\JBoss3.0 下配置和部署EJB簡(jiǎn)介.doc"); 

   try { 

    FileInputStream fis = new FileInputStream(file); 

    WordExtractor wordExtractor = new WordExtractor(fis); 

    System.out.println("【 使用getText()方法提取的Word文件的內(nèi)容如下所示：】"); 

    String[] paragraph = wordExtractor.getParagraphText(); 

    System.out.println("該Word文件共有"+paragraph.length+"段。"); 

    for(int i=0;i<paragraph.length;i++){ 

     System.out.println("< 第 "+(i+1)+" 段的內(nèi)容為 >"); 

     System.out.println(paragraph[i]); 

    } 

   } catch (FileNotFoundException e) { 

    e.printStackTrace(); 

   } catch (IOException e) { 

   e.printStackTrace(); 

} 

} 

}