读取word中的内容

/**
 * 利用POI实现从word中读取内容
 */

============================================

将读取的内容写入另外一个文件中

package com.cy;
/**
 * WordReader类中readDoc的作用为从word中将数据读出
 */

import com.cy.WordWriter;
import java.io.ByteArrayInputStream;
import java.io.FileOutputStream;
import java.io.IOException;

import org.apache.poi.poifs.filesystem.DirectoryEntry;
import org.apache.poi.poifs.filesystem.DocumentEntry;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;

public class WordWriter {
 public static boolean writeDoc(String path, String content) {
  boolean w = false;
  try {

// byte b[] = content.getBytes("ISO-8859-1");
  byte b[] = content.getBytes();

ByteArrayInputStream bais = new ByteArrayInputStream(b);

POIFSFileSystem fs = new POIFSFileSystem();
  DirectoryEntry directory = fs.getRoot();

DocumentEntry de = directory.createDocument("WordDocument", bais);

FileOutputStream ostream = new FileOutputStream(path);

fs.writeFilesystem(ostream);

bais.close();
  ostream.close();

} catch (IOException e) {
  e.printStackTrace();
  }
  return w;
  }
  public static void main(String[] args) throws Exception{
  String wr=WordReader.readDoc("D://test.doc");
  boolean b = writeDoc("D://result.doc",wr);
  }
}
 //目前该程序只能实现对简单的文字的操作，无法实现对表格样式的操作，继续改进，请关注！！

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

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

public class WordReader {
 public static String readDoc(String doc) throws Exception {

// 创建输入流读取DOC文件

FileInputStream in = new FileInputStream(new File(doc));

WordExtractor extractor = null;

String text = null;

// 创建WordExtractor

extractor = new WordExtractor(in);

// 对DOC文件进行提取

text = extractor.getText();

return text;

}
 
 
 public static void main(String[] args) {

try{
           String text = WordReader.readDoc("d://test.doc");
           System.out.println(text);
        }catch(Exception e){
            e.printStackTrace();
        }

}

}

摘自：http://blog.csdn.net/sunrise353/article/details/1762324

import java.io.File;

import java.io.FileInputStream;

import java.io.FileNotFoundException;

import org.apache.poi.hwpf.HWPFDocument;

import org.apache.poi.hwpf.usermodel.Paragraph;

import org.apache.poi.hwpf.usermodel.Range;

import org.apache.poi.hwpf.usermodel.Table;

import org.apache.poi.hwpf.usermodel.TableCell;

import org.apache.poi.hwpf.usermodel.TableIterator;

import org.apache.poi.hwpf.usermodel.TableRow;

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;

import org.apache.poi.poifs.filesystem.POIFSFileSystem;

public class ExportDocImpl {

public void testWord(){

try{

FileInputStream in = new FileInputStream("D:\\sinye.doc");//载入文档

POIFSFileSystem pfs = new POIFSFileSystem(in);

HWPFDocument hwpf = new HWPFDocument(pfs);

Range range = hwpf.getRange();//得到文档的读取范围

TableIterator it = new TableIterator(range);

//迭代文档中的表格

while (it.hasNext()) {

Table tb = (Table) it.next();

//迭代行，默认从0开始

for (int i = 0; i < tb.numRows(); i++) {

TableRow tr = tb.getRow(i);

//迭代列，默认从0开始

for (int j = 0; j < tr.numCells(); j++) {

TableCell td = tr.getCell(j);//取得单元格

//取得单元格的内容

for(int k=0;k<td.numParagraphs();k++){

Paragraph para =td.getParagraph(k);

String s = para.text();

System.out.println(s);

} //end for

}   //end for

}   //end for

} //end while

}catch(Exception e){

e.printStackTrace();

}

}//end method

public void testWord1(){

try {

//word 2003： 图片不会被读取

InputStream is = new FileInputStream(new File("D:\\sinye.doc"));

WordExtractor ex = new WordExtractor(is);

String text2003 = ex.getText();

System.out.println(text2003);

//word 2007 图片不会被读取， 表格中的数据会被放在字符串的最后

OPCPackage opcPackage = POIXMLDocument.openPackage("D:\\sinye.doc");

POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);

String text2007 = extractor.getText();

System.out.println(text2007);

} catch (Exception e) {

e.printStackTrace();

}

}

}

import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.hwpf.usermodel.Table;
import org.apache.poi.hwpf.usermodel.TableCell;
import org.apache.poi.hwpf.usermodel.TableIterator;
import org.apache.poi.hwpf.usermodel.TableRow;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;  import org.apache.poi.poifs.filesystem.POIFSFileSystem;public class ExportDocImpl
{public void testWord(){try{FileInputStream in = new FileInputStream("D:\\sinye.doc");//载入文档POIFSFileSystem pfs = new POIFSFileSystem(in);   HWPFDocument hwpf = new HWPFDocument(pfs);   Range range = hwpf.getRange();//得到文档的读取范围TableIterator it = new TableIterator(range);//迭代文档中的表格while (it.hasNext()) {   Table tb = (Table) it.next();   //迭代行，默认从0开始for (int i = 0; i < tb.numRows(); i++) {   TableRow tr = tb.getRow(i);   //迭代列，默认从0开始for (int j = 0; j < tr.numCells(); j++) {   TableCell td = tr.getCell(j);//取得单元格//取得单元格的内容for(int k=0;k<td.numParagraphs();k++){   Paragraph para =td.getParagraph(k);   String s = para.text();   System.out.println(s);} //end for    }   //end for}   //end for} //end while}catch(Exception e){e.printStackTrace();}}//end methodpublic void testWord1(){try {   //word 2003： 图片不会被读取   InputStream is = new FileInputStream(new File("D:\\sinye.doc"));   WordExtractor ex = new WordExtractor(is);   String text2003 = ex.getText();   System.out.println(text2003);   //word 2007 图片不会被读取， 表格中的数据会被放在字符串的最后   OPCPackage opcPackage = POIXMLDocument.openPackage("D:\\sinye.doc");   POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);   String text2007 = extractor.getText();   System.out.println(text2007);   } catch (Exception e) {   e.printStackTrace();   } }
}