java读取word，excel和pdf文档内容_java使用poi读取odf文件中数据-优快云博客

import java.io.File;   
import java.io.FileInputStream;   
import org.apache.poi.hwpf.HWPFDocument;   
import org.apache.poi.hwpf.usermodel.Range;   

/** 
* 
* @author 曹胜欢
*/ 
public class DocFile{   


    @Override 
    public String getContent(File f) throws Exception {   
        FileInputStream fis = new FileInputStream(f);   
        HWPFDocument doc = new HWPFDocument(fis);   
        Range rang = doc.getRange();   
        String text = rang.text();   
        fis.close();   
        return text;   
    }

2. 引用 jxl 包读取 excel 文档的内容

[java] view plain copy print ?

import java.io.File;
import java.io.FileInputStream;
import jxl.Cell;
import jxl.Sheet;
import jxl.Workbook;
/**
*
* @author 曹胜欢
*/
public class XlsFile{
@Override
public String getContent(File f) throws Exception {
//构建Workbook对象, 只读Workbook对象
//直接从本地文件创建Workbook
//从输入流创建Workbook
FileInputStream fis = new FileInputStream(f);
StringBuilder sb = new StringBuilder();
jxl.Workbook rwb = Workbook.getWorkbook(fis);
//一旦创建了Workbook，我们就可以通过它来访问
//Excel Sheet的数组集合(术语：工作表)，
//也可以调用getsheet方法获取指定的工资表
Sheet[] sheet = rwb.getSheets();
for (int i = 0; i < sheet.length; i++) {
Sheet rs = rwb.getSheet(i);
for (int j = 0; j < rs.getRows(); j++) {
Cell[] cells = rs.getRow(j);
for(int k=0;k<cells.length;k++)
sb.append(cells[k].getContents());
}
}
fis.close();
return sb.toString();
}
}

import java.io.File;   
import java.io.FileInputStream;   
import jxl.Cell;   
import jxl.Sheet;   
import jxl.Workbook;   

/** 
* 
* @author 曹胜欢
*/ 
public class XlsFile{   

    @Override   
    public String getContent(File f) throws Exception {   
     //构建Workbook对象, 只读Workbook对象
     //直接从本地文件创建Workbook
      //从输入流创建Workbook

        FileInputStream fis = new FileInputStream(f);   
        StringBuilder sb = new StringBuilder();   
        jxl.Workbook rwb = Workbook.getWorkbook(fis);   
//一旦创建了Workbook，我们就可以通过它来访问
//Excel Sheet的数组集合(术语：工作表)，
//也可以调用getsheet方法获取指定的工资表
        Sheet[] sheet = rwb.getSheets();   
        for (int i = 0; i < sheet.length; i++) {   
            Sheet rs = rwb.getSheet(i);   
            for (int j = 0; j < rs.getRows(); j++) {   
               Cell[] cells = rs.getRow(j);   
               for(int k=0;k<cells.length;k++)   
               sb.append(cells[k].getContents());   
            }   
        }   
        fis.close();   
        return sb.toString();   
    }   

}

由上面代码我们可知：一旦得到了Sheet，我们就可以通过它来访问Excel Cell(术语：单元格)。参考下面的代码片段：
//获取第一行，第一列的值
Cell c00 = rs.getCell(0, 0);
String strc00 = c00.getContents();
//获取第一行，第二列的值
Cell c10 = rs.getCell(1, 0);
String strc10 = c10.getContents();
当你完成对Excel电子表格数据的处理后，一定要使用close()方法来关闭先前创建的对象，以释放读取数据表的过程中所占用的内存空间，在读取大量数据时显得尤为重要。

3.引用PDFBox读取pdf文档的内容

[java] view plain copy print ?

import java.io.File;
import java.io.FileInputStream;
import org.pdfbox.pdfparser.PDFParser;
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.util.PDFTextStripper;
/**
*
* @author 曹胜欢
*/
<PRE class=java name="code">public class PdfFile{
public String getContent(File f) throws Exception {
FileInputStream fis = new FileInputStream(f);
PDFParser p = new PDFParser(fis);
p.parse();
PDDocument pdd = p.getPDDocument();
PDFTextStripper ts = new PDFTextStripper();
String c = ts.getText(pdd);
pdd.close();
fis.close();
return c;
}
}</PRE><BR>

import java.io.File;   
import java.io.FileInputStream;   
import org.pdfbox.pdfparser.PDFParser;   
import org.pdfbox.pdmodel.PDDocument;   
import org.pdfbox.util.PDFTextStripper;   

/** 
* 
* @author 曹胜欢
*/ 
<div class="dp-highlighter bg_java" sizcache="28" sizset="68"><div class="bar" sizcache="28" sizset="68"><div class="tools" sizcache="28" sizset="68"><strong>[java]</strong> <a target=_blank class="ViewSource" title="view plain" href="http://blog.youkuaiyun.com/csh624366188/article/details/8161122#">view plain</a><a target=_blank class="CopyToClipboard" title="copy" href="http://blog.youkuaiyun.com/csh624366188/article/details/8161122#">copy</a><a target=_blank class="PrintSource" title="print" href="http://blog.youkuaiyun.com/csh624366188/article/details/8161122#">print</a><a target=_blank class="About" title="?" href="http://blog.youkuaiyun.com/csh624366188/article/details/8161122#">?</a></div></div><ol class="dp-j"><li class="alt"><span><span class="keyword">public</span><span> </span><span class="keyword">class</span><span> PdfFile{     </span></span></li><li><span>  </span></li><li class="alt"><span>    </span><span class="keyword">public</span><span> String getContent(File f) </span><span class="keyword">throws</span><span> Exception {     </span></li><li><span>        FileInputStream fis = </span><span class="keyword">new</span><span> FileInputStream(f);     </span></li><li class="alt"><span>        PDFParser p = </span><span class="keyword">new</span><span> PDFParser(fis);     </span></li><li><span>        p.parse();     </span></li><li class="alt"><span>        PDDocument pdd = p.getPDDocument();     </span></li><li><span>        PDFTextStripper ts = </span><span class="keyword">new</span><span> PDFTextStripper();     </span></li><li class="alt"><span>        String c = ts.getText(pdd);     </span></li><li><span>        pdd.close();     </span></li><li class="alt"><span>        fis.close();     </span></li><li><span>        </span><span class="keyword">return</span><span> c;     </span></li><li class="alt"><span>    }     </span></li><li><span>}  </span></li></ol></div><pre style="DISPLAY: none" class="java" name="code">public class PdfFile{   

    public String getContent(File f) throws Exception {   
        FileInputStream fis = new FileInputStream(f);   
        PDFParser p = new PDFParser(fis);   
        p.parse();   
        PDDocument pdd = p.getPDDocument();   
        PDFTextStripper ts = new PDFTextStripper();   
        String c = ts.getText(pdd);   
        pdd.close();   
        fis.close();   
        return c;   
    }   
}