JAVA读取WORD,EXCEL,PDF,TXT,RTF,HTML文件文本内容的方法示例

以下是Java对几种文本文件内容读取代码。其中，OFFICE文档（WORD,EXCEL）使用了POI控件，PDF使用了PDFBOX控件。

WORD

Java代码

package textReader;

import java.io.*;

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

public class WordReader {

public WordReader(){

}

/**

* @param filePath 文件路径

* @return 读出的Word的内容

*/

public String getTextFromWord(String filePath){

String result = null;

File file = new File(filePath);

try{

FileInputStream fis = new FileInputStream(file);

WordExtractor wordExtractor = new WordExtractor(fis);

result = wordExtractor.getText();

}catch(FileNotFoundException e){

e.printStackTrace();

}catch(IOException e){

e.printStackTrace();

};

return result;

}

}

EXCEL

Java代码

package textReader;

import org.apache.poi.hssf.usermodel.HSSFWorkbook;

import org.apache.poi.hssf.usermodel.HSSFSheet;

import org.apache.poi.hssf.usermodel.HSSFRow;

import org.apache.poi.hssf.usermodel.HSSFCell;

import java.io.FileInputStream;

import java.io.FileNotFoundException;

import java.io.IOException;

public class ExcelReader {

@SuppressWarnings("deprecation")

/**

* @param filePath 文件路径

* @return 读出的Excel的内容

*/

public String getTextFromExcel(String filePath) {

StringBuffer buff = new StringBuffer();

try {

//创建对Excel工作簿文件的引用

HSSFWorkbook wb = new HSSFWorkbook(new FileInputStream(filePath));

//创建对工作表的引用。

for (int numSheets = 0; numSheets < wb.getNumberOfSheets(); numSheets++) {

if (null != wb.getSheetAt(numSheets)) {

HSSFSheet aSheet = wb.getSheetAt(numSheets);//获得一个sheet

for (int rowNumOfSheet = 0; rowNumOfSheet <= aSheet.getLastRowNum(); rowNumOfSheet++) {

if (null != aSheet.getRow(rowNumOfSheet)) {

HSSFRow aRow = aSheet.getRow(rowNumOfSheet); //获得一个行

for (int cellNumOfRow = 0; cellNumOfRow <= aRow.getLastCellNum(); cellNumOfRow++) {

if (null != aRow.getCell(cellNumOfRow)) {

HSSFCell aCell = aRow.getCell(cellNumOfRow);//获得列值

switch(aCell.getCellType()){

case HSSFCell.CELL_TYPE_FORMULA:

break;

case HSSFCell.CELL_TYPE_NUMERIC:

buff.append(aCell.getNumericCellValue()).append('\t');break;

case HSSFCell.CELL_TYPE_STRING:

buff.append(aCell.getStringCellValue()).append('\t');break;

}

}

}

buff.append('\n');

}

}

}

}

} catch (FileNotFoundException e) {

e.printStackT
9c2d
race();

} catch (IOException e) {

e.printStackTrace();

}

return buff.toString();

}

}

PDF

Java代码

package textReader;

import java.io.FileInputStream;

import java.io.FileNotFoundException;

import java.io.IOException;

import org.pdfbox.pdfparser.PDFParser;

import org.pdfbox.pdmodel.PDDocument;

import org.pdfbox.util.PDFTextStripper;

public class PdfReader {

public PdfReader(){

}

/**

* @param filePath 文件路径

* @return 读出的pdf的内容

*/

public String getTextFromPdf(String filePath) {

String result = null;

FileInputStream is = null;

PDDocument document = null;

try {

is = new FileInputStream(filePath);

PDFParser parser = new PDFParser(is);

parser.parse();

document = parser.getPDDocument();

PDFTextStripper stripper = new PDFTextStripper();

result = stripper.getText(document);

} catch (FileNotFoundException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

} finally {

if (is != null) {

try {is.close();}catch(IOException e){e.printStackTrace();}

}

if (document != null) {

try{document.close();}catch (IOException e){e.printStackTrace();}

}

}

return result;

}

}