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。

  点击这里 查看相关控件的下载地址和配置方法。

WORD

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

 

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);
                       &nbsp;for (int rowNumOfSheet = 0; rowNumOfSheet <= 
                             aSheet.getLastRowNum(); rowNumOfSheet++) {
				if (null != aSheet.getRow(rowNumOfSheet)) {
				HSSFRow aRow = aSheet.getRow(rowNumOfSheet); 							
				for (int cellNumOfRow = 0; cellNumOfRow <= 
				        aRow.getLastCellNum(); cellNumOfRow++) {
					if (null != aRow.getCell(cellNumOfRow)) {
					HSSFCell aCell = aRow.getCell(cellNumOfRow);									
					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.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
        return buff.toString();
	}			 
} 

PDF

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;
    }

}

   TXT

package textReader;
import java.io.*;


public class TxtReader {
	public TxtReader() {		
	}
	/**
	 * @param filePath 文件路径
	 * @return 读出的txt的内容
	 */
	public String getTextFromTxt(String filePath) throws Exception {
		
		FileReader fr = new FileReader(filePath);
		BufferedReader br = new BufferedReader(fr);
		StringBuffer buff = new StringBuffer();
		String temp = null;
		while((temp = br.readLine()) != null){
			buff.append(temp + "\r\n");
		}
		br.close();		
		return buff.toString();		
	}
}

RTF

package textReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;

import javax.swing.text.BadLocationException;
import javax.swing.text.DefaultStyledDocument;
import javax.swing.text.rtf.RTFEditorKit;


public class RtfReader {
	public RtfReader(){
	}
	/**
	 * @param filePath 文件路径
	 * @return 读出的rtf的内容
	 */
	public String getTextFromRtf(String filePath) {
		String result = null;
		File file = new File(filePath);
		try {	    
		    DefaultStyledDocument styledDoc = new DefaultStyledDocument();
		    InputStream is = new FileInputStream(file);
		    new RTFEditorKit().read(is, styledDoc, 0);
		    result = new String(styledDoc.getText(0,styledDoc.getLength()).
                                    getBytes("ISO8859_1"));
		    //提取文本，读取中文需要使用ISO8859_1编码，否则会出现乱码
		} catch (IOException e) {
			e.printStackTrace();
		} catch (BadLocationException e) {
			e.printStackTrace();
		}
		return result;
	}	
}

HTML

package textReader;
import java.io.*;

public class HtmlReader {
	public HtmlReader() {
	}
	/**
	 * @param filePath 文件路径
	 * @return 获得html的全部内容
	 */
	public String readHtml(String filePath) {
		BufferedReader br=null;
		StringBuffer sb = new  StringBuffer();
		try {
			br=new BufferedReader(new InputStreamReader(
                                     new FileInputStream(filePath),  "GB2312"));			
			String temp=null;		
			while((temp=br.readLine())!=null){
				sb.append(temp);
			}			
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
		return sb.toString();
	}
	/**
	 * @param filePath 文件路径
	 * @return 获得的html文本内容
	 */
	public String getTextFromHtml(String filePath) {
		//得到body标签中的内容
		String str= readHtml(filePath);
		StringBuffer buff = new StringBuffer();
		int maxindex = str.length() - 1;
		int begin = 0;
		int end;			
		//截取>和<之间的内容
		while((begin = str.indexOf('>',begin)) < maxindex){			
			end = str.indexOf('<',begin);
			if(end - begin > 1){
				buff.append(str.substring(++begin, end));				
			}			
			begin = end+1;
		};		
		return buff.toString();
	}

}

 注意 ：若使用WPS编辑相关文档，会有错误提示，应避免。错误文本提示如下：

WORD

 

Your document seemed to be mostly unicode, but the section definition was in bytes! Trying anyway, but things may well go wrong!

EXCEL

 

java.lang.RuntimeException: Expected an EXTERNSHEET record but got (org.apache.poi.hssf.record.SSTRecord)
at org.apache.poi.hssf.model.LinkTable.readExtSheetRecord(LinkTable.java:187)
at org.apache.poi.hssf.model.LinkTable.<init>(LinkTable.java:163)
at org.apache.poi.hssf.model.Workbook.createWorkbook(Workbook.java:199)
at org.apache.poi.hssf.usermodel.HSSFWorkbook.<init>(HSSFWorkbook.java:273)
at org.apache.poi.hssf.usermodel.HSSFWorkbook.<init>(HSSFWorkbook.java:196)
at org.apache.poi.hssf.usermodel.HSSFWorkbook.<init>(HSSFWorkbook.java:312)
at org.apache.poi.hssf.usermodel.HSSFWorkbook.<init>(HSSFWorkbook.java:293)
at textReader.ExcelReader.getTextFromExcel(ExcelReader.java:23)
at DocumentInfo.getContent(DocumentInfo.java:86)
at MainFunction.main(MainFunction.java:19)

RTF

 

java.io.IOException: Too many close-groups in RTF text
at javax.swing.text.rtf.RTFParser.write(Unknown Source)
at javax.swing.text.rtf.RTFParser.writeSpecial(Unknown Source)
at javax.swing.text.rtf.AbstractFilter.write(Unknown Source)
at javax.swing.text.rtf.AbstractFilter.readFromStream(Unknown Source)
at javax.swing.text.rtf.RTFEditorKit.read(Unknown Source)
at textReader.RtfReader.getTextFromRtf(RtfReader.java:25)
at DocumentInfo.getContent(DocumentInfo.java:74)
at MainFunction.main(MainFunction.java:19)

 

顺便说一下，这里为什么会在write出错呢？因为 level是根据{和}来进行自增和自减的，当括号不匹配的时候就会提示该错误。 wps编辑rtf文件在格式上出了问题，{和}不匹配。 但用word或写字板下新建文件，编辑后另存为rtf文件（wps下不支持），用记事本打开可以发现添加了很多格式说明，但是{和}是匹配的，这样才不会报错。下面是具体说明：

http://www.chinaitpower.com/source/jdk122/javax/swing/text/rtf/RTFParser.java.html

 

（完）

create@2009-08-17