java는 ppt 파일과poi를 사용하여 excel,word 예시를 읽습니다

Apache의 POI 프로젝트는 MS Office 문서를 처리하는 데 사용할 수 있으며, codeplex에 그것의 것이 하나 더 있습니다.net 버전.POI 프로젝트는 OOXML 및 OLE2 파일 형식을 기반으로 하는 다양한 Java API를 만들고 유지관리할 수 있습니다.대부분의 MS Office는 OLE2 형식입니다.POI 통 HSMF 하위 프로젝트는 Outlook을 지원하고, HDGF 하위 프로젝트를 통해 Visio를 지원하며, HPBF 하위 프로젝트를 통해 Publisher를 지원합니다.
POI 추출 Word를 사용한 간단한 예:
poi-3.7.jat와poi-scratchpad-3.7.ajr 이 가방 두 개.

package msoffice;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.hwpf.usermodel.CharacterRun;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.hwpf.usermodel.Section;
public class Word {
    //  
    public static String readDoc1(InputStream is) throws IOException {
        WordExtractor extractor = new WordExtractor(is);
        return extractor.getText();
    }

    // Section、 Paragraph、 CharacterRun 
    public static void readDoc2(InputStream is) throws IOException {
        HWPFDocument doc=new HWPFDocument(is);
        Range r=doc.getRange();
        for(int x=0;x<r.numSections();x++){
            Section s=r.getSection(x);
            for(int y=0;y<s.numParagraphs();y++){
                Paragraph p=s.getParagraph(y);
                for(int z=0;z<p.numCharacterRuns();z++){
                    CharacterRun run=p.getCharacterRun(z);
                    String text=run.text();
                    System.out.print(text);
                }
            }
        }
    }
    public static void main(String[] args) {
        File file = new File("/home/orisun/1.doc");
        try {
            FileInputStream fin = new FileInputStream(file);
            String cont = readDoc1(fin);
            System.out.println(cont);
            fin.close();
            fin = new FileInputStream(file);
            readDoc2(fin);
            fin.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

POI PPT 추출 예제:

package msoffice;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.extractor.PowerPointExtractor;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
public class PPT {
    // 
    public static String readDoc1(InputStream is) throws IOException{
        PowerPointExtractor extractor=new PowerPointExtractor(is);
        return extractor.getText();
    }

    // 
    public static void readDoc2(InputStream is) throws IOException{
        SlideShow ss=new SlideShow(new HSLFSlideShow(is));
        Slide[] slides=ss.getSlides();
        for(int i=0;i<slides.length;i++){
            // 
            String title=slides[i].getTitle();
            System.out.println(" :"+title);
            // ( )
            TextRun[] runs=slides[i].getTextRuns();
            for(int j=0;j<runs.length;j++){
                System.out.println(runs[j].getText());
            }
        }
    }

    public static void main(String[] args){
        File file = new File("/home/orisun/2.ppt");
        try{
            FileInputStream fin=new FileInputStream(file);
            String cont=readDoc1(fin);
            System.out.println(cont);
            fin.close();
            fin=new FileInputStream(file);
            readDoc2(fin);
            fin.close();
        }catch(IOException e){
            e.printStackTrace();
        }
    }
}

Excel 파일은 여러 개의 Workbook으로 구성되며, 하나의 Workbook은 여러 개의 Sheet로 구성됩니다.
POI Excel 추출의 간단한 예:

package msoffice;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.Iterator;
import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hssf.extractor.ExcelExtractor;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.ss.usermodel.Row;
public class Excel {
    // Excel 
    public static String readDoc1(InputStream is)throws IOException{
        HSSFWorkbook wb=new HSSFWorkbook(new POIFSFileSystem(is));
        ExcelExtractor extractor=new ExcelExtractor(wb);
        extractor.setFormulasNotResults(false);
        extractor.setIncludeSheetNames(true);
        return extractor.getText();
    }

    // Sheet、 
    public static double getAvg(InputStream is)throws IOException{
        HSSFWorkbook wb=new HSSFWorkbook(new POIFSFileSystem(is));
        // sheet
        HSSFSheet sheet=wb.getSheetAt(0);
        double molecule=0.0;
        double denominator=0.0;
        // sheet
        Iterator<Row> riter=sheet.rowIterator();
        while(riter.hasNext()){
            HSSFRow row=(HSSFRow)riter.next();
            HSSFCell cell1=row.getCell(4);
            HSSFCell cell2=row.getCell(4);
            if(cell1.getCellType()!=HSSFCell.CELL_TYPE_NUMERIC){
                System.err.println(" ！");
                System.exit(-2);
            }
            if(cell2.getCellType()!=HSSFCell.CELL_TYPE_NUMERIC){
                System.err.println(" ！");
                System.exit(-2);
            }
            denominator+=Double.parseDouble(cell2.toString().trim());
            molecule+=Double.parseDouble(cell2.toString().trim())*Float.parseFloat(cell1.toString().trim());
        }
        return molecule/denominator;
    }

    public static void main(String[] args){
        File file = new File("/home/orisun/3.xls");
        try{
            FileInputStream fin=new FileInputStream(file);
            String cont=readDoc1(fin);
            System.out.println(cont);
            fin.close();
            fin=new FileInputStream(file);
            System.out.println(" "+getAvg(fin));
            fin.close();
        }catch(IOException e){
            e.printStackTrace();
        }
    }
}