[原创]最近做搜索引擎时对WORD,EXCEL,PDF,POWERPOINT文件全文检索的总结

billyng 2007-06-08 11:19:23

文章写的不好，不过希望对大家有用

JAVA读取WORD,EXCEL,POWERPOINT,PDF文件的方法
http://blog.sina.com.cn/u/54c1567b010008vh

OFFICE文档使用POI控件，PDF可以使用PDFBOX0.7.3控件，完全支持中文，用XPDF也行，不过感觉PDFBOX比较好，而且作者也在更新。水平有限，万望各位指正

WORD:
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.poi.hwpf.extractor.WordExtractor;

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

import com.search.code.Index;

public Document getDocument(Index index, String url, String title, InputStream is) throws DocCenterException {

String bodyText = null;
try {
WordExtractor ex = new WordExtractor(is);//is是WORD文件的InputStream
bodyText = ex.getText();
if(!bodyText.equals("")){
index.AddIndex(url, title, bodyText);
}
}catch (DocCenterException e) {
throw new DocCenterException("无法从该Mocriosoft Word文档中提取内容", e);
}catch(Exception e){
e.printStackTrace();
}
}
return null;
}

Excel:

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;

import org.apache.poi.hwpf.extractor.WordExtractor;
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.File;
import java.io.InputStream;
import java.io.FileInputStream;

import com.search.code.Index;

public Document getDocument(Index index, String url, String title, InputStream is) throws DocCenterException {
StringBuffer content = new StringBuffer();
try{
HSSFWorkbook workbook = new HSSFWorkbook(is);//创建对Excel工作簿文件的引用
for (int numSheets = 0; numSheets < workbook.getNumberOfSheets(); numSheets++) {
if (null != workbook.getSheetAt(numSheets)) {
HSSFSheet aSheet = workbook.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 (short cellNumOfRow = 0; cellNumOfRow <= aRow.getLastCellNum(); cellNumOfRow++) {
if (null != aRow.getCell(cellNumOfRow)) {
HSSFCell aCell = aRow.getCell(cellNumOfRow);//获得列值
content.append(aCell.getStringCellValue());
}
}
}
}
}
}
if(!content.equals("")){
index.AddIndex(url, title, content.toString());
}
}catch (DocCenterException e) {

throw new DocCenterException("无法从该Mocriosoft Word文档中提取内容", e);
}catch(Exception e) {
System.out.println("已运行xlRead() : " + e );
}
return null;
}

PowerPoint:

import java.io.InputStream;

import org.apache.lucene.document.Document;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.usermodel.SlideShow;

public Document getDocument(Index index, String url, String title, InputStream is)
throws DocCenterException {
StringBuffer content = new StringBuffer("");
try{
SlideShow ss = new SlideShow(new HSLFSlideShow(is));//is 为文件的InputStream，建立SlideShow
Slide[] slides = ss.getSlides();//获得每一张幻灯片
for(int i=0;i<slides.length;i++){
TextRun[] t = slides[i].getTextRuns();//为了取得幻灯片的文字内容，建立TextRun
for(int j=0;j<t.length;j++){
content.append(t[j].getText());//这里会将文字内容加到content中去
}
content.append(slides[i].getTitle());
}
index.AddIndex(url, title, content.toString());
}catch(Exception ex){
System.out.println(ex.toString());
}
return null;
}

PDF:

import java.io.InputStream;
import java.io.IOException;
import org.apache.lucene.document.Document;

import org.pdfbox.cos.COSDocument;
import org.pdfbox.pdfparser.PDFParser;
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.pdmodel.PDDocumentInformation;
import org.pdfbox.util.PDFTextStripper;

import com.search.code.Index;

public Document getDocument(Index index, String url, String title, InputStream is)throws DocCenterException {

COSDocument cosDoc = null;
try {
cosDoc = parseDocument(is);
} catch (IOException e) {
closeCOSDocument(cosDoc);
throw new DocCenterException("无法处理该PDF文档", e);
}
if (cosDoc.isEncrypted()) {
if (cosDoc != null)
closeCOSDocument(cosDoc);
throw new DocCenterException("该PDF文档是加密文档，无法处理");
}
String docText = null;
try {
PDFTextStripper stripper = new PDFTextStripper();
docText = stripper.getText(new PDDocument(cosDoc));
} catch (IOException e) {
closeCOSDocument(cosDoc);
throw new DocCenterException("无法处理该PDF文档", e);
}

PDDocument pdDoc = null;
try {
pdDoc = new PDDocument(cosDoc);
PDDocumentInformation docInfo = pdDoc.getDocumentInformation();
if(docInfo.getTitle()!=null && !docInfo.getTitle().equals("")){
title = docInfo.getTitle();
}

} catch (Exception e) {
closeCOSDocument(cosDoc);
closePDDocument(pdDoc);
System.err.println("无法取得该PDF文档的元数据" + e.getMessage());
} finally {
closeCOSDocument(cosDoc);
closePDDocument(pdDoc);
}

return null;
}

private static COSDocument parseDocument(InputStream is) throws IOException {
PDFParser parser = new PDFParser(is);
parser.parse();
return parser.getDocument();
}

private void closeCOSDocument(COSDocument cosDoc) {
if (cosDoc != null) {
try {
cosDoc.close();
} catch (IOException e) {
}
}
}

private void closePDDocument(PDDocument pdDoc) {
if (pdDoc != null) {
try {
pdDoc.close();
} catch (IOException e) {
}
}
}

代码复制可能出错，不过代码经过测试，绝对能用，POI为3.0-rc4，PDFBOX为0.7.3

POI: http://jakarta.apache.org/poi/index.html

PDFBOX: http://www.pdfbox.org/

...全文