java使用poi读取ppt文件和poi读取excelword示例.docxVIP

java使用poi读取ppt文件和poi读取excel、word示例Apache的POI项目可以用来处理MS Office文档，codeplex上还有一个它的.net版本。POI项目可创建和维护操作各种基于OOXML和OLE2文件格式的Java API。大多数MS Office都是OLE2格式的。POI通HSMF子项目来支持Outlook，通过HDGF子项目来支持Visio，通过HPBF子项目来支持Publisher。使用POI抽取Word简单示例：要引入poi-3.7.jat和poi-scratchpad-3.7.ajr这两个包。复制代码代码如下:packagemsoffice;importjava.io.File;import java.io.FileInputStream;import java.io.IOException;import java.io.InputStream;importorg.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 {??? // 直接抽取全部内容??? public static String readDoc1(InputStream is) throws IOException {??????? WordExtractor extractor = new WordExtractor(is);??????? return extractor.getText();??? }??? //分章节Section、段落Paragraph、字符串CharacterRun抽取??? public static void readDoc2(InputStream is) throws IOException {??????? HWPFDocument doc=new HWPFDocument(is);??????? Range r=doc.getRange();??????? for(int x=0;xr.numSections();x++){??????????? Section s=r.getSection(x);??????????? for(int y=0;ys.numParagraphs();y++){??????????????? Paragraph p=s.getParagraph(y);??????????????? for(int z=0;zp.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抽取PPT示例：复制代码代码如下:packagemsoffice;importjava.io.File;import java.io.FileInpu