docx poi 原理_Java poi如何读取office原理细节？

Atitit word ppt excel convert txt bp 等文档转换纯文本问题最佳实践.docx

Atitit word ppt excel等文档转换txt问题最佳实践

目录

1.1. // Word 直接抽取全部内容 1

1.2. //分章节Section、段落Paragraph、字符串CharacterRun抽取 1

1.3. //直接抽取幻灯片的全部内容2

1.4. //一张幻灯片一张幻灯片地读取 3

1.5. //直接读取Excel的全部内容 4

1.6. //读取时细化到Sheet、行甚至单元格 4

public class Word {

1.1. // 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();

}

1.2. //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;x

Section s=r.getSection(x);

for(int y=0;y

Paragraph p=s.getParagraph(y);

for(int z=0;z

CharacterRun run=p.getCharacterRun(z);

String text=run.text();

System.out.print(text);

}

}

}

}

1.3. //直接抽取幻灯片的全部内容

public static String readDoc1(InputStream is) throws IOException{

PowerPointExtractor extractor=new PowerPointExtractor(is);

return extractor.getText();

}

1.4. //一张幻灯片一张幻灯片地读取

public static void readDoc2(InputStream is) throws IOException{

SlideShow ss=new SlideShow(new HSLFSlideShow(is));

Slide[] slides=ss.getSlides();

for(int i=0;i

//读取一张幻灯片的标题

String title=slides[i].getTitle();

System.out.println("标题:"+title);

//读取一张幻灯片的内容(包括标题)

TextRun[] runs=slides[i].getTextRuns();

for(int j=0;j

System.out.println(runs[j].getText());

}

}

}

public class Excel {

1.5. //直接读取Excel的全部内容

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();

}

1.6. //读取时细化到Sheet、行甚至单元格

public static double getAvg(InputStream is)throws IOException{

HSSFWorkbook wb=new HSSFWorkbook(new POIFSFileSystem(is));

//获取第一张sheet

HSSFSheet sheet=wb.getSheetAt(0);

double molecule=0.0;

double denominator=0.0;

//按行遍历sheet

Iterator 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("数字类型错误！");

System.exit(-2);

}

if(cell2.getCellType()!=HSSFCell.CELL_TYPE_NUMERIC){

System.err.println("数字类型错误！");

System.exit(-2);

}

denominator+=Double.parseDouble(cell2.toString().trim());

molecule+=Double.parseDouble(cell2.toString().trim())*Float.parseFloat(cell1.toString().trim());

}

return molecule/denominator;

}

java使用poi读取ppt文件和poi读取excel、word示例 - CSDN博客.html

M