非doc类型html,［原创］java解析非结构化文本 doc xls pdf ppt xml html

packagecom.ducklyl;importjava.io.File;importjava.io.FileInputStream;importjava.util.Iterator;importorg.apache.poi.hslf.model.Slide;importorg.apache.poi.hslf.model.TextRun;importorg.apache.poi.hslf.usermodel.SlideShow;importorg.apache.poi.hssf.usermodel.HSSFCell;importorg.apache.poi.hssf.usermodel.HSSFRow;importorg.apache.poi.hssf.usermodel.HSSFSheet;importorg.apache.poi.hssf.usermodel.HSSFWorkbook;importorg.apache.poi.hwpf.HWPFDocument;importorg.apache.poi.hwpf.usermodel.Paragraph;importorg.apache.poi.hwpf.usermodel.Range;importorg.dom4j.Document;importorg.dom4j.Element;importorg.dom4j.io.SAXReader;importorg.htmlparser.Parser;importorg.htmlparser.filters.*;importorg.htmlparser.*;importorg.htmlparser.nodes.TextNode;importorg.htmlparser.util.*;importorg.pdfbox.pdfparser.PDFParser;importorg.pdfbox.pdmodel.PDDocument;importorg.pdfbox.util.PDFTextStripper;publicclassHandleFile {publicstaticvoidmain(String args[]){

String str="e:\\test.HTML";

System.out.println(handleFile(str));

}publicstaticString handleFile(String filename){

String result="";

String fileType=filename.substring(filename.lastIndexOf(".")+1, filename.length());if(fileType.equalsIgnoreCase("pdf"))

result=handlePdf(filename);elseif(fileType.equalsIgnoreCase("xls"))

result=handleExcel(filename);elseif(fileType.equalsIgnoreCase("doc"))

result=handleDoc(filename);elseif(fileType.equalsIgnoreCase("xml"))

result=handleXml(filename);elseif(fileType.equalsIgnoreCase("ppt"))

result=handlePPT(filename);elseif(fileType.equalsIgnoreCase("htm")||fileType.equalsIgnoreCase("html"))

result=handleHtml(filename);returnresult;

}/*** 解析HTML

*@paramfilename

*@return*/publicstaticString handleHtml(String filename){

String content="";try{

File file=newFile(filename);if(!file.exists())returncontent;

Parser parser=newParser(filename);

parser.setEncoding("UTF-8");

NodeFilter textFilter=newNodeClassFilter(TextNode.class);

NodeList nodes=parser.extractAllNodesThatMatch(textFilter);for(inti=0;i

TextNode textnode=(TextNode)nodes.elementAt(i);

String line=textnode.toPlainTextString().trim();if(line.equals(""))continue;

content=content+line;

}

}catch(Exception e){

e.printStackTrace();

}returncontent;

}/*** 解析PPT

*@paramfilename

*@return*/publicstaticString handlePPT(String filename){

StringBuffer content=newStringBuffer("");try{

File file=newFile(filename);if(!file.exists()) {returncontent.toString();

}

FileInputStream instream=newFileInputStream(file);

SlideShow ppt=newSlideShow(instream);

Slide[] slides=ppt.getSlides();for(inti=0;i

TextRun[] t=slides[i].getTextRuns();//为了取得幻灯片的文字内容，建立TextRunfor(intj=0;j

content.append(t[j].getText());//这里会将文字内容加到content中去}

content.append(slides[i].getTitle());

}

}catch(Exception e){

e.printStackTrace();

}returncontent.toString();

}/*** 解析XML

*@paramfilename

*@return*/publicstaticString handleXml(String filename){

String content="",value="",text="";try{

File file=newFile(filename);if(!file.exists()) {returncontent;

}

SAXReader saxReader=newSAXReader();

Document document=saxReader.read(file);

Element root=document.getRootElement() ;

Iterator iter=root.elementIterator() ;while(iter.hasNext()){

Element element=(Element)iter.next();

value=element.getStringValue();if(!value.trim().equals(""))    content=content+value;

}

}catch(Exception e){

e.printStackTrace();

}returncontent;

}/*** 解析DOC

*@paramfilename

*@return*/publicstaticString handleDoc(String filename){

String content="";try{

File file=newFile(filename);if(!file.exists()) {returncontent;

}

FileInputStream instream=newFileInputStream(file);

HWPFDocument doc=newHWPFDocument(instream);

Range range=doc.getRange();

String text=range.text();for(inti=0;i

Paragraph p=range.getParagraph(i);

content=content+p.text().trim()+"\n";

}

}catch(Exception e){

e.printStackTrace();

}returncontent;

}/*** 解析PDF

*@paramfilename

*@return*/publicstaticString handlePdf(String filename){

String contenttxt="";try{

File file=newFile(filename);if(!file.exists()){returncontenttxt;

}

FileInputStream instream=newFileInputStream(file);

PDFParser parser=newPDFParser(instream);

parser.parse();

PDDocument pdfdocument=parser.getPDDocument();

PDFTextStripper pdfstripper=newPDFTextStripper();

contenttxt=pdfstripper.getText(pdfdocument);

}catch(Exception e){

e.printStackTrace();

}returncontenttxt;

}/*** 解析EXCEL

*@paramfilename

*@return*/publicstaticString handleExcel(String filename){

String content="";try{

File file=newFile(filename);if(!file.exists()) {returncontent;

}

HSSFWorkbook workbook=newHSSFWorkbook(newFileInputStream(file));

HSSFSheet sheet=workbook.getSheetAt(0);for(inti=0;i

sheet=workbook.getSheetAt(i);if(sheet!=null){for(intm=0;m

HSSFRow row=sheet.getRow(m);if(row==null)break;for(intn=0;n

HSSFCell cell=row.getCell(n);if(cell==null)break;inttype=cell.getCellType();switch(type){case0:

content=content+cell.getNumericCellValue();break;case1:

content=content+cell.getStringCellValue();break;case3:break;default:

;

}

}

content=content+"\n";

}

}

content=content+"\n";

}

}catch(Exception e){

e.printStackTrace();

}returncontent;

}

}