需要的jar包有：有一些是依赖包，可以使用maven下载

doc文件转换为html文件

packagecom.gsww.sxzz.controller.service;importorg.apache.poi.hwpf.HWPFDocument;importorg.apache.poi.hwpf.converter.PicturesManager;importorg.apache.poi.hwpf.converter.WordToHtmlConverter;importorg.apache.poi.hwpf.usermodel.Picture;importorg.apache.poi.hwpf.usermodel.PictureType;importorg.jsoup.Jsoup;importorg.w3c.dom.Document;importjavax.xml.parsers.DocumentBuilderFactory;importjavax.xml.parsers.ParserConfigurationException;importjavax.xml.transform.OutputKeys;importjavax.xml.transform.Transformer;importjavax.xml.transform.TransformerException;importjavax.xml.transform.TransformerFactory;importjavax.xml.transform.dom.DOMSource;importjavax.xml.transform.stream.StreamResult;import java.io.*;importjava.util.List;/*** Created by Carey on 15-2-2.*/
public classdocTohtml {public static voidmain(String argv[]) {try{convert2Html("D:\\b.doc","D:\\1.html");}catch(Exception e) {e.printStackTrace();}}//输出html文件public static voidwriteFile(String content, String path) {FileOutputStream fos= null; BufferedWriter bw= null;org.jsoup.nodes.Document doc=Jsoup.parse(content);String styleOld=doc.getElementsByTag("style").html();//统一字体格式为宋体styleOld=styleOld.replaceAll("font-family:.+(?=;\\b)", "font-family:SimSun");doc.getElementsByTag("head").empty();doc.getElementsByTag("head").append("<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\"></meta>");doc.getElementsByTag("head").append(" <style type=\"text/css\"></style>");doc.getElementsByTag("style").append(styleOld);/*正则表达式查询字体内容：font-family:.+(?=;\b)*/System.out.println(content);content=doc.html();content=content.replace("<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\">", "<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\"></meta>");try{File file= newFile(path);fos= newFileOutputStream(file);bw= new BufferedWriter(new OutputStreamWriter(fos,"UTF-8"));bw.write(content);}catch(FileNotFoundException fnfe) {fnfe.printStackTrace();}catch(IOException ioe) {ioe.printStackTrace();}finally{try{if (bw != null)bw.close();if (fos != null)fos.close();}catch(IOException ie) {}}}//word 转 htmlpublic static voidconvert2Html(String fileName, String outPutFile)throwsTransformerException, IOException,ParserConfigurationException {HWPFDocument wordDocument= new HWPFDocument(new FileInputStream(fileName));//WordToHtmlUtils.loadDoc(new FileInputStream(inputFile));//兼容2007 以上版本//XSSFWorkbook  xssfwork=new XSSFWorkbook(new FileInputStream(fileName));WordToHtmlConverter wordToHtmlConverter = newWordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());wordToHtmlConverter.setPicturesManager(newPicturesManager(){public String savePicture( byte[] content,PictureType pictureType, String suggestedName,float widthInches, floatheightInches ){return "test/"+suggestedName;}} );wordToHtmlConverter.processDocument(wordDocument);//save picturesList pics=wordDocument.getPicturesTable().getAllPictures();if(pics!=null){for(int i=0;i<pics.size();i++){Picture pic=(Picture)pics.get(i);System.out.println();try{pic.writeImageContent(new FileOutputStream("D:/test/"+pic.suggestFullFileName()));}catch(FileNotFoundException e) {e.printStackTrace();}}}Document htmlDocument=wordToHtmlConverter.getDocument();ByteArrayOutputStream out= newByteArrayOutputStream();DOMSource domSource= newDOMSource(htmlDocument);StreamResult streamResult= newStreamResult(out);TransformerFactory tf=TransformerFactory.newInstance();Transformer serializer=tf.newTransformer();serializer.setOutputProperty(OutputKeys.ENCODING,"UTF-8");serializer.setOutputProperty(OutputKeys.INDENT,"yes");serializer.setOutputProperty(OutputKeys.METHOD,"HTML");serializer.transform(domSource, streamResult);out.close();writeFile(newString(out.toByteArray()), outPutFile);}
}

遇到的问题，当doc转换为html时不会将图像的线条给转换过来。只有在table表格中才可以转换为span标签。如果要作下滑线，可以放一个table的单元格只设定下边框就可以完美转换为html了。

将html转换为pdf

packagecom.gsww.sxzz.controller.service;importcom.lowagie.text.pdf.BaseFont;importorg.xhtmlrenderer.pdf.ITextFontResolver;importorg.xhtmlrenderer.pdf.ITextRenderer;importjava.io.File;importjava.io.FileNotFoundException;importjava.io.FileOutputStream;importjava.io.OutputStream;/*** Created by Carey on 15-2-2.*/
public classhtmlToPdf {public booleanconvertHtmlToPdf(String inputFile, String outputFile){try{OutputStream     os= newFileOutputStream(outputFile);ITextRenderer renderer= newITextRenderer();String url= newFile(inputFile).toURI().toURL().toString();renderer.setDocument(url);//解决中文支持问题ITextFontResolver fontResolver =renderer.getFontResolver();/*fontResolver.addFont("C:\\Windows\\Fonts\\simsunb.ttf", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED);*///宋体文件的相对路径fontResolver.addFont("C:\\Windows\\Fonts\\simsun.ttc", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED);     renderer.getSharedContext().setBaseURL("file:/D:/");renderer.layout();renderer.createPDF(os);os.flush();os.close();}catch(Exception e) {//TODO Auto-generated catch block
e.printStackTrace();}return true;}public   static  voidmain(String [] args){htmlToPdf html2Pdf=newhtmlToPdf();try{html2Pdf.convertHtmlToPdf("D:\\1.html","D:\\index.pdf");}catch(Exception e) {e.printStackTrace();}}
}