本篇教程介紹了HTML+CSS入門 如何使用POI將doc文件轉換為HTML，希望閱讀本篇文章以后大家有所收獲，幫助大家HTML+CSS入門。

<

需要的jar包有：有一些是依賴包，可以使用maven下載

doc文件轉換為html文件

package?com.gsww.sxzz.controller.service;

import?org.apache.poi.hwpf.HWPFDocument;

import?org.apache.poi.hwpf.converter.PicturesManager;

import?org.apache.poi.hwpf.converter.WordToHtmlConverter;

import?org.apache.poi.hwpf.usermodel.Picture;

import?org.apache.poi.hwpf.usermodel.PictureType;

import?org.jsoup.Jsoup;

import?org.w3c.dom.Document;

import?javax.xml.parsers.DocumentBuilderFactory;

import?javax.xml.parsers.ParserConfigurationException;

import?javax.xml.transform.OutputKeys;

import?javax.xml.transform.Transformer;

import?javax.xml.transform.TransformerException;

import?javax.xml.transform.TransformerFactory;

import?javax.xml.transform.dom.DOMSource;

import?javax.xml.transform.stream.StreamResult;

import?java.io.*;

import?java.util.List;

/**

*?Created?by?Carey?on?15-2-2.

*/

public?class?docTohtml?{

public?static?void?main(String?argv[])?{

try?{

convert2Html("D:\\b.doc","D:\\1.html");

}?catch?(Exception?e)?{

e.printStackTrace();

}

}

//輸出html文件

public?static?void?writeFile(String?content,?String?path)?{

FileOutputStream?fos?=?null;

BufferedWriter?bw?=?null;

org.jsoup.nodes.Document?doc?=?Jsoup.parse(content);

String?styleOld=doc.getElementsByTag("style").html();

//統一字體格式為宋體

styleOld=styleOld.replaceAll("font-family:.+(?=;\\b)",?"font-family:SimSun");

doc.getElementsByTag("head").empty();

doc.getElementsByTag("head").append("");

doc.getElementsByTag("head").append("?");

doc.getElementsByTag("style").append(styleOld);

/*正則表達式查詢字體內容：font-family:.+(?=;\b)*/

System.out.println(content);

content=doc.html();

content=content.replace("",?"");

try?{

File?file?=?new?File(path);

fos?=?new?FileOutputStream(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?轉?html

public?static?void?convert2Html(String?fileName,?String?outPutFile)

throws?TransformerException,?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?=?new?WordToHtmlConverter(

DocumentBuilderFactory.newInstance().newDocumentBuilder()

.newDocument());

wordToHtmlConverter.setPicturesManager(?new?PicturesManager()

{

public?String?savePicture(?byte[]?content,

PictureType?pictureType,?String?suggestedName,

float?widthInches,?float?heightInches?)

{

return?"test/"+suggestedName;

}

}?);

wordToHtmlConverter.processDocument(wordDocument);

//save?pictures

List?pics=wordDocument.getPicturesTable().getAllPictures();

if(pics!=null){

for(int?i=0;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?=?new?ByteArrayOutputStream();

DOMSource?domSource?=?new?DOMSource(htmlDocument);

StreamResult?streamResult?=?new?StreamResult(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(new?String(out.toByteArray()),?outPutFile);

}

}

遇到的問題，當doc轉換為html時不會將圖像的線條給轉換過來。只有在table表格中才可以轉換為span標簽。如果要作下滑線，可以放一個table的單元格只設定下邊框就可以完美轉換為html了。

將html轉換為pdf

package?com.gsww.sxzz.controller.service;

import?com.lowagie.text.pdf.BaseFont;

import?org.xhtmlrenderer.pdf.ITextFontResolver;

import?org.xhtmlrenderer.pdf.ITextRenderer;

import?java.io.File;

import?java.io.FileNotFoundException;

import?java.io.FileOutputStream;

import?java.io.OutputStream;

/**

*?Created?by?Carey?on?15-2-2.

*/

public?class?htmlToPdf?{

public?boolean?convertHtmlToPdf(String?inputFile,?String?outputFile)

{

try?{

OutputStream?????os?=?new?FileOutputStream(outputFile);

ITextRenderer?renderer?=?new?ITextRenderer();

String?url?=?new?File(inputFile).toURI().toURL().toString();

renderer.setDocument(url);

//?解決中文支持問題

ITextFontResolver?fontResolver?=?renderer.getFontResolver();

/*fontResolver.addFont("C:\\Windows\\Fonts\\simsunb.ttf",?BaseFont.IDENTITY_H,?BaseFont.NOT_EMBEDDED);

*///宋體文件的相對路徑

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??void??main(String?[]?args){

htmlToPdf?html2Pdf?=new?htmlToPdf();

try?{

html2Pdf.convertHtmlToPdf("D:\\1.html","D:\\index.pdf");

}?catch?(Exception?e)?{

e.printStackTrace();

}

}

}

本文由職坐標整理發布，歡迎關注職坐標WEB前端HTML/CSS頻道，獲取更多HTML/CSS知識！

總結

以上是生活随笔為你收集整理的doc文件转换html,HTML+CSS入门 如何使用POI将doc文件转换为HTML的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。