html word转换pdf,pdf转html，word转pdf

import java.io.BufferedReader;

import java.io.File;

import java.io.FileNotFoundException;

import java.io.IOException;

import java.io.InputStream;

import java.io.InputStreamReader;

import org.apache.commons.io.FilenameUtils;

import com.artofsolving.jodconverter.DocumentConverter;

import com.artofsolving.jodconverter.DocumentFormat;

import com.artofsolving.jodconverter.DocumentFormatRegistry;

import com.artofsolving.jodconverter.openoffice.connection.OpenOfficeConnection;

import com.artofsolving.jodconverter.openoffice.connection.SocketOpenOfficeConnection;

import com.artofsolving.jodconverter.openoffice.converter.OpenOfficeDocumentConverter;

public class OpenOfficeUtils {

public  String   pdf2html(String pdfFilePath) throws InterruptedException{

String htmlFilePath="";

if(!pdfFilePath.equals("")||pdfFilePath!=null){

String  filePath = pdfFilePath.substring(0,pdfFilePath.lastIndexOf("\\"));

File htmlFile  = new File(filePath+".html");//html文件路径(包括有html文件名)

htmlFilePath = filePath;//html文件路径

System.out.println("html文件的路径是 "+htmlFilePath);

String pdfName = pdfFilePath.substring(pdfFilePath.lastIndexOf("\\")+1);

String htmlFileName = pdfName.substring(0,pdfName.lastIndexOf("."))+".html";//html文件的name

//pdf2html的插件的路径

String pdf2htmlexePath = "E:\\servers\\pdf2htmlEX-v1.0\\pdf2htmlEX.exe";

if (!(pdf2htmlexePath != null && !"".equals(pdf2htmlexePath) && pdfFilePath != null

&& !"".equals(pdfFilePath) && htmlFileName != null && !""

.equals(htmlFileName))) {

System.out.println("传递的参数有误！");

return null;

}

Runtime rt = Runtime.getRuntime();

StringBuilder command = new StringBuilder();

command.append(pdf2htmlexePath).append(" ");

if (htmlFilePath != null && !"".equals(htmlFilePath.trim()))// 生成文件存放位置,需要替换文件路径中的空格

command.append("--dest-dir ").append(htmlFilePath.replace(" ", "\" \"")).append(" ");

command.append("--optimize-text 1 ");// 尽量减少用于文本的HTML元素的数目 (default: 0)

command.append("--zoom 1.4 ");

command.append("--process-outline 0 ");// html中显示链接：0——false，1——true

command.append("--font-format woff ");// 嵌入html中的字体后缀(default ttf)

// ttf,otf,woff,svg

command.append(pdfFilePath.replace(" ", "\" \"")).append(" ");// 需要替换文件路径中的空格

if (htmlFileName != null && !"".equals(htmlFileName.trim())) {

command.append(htmlFileName);

if (htmlFileName.indexOf(".html") == -1)

command.append(".html");

}

try {

Process p = rt.exec(command.toString());

StreamGobbler errorGobbler = new StreamGobbler(p.getErrorStream(), "ERROR");

// 开启屏幕标准错误流

errorGobbler.start();

StreamGobbler outGobbler = new StreamGobbler(p.getInputStream(), "STDOUT");

// 开启屏幕标准输出流

long o1 = System.currentTimeMillis();

outGobbler.start();

int w = p.waitFor();

int v = p.exitValue();

if (w == 0 && v == 0) {

System.out.println("转化html文件路径是 "+htmlFilePath);

return htmlFilePath+"\\"+htmlFileName;

}

} catch (Exception e) {

e.printStackTrace();

}

}else{

System.out.println("要转化的pdf文件不存在");

}

return null;

}

public static void convert(File sourceFile, File targetFile) {

try {

// 1: 打开连接

OpenOfficeConnection connection = new SocketOpenOfficeConnection(8100);

connection.connect();

DocumentConverter converter = new OpenOfficeDocumentConverter(connection);

// 2:获取Format

DocumentFormatRegistry factory = new BasicDocumentFormatRegistry();

DocumentFormat inputDocumentFormat = factory

.getFormatByFileExtension(getExtensionName(sourceFile.getAbsolutePath()));

DocumentFormat outputDocumentFormat = factory

.getFormatByFileExtension(getExtensionName(targetFile.getAbsolutePath()));

// 3:执行转换

converter.convert(sourceFile, inputDocumentFormat, targetFile, outputDocumentFormat);

} catch (Exception e) {

System.err.println("文档转换PDF失败");

e.printStackTrace();

}

}

public static String getExtensionName(String filePath){

return FilenameUtils.getExtension(filePath);

}

public static int office2PDF(String sourceFile, String destFile) {

String openOfficePath ="C:\\Program Files (x86)\\OpenOffice 4\\";

try {

File inputFile = new File(sourceFile);

if (!inputFile.exists()) {

return -1;

// 找不到源文件, 则返回-1

}

// 如果目标路径不存在, 则新建该路径

File outputFile = new File(destFile);

if (!outputFile.getParentFile().exists()) {

outputFile.getParentFile().mkdirs();

}

String OpenOffice_HOME = openOfficePath;

//这里是OpenOffice的安装目录

// 如果从文件中读取的URL地址最后一个字符不是 '\'，则添加'\'

if (OpenOffice_HOME.charAt(OpenOffice_HOME.length() - 1) != '\\') {

OpenOffice_HOME += "\\";

}

// 启动OpenOffice的服务

String command = OpenOffice_HOME + "program\\soffice.exe -headless -accept=\"socket,host=127.0.0.1,port=8100;urp;          \"";

Process pro = Runtime.getRuntime().exec(command);

// connect to an OpenOffice.org instance running on port 8100

OpenOfficeConnection connection = new SocketOpenOfficeConnection(

"127.0.0.1", 8100);

connection.connect();

// convert

DocumentConverter converter = new OpenOfficeDocumentConverter(

connection);

converter.convert(inputFile, outputFile);

// close the connection

connection.disconnect();

// 关闭OpenOffice服务的进程

pro.destroy();

return 0;

}

catch (FileNotFoundException e) {

e.printStackTrace();

return -1;

}

catch (IOException e) {

e.printStackTrace();

}

return 1;

}

class StreamGobbler extends Thread

{

InputStream is;

String type;  //输出流的类型ERROR或OUTPUT

StreamGobbler(InputStream is, String type)

{

this.is = is;

this.type = type;

}

public void run()

{

try

{

InputStreamReader isr = new InputStreamReader(is);

BufferedReader br = new BufferedReader(isr);

String line=null;

while ( (line = br.readLine()) != null)

{

System.out.println(type + ">" + line);

System.out.flush();

}

} catch (IOException ioe)

{

ioe.printStackTrace();

}

}

}

public static void main(String[] args) throws InterruptedException {

OpenOfficeUtils o = new OpenOfficeUtils();

o.pdf2html("E:\\zl\\323.pdf");

}

}