使用java将word文档docx，doc（包含图形，文本框，图片等）完美转换成所有格式图片（pdf，png，gif，jpeg等等）下文中附带代码，效果图等
思路使用到的包实现代码效果图：思路
使用jacob将docx转换成doc，用openoffice将doc转成pdf，最后是用pdfbox将pdf转成任意格式图片
使用到的包
/download/weixin_44396516/11393966
实现代码
把上面的包下载并导入，代码中有些内容自行修改，有问题请留言，看到会回复。
import java.awt.image.BufferedImage;import java.io.ByteArrayOutputStream;import java.io.File;import java.io.FileInputStream;import java.io.FileOutputStream;import java.io.IOException;import java.io.InputStream;import .ConnectException;import java.util.ArrayList;import java.util.Date;import java.util.List;import java.util.Properties;import javax.xml.parsers.DocumentBuilderFactory;import javax.xml.transform.OutputKeys;import javax.xml.transform.Transformer;import javax.xml.transform.TransformerFactory;import javax.xml.transform.dom.DOMSource;import javax.xml.transform.stream.StreamResult;import org.apache.pdfbox.pdmodel.PDDocument;import org.apache.pdfbox.pdmodel.PDPage;import org.apache.pdfbox.pdmodel.encryption.InvalidPasswordException;import org.apache.pdfbox.rendering.ImageType;import org.apache.pdfbox.rendering.PDFRenderer;import org.apache.pdfbox.tools.imageio.ImageIOUtil;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.model.PAPX;import org.apache.poi.hwpf.usermodel.PictureType;import org.apache.poi.xwpf.converter.core.BasicURIResolver;import org.apache.poi.xwpf.converter.core.FileImageExtractor;import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;import org.apache.poi.xwpf.usermodel.XWPFDocument;import org.apache.poi.xwpf.usermodel.XWPFParagraph;import org.w3c.dom.Document;import com.artofsolving.jodconverter.DocumentConverter;import com.artofsolving.jodconverter.openoffice.connection.OpenOfficeConnection;import com.artofsolving.jodconverter.openoffice.connection.SocketOpenOfficeConnection;import com.artofsolving.jodconverter.openoffice.converter.OpenOfficeDocumentConverter;import com.artofsolving.jodconverter.openoffice.converter.StreamOpenOfficeDocumentConverter;import com.jacob.activeX.ActiveXComponent;import .ComThread;import .Dispatch;import .Variant;public class POIWordToPng {/*** 使用jacob进行Word文档格式互转(例:doc2docx、docx2doc)* * @author Harley Hong* @created /08/09 16:09:32*//*** doc格式*/private static final int DOC_FMT = 0;/*** docx格式*/private static final int DOCX_FMT = 12;static String picp=null;static String docn="/"+new Date().getTime()+".doc";public static String getSystemFileCharset(){Properties pro = System.getProperties();return pro.getProperty("file.encoding");}public static void main(String[] args) throws IOException {String sourcePath="D:\\软件\\Tomcat\\Tomcat7.075\\webapps\\jhwx\\file\\-07-22\\8_0722111135.docx";String picturesPath="D:\\软件\\Tomcat\\Tomcat7.075\\webapps\\jhwx\\file\\-07-22\\image";try {convertDocFmt(sourcePath, picturesPath+docn, DOC_FMT);} catch (Exception e) {e.printStackTrace();}convert(new File(picturesPath+docn), picturesPath);String str=picturesPath+"\\"+picp.substring(6);pdf2Gif(str);}/*** 将doc文档转换成pdf文档* * @param docFile*需要转换的word文档* @param filepath*转换之后html的存放路径* @return 转换之后的html文件*/ public static File convert(File docFile, String filepath) throws IOException {// 创建保存html的文件String allpath=filepath + "/" + new Date().getTime() + ".pdf";File htmlFile = new File(allpath);picp=allpath.substring(54);// 启动OpenofficeString OpenOffice_HOME = "C:\\Program Files (x86)\\OpenOffice 4";if (OpenOffice_HOME.charAt(OpenOffice_HOME.length() - 1) != '\\') {OpenOffice_HOME += "\\";}String command = OpenOffice_HOME+ "program\\soffice -headless -accept=\"socket,host=127.0.0.1,port=8100;urp;\" -nofirststartwizard";Process pro = Runtime.getRuntime().exec(command);// 创建Openoffice连接OpenOfficeConnection connection = new SocketOpenOfficeConnection("127.0.0.1", 8100);connection.connect();// 创建转换器// DocumentConverter converter = new OpenOfficeDocumentConverter(connection);DocumentConverter converter = new StreamOpenOfficeDocumentConverter(connection);// 转换文档converter.convert(docFile, htmlFile);// 关闭openoffice连接connection.disconnect();// 关闭OpenOffice服务的进程pro.destroy();return htmlFile;}/*** 根据docx类型转换doc文件* * @param srcPaththe doc path 源文件* @param descPath the docx path 目标文件* @param fmtthefmt 所转格式* @return the file* @throws Exception the exception*/public static File convertDocFmt(String srcPath, String descPath, int fmt) throws Exception {// 实例化ComThread线程与ActiveXComponentComThread.InitSTA();ActiveXComponent app = new ActiveXComponent("Word.Application");try {// 文档隐藏时进行应用操作 app.setProperty("Visible", new Variant(false));// 实例化模板Document对象 Dispatch document = app.getProperty("Documents").toDispatch();// 打开Document进行另存为操作 Dispatch doc = Dispatch.invoke(document, "Open", Dispatch.Method,new Object[] { srcPath, new Variant(true), new Variant(true) }, new int[1]).toDispatch();Dispatch.invoke(doc, "SaveAs", Dispatch.Method, new Object[] { descPath, new Variant(fmt) }, new int[1]);Dispatch.call(doc, "Close", new Variant(false));return new File(descPath);} catch (Exception e) {throw e;} finally {// 释放线程与ActiveXComponent app.invoke("Quit", new Variant[] {});ComThread.Release();}}/*** pdf转png* @param pdfFilename* @throws InvalidPasswordException* @throws IOException*/public static void pdf2Gif(String pdfFilename ) throws InvalidPasswordException, IOException {//合成一张图片PDDocument document = PDDocument.load(new File(pdfFilename));PDFRenderer pdfRenderer = new PDFRenderer(document);List<BufferedImage> images = new ArrayList();int pageCounter = 0;for (PDPage page : document.getPages()) {// note that the page number parameter is zero basedBufferedImage bim = pdfRenderer.renderImageWithDPI(pageCounter++, 100, ImageType.RGB);images.add(bim);}BufferedImage result = mergeImage(false,images.toArray(new BufferedImage[0]));ImageIOUtil.writeImage(result, pdfFilename + "-" + (pageCounter++) + ".gif", 100);document.close();//不合成一张// PDDocument document = PDDocument.load(new File(pdfFilename));//PDFRenderer pdfRenderer = new PDFRenderer(document);//int pageCounter = 0;//int pages = document.getNumberOfPages();//pngp=new String[pages];//for (PDPage page : document.getPages()) {//// note that the page number parameter is zero based//BufferedImage bim = pdfRenderer.renderImageWithDPI(pageCounter++, 200, ImageType.RGB);//ImageIOUtil.writeImage(bim, pdfFilename + "-" + pageCounter + ".gif", 72);//pngp[pageCounter-1]=pdfFilename.substring(54)+ "-" + pageCounter + ".gif";////}//document.close();}/*** 合并任数量的图片成一张图片* * @param isHorizontal* true代表水平合并，fasle代表垂直合并* @param imgs* 欲合并的图片数组* @return* @throws IOException*/public static BufferedImage mergeImage(boolean isHorizontal, BufferedImage... imgs) throws IOException {// 生成新图片BufferedImage destImage = null;// 计算新图片的长和高int allw = 0, allh = 0, allwMax = 0, allhMax = 0;for (BufferedImage img : imgs) {allw += img.getWidth();allh += img.getHeight();if (img.getWidth() > allwMax) {allwMax = img.getWidth();}if (img.getHeight() > allhMax) {allhMax = img.getHeight();}}// 创建新图片if (isHorizontal) {destImage = new BufferedImage(allw, allhMax, BufferedImage.TYPE_INT_RGB);} else {destImage = new BufferedImage(allwMax, allh, BufferedImage.TYPE_INT_RGB);}// 合并所有子图片到新图片int wx = 0, wy = 0;for (int i = 0; i < imgs.length; i++) {BufferedImage img = imgs[i];int w1 = img.getWidth();int h1 = img.getHeight();// 从图片中读取RGBint[] ImageArrayOne = new int[w1 * h1];ImageArrayOne = img.getRGB(0, 0, w1, h1, ImageArrayOne, 0, w1); // 逐行扫描图像中各个像素的RGB到数组中if (isHorizontal) { // 水平方向合并destImage.setRGB(wx, 0, w1, h1, ImageArrayOne, 0, w1); // 设置上半部分或左半部分的RGB} else { // 垂直方向合并destImage.setRGB(0, wy, w1, h1, ImageArrayOne, 0, w1); // 设置上半部分或左半部分的RGB}wx += w1;wy += h1;}return destImage;}}
效果图：
转换前的docx文档（包含图形，文本框）
效果图：转换后的png文件
