项目开发过程中,需求涉及到了各种文档转换为HTML或者网页易显示格式,现在将实现方式整理如下: 1public class JacobUtil
2{ 3 public static final int WORD_HTML = 8; 4 5 public static final int WORD_TXT = 7; 6 7 public static final int EXCEL_HTML = 44; 8 9 /** 10 * WORD转HTML 11 * @param docfile WORD文件全路径 12 * @param htmlfile 转换后HTML存放路径 13 */ 14 public static void wordToHtml(String docfile, String htmlfile) 15 { 16 ActiveXComponent app = new ActiveXComponent("Word.Application"); // 启动word 17 try 18 { 19 app.setProperty("Visible", new Variant(false)); 20 Dispatch docs = app.getProperty("Documents").toDispatch(); 21 Dispatch doc = Dispatch.invoke( 22 docs, 23 "Open", 24 Dispatch.Method, 25 new Object[] { docfile, new Variant(false), 26 new Variant(true) }, new int[1]).toDispatch(); 27 Dispatch.invoke(doc, "SaveAs", Dispatch.Method, new Object[] { 28 htmlfile, new Variant(WORD_HTML) }, new int[1]); 29 Variant f = new Variant(false); 30 Dispatch.call(doc, "Close", f); 31 } 32 catch (Exception e) 33 { 34 e.printStackTrace(); 35 } 36 finally 37 { 38 app.invoke("Quit", new Variant[] {}); 39 } 40 } 41 42 /** 43 * EXCEL转HTML 44 * @param xlsfile EXCEL文件全路径 45 * @param htmlfile 转换后HTML存放路径 46 */ 47 public static void excelToHtml(String xlsfile, String htmlfile) 48 { 49 ActiveXComponent app = new ActiveXComponent("Excel.Application"); // 启动word 50 try 51 { 52 app.setProperty("Visible", new Variant(false)); 53 Dispatch excels = app.getProperty("Workbooks").toDispatch(); 54 Dispatch excel = Dispatch.invoke( 55 excels, 56 "Open", 57 Dispatch.Method, 58 new Object[] { xlsfile, new Variant(false), 59 new Variant(true) }, new int[1]).toDispatch(); 60 Dispatch.invoke(excel, "SaveAs", Dispatch.Method, new Object[] { 61 htmlfile, new Variant(EXCEL_HTML) }, new int[1]); 62 Variant f = new Variant(false); 63 Dispatch.call(excel, "Close", f); 64 } 65 catch (Exception e) 66 { 67 e.printStackTrace(); 68 } 69 finally 70 { 71 app.invoke("Quit", new Variant[] {}); 72 } 73 } 74 75} 76 当时我在找转换控件时,发现网易也转载了一偏关于Jacob使用帮助,但其中出现了比较严重的错误:String htmlfile = "C:\\AA"; 只指定到了文件夹一级,正确写法是String htmlfile = "C:\\AA\\xxx.html";
到此WORD/EXCEL转换HTML就已经差不多了,相信大家应该很清楚了:)
二、使用XPDF将PDF转换为HTML
1、下载xpdf最新版本,地址:http://www./xpdf/download.html
2、下载中文支持包 我下载的是xpdf-chinese-simplified.tar.gz
3、下载pdftohtml支持包 地址:http:///projects/pdftohtml/ 我下载的是:pdftohtml-0.39-win32.tar.gz
4、解压调试 1) 先将xpdf-3.02pl2-win32.zip解压,解压后的内容可根据需要进行删减,如果只需要转换为txt格式,其他的exe文件可以删除,只保留pdftotext.exe,以此类推; 2) 然后将xpdf-chinese-simplified.tar.gz解压到刚才xpdf-3.02pl2-win32.zip的解压目录; 3) 将pdftohtml-0.39-win32.tar.gz解压,pdftohtml.exe解压到xpdf-3.02pl2-win32.zip的解压目录; 4) 目录结构: +---[X:\xpdf] |-------各种转换用到的exe文件 | |-------xpdfrc | +------[X:\xpdf\xpdf-chinese-simplified] | | +-------很多转换时需要用到的字符文件
xpdfrc:此文件是用来声明转换字符集对应路径的文件
5) 修改xpdfrc文件(文件原名为sample-xpdfrc) 修改文件内容为: Txt代码#----- begin Chinese Simplified support package cidToUnicode Adobe-GB1 xpdf-chinese-simplified\Adobe-GB1.cidToUnicode unicodeMap ISO-2022-CN xpdf-chinese-simplified\ISO-2022-CN.unicodeMap unicodeMap EUC-CN xpdf-chinese-simplified\EUC-CN.unicodeMap unicodeMap GBK xpdf-chinese-simplified\GBK.unicodeMap cMapDir Adobe-GB1 xpdf-chinese-simplified\CMap toUnicodeDir xpdf-chinese-simplified\CMap fontDir C:\WINDOWS\Fonts displayCIDFontTT Adobe-GB1 C:\WINDOWS\Fonts\simhei.ttf #----- end Chinese Simplified support package 6) 创建bat文件pdftohtml.bat(放置的路径不能包含空格) 内容为: Txt代码@echo off 7) 创建类set folderPath=%1 set filePath=%2 cd /d %folderPath% pdftohtml -enc GBK %filePath% exit JAVA代码 public class ConvertPdf { private static String INPUT_PATH; private static String PROJECT_PATH; public static void convertToHtml(String file, String project) { INPUT_PATH = file; PROJECT_PATH = project; if(checkContentType()==0) { toHtml(); } } private static int checkContentType() { String type = INPUT_PATH.substring(INPUT_PATH.lastIndexOf(".") + 1, INPUT_PATH.length()) .toLowerCase(); if (type.equals("pdf")) return 0; else return 9; } private static void toHtml() { if(new File(INPUT_PATH).isFile()) { try { String cmd = "cmd /c start X:\\pdftohtml.bat \"" + PROJECT_PATH + "\" \"" + INPUT_PATH + "\""; Runtime.getRuntime().exec(cmd); } catch (IOException e) { e.printStackTrace(); } } } } String cmd = "....";此处代码是调用创建的bat文件进行转换
8) 测试转换 public static void main(String[] args)
{ ConvertPdf.convertToHtml("C:\\test.pdf", "X:\\xpdf"); } |
|