C#实现HTML转WORD及WORD转PDF的方法

本文实例讲述了c#实现html转word及word转pdf的方法。分享给大家供大家参考。具体如下：

功能：实现html转word，word转pdf

具体代码如下：

using system;
using system.collections.generic;
using system.componentmodel;
using system.data;
using system.drawing;
using system.text;
using system.windows.forms;
using word = microsoft.office.interop.word;
using oword = microsoft.office.interop.word;
using system.reflection;
using system.configuration;
using system.web;
using system.web.security;
using system.web.ui;
using system.web.ui.webcontrols;
using system.web.ui.webcontrols.webparts;
using system.web.ui.htmlcontrols;
using microsoft.office.core;
using system.text.regularexpressions;
namespace windowsapplication2
{
 public partial class form1 : form
 {
  public form1()
  {
   initializecomponent();
  }
  private void button1_click(object sender, eventargs e)
  {
   object omissing = system.reflection.missing.value;
   object oendofdoc = "\\endofdoc"; /* \endofdoc is a predefined bookmark */
   //start word and create a new document.
   word._application oword;
   word._document odoc;
   oword = new word.application();
   oword.visible = true;
   odoc = oword.documents.add(ref omissing, ref omissing,
    ref omissing, ref omissing);
   //insert a paragraph at the beginning of the document.
   word.paragraph opara1;
   opara1 = odoc.content.paragraphs.add(ref omissing);
   opara1.range.text = "heading 1";
   opara1.range.font.bold = 1;
   opara1.format.spaceafter = 24; //24 pt spacing after paragraph.
   opara1.range.insertparagraphafter();
   //insert a paragraph at the end of the document.
   word.paragraph opara2;
   object orng = odoc.bookmarks.get_item(ref oendofdoc).range;
   opara2 = odoc.content.paragraphs.add(ref orng);
   opara2.range.text = "heading 2";
   opara2.format.spaceafter = 6;
   opara2.range.insertparagraphafter();
   //insert another paragraph.
   word.paragraph opara3;
   orng = odoc.bookmarks.get_item(ref oendofdoc).range;
   opara3 = odoc.content.paragraphs.add(ref orng);
   opara3.range.text = "this is a sentence of normal text. now here is a table:";
   opara3.range.font.bold = 0;
   opara3.format.spaceafter = 24;
   opara3.range.insertparagraphafter();
   //insert a 3 x 5 table, fill it with data, and make the first row
   //bold and italic.
   word.table otable;
   word.range wrdrng = odoc.bookmarks.get_item(ref oendofdoc).range;
   otable = odoc.tables.add(wrdrng, 3, 5, ref omissing, ref omissing);
   otable.range.paragraphformat.spaceafter = 6;
   int r, c;
   string strtext;
   for (r = 1; r <= 3; r++)
    for (c = 1; c <= 5; c++)
    {
     strtext = "r" + r + "c" + c;
     otable.cell(r, c).range.text = strtext;
    }
   otable.rows[1].range.font.bold = 1;
   otable.rows[1].range.font.italic = 1;
   //add some text after the table.
   word.paragraph opara4;
   orng = odoc.bookmarks.get_item(ref oendofdoc).range;
   opara4 = odoc.content.paragraphs.add(ref orng);
   opara4.range.insertparagraphbefore();
   opara4.range.text = "and here's another table:";
   opara4.format.spaceafter = 24;
   opara4.range.insertparagraphafter();
   //insert a 5 x 2 table, fill it with data, and change the column widths.
   wrdrng = odoc.bookmarks.get_item(ref oendofdoc).range;
   otable = odoc.tables.add(wrdrng, 5, 2, ref omissing, ref omissing);
   otable.range.paragraphformat.spaceafter = 6;
   for (r = 1; r <= 5; r++)
    for (c = 1; c <= 2; c++)
    {
     strtext = "r" + r + "c" + c;
     otable.cell(r, c).range.text = strtext;
    }
   otable.columns[1].width = oword.inchestopoints(2); //change width of columns 1 & 2
   otable.columns[2].width = oword.inchestopoints(3);
   //keep inserting text. when you get to 7 inches from top of the
   //document, insert a hard page break.
   object opos;
   double dpos = oword.inchestopoints(7);
   odoc.bookmarks.get_item(ref oendofdoc).range.insertparagraphafter();
   do
   {
    wrdrng = odoc.bookmarks.get_item(ref oendofdoc).range;
    wrdrng.paragraphformat.spaceafter = 6;
    wrdrng.insertafter("a line of text");
    wrdrng.insertparagraphafter();
    opos = wrdrng.get_information
        (word.wdinformation.wdverticalpositionrelativetopage);
   }
   while (dpos >= convert.todouble(opos));
   object ocollapseend = word.wdcollapsedirection.wdcollapseend;
   object opagebreak = word.wdbreaktype.wdpagebreak;
   wrdrng.collapse(ref ocollapseend);
   wrdrng.insertbreak(ref opagebreak);
   wrdrng.collapse(ref ocollapseend);
   wrdrng.insertafter("we're now on page 2. here's my chart:");
   wrdrng.insertparagraphafter();
   //insert a chart.
   word.inlineshape oshape;
   object oclasstype = "msgraph.chart.8";
   wrdrng = odoc.bookmarks.get_item(ref oendofdoc).range;
   oshape = wrdrng.inlineshapes.addoleobject(ref oclasstype, ref omissing,
    ref omissing, ref omissing, ref omissing,
    ref omissing, ref omissing, ref omissing);
   //demonstrate use of late bound ochart and ochartapp objects to
   //manipulate the chart object with msgraph.
   object ochart;
   object ochartapp;
   ochart = oshape.oleformat.object;
   ochartapp = ochart.gettype().invokemember("application",
    bindingflags.getproperty, null, ochart, null);
   //change the chart type to line.
   object[] parameters = new object[1];
   parameters[0] = 4; //xlline = 4
   ochart.gettype().invokemember("charttype", bindingflags.setproperty,
    null, ochart, parameters);
   //update the chart image and quit msgraph.
   ochartapp.gettype().invokemember("update",
    bindingflags.invokemethod, null, ochartapp, null);
   ochartapp.gettype().invokemember("quit",
    bindingflags.invokemethod, null, ochartapp, null);
   //... if desired, you can proceed from here using the microsoft graph 
   //object model on the ochart and ochartapp objects to make additional
   //changes to the chart.
   //set the width of the chart.
   oshape.width = oword.inchestopoints(6.25f);
   oshape.height = oword.inchestopoints(3.57f);
   //add text after the chart.
   wrdrng = odoc.bookmarks.get_item(ref oendofdoc).range;
   wrdrng.insertparagraphafter();
   wrdrng.insertafter("the end.");
   //close this form.
   this.close();
  }
  private void button2_click(object sender, eventargs e)
  {
   string s = "";
   if (openfiledialog1.showdialog() == dialogresult.ok)
   {
    s = openfiledialog1.filename;
   }
   else
   {
    return;
   }
   // 在此处放置用户代码以初始化页面
   word.applicationclass word = new word.applicationclass();
   type wordtype = word.gettype();
   word.documents docs = word.documents;
   // 打开文件
   type docstype = docs.gettype();
   object filename = s;
   word.document doc = (word.document)docstype.invokemember("open",
   system.reflection.bindingflags.invokemethod, null, docs, new object[] { filename, false, false });
   // 转换格式，另存为
   type doctype = doc.gettype();
   object savefilename = "d:\\reports\\aaa.doc";
   //下面是microsoft word 9 object library的写法，如果是10，可能写成：
   /*
   doctype.invokemember("saveas", system.reflection.bindingflags.invokemethod,
    null, doc, new object[]{savefilename, word.wdsaveformat.wdformatfilteredhtml});
   */
   ///其它格式：
   ///wdformathtml
   ///wdformatdocument
   ///wdformatdostext
   ///wdformatdostextlinebreaks
   ///wdformatencodedtext
   ///wdformatrtf
   ///wdformattemplate
   ///wdformattext
   ///wdformattextlinebreaks
   ///wdformatunicodetext
   doctype.invokemember("saveas", system.reflection.bindingflags.invokemethod,
    null, doc, new object[] { savefilename, word.wdsaveformat.wdformatdocument });
   // 退出 word
   wordtype.invokemember("quit", system.reflection.bindingflags.invokemethod,
    null, word, null);
  }
  private void wordconvert(string s)
  {
   oword.applicationclass word = new microsoft.office.interop.word.applicationclass();
   type wordtype = word.gettype();
   //打开word文档
   /*对应脚本中的
    var word = new activexobject("word.application");
    var doc = word.documents.open(docfile);
   */
   oword.documents docs = word.documents;
   type docstype = docs.gettype();
   object objdocname =s;
   oword.document doc = (oword.document)docstype.invokemember("open", system.reflection.bindingflags.invokemethod, null, docs, new object[] { objdocname, true, true });
   //打印输出到指定文件
   //你可以使用 doc.printout();方法,次方法调用中的参数设置较繁琐,建议使用 type.invokemember 来调用时可以不用将printout的参数设置全,只设置4个主要参数
   type doctype = doc.gettype();
   object printfilename = @"c:\aaa.ps";
   doctype.invokemember("printout", system.reflection.bindingflags.invokemethod, null, doc, new object[] { false, false, oword.wdprintoutrange.wdprintalldocument, printfilename });
   //new object[]{false,false,oword.wdprintoutrange.wdprintalldocument,printfilename}
   //对应脚本中的word.printout(false, false, 0, psfile);的参数
   //退出word
   //对应脚本中的word.quit();
   wordtype.invokemember("quit", system.reflection.bindingflags.invokemethod, null, word, null);
   object o1 = "c:\\aaa.ps";
   object o2 = "c:\\aaa.pdf";
   object o3 = "";
   //引用将ps转换成pdf的对象
   //try catch之间对应的是脚本中的 pdf.filetopdf(psfile,pdffile,"");  //你可以使用 pdfconvert.filetopdf("c:\\test.ps","c:\\test.pdf","");这样的转换方法,本人只是为了保持与word相同的调用方式
   try
   {
    acrodistxlib.pdfdistillerclass pdf = new acrodistxlib.pdfdistillerclass();
    type pdftype = pdf.gettype();
    pdftype.invokemember("filetopdf", system.reflection.bindingflags.invokemethod, null, pdf, new object[] { o1, o2, o3 });
    pdf = null;
   }
   catch { } //读者自己补写错误处理
   //为防止本方法调用多次时发生错误,必须停止acrodist.exe进程
   foreach (system.diagnostics .process proc in system.diagnostics.process.getprocesses())
   {
    int begpos;
    int endpos;
    string sprocname = proc.tostring();
    begpos = sprocname.indexof("(") + 1;
    endpos = sprocname.indexof(")");
    sprocname = sprocname.substring(begpos, endpos - begpos);
    if (sprocname.tolower().compareto("acrodist") == 0)
    {
     try
     {
      proc.kill(); //停止进程
     }
     catch { } //读者自己补写错误处理
     break;
    }
   }
  }
  private void button3_click(object sender, eventargs e)
  {
   if (openfiledialog1.showdialog() == dialogresult.ok)
   {
    string s = openfiledialog1.filename;
    wordconvert(s);
   }
  }
  //getnextcode
  private void button4_click(object sender, eventargs e)
  {
   workcell myworkcell = new workcell(textbox2.text,textbox1.text);
   textbox3.text = myworkcell.getnextcode();
  }
 }
 public class workcell
 {
  private string workcellcode;
  private string parentcellcode;
  private string commoncode;
  private char[] code;
  private char[] pcode;
  private char[] standcode;
  private string s;
  public workcell( string mycode,string parentcode)
  {
   workcellcode = mycode;
   parentcellcode = parentcode;
   standcode = new char[] { '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 'w', 't', 'u', 'v', 'w', 'x', 'y', 'z' };
   commoncode = regex.replace(parentcellcode,@"0+","");
   code = workcellcode.substring(commoncode.length).tochararray();
  }
  public string workcellcode
  {
   set
   {
    workcellcode = value;
   }
   get
   {
    return workcellcode;
   }
  }
  public string parentcellcode
  { 
   set
   {
    workcellcode = value;
   }
   get
   {
    return workcellcode;
   }
  }
  public string getnextcode()
  {
   string s="";
   if (code.length > 0)
   {
    int i = 0;
    for (i = code.length - 1; i >= 0; i--)
    {
     if (code[i] != '0')
     {
      getnextchar(i);
      break;
     }
    }
    for(i=0;i<code.length;i++)
    {
     s+=code[i].tostring();
    }
    return commoncode + s;
   }
   else
   {
    return "null";
   }
  }
  //设置code中的下一个代码，从右边起，找到第一个非0字符，将其按标准代码自加1，溢出则进位
  private char getnextchar(int j)
  {
   int i = -1;
   int flag = 0;
   for (i = 0; i < standcode.length; i++)
   {
    if (code[j] == standcode[i])
    {
     flag = 1;
     break;
    }
   }
   //messagebox.show(code[j].tostring()+" "+standcode[i].tostring()+" "+i.tostring());
   if (i >= standcode.length-1 || flag==0)
   {
    code[j] = standcode[0];
    if (j > 0)
     code[j - 1] = getnextchar(j - 1);
   }
   else
   {
    code[j] = standcode[i + 1];
   }
   return code[j];
  }
 }
}

希望本文所述对大家的c#程序设计有所帮助。