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。

(0)

相关推荐

  • c#开发word批量转pdf源码分享

    微软Office Word本身已经提供了另存为PDF文档功能,对于少量文档,手工使用该方式进行Word转换为PDF尚可,一旦需要处理大量的文档,可能就显得有些捉襟见肘了.不过对于已经安装有Office环境,借助一些简单的代码即可实现批量Word转PDF了. 源码: 复制代码 代码如下: using System;using System.Collections.Generic;using System.ComponentModel;using System.Data;using System.D

  • C#编程读取文档Doc、Docx及Pdf内容的方法

    本文实例讲述了C#编程读取文档Doc.Docx及Pdf内容的方法.分享给大家供大家参考.具体分析如下: Doc文档:Microsoft Word 14.0 Object Library (GAC对象,调用前需要安装word.安装的word版本不同,COM的版本号也会不同) Docx文档:Microsoft Word 14.0 Object Library (GAC对象,调用前需要安装word.安装的word版本不同,COM的版本号也会不同) Pdf文档:PDFBox /* 作者:GhostBea

  • C# 生转换网页为pdf

    从htm生成pdf大概可以分两步实现,第一步,解析htm,就是将htm源文件中那一对文本转换为浏览器最终呈现给我们那种图文并茂的结果.这是一个不可完成的任务,因为目前为止业界的软件巨头也没有谁把htm解析做得很好的.对比ie.firefox等浏览器的显示结果便可想而知.既然业界难题,我也就不去钻牛角尖做技术攻关了,先跳过这步,考虑下一步的事情. 第二步,绘制pdf,这个简单,网上有很多资料,有兴趣的朋友可以研究 pdf的文件格式,安装二进制组装pdf.我有兴趣,然而没有时间,我觉得软件从业者时刻

  • C#编程简单实现生成PDF文档的方法示例

    本文实例讲述了C#编程简单实现生成PDF文档的方法.分享给大家供大家参考,具体如下: using System; using System.IO; using System.Text; using System.Collections; namespace PDFGenerator { public class PDFGenerator { static float pageWidth = 594.0f; static float pageDepth = 828.0f; static float

  • C# WinForm打开PDF文件并在窗体中显示

    1.添加引用 工具箱---右键---选择项--COM组件--Adobe PDF Reader 2.使用方法 复制代码 代码如下: OpenFileDialog openFile=new OpenFileDialog(); open..Filter = "PDF文件|*.pdf"; openFile.ShowDialog(); axAcroPDF1.src = openFile.FileName; //axAcroPDF1.LoadFile(of.FileName);   //使用方法二

  • C#将jpg转换为pdf的方法

    本文实例讲述了C#将jpg转换为pdf的方法.分享给大家供大家参考.具体实现方法如下: C#生成pdf文件需要使用到一个itextsharp.dll文件,itextsharp.dll是一个开源的在C#中用来生成PDF文档的库文件,下面我们来给大家介绍利用itextsharp来生成库文件. 介绍 PDF生成所需类库itextsharp.dll,是一个开源的在C#中用来生成PDF文档的库文件,不少C#爱好者用它制作出了PDF文档生成器 具体代码如下: 复制代码 代码如下: void ConvertJ

  • word ppt excel文档转换成pdf的C#实现代码

    复制代码 代码如下: using System;using System.Collections.Generic;using System.ComponentModel;using System.Data;using System.Drawing;using System.Linq;using System.Text;using System.Windows.Forms; using Word = Microsoft.Office.Interop.Word;using Excel = Micro

  • c#实现pdf的另存为功能

    今天跟大家分享一个实现PDF另存为的效果,是调用Acrobat SDK的JavaScript实现的. 复制代码 代码如下: /// <summary>        /// PDF另存为效果        /// </summary>        /// <param name="fileName">PDF文件名</param>        /// <param name="saveFileName">

  • C#使用iTextSharp从PDF文档获取内容的方法

    本文实例讲述了C#使用iTextSharp从PDF文档获取内容的方法.分享给大家供大家参考.具体实现方法如下: using System; using System.Collections.Generic; using System.ComponentModel; using System.Data; using System.Drawing; using System.Linq; using System.Text; using System.Windows.Forms; using iTex

  • C# 中使用iTextSharp组件创建PDF的简单方法

    将iTextSharp.dll文件拷贝到项目的bin目录,然后在项目中添加引用: 然后在后台代码添加引用: 复制代码 代码如下: using iTextSharp.text;using iTextSharp.text.pdf;using System.IO;using System.Diagnostics; //创建PDF private void CreatePdf() {     //定义一个Document,并设置页面大小为A4,竖向      iTextSharp.text.Docume

  • C# 利用Aspose.Words.dll将 Word 转成PDF

    只要把aspose.words.dll 在bin中添加引用即可. 复制代码 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 Aspose.Words;using Aspose.Words.Saving;usi

  • 用C#来解析PDF文件

    1. 介绍 这个项目让你可以去读取并解析一个PDF文件,并将其内部结构展示出来. PDF文件的格式标准文档可以从Adobe那儿获取到. 这个项目基于"PDF指南,第六版,Adobe便携文档格式1.7 2006年11月". 它是一个恐怕有1310页的大部头. 本文提供了对这份文档的简洁概述. 与此相关的项目定义了用来读取和解析PDF文件的C#类. 为了测试这些类,附带的测试程序PdfFileAnalyzer让你可以去读取一个PDF文件,分析它并展示和保存结果. 程序将PDF文件分割成单独

随机推荐