从WORD文本生成相应的HTML网页

最新推荐文章于 2023-06-14 20:00:09 发布

laixingrong

最新推荐文章于 2023-06-14 20:00:09 发布

阅读量5.3k

点赞数

分类专栏： .NET C# 文章标签： html object string 文档 byte path

本文链接：https://blog.youkuaiyun.com/laixingrong/article/details/2064570

版权

.NET C# 专栏收录该内容

4 篇文章

订阅专栏

本文介绍了如何利用word.application对象读取Word文件内容，并转换为HTML格式，创建网页。目前作者正在探索处理Word中的复杂控件对象。此外，提到了一个向Word文件插入图片的示例。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

使用word.application对象从word文件中读取出文本信息，然后进行编码转换，再构造HTML网页并且存储。

操作word中其他控件对象相对麻烦一些，正在学习研究中。

// 打开文件读取内容

Microsoft.Office.Interop.Word.Application myWordApp = new Microsoft.Office.Interop.Word.ApplicationClass();

int num = myWordApp.Documents.Count;

object path = @" D:RogerWithLogWORD est.doc " ;

Document myWordDoc;

object oMissing = System.Reflection.Missing.Value;

object read = true ;

myWordDoc = myWordApp.Documents.Open( ref path, ref oMissing, ref read, ref oMissing, ref oMissing,

ref oMissing, ref oMissing, ref oMissing, ref oMissing, ref oMissing, ref oMissing,

ref oMissing, ref oMissing, ref oMissing, ref oMissing, ref oMissing);

string temp = myWordDoc.Content.Text;

this .Literal1.Text = temp;

myWordDoc.Close( ref oMissing, ref oMissing, ref oMissing);

myWordApp.Quit( ref oMissing, ref oMissing, ref oMissing);

StreamWriter sw = new StreamWriter(FilePath);

sw.Write( " <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"><html><head><meta http-equiv="Content-Type" content="text/html; charset=gb2312"><title>无标题文档</title></head><body> " + myWordDoc.Content.Text.Trim().ToString() + " </body></html> " );

sw.Close();

myWordDoc.Close( ref oMissing, ref oMissing, ref oMissing);

myWordApp.Quit( ref oMissing, ref oMissing, ref oMissing); */

string FilePath = @" D:RogerWithLogsubFileTest.html " ;

StreamWriter sw = new StreamWriter(FilePath);

// 进行编码之间的转换

string unicodeString = temp;

// Create two different encodings.

Encoding ascii = Encoding.ASCII;

Encoding unicode = Encoding.Unicode;

// Convert the string into a byte[].

byte [] unicodeBytes = unicode.GetBytes(unicodeString);

// Perform the conversion from one encoding to the other.

byte [] asciiBytes = Encoding.Convert(unicode, ascii, unicodeBytes);

// Convert the new byte[] into a char[] and then into a string.

// This is a slightly different approach to converting to illustrate

// the use of GetCharCount/GetChars.

char [] asciiChars = new char [ascii.GetCharCount(asciiBytes, 0 , asciiBytes.Length)];

ascii.GetChars(asciiBytes, 0 , asciiBytes.Length, asciiChars, 0 );

string test = new string (asciiChars);

// 构造HTML文件

sw.Write( " <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> <html> <head> <meta http-equiv="Content-Type" content="text/html; charset=Unicode"> <title>无标题文档</title> </head> <body> " + test + " </body> </html> " );

sw.Close();

Server.Transfer( @" ../sub/FileTest.html " );

补充一个往word文件中添加图片的示例：

string FileName = @" D:RogerWithLogWORDNewTest2.doc " ;

string fileName0 = FileName;

object fileName1 = FileName;

object readOnly = false ;

object isVisible = true ;

object missing = System.Reflection.Missing.Value;

Microsoft.Office.Interop.Word.ApplicationClass WordApp = new Microsoft.Office.Interop.Word.ApplicationClass();

WordApp.Visible = true ;

WordApp.

// 打开word文档

Microsoft.Office.Interop.Word.Document aDoc = WordApp.Documents.Open( ref fileName1, ref missing, ref readOnly,

ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref missing, ref isVisible, ref missing, ref missing, ref missing, ref missing);

aDoc.Activate();

// 插入图片

object a = true ;

object b = true ;

// 定义位置