word文档转换成html格式
'**********************************************************
'
' 调用方法:doc2html c:\doc2html c:\doc2html
' 调用方法:doc2html -s c:\doc2html\a.doc c:\doc2html
'
'**********************************************************
Dim Objword
Dim Objdoc
Dim Objfso
Dim Strsource
Dim Strtarget
Dim Bbatch
'得到命令行参数,有三种可能的格式:[-s] 要进行转换的源文件目录或文件 转换成Html文件后保存的目录
Function Getparams()
Dim Objarg
If Wscript.Arguments.Count >= 2 Then
If Wscript.Arguments.Item(0) = "-s" Or Wscript.Arguments.Item(0) = "-S" Then
Strsource = Wscript.Arguments.Item(1)
Strtarget = Wscript.Arguments.Item(2)
Bbatch = False
Else
Strsource = Wscript.Arguments.Item(0)
Strtarget = Wscript.Arguments.Item(1)
Bbatch = True
End If
Else
Wscript.Quit(1)
End If
End Function
Function Batchprocessing()
Dim Objfolder
Dim Objfile
Dim Lpos
Dim Strfilename
Lpos = 0
Set Objfolder = Objfso.Getfolder(Strsource)
For Each Objfile In Objfolder.Files
Lpos = Instr(1,Mid(Objfile.Path,Len(Objfile.Path) - 3,4),"Doc",1)
If Lpos > 0 Then
Strfilename = Objfso.Getbasename(Objfile.Path)
Wordinterface Objfile.Path,Strfilename
End If
Next
End Function
Function Singleprocessing()
Dim Objfile
Set Objfile = Objfso.Getfile(Strsource)
Strfilename = Objfso.Getbasename(Objfile.Path)
Wordinterface Objfile.Path,Strfilename
End Function
Function Wordinterface(Strfilename,Formattedfilename)
Objword.Documents.Open Strfilename
Set Objdoc = Objword.Activedocument
'Stop
'set The Title Of The Document To Match The Filename
Objdoc.Builtindocumentproperties(1) = Formattedfilename
'1 = Wdpropertytitle In Vba
Objdoc.Saveas Strtarget & "\" & Formattedfilename & ".htm",8
'objdoc.Saveas "C:\Doc2Html\" & Formattedfilename & ".htm",8
On Error Resume Next
Objdoc.Close
End Function
'stop
Set Objfso = Createobject("Scripting.FileSystemObject")
Set Objword = Createobject("Word.Application")
Objword.Visible = False
Call Getparams
If Bbatch Then
Call Batchprocessing
Else
Call Singleprocessing
End If
Objword.Quit
Set Objword = Nothing
Top
// 清除WORD冗余格式并粘贴
function cleanAndPaste( html ) {
// Remove all SPAN tags
html = html.replace(/]*>/gi, "" );
// Remove Class attributes
html = html.replace(/]*) class=([^ |>]*)([^>]*)/gi, "
// Remove Style attributes
html = html.replace(/]*) style="([^"]*)"([^>]*)/gi, "
// Remove Lang attributes
html = html.replace(/]*) lang=([^ |>]*)([^>]*)/gi, "
// Remove XML elements and declarations
html = html.replace(/]*>/gi, "") ;
// Remove Tags with XML namespace declarations:
html = html.replace(/]*>/gi, "") ;
// Replace the
html = html.replace(/ /, " " );
// Transform
to
var re = new RegExp("(
]*>.*?)()","gi") ; // Different because of a IE 5.0 error
html = html.replace( re, "
insertHTML( html ) ;
}