Guidance:
Use Java to convert Word to HTML or TXT. Some time ago, I had a headache for this problem. Later I checked the materials and finally solved the problem. Now I am releasing the program for future reference.
//-------------------------------------------------------
// Copyright (c) inspur group Commercial Systems Ltd. reserves all rights
// File name: wordtohtml file version: 1.00.00
// Author: Guo casting author Email: guozhu@langchao.com completion date:
// File description:
// Other descriptions:
// Class column table:
// Wordtohtml: Convert all DOC files in the specified directory to HTML and store them in the same directory.
// Modification history:
// # Version modification date modified by the author
//-------------------------------------------
// 1 1.00.01 description of the author's name Modification
//----------------------------------------------------------
//-------------------------------------------------------
Import com.jacb.com .*;
Import com. Jacob. ActiveX .*;
Import java. Io .*;
// Obtain the names of all DOC files under the specified directory
Public groovy wordtohtml
{
//-------------------------------------------------
// Method prototype: Change (string paths)
// Function Description: Convert all DOC files in the specified directory to HTML and store them in the same directory.
// Input parameter: String
// Output parameter: None
// Return value: None
// Other instructions: Recursion
//--------------------------------------------
Public static void change (string paths, string savepaths)
{
File d = new file (paths );
// Obtain the list of all files and directories in the current folder
File lists [] = D. listfiles ();
String Path = new string ("");
// Search all files in the current directory
For (INT I = 0; I {
If (lists. isfile ())
{
String filename = lists. getname ();
String filetype = new string ("");
// Obtain the file type
Filetype = filename. Su tring (filename. Length ()-3), filename. Length ());
// Determine whether the file is a DOC file
If (filetype. Equals ("Doc "))
{
System. Out. println ("converting ......");
// Print the current directory path
System. Out. println (paths );
// Print the DOC file name
System. Out. println (filename. Su tring (0, (filename. Length ()-4 )));
Activexcomponent A = new activexcomponent ("word. A lication"); // start the word
String docpath = paths filename;
String htmlpath = savepaths filename. Su tring (0, (filename. Length ()-4 ));
String infile = docpath;
// The Word file to be converted
String tpfile = htmlpath;
// Html file
Boolean flag = false;
Try
{
A. setproperty ("visible", new variant (false ));
// Set word invisible
Object docs = A. getproperty ("events"). todi atch ();
Object Doc = di atch. invoke (Docs, "open", di atch. method, new object [] {infile, new variant (false), new variant (true)}, new int [1]). todi atch ();
// Open the Word file
Di atch. Invoke (Doc, "saveas", di atch. method, new object [] {tpfile, new variant (8)}, new int [1]);
// Save it as a temporary file in HTML Format
Variant F = new variant (false );
Di atch. Call (Doc, "close", F );
Flag = true;
}
Catch (exception E)
{
E. printstacktrace ();
}
Finally
{
A. Invoke ("quit", new variant [] {});
}
System. Out. println ("converted! ");
}
}
Else
{
Path = path
// Enter the directory at the next level
Path = path lists. getname ()"//"
// Recursively traverse all directories
Change (path, savepaths );
}
}
}
//---------------------------------------------------------
// Method prototype: Main (string [] ARGs)
// Function Description: main file
// Input parameter: None
// Output parameter: None
// Return value: None
// Other instructions: None
//----------------------------------------------------------
Public static void main (string [] ARGs)
{
String paths = new string ("D: // work // 2004.10.8 // test system // test01 // word //");
String savepaths = new string ("D: // work // 2004.10.8 // test system // test01 // html //");
Change (paths, savepaths );
}
}
The jar package for import is an open source, which can be searched on the Internet.
Di atch. Invoke (Doc, "saveas", di atch. method, new object [] {tpfile, new variant (8)}, new int [1]);
Modify variant (8)} to convert Word to various types.
This article is transferred from
Http://www.phpap.com/view.php? Tid = 1630