Convert HTML files into XML files

ImportJava. Io. bufferedinputstream;

ImportJava. Io. fileoutputstream;

ImportJava. Io. filewriter;

ImportJava. Io. ioexception;

ImportJava. Io. printwriter;

ImportJava.net. url;

ImportOrg. W3C. Tidy. Tidy;

Public ClassHtml2xml {

PrivateStringURL;

PrivateStringOutfilename;

PrivateStringErroutfilename;

PublicHtml2xml (string URL, string outfilename, string erroutfilename ){

This . URL = URL; /// provides an ingress URL

This . outfilename = outfilename; /// export a file

This.Erroutfilename= Erroutfilename;//Zookeeper File

}

Public static void main (string [] ARGs) {

/// metric data: HTML file utl , export the file and upload the file name

system. out . println ( " Program Start Operation ...... " );

html2xml T = New html2xml ( " http: // hswebuat01/Maximo/help.html " ,

"C: \ temp \ html2xml. xml","C: \ temp \ err.txt");

T. Convert ();

System.Out. Println ("End of program operation...... ");

}

Public VoidConvert (){

Url u;

Bufferedinputstream in;

Fileoutputstream out;

tidy = New tidy ();

tidy. setxmlout ( true ); /// notification tidy about HTML scaled to XML

Try{

Tidy. seterrout ( New Printwriter ( New Filewriter ( Erroutfilename ), True )); // Save zookeeper information to a file

U =NewURL (URL);

In = New bufferedinputstream (U. openstream (); /// Create a sequence to input and output streams

Out =NewFileoutputstream (Outfilename);

Tidy. parse (In, out );//Zookeeper File

In. Close ();

Out. Close ();

}Catch(Ioexception e ){

System.Out. Println (This. Tostring () + E. tostring ());

}

}

}

 

 

 

 

/Files/snowfun/html2xml.zip

// Files/snowfun/jtidy-r938.zip

Key points:

(1) bufferedinputstream () Application

(2) Java extension standard library org. W3C. Tidy. Tidy

(3) Use of URLs

Note:

The Org. W3C. tidy package used in this program is downloaded at http://sourceforge.net/projects/jtidy. Decompress the package and reference the tidy package in the build folder.