htmlparser-user

[Htmlparser-user] Change Attributes of TDs and TRs

[Fuhrmann, M. <mic...@sa...>]

Hi All!

I want to change several attributes of the td and tr tags of certain =
tables but I don't know if do it the right way.
The problem is that I find the right table (only tables with ids) but I =
don't reach the td or tr tags....
My code looks like that:

public void cleanDokument(HttpServletRequest request,HttpServletResponse =
response) throws IOException
	{=09
		// Get the calling HTML Document define the Writer and open the =
connection
		URLConnection connection;
		URL request_url =3D new URL(request.getHeader("referer").toString());

		PrintWriter out =3D response.getWriter();
		connection =3D (HttpURLConnection)request_url.openConnection ();
	=09
		try
		{
		   Parser parser =3D new Parser ();
		   parser.setConnection(connection);
		  =20
		   NodeFilter all_tables =3D new TagNameFilter("table");
		   NodeList list =3D parser.parse (all_tables);
           	   Node[] nodelist;

           // Seperate all table tags
		   for (NodeIterator e =3D parser.elements (); e.hasMoreNodes ();)
		   e.nextNode ().collectInto (list,all_tables);
		  =20
		   nodelist=3Dlist.toNodeArray();
		  =20
		   for (int h=3D0; h<nodelist.length;h++)=20
		   {
		   	if (nodelist[h] instanceof TableTag)=20
		   	{=09
		   		//for schleife f=FCr die td's und tr's=09
		   		if(((TableTag)nodelist[h]).getAttribute("id")!=3D null)=20
		   		{
					for (int i=3D0; i<nodelist.length; i++)
					{
						out.println(nodelist.toString());
		   				if(nodelist[i] instanceof TableRow)
						{
							out.println("Row found!");
							((TableRow)nodelist[i]).removeAttribute ("nowrap");
						}
						else if (nodelist[i] instanceof TableColumn)
						{
							out.println("Column found!");
							((TableColumn)nodelist[i]).removeAttribute ("nowrap");
						}
		   			}
					out.println(nodelist[h].toHtml());
		   		}
		   	}
		   	else if(nodelist[h] instanceof TableRow || nodelist[h] instanceof =
TableColumn)
		   	{
				out.println("Else erreicht!");
		   		out.println(((TableRow)nodelist[h]).getText());
		   	}
		   }
		   //makePdf(out,response);
		}
		catch(Exception e)
		{
			out.println("Fehler beim Parsen!");
			e.printStackTrace(out);
		}
	}

Does my nodelist contain the tr and td tags? Is it right to say =
instanceof TableRow????

Many thanks and best regards
Michael

Re: [Htmlparser-user] Change Attributes of TDs and TRs

[Third E. <nav...@gm...>]
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Re: [Htmlparser-user] Change Attributes of TDs and TRs

[Derrick O. <Der...@Ro...>]

By the way, after this call: 
  NodeList list = parser.parse (all_tables);
the parser will be at the end of the page and return no more nodes.
So, this:
           // Seperate all table tags
                  * for* (NodeIterator e = parser.elements (); 
e.hasMoreNodes ();)
                   e.nextNode ().collectInto (list,all_tables);
doesn't do anything.

You can use:
  parser.reset ();
to start again, if that is what you really want to do, but in your case 
you would get duplicates of everything.


Third Eye wrote:

>Table tag object already has a fucntion to get the rows and TableRow
>has function to get columns. You don't need to iterate yourself.
>
>On 1/11/06, Fuhrmann, Michael <mic...@sa...> wrote:
>  
>
>>Hi All!
>>
>>I want to change several attributes of the td and tr tags of certain tables
>>but I don't know if do it the right way.
>>The problem is that I find the right table (only tables with ids) but I
>>don't reach the td or tr tags….
>>My code looks like that:
>>
>>public void cleanDokument(HttpServletRequest
>>request,HttpServletResponse response) throws IOException
>>        {
>>                // Get the calling HTML Document define the Writer and open
>>the connection
>>                URLConnection connection;
>>                URL request_url = new
>>URL(request.getHeader("referer").toString());
>>
>>                PrintWriter out = response.getWriter();
>>                connection =
>>(HttpURLConnection)request_url.openConnection ();
>>
>>                try
>>                {
>>                   Parser parser = new Parser ();
>>                   parser.setConnection(connection);
>>
>>                   NodeFilter all_tables = new TagNameFilter("table");
>>                   NodeList list = parser.parse (all_tables);
>>                   Node[] nodelist;
>>
>>           // Seperate all table tags
>>                   for (NodeIterator e = parser.elements (); e.hasMoreNodes
>>();)
>>                   e.nextNode ().collectInto (list,all_tables);
>>
>>                   nodelist=list.toNodeArray();
>>
>>                   for (int h=0; h<nodelist.length;h++)
>>                   {
>>                        if (nodelist[h] instanceof TableTag)
>>                        {
>>                                //for schleife f�r die td's und tr's
>>
>>if(((TableTag)nodelist[h]).getAttribute("id")!= null)
>>                                {
>>                                        for (int i=0; i<nodelist.length;
>>i++)
>>                                        {
>>
>>out.println(nodelist.toString());
>>                                                if(nodelist[i] instanceof
>>TableRow)
>>                                                {
>>                                                        out.println("Row
>>found!");
>>
>>((TableRow)nodelist[i]).removeAttribute ("nowrap");
>>                                                }
>>                                                else if (nodelist[i]
>>instanceof TableColumn)
>>                                                {
>>                                                        out.println("Column
>>found!");
>>
>>((TableColumn)nodelist[i]).removeAttribute ("nowrap");
>>                                                }
>>                                        }
>>                                        out.println(nodelist[h].toHtml());
>>                                }
>>                        }
>>                        else if(nodelist[h] instanceof TableRow ||
>>nodelist[h] instanceof TableColumn)
>>                        {
>>                                out.println("Else erreicht!");
>>
>>out.println(((TableRow)nodelist[h]).getText());
>>                        }
>>                   }
>>                   //makePdf(out,response);
>>                }
>>                catch(Exception e)
>>                {
>>                        out.println("Fehler beim Parsen!");
>>                        e.printStackTrace(out);
>>                }
>>        }
>>
>>Does my nodelist contain the tr and td tags? Is it right to say instanceof
>>TableRow????
>>
>>Many thanks and best regards
>>Michael
>>    
>>
>
>
>--
>Naveen K Kohli
>http://www.netomatix.com
>N?HY޵隊X???'???u???[???????
>ަ?k??!???W?~?鮆?zk??C?	塧m????@^ǚ??^??z?Z?f?z?j?!?x2???????ɫ,???a{??,?H??4?m???i?(??ܢo?v'??jYhr'ׯ:?rX??{f????????j)b?	b???ZZ?ǫ?ǫ?+-??.?ǟ????a??l??b??,???y?+??޷?b????+-?w??f??????ser=
>