
<%
'extract.asp (c) 2000 Thomas Winningham - use freely!

Function GetCell(cellnumber, extracturl)
   'Variables: Cellnumber: Number of the cell to get data from
   'ExtractURL: complete url that contains the cells and data
   'Returns a string of the cells data (including html)

   'Use the SOFTWING.AspTear component to get the HTML (but any 
   'will do... just rewrite this part) connection is including in 
   'Function for purpose of being self-contained
   Const Request_POST = 1
   Const Request_GET = 2

   Set xObj = Server.CreateObject("SOFTWING.AspTear")
   strRetVal = xObj.Retrieve(extracturl,Request_GET,"","","")
   set xobj = nothing

   i = 1              ' HTML Text Location Start
   q = 1              ' Cell Number Start

   ' Loop until we have processed the cell we're looking for   
   Do until q > cellnumber
      ' Look for <TD the start of a cell
      i = InStr(i, UCase(strRetVal), "<TD")
      
      ' Find the location of the end of the <TD tag
      r = InStr(i, strRetVal, ">")          
      
      ' Let the next loop start looking after this <TD tag we found
      i = r + 1                             
      
      ' increase the count of which cell we're at
      q = q + 1                             
   Loop

   ' The start of our cell text is right after the last found tag
   StartCellText = i                    

   ' Now... to find the end of this cell's text, we look for either <TABLE 
   ' or <TD - whichever comes first (but we have to check if they exist or not)
   ' We don't include nested tables in the cell data because those tables have 
   ' cells of their own.
   If (InStr(r, UCase(strRetVal), "<TABLE") > 0) AND _
         (InStr(r, UCase(strRetVal), "<TABLE") < _
              InStr(r, UCase(strRetVal), "</TD>")) then
      ThisCellText = mid(strRetVal, StartCellText, _
               InStr(r, UCase(strRetVal),"<TABLE")- StartCellText )
   Else
      ThisCellText = mid(strRetVal, StartCellText, _
               InStr(r, UCase(strRetVal), "</TD>")- StartCellText )
   End If

   GetCell = ThisCellText
End Function



Function NumberCells(extracturl)
   'Variables: ExtractUrl: The URL (eg http://www.cnn.com) to number
   'returns a string of the entire HTML document with numbers at the beginning
   'of each cell

   'Use the SOFTWING.AspTear component to get the HTML (but any will do... 
   'just rewrite this part)
   'connection is including in Function for purpose of being self-contained
   Const Request_POST = 1
   Const Request_GET = 2

   Set xObj = Server.CreateObject("SOFTWING.AspTear")
   strRetVal = xObj.Retrieve(extracturl,Request_GET,"","","")
   set xobj = nothing

   i = 1           ' HTML Text Location Start
   q = 1           ' Cell Number Start

   ' So long as <TD cells exist- number them
   Do while InStr(i, UCase(strRetVal), "<TD") > 0
       ' find next <TD
       i = InStr(i, UCase(strRetVal), "<TD")
       
       ' fomd the end of the <TD
       r = InStr(i, strRetVal, ">")
       strRetVal =  left(strRetVal, r) & q & _
             right(strRetVal, len(strRetVal) - r)

       'Number the cells: the string equals all the html we've check, 
       'our cell number, and then the html we've yet to check
       ' Let the next loop start looking after this <TD tag we found
       i = r + 1
 
       ' increase the count of which cell we're at
       q = q + 1
   Loop

   NumberCells = strRetVal
End Function
%>