Android Question Scraping web with html

    Dim m As Matcher = Regex.Matcher("table class=""t2""><td class=\""", page)' originale

        html = html.Replace(Chr(10), "")    ' HTML page with line feeds removed
        Dim start As Int = html.IndexOf($"<table id="performances">"$)
        Dim stop As Int = html.IndexOf2($"</table>"$, start)
        If (stop > start) Then
            html = html.SubString2(start, stop + 8)
            extractList
        End If

Private Sub extractPerformance(data As String, p As performance)
    Dim pattern As String = $"class=.+?>[^\<]*"$
    Dim m As Matcher = Regex.Matcher(pattern, data)
    Do While m.Find
        item = m.Match
        If item.StartsWith($"class="association""$) Then p.association = extractData(item)
        If item.StartsWith($"class="place""$) Then p.place = extractData(item)
        If item.StartsWith($"class="address""$) Then p.address = extractData(item)
        If item.StartsWith($"class="changes""$) Then changes = extractData(item)
        If item.StartsWith($"class="title""$) Then p.title = changes & " " & extractData(item)
        If item.StartsWith($"class="footnote""$) Then p.footnote = p.footnote & " " & extractData(item)
    Loop
End Sub

' Extract the data content from a RegEx match item
Private Sub extractData(item As String) As String
    Dim result As String
    result = item.SubString(item.IndexOf(">") + 1) "
    Return result
End Sub

Sub Process_Globals
    Private fx As JFX
    Private MainForm As Form
    
'    --- Variable for Jsoup
    Private js As jSoup
    Private Extract01 As List
    Private Extract02 As List
    Private Extract03 As List
    Private Extract04 As List
End Sub

Sub AppStart (Form1 As Form, Args() As String)
    MainForm = Form1
'    MainForm.RootPane.LoadLayout("Layout1") 'Load the layout file.
'    MainForm.Show

    Extract01.Initialize
    Extract02.Initialize
    Extract03.Initialize
    Extract04.Initialize
    
    ScrapeTable
    
#IF B4A
    Activity.Finish
#End If

#if B4J
    ExitApplication        ' ends the program
#End If
    
End Sub

Private Sub ScrapeTable

'    --- Load the url
    Dim url As String = "https://www.superenalotto.com/archivio"
    
'    ---  Get the page content
    Dim HTML As String = js.connect(url)
'    Log (HTML)

'    --- Get the date for the numbers    
    Dim FirstDateRow As String = js.getElementsByClass(HTML, "t1").Get(0)

'    --- Get the first (op top row) of the table in t2 class
    Dim FirstTableRow As String = js.getElementsByClass(HTML, "t2").Get(0)

'    --- We need the t1 class for the date    
    Extract01 = js.selectorElementText(FirstDateRow, "a")

'    --- We need only the td rows of the wanted table    
    Extract02 = js.getElementsByClass(FirstTableRow, "ball-24px")
    Extract03 = js.getElementsByClass(FirstTableRow, "jolly-24px")
    Extract04 = js.getElementsByClass(FirstTableRow, "superstar-24px")

'    --- Show results during test periode
'    Log("Extract01: "& Extract01)
'    Dim Count As Int = Extract01.Size
'    Log("Count: "& Count)
'    
'    Log("Extract02: "& Extract02)
'    Dim Count As Int = Extract02.Size
'    Log("Count: "& Count)
    '
'    Log("Extract03: "& Extract03)
'    Dim Count As Int = Extract03.Size
'    Log("Count: "& Count)
    '
'    Log("Extract04: "& Extract04)
'    Dim Count As Int = Extract04.Size
'    Log("Count: "& Count)
    
'    --- Start with the date which is the first line
    Log($"The number from ${Extract01.Get(0)} are: ${CRLF}"$)
    
'    --- We need to scrape the rows and columns
    Dim columns As List
    columns.Initialize
    
'    --- To display a counter at the variables end
    Dim x As Int = 0
    
'    --- Scrape the first 6 numbers with the same class
    For i = 0 To Extract02.Size -1
        columns = js.selectorElementText($"<table>${Extract02.Get(i)}</table>"$, "td")
        
        For j = 0 To columns.Size -1
            x = x + 1
            Log($"Number${x}: ${columns.Get(j)}"$)
        Next
    Next
    
'    --- And scrape the Jolly number with different class
    For i = 0 To Extract03.Size -1
        columns = js.selectorElementText($"<table>${Extract03.Get(i)}</table>"$, "td")
        
        For j = 0 To columns.Size -1
            x = x + 1
            Log($"Jolly Number${x}: ${columns.Get(j)}"$)
        Next
    Next
    
'    --- And scrape the super number with different class 
    For i = 0 To Extract04.Size -1
        columns = js.selectorElementText($"<table>${Extract04.Get(i)}</table>"$, "td")
        
        For j = 0 To columns.Size -1
            x = x + 1
            Log($"Super Number${x}: ${columns.Get(j)}"$)
        Next
    Next
End Sub

'    --- Get the date for the numbers    
    Dim FirstDateRow As String = js.getElementsByClass(HTML, "t1").Get(0)

Sub InterpretaTabella(WWW As String)
    Dim TabellaHTML As String
    TabellaHTML=WWW.SubString(WWW.ToUpperCase.IndexOf($"<TABLE CLASS="T2">"$)) 'funziona la data
    TabellaHTML=TabellaHTML.SubString2(0,TabellaHTML.ToUpperCase.IndexOf("</TR"))'originale
    Dim Righe() As String = Regex.Split("</td>",TabellaHTML)'originale
  
    For Rg=0 To Righe.Length-1
        Dim celle() As String = Regex.Split("</td>",Righe(Rg))
        For Col=0 To celle.Length-1
            Dim Cella As String
            Cella=TogliTag(celle(Col))
            'Log("Cella (" & Rg & "," & Col & ") :" & Cella)
            Log (Cella.Trim)
        Next
    Next
End Sub

Sub TogliTag(cella As String) As String
    Dim Ret As String =""
    Dim Tag As Boolean = False
 
    For i=0 To cella.Length-1
        If cella.SubString2(i,i+1)="<" Then Tag=True
        If Not(Tag) Then Ret=Ret & cella.SubString2(i,i+1)
        If cella.SubString2(i,i+1)=">" Then Tag=False
    Next

    Return Ret
End Sub

'    --- Load the raw text file
    Dim RawHTML As String = ""
    Dim read1 As String="miotesto.txt"
    RawHTML = File.ReadString(File.DirAssets,read1)
'    Log("Raw RawHTML: " & RawHTML)  'displays the content of file
       
'    --- Remove empty lines and reformat the layout
    Dim HTML As String = js.parse_HTML(RawHTML)
    Log("Clean HTML: " & HTML)