Imports System.Net.WebClient
Imports System.Text.RegularExpressions

' Simple structure representing a URL and the file at the end of it (if any)
' Example: New Link(\"http://me.h/bl.a\").File - returns \"bl.a\"
' Example 2: New Link(\"http://me.h/bl.a\").URL - returns \"http://me.h/bl.a\"
Public Class Link

	Private link_url As String
	Private link_file As String

	Public Sub New(ByVal url As String)
		link_url = url
		link_file = url.Substring(url.LastIndexOf(\"/\") + 1)
	End Sub

	ReadOnly Property URL() As String
		Get
			Return link_url
		End Get
	End Property

	ReadOnly Property File() As String
		Get
			Return link_file
		End Get
	End Property

End Class

' Class for extracting links from HTML over HTTP
' Builds a list of Link objects representing both the full URL and file (if any)
' Supports only absolute links (ie. 'http://')
Public Class LinkReaper

	Private link_list As ArrayList

	Private Sub ParseURLsFromHTML(ByVal html As String)
		Dim links_found As MatchCollection
		links_found = Regex.Matches(html, \"<a.*?href=\"\"(.*?)\"\".*?>(.*?)</a>\")
		For Each match As Match In links_found
			Dim match_url As String = match.Groups(1).Value
			If match_url.StartsWith(\"http\") Then
				link_list.Add(New Link(match_url))
			End If
		Next
	End Sub

	Public Sub New(ByVal url As String)
		link_list = New ArrayList()
		Dim client As New System.Net.WebClient
		ParseURLsFromHTML(client.DownloadString(url))
	End Sub

	ReadOnly Property GetLinks() As ArrayList
		Get
			Return link_list
		End Get
	End Property
	
End Class

Dim links As LinkReaper = New LinkReaper(\"http://google.co.uk\")
For Each link As Link in links.GetLinks() ' lol, funny to say out loud.
    System.Console.WriteLine(link.URL) ' full URL
    System.Console.WriteLine(link.File) ' file at the end of the URL (if any)
Next