If you know the document is well-formed XHTML you can use XPath and/or LINQ. Sorry, I don't know VB, but hopefully this is self-explanatory.
using System;
using System.Xml;
using System.Xml.Linq;
using System.Xml.XPath;
...
var xhtml = "put your xhtml here";
var xml = XDocument.Parse(xhtml);
var visitNodes = xml.XPathSelectElements("//span[@class='visit']/a/@href");
var links = from n in visitNodes select n.Value;
foreach(var l in links)
Console.WriteLine(l);
If you're stuck with .NET 2.0 or older, you can do the same thing with a few more lines of code using XmlDocument instead of XDocument.
If the HTML isn't well-formed, you'll need to use regular expressions.
Here's a good starting point.[
^]