在使用 HttpWebRequest HttpWebResponse 二个虚拟类进行多线程序获取网页文件时，得到的是网页源码。这就存在一个“从网页源码中分离文本”的工作。

下面的函数就是从网页源码中分离文本的一种算法，实用效果还行。不知道还有没有更好的算法？

Private Function GetHtmlText(ByVal HTML As String) As String
'HTML = StrConv(HTML, VbStrConv.SimplifiedChinese)
HTML = HTML.Replace(" ", "")
Dim temp As String = String.Empty
Dim HtmlText As String = String.Empty
Dim i As Integer = 0
Dim j As Integer = 0
Dim k As Integer = HTML.IndexOf("<body")
Do
i = HTML.IndexOf(">", k)
If i > 1 Then
j = HTML.IndexOf("<", i + 1)
If j > 1 Then
temp = temp.Substring(i + 1, j - i - 1)
If temp.Length > 0 Then
HtmlText = HtmlText & temp
End If
Else
Exit Do
End If
Else
Exit Do
End If
k = j
Loop
Return HtmlText
End Function