VB.NET 获取HTML中的文字

最新推荐文章于 2025-11-24 10:02:38 发布

翻译最新推荐文章于 2025-11-24 10:02:38 发布 · 1.2k 阅读

标签

#vb.net #html #string #regex #function

#integer

收录于

asp.net 专栏收录该内容

59 篇文章

订阅专栏

本文介绍了一个用于从包含HTML的字符串中提取纯文本的VB.NET函数。该函数通过正则表达式移除所有HTML标签及特殊字符，返回干净的文字内容。

  ''' <summary>
    ''' 去除HTML标记
    ''' </summary>
    ''' <param name="strHtml">包括HTML的源码 </param>
    ''' <returns>已经去除后的文字</returns>
    Public Shared Function GetStrfromHTML(ByVal strHtml As String) As String


        Dim aryReg As String() = {"<script[^>]*?>.*?</script>", "<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", "([\r\n])[\s]+", "&(quot|#34);", "&(amp|#38);", "&(lt|#60);", _
         "&(gt|#62);", "&(nbsp|#160);", "&(iexcl|#161);", "&(cent|#162);", "&(pound|#163);", "&(copy|#169);", _
         "&#(\d+);", "-->", "<!--.*\n"}

        'chr(161),
        'chr(162),
        'chr(163),
        'chr(169),
        Dim aryRep As String() = {"", "", "", """", "&", "<", _
         ">", " ", "¡", "¢", "£", "©", _
         "", vbCr & vbLf, ""}

        Dim newReg As String = aryReg(0)
        Dim strOutput As String = strHtml
        For i As Integer = 0 To aryReg.Length - 1
            Dim regex As New Regex(aryReg(i), RegexOptions.IgnoreCase)
            strOutput = regex.Replace(strOutput, aryRep(i))
        Next

        strOutput.Replace("<", "")
        strOutput.Replace(">", "")
        strOutput.Replace(vbCr & vbLf, "")


        Return strOutput
    End Function