繁体   English   中英

从单元格字符串中删除HTML标记:excel Formula

[英]remove HTML tags from cell strings : excel Formula

我在excel表中有一个带HTML标签的数据,如下所示:

<b>This is test data<br>Nice
<div> Go on this is next Cell
Very goood <b>.....</b>

所以,基本上我想在Excel工作表中删除或替换所有带有空格的html标签。

使用<*>模式应用Replace All

替换标签模式

要打开此功能,请转到功能区Home > Find & Select > Replace...或只需按CTRL + H.

使用TRIM功能可以进一步移除额外的空间。 祝好运!

在Excel中打开VBA(Alt + F11),单击右侧项目浏览器中的项目名称(电子表格名称)。 插入 - >新模块。 将用户定义的函数粘贴到模块窗口中。 保存为允许宏的.XLSM。

假设您的数据在单元格A2中,键入函数'= StripHTML(A2)'。 你也可以在这里下载一个工作示例:

http://jfrancisconsulting.com/how-to-strip-html-tags-in-excel/

Function StripHTML(cell As Range) As String
    Dim RegEx As Object
    Set RegEx = CreateObject("vbscript.regexp")
    Dim sInput As String
    Dim sOut As String
    sInput = cell.Text

    sInput = Replace(sInput, "\x0D\x0A", Chr(10))
    sInput = Replace(sInput, "\x00", Chr(10))

    'replace HTML breaks and end of paragraphs with line breaks
    sInput = Replace(sInput, "</P>", Chr(10) & Chr(10))
    sInput = Replace(sInput, "<BR>", Chr(10))

    'replace bullets with dashes
    sInput = Replace(sInput, "<li>", "-")

    'add back all of the special characters
    sInput = Replace(sInput, "&ndash;", "–")
    sInput = Replace(sInput, "&mdash;", "—")
    sInput = Replace(sInput, "&iexcl;", "¡")
    sInput = Replace(sInput, "&iquest;", "¿")
    sInput = Replace(sInput, "&quot;", "")
    sInput = Replace(sInput, "&ldquo;", "")
    sInput = Replace(sInput, "&rdquo;", "")
    sInput = Replace(sInput, "", "'")
    sInput = Replace(sInput, "&lsquo;", "'")
    sInput = Replace(sInput, "&rsquo;", "’")
    sInput = Replace(sInput, "&laquo;", "«")
    sInput = Replace(sInput, "&raquo;", "»")
    sInput = Replace(sInput, "&nbsp;", " ")
    sInput = Replace(sInput, "&amp;", "&")
    sInput = Replace(sInput, "&cent;", "¢")
    sInput = Replace(sInput, "&copy;", "©")
    sInput = Replace(sInput, "&divide;", "÷")
    sInput = Replace(sInput, "&gt;", ">")
    sInput = Replace(sInput, "&lt;", "<")
    sInput = Replace(sInput, "&micro;", "µ")
    sInput = Replace(sInput, "&middot;", "·")
    sInput = Replace(sInput, "&para;", "¶")
    sInput = Replace(sInput, "&plusmn;", "±")
    sInput = Replace(sInput, "&euro;", "€")
    sInput = Replace(sInput, "&pound;", "£")
    sInput = Replace(sInput, "&reg;", "®")
    sInput = Replace(sInput, "&sect;", "§")
    sInput = Replace(sInput, "&trade;", "™")
    sInput = Replace(sInput, "&yen;", "¥")
    sInput = Replace(sInput, "&aacute;", "á")
    sInput = Replace(sInput, "&Aacute;", "Á")
    sInput = Replace(sInput, "&agrave;", "à")
    sInput = Replace(sInput, "&Agrave;", "À")
    sInput = Replace(sInput, "&acirc;", "â")
    sInput = Replace(sInput, "&Acirc;", "Â")
    sInput = Replace(sInput, "&aring;", "å")
    sInput = Replace(sInput, "&Aring;", "Å")
    sInput = Replace(sInput, "&atilde;", "ã")
    sInput = Replace(sInput, "&Atilde;", "Ã")
    sInput = Replace(sInput, "&auml;", "ä")
    sInput = Replace(sInput, "&Auml;", "Ä")
    sInput = Replace(sInput, "&aelig;", "æ")
    sInput = Replace(sInput, "&AElig;", "Æ")
    sInput = Replace(sInput, "&ccedil;", "ç")
    sInput = Replace(sInput, "&Ccedil;", "Ç")
    sInput = Replace(sInput, "&eacute;", "é")
    sInput = Replace(sInput, "&Eacute;", "É")
    sInput = Replace(sInput, "&egrave;", "è")
    sInput = Replace(sInput, "&Egrave;", "È")
    sInput = Replace(sInput, "&ecirc;", "ê")
    sInput = Replace(sInput, "&Ecirc;", "Ê")
    sInput = Replace(sInput, "&euml;", "ë")
    sInput = Replace(sInput, "&Euml;", "Ë")
    sInput = Replace(sInput, "&iacute;", "í")
    sInput = Replace(sInput, "&Iacute;", "Í")
    sInput = Replace(sInput, "&igrave;", "ì")
    sInput = Replace(sInput, "&Igrave;", "Ì")
    sInput = Replace(sInput, "&icirc;", "î")
    sInput = Replace(sInput, "&Icirc;", "Î")
    sInput = Replace(sInput, "&iuml;", "ï")
    sInput = Replace(sInput, "&Iuml;", "Ï")
    sInput = Replace(sInput, "&ntilde;", "ñ")
    sInput = Replace(sInput, "&Ntilde;", "Ñ")
    sInput = Replace(sInput, "&oacute;", "ó")
    sInput = Replace(sInput, "&Oacute;", "Ó")
    sInput = Replace(sInput, "&ograve;", "ò")
    sInput = Replace(sInput, "&Ograve;", "Ò")
    sInput = Replace(sInput, "&ocirc;", "ô")
    sInput = Replace(sInput, "&Ocirc;", "Ô")
    sInput = Replace(sInput, "&oslash;", "ø")
    sInput = Replace(sInput, "&Oslash;", "Ø")
    sInput = Replace(sInput, "&otilde;", "õ")
    sInput = Replace(sInput, "&Otilde;", "Õ")
    sInput = Replace(sInput, "&ouml;", "ö")
    sInput = Replace(sInput, "&Ouml;", "Ö")
    sInput = Replace(sInput, "&szlig;", "ß")
    sInput = Replace(sInput, "&uacute;", "ú")
    sInput = Replace(sInput, "&Uacute;", "Ú")
    sInput = Replace(sInput, "&ugrave;", "ù")
    sInput = Replace(sInput, "&Ugrave;", "Ù")
    sInput = Replace(sInput, "&ucirc;", "û")
    sInput = Replace(sInput, "&Ucirc;", "Û")
    sInput = Replace(sInput, "&uuml;", "ü")
    sInput = Replace(sInput, "&Uuml;", "Ü")
    sInput = Replace(sInput, "&yuml;", "ÿ")
    sInput = Replace(sInput, "", "´")
    sInput = Replace(sInput, "", "`")

    'replace all the remaining HTML Tags
    With RegEx
    .Global = True
    .IgnoreCase = True
    .MultiLine = True
    .Pattern = "<[^>]+>" 'Regular Expression for HTML Tags.

    End With
    sOut = RegEx.Replace(sInput, "")
    StripHTML = sOut
    Set RegEx = Nothing
    End Function

由于上面的宏对我不起作用,我自己修复了。 这是我的第一个剧本,如果你们可以改进它们,让它更快,添加更多,那么你们非常欢迎!

好吧,我以前没有编程经验(除了6年前的一些非常基本的Java),但是在一些帮助下,很多猜测(实际上是小时)我设法制作这个脚本,它就像一个魅力去除大多数和8#文本,但它不会用换行符替换<BR> (你可以通过按CTRL + H来执行此操作,“find: <br> ”“替换:(现在按住ALT并使用类型0010与你的NUMPAD。一个小点应该在替换窗口中闪烁,然后点击“全部替换”)。

将下面的代码粘贴到用户模块中(alt + f11,右键单击Sheet1-> insert-> Module-> paste code)

然后通过File-> Options-> Customize Ribbon->选中Developer复选框来创建一个按钮。 然后转到开发人员选项卡 - >插入 - >按钮 - >然后放置按钮并右键单击 - >指定宏 - >选择删除标记。

Sub RemoveTags()
    Dim r As Range

    Selection.NumberFormat = "@"  'set cells to text numberformat

    With CreateObject("vbscript.regexp")
      .Pattern = "\<.*?\>"
      .Global = True

      For Each r In Selection
        r.Value = Replace(.Replace(r.Value, ""), "&#8217;", " ")
        r.Value2 = Replace(.Replace(r.Value2, ""), "&#8211;", " ")
      Next r

      For Each r In Selection
        r.Value = Replace(.Replace(r.Value, ""), "&#8216;", " ")
        r.Value2 = Replace(.Replace(r.Value2, ""), "&#8232;", " ")
      Next r

      For Each r In Selection
        r.Value = Replace(.Replace(r.Value, ""), "&#8233;", " ")
        r.Value2 = Replace(.Replace(r.Value2, ""), "&#146;s", " ")
      Next r
    End With
End Sub


Private Sub CommandButton1_Click()

End Sub

暂无
暂无

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM