18

我有一个这样的html字符串：

<html><body><p>foo <a href='http://www.example.com'>bar</a> baz</p></body></html>

我希望剥离所有 html 标签，以便生成的字符串变为：

foo bar baz

从 SO 的另一篇文章中，我提出了这个功能（它使用 Html Agility Pack）：

  Public Shared Function stripTags(ByVal html As String) As String
    Dim plain As String = String.Empty
    Dim htmldoc As New HtmlAgilityPack.HtmlDocument

    htmldoc.LoadHtml(html)
    Dim invalidNodes As HtmlAgilityPack.HtmlNodeCollection = htmldoc.DocumentNode.SelectNodes("//html|//body|//p|//a")

    If Not htmldoc Is Nothing Then
      For Each node In invalidNodes
        node.ParentNode.RemoveChild(node, True)
      Next
    End If

    Return htmldoc.DocumentNode.WriteContentTo
  End Function

不幸的是，这并没有返回我所期望的，而是给出了：

bazbarfoo

拜托，我哪里出错了——这是最好的方法吗？

问候和快乐的编码！

更新：通过下面的答案，我想出了这个功能，可能对其他人有用：

  Public Shared Function stripTags(ByVal html As String) As String
    Dim htmldoc As New HtmlAgilityPack.HtmlDocument
    htmldoc.LoadHtml(html.Replace("</p>", "</p>" & New String(Environment.NewLine, 2)).Replace("<br/>", Environment.NewLine))
    Return htmldoc.DocumentNode.InnerText
  End Function
4

5 回答 5

33

为什么不直接返回htmldoc.DocumentNode.InnerText而不是删除所有非文本节点？它应该给你你想要的。

于 2010-06-29T13:19:12.390 回答
2

它会删除白名单中未找到的标签和属性。

Public NotInheritable Class HtmlSanitizer
    Private Sub New()
    End Sub
    Private Shared ReadOnly Whitelist As IDictionary(Of String, String())
    Private Shared DeletableNodesXpath As New List(Of String)()

    Shared Sub New()
        Whitelist = New Dictionary(Of String, String())() From { _
            {"a", New () {"href"}}, _
            {"strong", Nothing}, _
            {"em", Nothing}, _
            {"blockquote", Nothing}, _
            {"b", Nothing}, _
            {"p", Nothing}, _
            {"ul", Nothing}, _
            {"ol", Nothing}, _
            {"li", Nothing}, _
            {"div", New () {"align"}}, _
            {"strike", Nothing}, _
            {"u", Nothing}, _
            {"sub", Nothing}, _
            {"sup", Nothing}, _
            {"table", Nothing}, _
            {"tr", Nothing}, _
            {"td", Nothing}, _
            {"th", Nothing} _
        }
    End Sub

    Public Shared Function Sanitize(input As String) As String
        If input.Trim().Length < 1 Then
            Return String.Empty
        End If
        Dim htmlDocument = New HtmlDocument()

        htmlDocument.LoadHtml(input)
        SanitizeNode(htmlDocument.DocumentNode)
        Dim xPath As String = HtmlSanitizer.CreateXPath()

        Return StripHtml(htmlDocument.DocumentNode.WriteTo().Trim(), xPath)
    End Function

    Private Shared Sub SanitizeChildren(parentNode As HtmlNode)
        For i As Integer = parentNode.ChildNodes.Count - 1 To 0 Step -1
            SanitizeNode(parentNode.ChildNodes(i))
        Next
    End Sub

    Private Shared Sub SanitizeNode(node As HtmlNode)
        If node.NodeType = HtmlNodeType.Element Then
            If Not Whitelist.ContainsKey(node.Name) Then
                If Not DeletableNodesXpath.Contains(node.Name) Then
                    'DeletableNodesXpath.Add(node.Name.Replace("?",""));
                    node.Name = "removeableNode"
                    DeletableNodesXpath.Add(node.Name)
                End If
                If node.HasChildNodes Then
                    SanitizeChildren(node)
                End If

                Return
            End If

            If node.HasAttributes Then
                For i As Integer = node.Attributes.Count - 1 To 0 Step -1
                    Dim currentAttribute As HtmlAttribute = node.Attributes(i)
                    Dim allowedAttributes As String() = Whitelist(node.Name)
                    If allowedAttributes IsNot Nothing Then
                        If Not allowedAttributes.Contains(currentAttribute.Name) Then
                            node.Attributes.Remove(currentAttribute)
                        End If
                    Else
                        node.Attributes.Remove(currentAttribute)
                    End If
                Next
            End If
        End If

        If node.HasChildNodes Then
            SanitizeChildren(node)
        End If
    End Sub

    Private Shared Function StripHtml(html As String, xPath As String) As String
        Dim htmlDoc As New HtmlDocument()
        htmlDoc.LoadHtml(html)
        If xPath.Length > 0 Then
            Dim invalidNodes As HtmlNodeCollection = htmlDoc.DocumentNode.SelectNodes(xPath)
            For Each node As HtmlNode In invalidNodes
                node.ParentNode.RemoveChild(node, True)
            Next
        End If
        Return htmlDoc.DocumentNode.WriteContentTo()


    End Function

    Private Shared Function CreateXPath() As String
        Dim _xPath As String = String.Empty
        For i As Integer = 0 To DeletableNodesXpath.Count - 1
            If i IsNot DeletableNodesXpath.Count - 1 Then
                _xPath += String.Format("//{0}|", DeletableNodesXpath(i).ToString())
            Else
                _xPath += String.Format("//{0}", DeletableNodesXpath(i).ToString())
            End If
        Next
        Return _xPath
    End Function
End Class
于 2010-08-29T19:55:00.737 回答
1

您似乎假设 ForEach 从头到尾遍历文档。如果您想确保这样做，请使用常规 for 循环。您甚至无法确定节点是否按照您期望使用 xpath 选择器的顺序被拾取，但在这种情况下您可能是对的..

问候，布鲁尼斯

于 2011-02-08T13:13:40.433 回答
0

在下面几行编辑，然后你得到你想要的..

Private Shared Function StripHtml(html As String, xPath As String) As String
    Dim htmlDoc As New HtmlAgilityPack.HtmlDocument()
    htmlDoc.LoadHtml(html)
    If xPath.Length > 0 Then
        Dim invalidNodes As HtmlNodeCollection = htmlDoc.DocumentNode.SelectNodes(xPath)

        '------- edit this line -------------------
        'For Each node As HtmlNode In invalidNodes
        'node.ParentNode.RemoveChild(node, True)
        'Next
        '
        ' result-> bazbarfoo
        '

        '------- modify line ----------------------
        For i = invalidNodes.Count - 1 To 0 Step -1
            Dim Node As HtmlNode = invalidNodes.Item(i)
            Node.ParentNode.RemoveChild(Node, True)
        Next
        '
        ' result-> foo bar baz
        '
    End If
    Return htmlDoc.DocumentNode.WriteContentTo()


End Function
于 2014-05-05T03:04:16.227 回答
-6

您可以使用以下代码。

public string RemoveHTMLTags(string source)
{
     string expn = "<.*?>";
     return Regex.Replace(source, expn, string.Empty);
}
于 2010-06-29T13:16:15.400 回答