使用Html Agility Pack剥离所有html标签

html html-agility-pack strip vb.net

我有一个像这样的html字符串:

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

我希望删除所有html标记,以便生成的字符串变为:

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

从SO的另一篇文章中我得出了这个函数(使用Html Agility Pack):

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

不幸的是,这不会返回我的预期,而是给出:

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

请问,我哪里出错 - 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:

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

一般承认的答案

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东西。


热门答案

它会删除白名单中未找到的标记和属性。

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



许可下: CC-BY-SA with attribution
不隶属于 Stack Overflow
这个KB合法吗? 是的,了解原因
许可下: CC-BY-SA with attribution
不隶属于 Stack Overflow
这个KB合法吗? 是的,了解原因