VB.NET读取UBL电子XML发票cac:AdditionalItemProperty节点遇阻求助

尝试读取含电子发票的XML文件，已配置命名空间，但无法提取cac:AdditionalItemProperty元素里cbc:Name值为02、cbc:Value值为2023171843的节点数据。以下是XML片段及VB.NET代码：

XML文件片段 #

<AttachedDocument xmlns="urn:oasis:names:specification:ubl:schema:xsd:AttachedDocument-2" xmlns:ds="http://www.w3.org/2000/09/xmldsig#" xmlns:cac="urn:oasis:names:specification:ubl:schema:xsd:CommonAggregateComponents-2" xmlns:cbc="urn:oasis:names:specification:ubl:schema:xsd:CommonBasicComponents-2" xmlns:ccts="urn:un:unece:uncefact:data:specification:CoreComponentTypeSchemaModule:2" xmlns:ext="urn:oasis:names:specification:ubl:schema:xsd:CommonExtensionComponents-2" xmlns:xades="http://uri.etsi.org/01903/v1.3.2#" xmlns:xades141="http://uri.etsi.org/01903/v1.4.1#">
<ext:UBLExtensions>
...
</ext:UBLExtensions>
<cbc:UBLVersionID>UBL 2.1</cbc:UBLVersionID>
<cbc:CustomizationID>Doctos</cbc:CustomizationID>
<cbc:ID>DT41647</cbc:ID>
<cbc:IssueDate>2023-03-17</cbc:IssueDate>
<cbc:ParentDocumentID>DT41647</cbc:ParentDocumentID>
<cac:SenderParty>
...
</cac:SenderParty>
<cac:ReceiverParty>
...
</cac:ReceiverParty>
<cac:Attachment>
<cac:ExternalReference>
<cbc:MimeCode>text/xml</cbc:MimeCode>
<cbc:EncodingCode>UTF-8</cbc:EncodingCode>
<cbc:Description>
<![CDATA[ <?xml version="1.0" encoding="UTF-8" standalone="no"?><Invoice xmlns:cac="urn:oasis:names:specification:ubl:schema:xsd:CommonAggregateComponents-2" xmlns:cbc="urn:oasis:names:specification:ubl:schema:xsd:CommonBasicComponents-2" xmlns:ext="urn:oasis:names:specification:ubl:schema:xsd:CommonExtensionComponents-2" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:sts="xxxx" xmlns:xades="http://uri.etsi.org/01903/v1.3.2#" xmlns:xades141="http://uri.etsi.org/01903/v1.4.1#" xmlns:ds="http://www.w3.org/2000/09/xmldsig#" xmlns:oth="http://example.org/oth" xsi:schemaLocation="urn:oasis:names:specification:ubl:schema:xsd:Invoice-2 http://docs.oasis-open.org/ubl/os-UBL-2.1/xsd/maindoc/UBL-Invoice-2.1.xsd" xmlns="urn:oasis:names:specification:ubl:schema:xsd:Invoice-2"><ext:UBLExtensions><ext:UBLExtension><ext:ExtensionContent>
<sts:xxxExtensions><sts:InvoiceControl><sts:InvoiceAuthorization>99999999</sts:InvoiceAuthorization><sts:AuthorizationPeriod><cbc:StartDate>2023-02-23</cbc:StartDate><cbc:EndDate>2024-02-23</cbc:EndDate></sts:AuthorizationPeriod><cac:AdditionalItemProperty><cbc:Name>01</cbc:Name><cbc:Value>105584152</cbc:Value></cac:AdditionalItemProperty><cac:AdditionalItemProperty><cbc:Name>02</cbc:Name><cbc:Value>2023171843</cbc:Value></cac:AdditionalItemProperty><cac:AdditionalItemProperty><cbc:Name>03</cbc:Name><cbc:Value>184000</cbc:Value><cbc:ValueQuantity unitCode="KG">1280</cbc:ValueQuantity></cac:AdditionalItemProperty></cac:Item><cac:Price><cbc:PriceAmount currencyID="PP">184000.00</cbc:PriceAmount><cbc:BaseQuantity unitCode="94">1.00</cbc:BaseQuantity></cac:Price></cac:InvoiceLine></Invoice> ]]>
</cbc:Description>
</cac:ExternalReference>
</cac:Attachment>
<cac:ParentDocumentLineReference>
</cac:ParentDocumentLineReference>
</AttachedDocument>

VB.NET代码 #

m_xmld.Load(fileName)
Dim manager As XmlNamespaceManager = New XmlNamespaceManager(m_xmld.NameTable)
manager.AddNamespace("cbc", "urn:oasis:names:specification:ubl:schema:xsd:CommonBasicComponents-2")
manager.AddNamespace("cac", "urn:oasis:names:specification:ubl:schema:xsd:CommonAggregateComponents-2")
'manager.AddNamespace("qdt", "urn:oasis:names:specification:ubl:schema:xsd:QualifiedDatatypes-2")
'manager.AddNamespace("xsd", "http://www.w3.org/2001/XMLSchema")
'manager.AddNamespace("udt", "urn:un:unece:uncefact:data:specification:UnqualifiedDataTypesSchemaModule:2")
'manager.AddNamespace("ccts", "urn:un:unece:uncefact:documentation:2")
manager.AddNamespace("ext", "urn:oasis:names:specification:ubl:schema:xsd:CommonExtensionComponents-2")
Dim list As XmlNodeList = m_xmld.SelectNodes("//cac:Attachment//cac:ExternalReference//cbc:Description", manager) 'da resultado 2
'Dim nodeComprobante As XmlNode = m_xmld.SelectSingleNode("//cac:AdditionalItemProperty", manager)
Dim nodeComprobante As XmlNode
For Each Book As XmlNode In list
    nodeComprobante = m_xmld.SelectSingleNode("//cac:AdditionalItemProperty", manager)
    'TotalXML += Book.SelectSingleNode("//cac:AdditionalItemProperty", manager).InnerXml 'error
    'Dim mCodigo As Object = New Book.Attributes.GetNamedItem("Name").Value 'error
Next
MessageBox.Show("Tota: " & TotalXML, Me.Text, MessageBoxButtons.OK, MessageBoxIcon.Exclamation)

问题原因及解决方法 #

核心问题是目标节点位于CDATA块内部，CDATA中的内容是独立的XML文档，无法直接通过主XML的XPath查询。需要先提取CDATA内容，加载为新的XML文档后再进行查询。

修改后的VB.NET代码 #

m_xmld.Load(fileName)
Dim manager As XmlNamespaceManager = New XmlNamespaceManager(m_xmld.NameTable)
manager.AddNamespace("cbc", "urn:oasis:names:specification:ubl:schema:xsd:CommonBasicComponents-2")
manager.AddNamespace("cac", "urn:oasis:names:specification:ubl:schema:xsd:CommonAggregateComponents-2")
manager.AddNamespace("ext", "urn:oasis:names:specification:ubl:schema:xsd:CommonExtensionComponents-2")

Dim list As XmlNodeList = m_xmld.SelectNodes("//cac:Attachment//cac:ExternalReference//cbc:Description", manager)
Dim TotalXML As String = ""

For Each descNode As XmlNode In list
    ' 提取CDATA中的XML内容
    Dim innerXmlContent As String = descNode.InnerText
    If Not String.IsNullOrEmpty(innerXmlContent) Then
        ' 加载内部XML
        Dim innerXmlDoc As New XmlDocument()
        innerXmlDoc.LoadXml(innerXmlContent)
        
        ' 为内部XML配置命名空间，注意要包含Invoice的默认命名空间
        Dim innerManager As New XmlNamespaceManager(innerXmlDoc.NameTable)
        innerManager.AddNamespace("cac", "urn:oasis:names:specification:ubl:schema:xsd:CommonAggregateComponents-2")
        innerManager.AddNamespace("cbc", "urn:oasis:names:specification:ubl:schema:xsd:CommonBasicComponents-2")
        innerManager.AddNamespace("inv", "urn:oasis:names:specification:ubl:schema:xsd:Invoice-2") ' 默认命名空间
        
        ' 查询Name为02的AdditionalItemProperty节点
        Dim targetNode As XmlNode = innerXmlDoc.SelectSingleNode("//inv:Invoice//cac:AdditionalItemProperty[cbc:Name='02']", innerManager)
        If targetNode IsNot Nothing Then
            ' 获取对应的Value值
            Dim valueNode As XmlNode = targetNode.SelectSingleNode("cbc:Value", innerManager)
            If valueNode IsNot Nothing Then
                TotalXML &= $"找到目标值：{valueNode.InnerText}{Environment.NewLine}"
            End If
        End If
    End If
Next

MessageBox.Show("结果: " & TotalXML, Me.Text, MessageBoxButtons.OK, MessageBoxIcon.Information)

关键说明 #

1. 提取cbc:Description的InnerText获取CDATA中的完整XML内容
2. 加载内部XML时，必须配置Invoice的默认命名空间（urn:oasis:names:specification:ubl:schema:xsd:Invoice-2），否则无法查询到根节点下的内容
3. 使用带条件的XPath//inv:Invoice//cac:AdditionalItemProperty[cbc:Name='02']精准定位目标节点

内容的提问来源于stack exchange，提问作者Fernando Diaz