Sample code for 30+ languages & platforms
B4X

Extract Metadata XML from PDF

See more PDF Signatures Examples

Demonstrates how to extract the metadata XML from a PDF.

Chilkat B4X Downloads

Download Chilkat for B4X
B4X 
Dim success As Boolean = False

'  This example requires the Chilkat API to have been previously unlocked.
'  See Global Unlock Sample for sample code.

Dim pdf As ChilkatPdf
pdf.Initialize("pdf")

success = pdf.LoadFile("qa_data/pdf/blank_with_metadata.pdf")
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


Dim sbXml As ChilkatStringBuilder
sbXml.Initialize
'  Note: Not all PDF files have metadata.  Metadata is optional.
success = pdf.GetMetadata(sbXml)
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


Dim xml As ChilkatXml
xml.Initialize
xml.LoadSb(sbXml, True)

Log(xml.GetXml)

'  Sample PDF metadata XML:
'  (Code for parsing follows)

'  Use this online tool to generate parsing code from sample XML: 
'  Generate Parsing Code from XML

'  <?xml version="1.0" encoding="utf-8"?>
'  <x:xmpmeta xmlns:x="adobe:ns:meta/" x:xmptk="Adobe XMP Core 9.1-c001 79.675d0f7, 2023/06/11-19:21:16        ">
'      <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
'          <rdf:Description rdf:about="" xmlns:xmp="http://ns.adobe.com/xap/1.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xmpMM="http://ns.adobe.com/xap/1.0/mm/" xmlns:pdf="http://ns.adobe.com/pdf/1.3/" xmlns:xmpRights="http://ns.adobe.com/xap/1.0/rights/">
'              <xmp:ModifyDate>2024-11-27T11:33:12-06:00</xmp:ModifyDate>
'              <xmp:CreateDate>2024-11-27T11:28:23-06:00</xmp:CreateDate>
'              <xmp:MetadataDate>2024-11-27T11:33:12-06:00</xmp:MetadataDate>
'              <xmp:CreatorTool>Adobe Acrobat Pro (32-bit) 24.3.20112</xmp:CreatorTool>
'              <dc:format>application/pdf</dc:format>
'              <dc:title>
'                  <rdf:Alt>
'                      <rdf:li xml:lang="x-default">Blank</rdf:li>
'                  </rdf:Alt>
'              </dc:title>
'              <dc:creator>
'                  <rdf:Bag>
'                      <rdf:li>Chilkat Software</rdf:li>
'                  </rdf:Bag>
'              </dc:creator>
'              <dc:description>
'                  <rdf:Alt>
'                      <rdf:li xml:lang="x-default">Blank Document</rdf:li>
'                  </rdf:Alt>
'              </dc:description>
'              <dc:subject>
'                  <rdf:Bag>
'                      <rdf:li>blank</rdf:li>
'                      <rdf:li>metadata</rdf:li>
'                      <rdf:li>document</rdf:li>
'                  </rdf:Bag>
'              </dc:subject>
'              <xmpMM:DocumentID>uuid:34535ffa-b632-43f1-b1fd-80cea6fdc351</xmpMM:DocumentID>
'              <xmpMM:InstanceID>uuid:69ace620-4c54-407f-8d45-6eebc90f34c2</xmpMM:InstanceID>
'              <pdf:Producer>Adobe Acrobat Pro (32-bit) 24.3.20112</pdf:Producer>
'              <pdf:Keywords>blank; metadata; document</pdf:Keywords>
'              <xmpRights:WebStatement>https://www.chilkatsoft.com/</xmpRights:WebStatement>
'          </rdf:Description>
'      </rdf:RDF>
'  </x:xmpmeta>

Dim x_xmpmeta_xmlns_x As String = xml.GetAttrValue("xmlns:x")
Dim x_xmpmeta_x_xmptk As String = xml.GetAttrValue("x:xmptk")
Dim rdf_RDF_xmlns_rdf As String = xml.ChilkatPath("rdf:RDF|(xmlns:rdf)")
Dim rdf_Description_rdf_about As String = xml.ChilkatPath("rdf:RDF|rdf:Description|(rdf:about)")
Dim rdf_Description_xmlns_xmp As String = xml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmp)")
Dim rdf_Description_xmlns_dc As String = xml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:dc)")
Dim rdf_Description_xmlns_xmpMM As String = xml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpMM)")
Dim rdf_Description_xmlns_pdf As String = xml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:pdf)")
Dim rdf_Description_xmlns_xmpRights As String = xml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpRights)")
Dim xmp_ModifyDate As String = xml.GetChildContent("rdf:RDF|rdf:Description|xmp:ModifyDate")
Dim xmp_CreateDate As String = xml.GetChildContent("rdf:RDF|rdf:Description|xmp:CreateDate")
Dim xmp_MetadataDate As String = xml.GetChildContent("rdf:RDF|rdf:Description|xmp:MetadataDate")
Dim xmp_CreatorTool As String = xml.GetChildContent("rdf:RDF|rdf:Description|xmp:CreatorTool")
Dim dc_format As String = xml.GetChildContent("rdf:RDF|rdf:Description|dc:format")
Dim rdf_li_xml_lang As String = xml.ChilkatPath("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li|(xml:lang)")
Dim rdf_li As String = xml.GetChildContent("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li")
rdf_li = xml.GetChildContent("rdf:RDF|rdf:Description|dc:creator|rdf:Bag|rdf:li")
rdf_li_xml_lang = xml.ChilkatPath("rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li|(xml:lang)")
rdf_li = xml.GetChildContent("rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li")
Dim i As Int = 0
Dim count_i As Int = xml.NumChildrenHavingTag("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li")
Do While i < count_i
    xml.I = i
    rdf_li = xml.GetChildContent("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li[i]")
    i = i + 1
Loop
Dim xmpMM_DocumentID As String = xml.GetChildContent("rdf:RDF|rdf:Description|xmpMM:DocumentID")
Dim xmpMM_InstanceID As String = xml.GetChildContent("rdf:RDF|rdf:Description|xmpMM:InstanceID")
Dim pdf_Producer As String = xml.GetChildContent("rdf:RDF|rdf:Description|pdf:Producer")
Dim pdf_Keywords As String = xml.GetChildContent("rdf:RDF|rdf:Description|pdf:Keywords")
Dim xmpRights_WebStatement As String = xml.GetChildContent("rdf:RDF|rdf:Description|xmpRights:WebStatement")