Xbase++
Extract Metadata XML from PDF

Demonstrates how to extract the metadata XML from a PDF.
Chilkat Xbase++ Downloads

Xbase++
LOCAL nSuccess
LOCAL oPdf
LOCAL oSbXml
LOCAL oXml
LOCAL cX_xmpmeta_xmlns_x
LOCAL cX_xmpmeta_x_xmptk
LOCAL cRdf_RDF_xmlns_rdf
LOCAL cRdf_Description_rdf_about
LOCAL cRdf_Description_xmlns_xmp
LOCAL cRdf_Description_xmlns_dc
LOCAL cRdf_Description_xmlns_xmpMM
LOCAL cRdf_Description_xmlns_pdf
LOCAL cRdf_Description_xmlns_xmpRights
LOCAL cXmp_ModifyDate
LOCAL cXmp_CreateDate
LOCAL cXmp_MetadataDate
LOCAL cXmp_CreatorTool
LOCAL cDc_format
LOCAL cRdf_li_xml_lang
LOCAL cRdf_li
LOCAL i
LOCAL nCount_i
LOCAL cXmpMM_DocumentID
LOCAL cXmpMM_InstanceID
LOCAL cPdf_Producer
LOCAL cPdf_Keywords
LOCAL cXmpRights_WebStatement

nSuccess := 0

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

oPdf := CreateObject("Chilkat.Pdf")

nSuccess := oPdf:LoadFile("qa_data/pdf/blank_with_metadata.pdf")
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    RETURN
ENDIF

oSbXml := CreateObject("Chilkat.StringBuilder")
//  Note: Not all PDF files have metadata.  Metadata is optional.
nSuccess := oPdf:GetMetadata(oSbXml)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oSbXml:destroy()
    RETURN
ENDIF

oXml := CreateObject("Chilkat.Xml")
oXml:LoadSb(oSbXml, 1)

? oXml: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>

cX_xmpmeta_xmlns_x := oXml:GetAttrValue("xmlns:x")
cX_xmpmeta_x_xmptk := oXml:GetAttrValue("x:xmptk")
cRdf_RDF_xmlns_rdf := oXml:ChilkatPath("rdf:RDF|(xmlns:rdf)")
cRdf_Description_rdf_about := oXml:ChilkatPath("rdf:RDF|rdf:Description|(rdf:about)")
cRdf_Description_xmlns_xmp := oXml:ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmp)")
cRdf_Description_xmlns_dc := oXml:ChilkatPath("rdf:RDF|rdf:Description|(xmlns:dc)")
cRdf_Description_xmlns_xmpMM := oXml:ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpMM)")
cRdf_Description_xmlns_pdf := oXml:ChilkatPath("rdf:RDF|rdf:Description|(xmlns:pdf)")
cRdf_Description_xmlns_xmpRights := oXml:ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpRights)")
cXmp_ModifyDate := oXml:GetChildContent("rdf:RDF|rdf:Description|xmp:ModifyDate")
cXmp_CreateDate := oXml:GetChildContent("rdf:RDF|rdf:Description|xmp:CreateDate")
cXmp_MetadataDate := oXml:GetChildContent("rdf:RDF|rdf:Description|xmp:MetadataDate")
cXmp_CreatorTool := oXml:GetChildContent("rdf:RDF|rdf:Description|xmp:CreatorTool")
cDc_format := oXml:GetChildContent("rdf:RDF|rdf:Description|dc:format")
cRdf_li_xml_lang := oXml:ChilkatPath("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li|(xml:lang)")
cRdf_li := oXml:GetChildContent("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li")
cRdf_li := oXml:GetChildContent("rdf:RDF|rdf:Description|dc:creator|rdf:Bag|rdf:li")
cRdf_li_xml_lang := oXml:ChilkatPath("rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li|(xml:lang)")
cRdf_li := oXml:GetChildContent("rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li")
i := 0
nCount_i := oXml:NumChildrenHavingTag("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li")
DO WHILE i < nCount_i
    oXml:I := i
    cRdf_li := oXml:GetChildContent("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li[i]")
    i := i + 1
ENDDO
cXmpMM_DocumentID := oXml:GetChildContent("rdf:RDF|rdf:Description|xmpMM:DocumentID")
cXmpMM_InstanceID := oXml:GetChildContent("rdf:RDF|rdf:Description|xmpMM:InstanceID")
cPdf_Producer := oXml:GetChildContent("rdf:RDF|rdf:Description|pdf:Producer")
cPdf_Keywords := oXml:GetChildContent("rdf:RDF|rdf:Description|pdf:Keywords")
cXmpRights_WebStatement := oXml:GetChildContent("rdf:RDF|rdf:Description|xmpRights:WebStatement")

oPdf:destroy()
oSbXml:destroy()
oXml:destroy()