(AutoIt) Extract Metadata XML from PDF

See more PDF Signatures Examples

Demonstrates how to extract the metadata XML from a PDF.

Chilkat ActiveX Downloads

ActiveX for 32-bit and 64-bit Windows

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

$oPdf = ObjCreate("Chilkat.Pdf")

Local $bSuccess = $oPdf.LoadFile("qa_data/pdf/blank_with_metadata.pdf")
If ($bSuccess = False) Then
    ConsoleWrite($oPdf.LastErrorText & @CRLF)
    Exit
EndIf

$oSbXml = ObjCreate("Chilkat.StringBuilder")
; Note: Not all PDF files have metadata.  Metadata is optional.
$bSuccess = $oPdf.GetMetadata($oSbXml)
If ($bSuccess = False) Then
    ConsoleWrite($oPdf.LastErrorText & @CRLF)
    Exit
EndIf

$oXml = ObjCreate("Chilkat.Xml")
$oXml.LoadSb($oSbXml,True)

ConsoleWrite($oXml.GetXml() & @CRLF)

; 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>

Local $sX_xmpmeta_xmlns_x = $oXml.GetAttrValue("xmlns:x")
Local $sX_xmpmeta_x_xmptk = $oXml.GetAttrValue("x:xmptk")
Local $sRdf_RDF_xmlns_rdf = $oXml.ChilkatPath("rdf:RDF|(xmlns:rdf)")
Local $sRdf_Description_rdf_about = $oXml.ChilkatPath("rdf:RDF|rdf:Description|(rdf:about)")
Local $sRdf_Description_xmlns_xmp = $oXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmp)")
Local $sRdf_Description_xmlns_dc = $oXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:dc)")
Local $sRdf_Description_xmlns_xmpMM = $oXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpMM)")
Local $sRdf_Description_xmlns_pdf = $oXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:pdf)")
Local $sRdf_Description_xmlns_xmpRights = $oXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpRights)")
Local $sXmp_ModifyDate = $oXml.GetChildContent("rdf:RDF|rdf:Description|xmp:ModifyDate")
Local $sXmp_CreateDate = $oXml.GetChildContent("rdf:RDF|rdf:Description|xmp:CreateDate")
Local $sXmp_MetadataDate = $oXml.GetChildContent("rdf:RDF|rdf:Description|xmp:MetadataDate")
Local $sXmp_CreatorTool = $oXml.GetChildContent("rdf:RDF|rdf:Description|xmp:CreatorTool")
Local $sDc_format = $oXml.GetChildContent("rdf:RDF|rdf:Description|dc:format")
Local $sRdf_li_xml_lang = $oXml.ChilkatPath("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li|(xml:lang)")
Local $sRdf_li = $oXml.GetChildContent("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li")
$sRdf_li = $oXml.GetChildContent("rdf:RDF|rdf:Description|dc:creator|rdf:Bag|rdf:li")
$sRdf_li_xml_lang = $oXml.ChilkatPath("rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li|(xml:lang)")
$sRdf_li = $oXml.GetChildContent("rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li")
Local $i = 0
Local $iCount_i = $oXml.NumChildrenHavingTag("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li")
While $i < $iCount_i
    $oXml.I = $i
    $sRdf_li = $oXml.GetChildContent("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li[i]")
    $i = $i + 1
Wend
Local $sXmpMM_DocumentID = $oXml.GetChildContent("rdf:RDF|rdf:Description|xmpMM:DocumentID")
Local $sXmpMM_InstanceID = $oXml.GetChildContent("rdf:RDF|rdf:Description|xmpMM:InstanceID")
Local $sPdf_Producer = $oXml.GetChildContent("rdf:RDF|rdf:Description|pdf:Producer")
Local $sPdf_Keywords = $oXml.GetChildContent("rdf:RDF|rdf:Description|pdf:Keywords")
Local $sXmpRights_WebStatement = $oXml.GetChildContent("rdf:RDF|rdf:Description|xmpRights:WebStatement")