(Tcl) Extract Metadata XML from PDF

See more PDF Signatures Examples

Demonstrates how to extract the metadata XML from a PDF.

Chilkat Tcl Extension Downloads

Chilkat Tcl Extension Downloads

load ./chilkat.dll

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

set pdf [new_CkPdf]

set success [CkPdf_LoadFile $pdf "qa_data/pdf/blank_with_metadata.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    exit
}

set sbXml [new_CkStringBuilder]

# Note: Not all PDF files have metadata.  Metadata is optional.
set success [CkPdf_GetMetadata $pdf $sbXml]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkStringBuilder $sbXml
    exit
}

set xml [new_CkXml]

CkXml_LoadSb $xml $sbXml 1

puts [CkXml_getXml $xml]

# 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>

set x_xmpmeta_xmlns_x [CkXml_getAttrValue $xml "xmlns:x"]
set x_xmpmeta_x_xmptk [CkXml_getAttrValue $xml "x:xmptk"]
set rdf_RDF_xmlns_rdf [CkXml_chilkatPath $xml "rdf:RDF|(xmlns:rdf)"]
set rdf_Description_rdf_about [CkXml_chilkatPath $xml "rdf:RDF|rdf:Description|(rdf:about)"]
set rdf_Description_xmlns_xmp [CkXml_chilkatPath $xml "rdf:RDF|rdf:Description|(xmlns:xmp)"]
set rdf_Description_xmlns_dc [CkXml_chilkatPath $xml "rdf:RDF|rdf:Description|(xmlns:dc)"]
set rdf_Description_xmlns_xmpMM [CkXml_chilkatPath $xml "rdf:RDF|rdf:Description|(xmlns:xmpMM)"]
set rdf_Description_xmlns_pdf [CkXml_chilkatPath $xml "rdf:RDF|rdf:Description|(xmlns:pdf)"]
set rdf_Description_xmlns_xmpRights [CkXml_chilkatPath $xml "rdf:RDF|rdf:Description|(xmlns:xmpRights)"]
set xmp_ModifyDate [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|xmp:ModifyDate"]
set xmp_CreateDate [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|xmp:CreateDate"]
set xmp_MetadataDate [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|xmp:MetadataDate"]
set xmp_CreatorTool [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|xmp:CreatorTool"]
set dc_format [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|dc:format"]
set rdf_li_xml_lang [CkXml_chilkatPath $xml "rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li|(xml:lang)"]
set rdf_li [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li"]
set rdf_li [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|dc:creator|rdf:Bag|rdf:li"]
set rdf_li_xml_lang [CkXml_chilkatPath $xml "rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li|(xml:lang)"]
set rdf_li [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li"]
set i 0
set count_i [CkXml_NumChildrenHavingTag $xml "rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li"]
while {$i < $count_i} {
    CkXml_put_I $xml $i
    set rdf_li [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li[i]"]
    set i [expr $i + 1]
}
set xmpMM_DocumentID [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|xmpMM:DocumentID"]
set xmpMM_InstanceID [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|xmpMM:InstanceID"]
set pdf_Producer [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|pdf:Producer"]
set pdf_Keywords [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|pdf:Keywords"]
set xmpRights_WebStatement [CkXml_getChildContent $xml "rdf:RDF|rdf:Description|xmpRights:WebStatement"]

delete_CkPdf $pdf
delete_CkStringBuilder $sbXml
delete_CkXml $xml