(CkPython) PDF Update or Add XML Metadata

Demonstrates how to add or update the XML metadata stored in a PDF.

Note: This example requires Chilkat v10.1.0 or later.

Chilkat Python Downloads install with pip pip3 install chilkat or download... Python Module for Windows, MacOS, Linux, Alpine Linux, Solaris

import sys
import chilkat

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

pdf = chilkat.CkPdf()

# Load a PDF file.
# If the PDF file already has metadata, we'll update it.
# Otherwise this example adds the metadata.
success = pdf.LoadFile("qa_data/pdf/blank_with_metadata.pdf")
if (success == False):
    print(pdf.lastErrorText())
    sys.exit()

xml = chilkat.CkXml()
sbExisting = chilkat.CkStringBuilder()

hasMetadata = pdf.GetMetadata(sbExisting)
if (hasMetadata == True):
    xml.LoadSb(sbExisting,True)
else:

    # Otherwise create the bare minimum XMP metadata.
    xml.put_Tag("x:xmpmeta")
    xml.AddAttribute("xmlns:x","adobe:ns:meta/")
    xml.AddAttribute("x:xmptk","Adobe XMP Core 9.1-c001 79.675d0f7, 2023/06/11-19:21:16 ")
    xml.UpdateAttrAt("rdf:RDF",True,"xmlns:rdf","http://www.w3.org/1999/02/22-rdf-syntax-ns#")
    xml.UpdateAttrAt("rdf:RDF|rdf:Description",True,"rdf:about","")
    xml.UpdateAttrAt("rdf:RDF|rdf:Description",True,"xmlns:xmp","http://ns.adobe.com/xap/1.0/")
    xml.UpdateAttrAt("rdf:RDF|rdf:Description",True,"xmlns:dc","http://purl.org/dc/elements/1.1/")
    xml.UpdateAttrAt("rdf:RDF|rdf:Description",True,"xmlns:xmpMM","http://ns.adobe.com/xap/1.0/mm/")
    xml.UpdateAttrAt("rdf:RDF|rdf:Description",True,"xmlns:pdf","http://ns.adobe.com/pdf/1.3/")
    xml.UpdateAttrAt("rdf:RDF|rdf:Description",True,"xmlns:xmpRights","http://ns.adobe.com/xap/1.0/rights/")

    dt = chilkat.CkDateTime()
    dt.SetFromCurrentSystemTime()
    ts = dt.getAsTimestamp(True)

    xml.UpdateChildContent("rdf:RDF|rdf:Description|xmp:ModifyDate",ts)
    xml.UpdateChildContent("rdf:RDF|rdf:Description|xmp:CreateDate",ts)
    xml.UpdateChildContent("rdf:RDF|rdf:Description|xmp:MetadataDate",ts)

    xml.UpdateChildContent("rdf:RDF|rdf:Description|xmp:CreatorTool","My Custom Application")
    xml.UpdateChildContent("rdf:RDF|rdf:Description|dc:format","application/pdf")

    sbDocId = chilkat.CkStringBuilder()
    sbDocId.Append("uuid:")
    sbDocId.AppendUuid(True)
    xml.UpdateChildContent("rdf:RDF|rdf:Description|xmpMM:DocumentID",sbDocId.getAsString())

    sbInstanceId = chilkat.CkStringBuilder()
    sbInstanceId.Append("uuid:")
    sbInstanceId.AppendUuid(True)
    xml.UpdateChildContent("rdf:RDF|rdf:Description|xmpMM:InstanceID",sbInstanceId.getAsString())

# Add our custom metadata tags to either the existing XML metdata, or the newly created metadata.
xml.UpdateAttrAt("rdf:RDF|rdf:Description",True,"xmlns:zf","urn:ferd:pdfa:CrossIndustryDocument:invoice:1p0#")
xml.UpdateAttrAt("rdf:RDF|rdf:Description",True,"rdf:about"," ")
xml.UpdateChildContent("rdf:RDF|rdf:Description|zf:ConformanceLevel","BASIC")
xml.UpdateChildContent("rdf:RDF|rdf:Description|zf:DocumentFileName","ZZZZZZ-invoice.xml")
xml.UpdateChildContent("rdf:RDF|rdf:Description|zf:DocumentType","INVOICE")
xml.UpdateChildContent("rdf:RDF|rdf:Description|zf:Version","1.0")

# Create a new PDF with the updated metadata.
sb = chilkat.CkStringBuilder()
xml.GetXmlSb(sb)
success = pdf.UpdateMetadata(sb,"c:/temp/qa_output/out.pdf")
if (success == True):
    print("Success")
else:
    print(pdf.lastErrorText())

# To see the metadata in Adobe Acrobat DC,
# 1) Open the PDF.
# 2) CTRL-D to show the Document Properties dialog.
# 3) In the dialog, click on the "Additional Metadata" button.
# 4) In the Additional Data dialog, click on "Advanced"
# 5) Expand the namespace tree for the metadata you added.

print("OK")