(CkPython) Extract Metadata XML from PDF

See more PDF Signatures Examples

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

import sys
import chilkat

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

pdf = chilkat.CkPdf()

success = pdf.LoadFile("qa_data/pdf/blank_with_metadata.pdf")
if (success == False):
    print(pdf.lastErrorText())
    sys.exit()

sbXml = chilkat.CkStringBuilder()
# Note: Not all PDF files have metadata.  Metadata is optional.
success = pdf.GetMetadata(sbXml)
if (success == False):
    print(pdf.lastErrorText())
    sys.exit()

xml = chilkat.CkXml()
xml.LoadSb(sbXml,True)

print(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>

x_xmpmeta_xmlns_x = xml.getAttrValue("xmlns:x")
x_xmpmeta_x_xmptk = xml.getAttrValue("x:xmptk")
rdf_RDF_xmlns_rdf = xml.chilkatPath("rdf:RDF|(xmlns:rdf)")
rdf_Description_rdf_about = xml.chilkatPath("rdf:RDF|rdf:Description|(rdf:about)")
rdf_Description_xmlns_xmp = xml.chilkatPath("rdf:RDF|rdf:Description|(xmlns:xmp)")
rdf_Description_xmlns_dc = xml.chilkatPath("rdf:RDF|rdf:Description|(xmlns:dc)")
rdf_Description_xmlns_xmpMM = xml.chilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpMM)")
rdf_Description_xmlns_pdf = xml.chilkatPath("rdf:RDF|rdf:Description|(xmlns:pdf)")
rdf_Description_xmlns_xmpRights = xml.chilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpRights)")
xmp_ModifyDate = xml.getChildContent("rdf:RDF|rdf:Description|xmp:ModifyDate")
xmp_CreateDate = xml.getChildContent("rdf:RDF|rdf:Description|xmp:CreateDate")
xmp_MetadataDate = xml.getChildContent("rdf:RDF|rdf:Description|xmp:MetadataDate")
xmp_CreatorTool = xml.getChildContent("rdf:RDF|rdf:Description|xmp:CreatorTool")
dc_format = xml.getChildContent("rdf:RDF|rdf:Description|dc:format")
rdf_li_xml_lang = xml.chilkatPath("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li|(xml:lang)")
rdf_li = 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")
i = 0
count_i = xml.NumChildrenHavingTag("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li")
while i < count_i :
    xml.put_I(i)
    rdf_li = xml.getChildContent("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li[i]")
    i = i + 1

xmpMM_DocumentID = xml.getChildContent("rdf:RDF|rdf:Description|xmpMM:DocumentID")
xmpMM_InstanceID = xml.getChildContent("rdf:RDF|rdf:Description|xmpMM:InstanceID")
pdf_Producer = xml.getChildContent("rdf:RDF|rdf:Description|pdf:Producer")
pdf_Keywords = xml.getChildContent("rdf:RDF|rdf:Description|pdf:Keywords")
xmpRights_WebStatement = xml.getChildContent("rdf:RDF|rdf:Description|xmpRights:WebStatement")