Sample code for 30+ languages & platforms
Lua

Extract Metadata XML from PDF

See more PDF Signatures Examples

Demonstrates how to extract the metadata XML from a PDF.

Chilkat Lua Downloads

Download Chilkat for Lua
Lua 
local chilkat = require("chilkat")

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

local pdf = chilkat.Pdf.new()

local success = pdf:load_file("qa_data/pdf/blank_with_metadata.pdf")
if not success then
    print(pdf.last_error_text)
    return
end

local sbXml = chilkat.StringBuilder.new()
-- Note: Not all PDF files have metadata.  Metadata is optional.
success = pdf:get_metadata(sbXml)
if not success then
    print(pdf.last_error_text)
    return
end

local xml = chilkat.Xml.new()
xml:load_sb(sbXml, true)

print(xml:get_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>

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

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