Visual FoxPro

Extract Metadata XML from PDF

See more PDF Signatures Examples

Demonstrates how to extract the metadata XML from a PDF. Visual FoxPro

LOCAL lnSuccess
LOCAL loPdf
LOCAL loSbXml
LOCAL loXml
LOCAL lcX_xmpmeta_xmlns_x
LOCAL lcX_xmpmeta_x_xmptk
LOCAL lcRdf_RDF_xmlns_rdf
LOCAL lcRdf_Description_rdf_about
LOCAL lcRdf_Description_xmlns_xmp
LOCAL lcRdf_Description_xmlns_dc
LOCAL lcRdf_Description_xmlns_xmpMM
LOCAL lcRdf_Description_xmlns_pdf
LOCAL lcRdf_Description_xmlns_xmpRights
LOCAL lcXmp_ModifyDate
LOCAL lcXmp_CreateDate
LOCAL lcXmp_MetadataDate
LOCAL lcXmp_CreatorTool
LOCAL lcDc_format
LOCAL lcRdf_li_xml_lang
LOCAL lcRdf_li
LOCAL i
LOCAL lnCount_i
LOCAL lcXmpMM_DocumentID
LOCAL lcXmpMM_InstanceID
LOCAL lcPdf_Producer
LOCAL lcPdf_Keywords
LOCAL lcXmpRights_WebStatement

lnSuccess = 0

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

loPdf = CreateObject('Chilkat.Pdf')

lnSuccess = loPdf.LoadFile("qa_data/pdf/blank_with_metadata.pdf")
IF (lnSuccess = 0) THEN
    ? loPdf.LastErrorText
    RELEASE loPdf
    CANCEL
ENDIF

loSbXml = CreateObject('Chilkat.StringBuilder')
* Note: Not all PDF files have metadata.  Metadata is optional.
lnSuccess = loPdf.GetMetadata(loSbXml)
IF (lnSuccess = 0) THEN
    ? loPdf.LastErrorText
    RELEASE loPdf
    RELEASE loSbXml
    CANCEL
ENDIF

loXml = CreateObject('Chilkat.Xml')
loXml.LoadSb(loSbXml,1)

? loXml.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>

lcX_xmpmeta_xmlns_x = loXml.GetAttrValue("xmlns:x")
lcX_xmpmeta_x_xmptk = loXml.GetAttrValue("x:xmptk")
lcRdf_RDF_xmlns_rdf = loXml.ChilkatPath("rdf:RDF|(xmlns:rdf)")
lcRdf_Description_rdf_about = loXml.ChilkatPath("rdf:RDF|rdf:Description|(rdf:about)")
lcRdf_Description_xmlns_xmp = loXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmp)")
lcRdf_Description_xmlns_dc = loXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:dc)")
lcRdf_Description_xmlns_xmpMM = loXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpMM)")
lcRdf_Description_xmlns_pdf = loXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:pdf)")
lcRdf_Description_xmlns_xmpRights = loXml.ChilkatPath("rdf:RDF|rdf:Description|(xmlns:xmpRights)")
lcXmp_ModifyDate = loXml.GetChildContent("rdf:RDF|rdf:Description|xmp:ModifyDate")
lcXmp_CreateDate = loXml.GetChildContent("rdf:RDF|rdf:Description|xmp:CreateDate")
lcXmp_MetadataDate = loXml.GetChildContent("rdf:RDF|rdf:Description|xmp:MetadataDate")
lcXmp_CreatorTool = loXml.GetChildContent("rdf:RDF|rdf:Description|xmp:CreatorTool")
lcDc_format = loXml.GetChildContent("rdf:RDF|rdf:Description|dc:format")
lcRdf_li_xml_lang = loXml.ChilkatPath("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li|(xml:lang)")
lcRdf_li = loXml.GetChildContent("rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li")
lcRdf_li = loXml.GetChildContent("rdf:RDF|rdf:Description|dc:creator|rdf:Bag|rdf:li")
lcRdf_li_xml_lang = loXml.ChilkatPath("rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li|(xml:lang)")
lcRdf_li = loXml.GetChildContent("rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li")
i = 0
lnCount_i = loXml.NumChildrenHavingTag("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li")
DO WHILE i < lnCount_i
    loXml.I = i
    lcRdf_li = loXml.GetChildContent("rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li[i]")
    i = i + 1
ENDDO
lcXmpMM_DocumentID = loXml.GetChildContent("rdf:RDF|rdf:Description|xmpMM:DocumentID")
lcXmpMM_InstanceID = loXml.GetChildContent("rdf:RDF|rdf:Description|xmpMM:InstanceID")
lcPdf_Producer = loXml.GetChildContent("rdf:RDF|rdf:Description|pdf:Producer")
lcPdf_Keywords = loXml.GetChildContent("rdf:RDF|rdf:Description|pdf:Keywords")
lcXmpRights_WebStatement = loXml.GetChildContent("rdf:RDF|rdf:Description|xmpRights:WebStatement")

RELEASE loPdf
RELEASE loSbXml
RELEASE loXml