(C) Extract Metadata XML from PDF

See more PDF Signatures Examples

Demonstrates how to extract the metadata XML from a PDF.

Chilkat C/C++ Library Downloads

MS Visual C/C++

C++ Builder

Linux C/C++

Alpine Linux C/C++

MacOS C/C++

iOS C/C++

Android C/C++

MinGW C/C++

#include <C_CkPdf.h>
#include <C_CkStringBuilder.h>
#include <C_CkXml.h>

void ChilkatSample(void)
    {
    HCkPdf pdf;
    BOOL success;
    HCkStringBuilder sbXml;
    HCkXml xml;
    const char *x_xmpmeta_xmlns_x;
    const char *x_xmpmeta_x_xmptk;
    const char *rdf_RDF_xmlns_rdf;
    const char *rdf_Description_rdf_about;
    const char *rdf_Description_xmlns_xmp;
    const char *rdf_Description_xmlns_dc;
    const char *rdf_Description_xmlns_xmpMM;
    const char *rdf_Description_xmlns_pdf;
    const char *rdf_Description_xmlns_xmpRights;
    const char *xmp_ModifyDate;
    const char *xmp_CreateDate;
    const char *xmp_MetadataDate;
    const char *xmp_CreatorTool;
    const char *dc_format;
    const char *rdf_li_xml_lang;
    const char *rdf_li;
    int i;
    int count_i;
    const char *xmpMM_DocumentID;
    const char *xmpMM_InstanceID;
    const char *pdf_Producer;
    const char *pdf_Keywords;
    const char *xmpRights_WebStatement;

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

    pdf = CkPdf_Create();

    success = CkPdf_LoadFile(pdf,"qa_data/pdf/blank_with_metadata.pdf");
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        return;
    }

    sbXml = CkStringBuilder_Create();
    // Note: Not all PDF files have metadata.  Metadata is optional.
    success = CkPdf_GetMetadata(pdf,sbXml);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkStringBuilder_Dispose(sbXml);
        return;
    }

    xml = CkXml_Create();
    CkXml_LoadSb(xml,sbXml,TRUE);

    printf("%s\n",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>

    x_xmpmeta_xmlns_x = CkXml_getAttrValue(xml,"xmlns:x");
    x_xmpmeta_x_xmptk = CkXml_getAttrValue(xml,"x:xmptk");
    rdf_RDF_xmlns_rdf = CkXml_chilkatPath(xml,"rdf:RDF|(xmlns:rdf)");
    rdf_Description_rdf_about = CkXml_chilkatPath(xml,"rdf:RDF|rdf:Description|(rdf:about)");
    rdf_Description_xmlns_xmp = CkXml_chilkatPath(xml,"rdf:RDF|rdf:Description|(xmlns:xmp)");
    rdf_Description_xmlns_dc = CkXml_chilkatPath(xml,"rdf:RDF|rdf:Description|(xmlns:dc)");
    rdf_Description_xmlns_xmpMM = CkXml_chilkatPath(xml,"rdf:RDF|rdf:Description|(xmlns:xmpMM)");
    rdf_Description_xmlns_pdf = CkXml_chilkatPath(xml,"rdf:RDF|rdf:Description|(xmlns:pdf)");
    rdf_Description_xmlns_xmpRights = CkXml_chilkatPath(xml,"rdf:RDF|rdf:Description|(xmlns:xmpRights)");
    xmp_ModifyDate = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|xmp:ModifyDate");
    xmp_CreateDate = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|xmp:CreateDate");
    xmp_MetadataDate = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|xmp:MetadataDate");
    xmp_CreatorTool = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|xmp:CreatorTool");
    dc_format = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|dc:format");
    rdf_li_xml_lang = CkXml_chilkatPath(xml,"rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li|(xml:lang)");
    rdf_li = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|dc:title|rdf:Alt|rdf:li");
    rdf_li = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|dc:creator|rdf:Bag|rdf:li");
    rdf_li_xml_lang = CkXml_chilkatPath(xml,"rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li|(xml:lang)");
    rdf_li = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|dc:description|rdf:Alt|rdf:li");
    i = 0;
    count_i = CkXml_NumChildrenHavingTag(xml,"rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li");
    while (i < count_i) {
        CkXml_putI(xml,i);
        rdf_li = CkXml_getChildContent(xml,"rdf:RDF|rdf:Description|dc:subject|rdf:Bag|rdf:li[i]");
        i = i + 1;
    }

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


    CkPdf_Dispose(pdf);
    CkStringBuilder_Dispose(sbXml);
    CkXml_Dispose(xml);

    }