Unicode C Requires Chilkat v11.7.0+

Extract One Section of a PDF by its Heading

See more PDF Text Extraction Examples

Demonstrates "labelValue": "section", which returns everything from a heading up to the next heading of the same or higher level. With the "markdown" operation the section keeps its own sub-headings. Unicode C

#include <C_CkPdfW.h>
#include <C_CkJsonObjectW.h>

void ChilkatSample(void)
    {
    BOOL success;
    HCkPdfW pdf;
    HCkJsonObjectW json;
    HCkJsonObjectW jsonOut;

    success = FALSE;

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

    //  The PDF used in this example is available at sectioned_doc.pdf

    pdf = CkPdfW_Create();
    success = CkPdfW_LoadFile(pdf,L"qa_data/pdf/sectioned_doc.pdf");
    if (success == FALSE) {
        wprintf(L"%s\n",CkPdfW_lastErrorText(pdf));
        CkPdfW_Dispose(pdf);
        return;
    }

    json = CkJsonObjectW_Create();
    jsonOut = CkJsonObjectW_Create();

    //  The document has the sections Introduction, Opening Hours, Terms and Conditions (with the
    //  sub-sections Admission, Safety and Liability) and Contact.  Get the Terms and Conditions:
    //  everything after that heading up to the next heading of the same level (Contact).  The heading
    //  itself is not part of the value; labelMatches[0].label has it.
    CkJsonObjectW_UpdateString(json,L"label",L"Terms and Conditions");
    CkJsonObjectW_UpdateString(json,L"labelValue",L"section");

    success = CkPdfW_ExtractText(pdf,L"markdown",json,jsonOut);
    if (success == FALSE) {
        wprintf(L"%s\n",CkPdfW_lastErrorText(pdf));
        CkPdfW_Dispose(pdf);
        CkJsonObjectW_Dispose(json);
        CkJsonObjectW_Dispose(jsonOut);
        return;
    }

    wprintf(L"%s\n",CkJsonObjectW_stringOf(jsonOut,L"markdown"));

    //  The same with the "text" operation gives the section as plain text.
    success = CkPdfW_ExtractText(pdf,L"text",json,jsonOut);
    if (success == FALSE) {
        wprintf(L"%s\n",CkPdfW_lastErrorText(pdf));
        CkPdfW_Dispose(pdf);
        CkJsonObjectW_Dispose(json);
        CkJsonObjectW_Dispose(jsonOut);
        return;
    }

    wprintf(L"---- as text ----\n");
    wprintf(L"%s\n",CkJsonObjectW_stringOf(jsonOut,L"text"));

    //  Sample output:

    //  ### Admission
    //  
    //  Admission is free. Groups of more than ten should book in advance so that a volunteer can be assigned to them.
    //  
    //  ### Safety
    //  
    //  No more than eight people may be on the stair at one time. Children under twelve must be accompanied by an adult, and the lantern room is closed in high winds.
    //  
    //  ### Liability
    //  
    //  Visitors climb the tower at their own risk. The society carries public liability insurance but accepts no responsibility for personal property.
    //  ---- as text ----
    //  Admission
    //  
    //  Admission is free. Groups of more than ten should book in advance so that a volunteer can be assigned to them.
    //  
    //  Safety
    //  
    //  No more than eight people may be on the stair at one time. Children under twelve must be accompanied by an adult, and the lantern room is closed in high winds.
    //  
    //  Liability
    //  
    //  Visitors climb the tower at their own risk. The society carries public liability insurance but accepts no responsibility for personal property.


    CkPdfW_Dispose(pdf);
    CkJsonObjectW_Dispose(json);
    CkJsonObjectW_Dispose(jsonOut);

    }