Unicode C Requires Chilkat v11.7.0+

Get the Text Block Below a PDF Caption

See more PDF Text Extraction Examples

Demonstrates the "label" option with labelValue "below", which captures the block of text directly under a caption such as "Ship To", ending at the next gap or heading. Combined with layout "lines", the lines of an address block are kept separate. 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 packing slip used in this example is available at packing_slip.pdf

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

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

    //  The packing slip has the captions "Bill To" and "Ship To" side by side,
    //  each with an address block below it.
    CkJsonObjectW_UpdateString(json,L"label",L"Ship To");

    //  "below" means the value is the block of text directly under the label.
    CkJsonObjectW_UpdateString(json,L"labelValue",L"below");

    //  With the default "flow" layout the lines of the block would be joined into one paragraph.
    //  "lines" keeps each line of the address on its own line.
    CkJsonObjectW_UpdateString(json,L"layout",L"lines");

    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"Ship To:\n");
    wprintf(L"%s\n",CkJsonObjectW_stringOf(jsonOut,L"text"));
    wprintf(L"\n");

    CkJsonObjectW_UpdateString(json,L"label",L"Bill To");
    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"Bill To:\n");
    wprintf(L"%s\n",CkJsonObjectW_stringOf(jsonOut,L"text"));
    wprintf(L"\n");

    //  A caption over a short paragraph works the same way.  Here the flow layout is better,
    //  because the two lines are one piece of text.
    CkJsonObjectW_UpdateString(json,L"label",L"Special Instructions");
    CkJsonObjectW_UpdateString(json,L"layout",L"flow");
    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"Special Instructions:\n");
    wprintf(L"%s\n",CkJsonObjectW_stringOf(jsonOut,L"text"));

    //  Sample output:

    //  Ship To:
    //  Frank Delgado
    //  c/o Harbor Pet Boarding
    //  9 Ferry Lane
    //  Portside, WA 98001
    //  
    //  Bill To:
    //  Frank Delgado
    //  Apartment 3B
    //  41 Mill Street
    //  Portside, WA 98000
    //  
    //  Special Instructions:
    //  Leave the carton with the boarding office if no one answers. Do not leave it outside; the cat tree is not packed for rain.


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

    }