Unicode C Requires Chilkat v11.7.0+

Extract PDF Text to a StringBuilder and Save to a File

See more PDF Text Extraction Examples

Demonstrates ExtractTextSb, which writes the extracted text to a StringBuilder instead of returning it as a JSON string. Use it for large documents. The JSON output still receives the quality report. Unicode C

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

void ChilkatSample(void)
    {
    BOOL success;
    HCkPdfW pdf;
    HCkJsonObjectW json;
    HCkStringBuilderW sbText;
    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 long_report.pdf

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

    wprintf(L"Number of pages: %d\n",CkPdfW_getNumPages(pdf));

    //  ExtractTextSb takes the same operation and options as ExtractText, but the text
    //  goes to a StringBuilder.  This avoids building a very large JSON string for
    //  documents with many pages.
    json = CkJsonObjectW_Create();
    sbText = CkStringBuilderW_Create();
    jsonOut = CkJsonObjectW_Create();

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

    wprintf(L"Extracted %d characters.\n",CkStringBuilderW_getLength(sbText));

    //  Save the text to a file.
    success = CkStringBuilderW_WriteFile(sbText,L"qa_output/long_report.txt",L"utf-8",FALSE);
    if (success == FALSE) {
        wprintf(L"%s\n",CkStringBuilderW_lastErrorText(sbText));
        CkPdfW_Dispose(pdf);
        CkJsonObjectW_Dispose(json);
        CkStringBuilderW_Dispose(sbText);
        CkJsonObjectW_Dispose(jsonOut);
        return;
    }

    //  The JSON output does not contain the text, but it still has the quality report.
    wprintf(L"Quality: %s\n",CkJsonObjectW_stringOf(jsonOut,L"quality.rating"));
    wprintf(L"Pages with no text (need OCR): [%s]\n",CkJsonObjectW_stringOf(jsonOut,L"quality.pagesNeedingOcr"));

    //  Sample output:

    //  Number of pages: 3
    //  Extracted 4522 characters.
    //  Quality: good
    //  Pages with no text (need OCR): []


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

    }