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. C

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

void ChilkatSample(void)
    {
    BOOL success;
    HCkPdf pdf;
    HCkJsonObject json;
    HCkStringBuilder sbText;
    HCkJsonObject 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 = CkPdf_Create();
    success = CkPdf_LoadFile(pdf,"qa_data/pdf/long_report.pdf");
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        return;
    }

    printf("Number of pages: %d\n",CkPdf_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 = CkJsonObject_Create();
    sbText = CkStringBuilder_Create();
    jsonOut = CkJsonObject_Create();

    success = CkPdf_ExtractTextSb(pdf,"text",json,sbText,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkStringBuilder_Dispose(sbText);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("Extracted %d characters.\n",CkStringBuilder_getLength(sbText));

    //  Save the text to a file.
    success = CkStringBuilder_WriteFile(sbText,"qa_output/long_report.txt","utf-8",FALSE);
    if (success == FALSE) {
        printf("%s\n",CkStringBuilder_lastErrorText(sbText));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkStringBuilder_Dispose(sbText);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

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

    //  Sample output:

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


    CkPdf_Dispose(pdf);
    CkJsonObject_Dispose(json);
    CkStringBuilder_Dispose(sbText);
    CkJsonObject_Dispose(jsonOut);

    }