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 <CkPdf.h>
#include <CkJsonObject.h>
#include <CkStringBuilder.h>

void ChilkatSample(void)
    {
    bool 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

    CkPdf pdf;
    success = pdf.LoadFile("qa_data/pdf/long_report.pdf");
    if (success == false) {
        std::cout << pdf.lastErrorText() << "\r\n";
        return;
    }

    std::cout << "Number of pages: " << pdf.get_NumPages() << "\r\n";

    //  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.
    CkJsonObject json;
    CkStringBuilder sbText;
    CkJsonObject jsonOut;

    success = pdf.ExtractTextSb("text",json,sbText,jsonOut);
    if (success == false) {
        std::cout << pdf.lastErrorText() << "\r\n";
        return;
    }

    std::cout << "Extracted " << sbText.get_Length() << " characters." << "\r\n";

    //  Save the text to a file.
    success = sbText.WriteFile("qa_output/long_report.txt","utf-8",false);
    if (success == false) {
        std::cout << sbText.lastErrorText() << "\r\n";
        return;
    }

    //  The JSON output does not contain the text, but it still has the quality report.
    std::cout << "Quality: " << jsonOut.stringOf("quality.rating") << "\r\n";
    std::cout << "Pages with no text (need OCR): [" << jsonOut.stringOf("quality.pagesNeedingOcr") << "]" << "\r\n";

    //  Sample output:

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