Node.js 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. Node.js

NODEJS_PRELUDE

function chilkatExample() {

    var 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

    var pdf = new chilkat.Pdf();
    success = pdf.LoadFile("qa_data/pdf/long_report.pdf");
    if (success == false) {
        console.log(pdf.LastErrorText);
        return;
    }

    console.log("Number of pages: " + pdf.NumPages);

    //  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.
    var json = new chilkat.JsonObject();
    var sbText = new chilkat.StringBuilder();
    var jsonOut = new chilkat.JsonObject();

    success = pdf.ExtractTextSb("text",json,sbText,jsonOut);
    if (success == false) {
        console.log(pdf.LastErrorText);
        return;
    }

    console.log("Extracted " + sbText.Length + " characters.");

    //  Save the text to a file.
    success = sbText.WriteFile("qa_output/long_report.txt","utf-8",false);
    if (success == false) {
        console.log(sbText.LastErrorText);
        return;
    }

    //  The JSON output does not contain the text, but it still has the quality report.
    console.log("Quality: " + jsonOut.StringOf("quality.rating"));
    console.log("Pages with no text (need OCR): [" + jsonOut.StringOf("quality.pagesNeedingOcr") + "]");

    //  Sample output:

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

}

chilkatExample();