Node.js Requires Chilkat v11.7.0+

Clipped, Off-Page and White-on-White Text in PDF Extraction

See more PDF Text Extraction Examples

Demonstrates the "clippedText", "offPageText" and "obscuredText" filters. Text that a reader never sees - hidden by a clipping path, outside the crop box, or drawn in the same color as the box beneath it - is excluded by default, and the quality report notes what was skipped. Each kind can be included. 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 hidden_text.pdf

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

    var json = new chilkat.JsonObject();
    var jsonOut = new chilkat.JsonObject();

    //  The page has a visible paragraph plus three hidden lines: one drawn outside its clipping
    //  rectangle, one below the crop box, and one in white on a white box.
    success = pdf.ExtractText("text",json,jsonOut);
    if (success == false) {
        console.log(pdf.LastErrorText);
        return;
    }

    console.log("---- default ----");
    console.log(jsonOut.StringOf("text"));

    //  The quality report says what was left out.
    var i = 0;
    var count_i = jsonOut.SizeOfArray("quality.pages[0].issues");
    while (i < count_i) {
        jsonOut.I = i;
        console.log("issue: " + jsonOut.StringOf("quality.pages[0].issues[i].code"));
        i = i+1;
    }

    //  Include everything.
    json.UpdateString("clippedText","include");
    json.UpdateString("offPageText","include");
    json.UpdateString("obscuredText","include");
    success = pdf.ExtractText("text",json,jsonOut);
    if (success == false) {
        console.log(pdf.LastErrorText);
        return;
    }

    console.log("---- clippedText, offPageText, obscuredText: include ----");
    console.log(jsonOut.StringOf("text"));

    //  Sample output:

    //  ---- default ----
    //  Visible Text
    //  
    //  This paragraph is visible. The page also carries three kinds of text a reader never sees.
    //  
    //  End of the visible text.
    //  issue: obscuredTextSkipped
    //  issue: clippedTextSkipped
    //  ---- clippedText, offPageText, obscuredText: include ----
    //  Visible Text
    //  
    //  This paragraph is visible. The page also carries three kinds of text a reader never sees.
    //  
    //  CLIPPED: this line is drawn outside its clipping rectangle.
    //  
    //  OBSCURED: this line is white on a white box.
    //  
    //  End of the visible text.
    //  
    //  OFFPAGE: this line sits below the crop box.

}

chilkatExample();