pdf.js with text selection

How to make the text in a PDF selectable?

Have tried here. The PDF is written fine, but no text selection

https://github.com/mozilla/pdf.js/blob/master/web/text_layer_builder.css
https://github.com/mozilla/pdf.js/blob/master/web/text_layer_builder.js

'use strict';

PDFJS.getDocument('file.pdf').then(function(pdf){
    var page_num = 1;
    pdf.getPage(page_num).then(function(page){
        var scale = 1.5;
        var viewport = page.getViewport(scale);
        var canvas = document.getElementById('the-canvas');
        var context = canvas.getContext('2d');
        canvas.height = viewport.height;
        canvas.width = viewport.width;

        var canvasOffset = $(canvas).offset();
        var $textLayerDiv = $('#text-layer').css({
            height : viewport.height+'px',
            width : viewport.width+'px',
            top : canvasOffset.top,
            left : canvasOffset.left
        });

        page.render({
            canvasContext : context,
            viewport : viewport
        });

        page.getTextContent().then(function(textContent){
            var textLayer = new TextLayerBuilder({
                textLayerDiv : $textLayerDiv.get(0),
                pageIndex : page_num - 1,
                viewport : viewport
            });

            textLayer.setTextContent(textContent);
            textLayer.render();
        });
    });
});

<body>
  <div>
    <canvas id="the-canvas" style="border:1px solid black;"></canvas>
    <div id="text-layer" class="textLayer"></div>
  </div>
</body>

Your javascript code is perfect. You just need to include the UI utilities that Text Layer Builder depends on:

https://github.com/mozilla/pdf.js/blob/master/web/ui_utils.js

Or in HTML:

<script src="https://raw.githubusercontent.com/mozilla/pdf.js/master/web/ui_utils.js"></script>

If you run your code (without ui_utils) and check the debug console, you will see ReferenceError: CustomStyle is not defined. A quick search in PDFjs's repo will show you it is defined in ui_utils.js.

Here is my minimal but complete code for your reference. I am using PDFjs's demo pdf here. Note that in production you should not link to raw.github.

<!DOCTYPE html><meta charset="utf-8">
<link rel="stylesheet" href="https://raw.githubusercontent.com/mozilla/pdf.js/master/web/text_layer_builder.css" />
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.4/jquery.min.js"></script>
<script src="https://raw.githubusercontent.com/mozilla/pdf.js/master/web/ui_utils.js"></script>
<script src="https://raw.githubusercontent.com/mozilla/pdf.js/master/web/text_layer_builder.js"></script>
<script src="https://mozilla.github.io/pdf.js/build/pdf.js"></script>
<body>
  <div>
    <canvas id="the-canvas" style="border:1px solid black;"></canvas>
    <div id="text-layer" class="textLayer"></div>
  </div>
<script>
'use strict';

PDFJS.getDocument('file.pdf').then(function(pdf){
    var page_num = 1;
    pdf.getPage(page_num).then(function(page){
        var scale = 1.5;
        var viewport = page.getViewport(scale);
        var canvas = $('#the-canvas')[0];
        var context = canvas.getContext('2d');
        canvas.height = viewport.height;
        canvas.width = viewport.width;

        var canvasOffset = $(canvas).offset();
        var $textLayerDiv = $('#text-layer').css({
            height : viewport.height+'px',
            width : viewport.width+'px',
            top : canvasOffset.top,
            left : canvasOffset.left
        });

        page.render({
            canvasContext : context,
            viewport : viewport
        });

        page.getTextContent().then(function(textContent){
           console.log( textContent );
            var textLayer = new TextLayerBuilder({
                textLayerDiv : $textLayerDiv.get(0),
                pageIndex : page_num - 1,
                viewport : viewport
            });

            textLayer.setTextContent(textContent);
            textLayer.render();
        });
    });
});
</script>

After hours of struggling with this I found this article to be very helpful about selecting text and using pdf.js without node. Custom PDF Rendering in JavaScript with Mozilla’s PDF.Js

Hello you have created canvas in your HTML content.

Canvas will not support text selection so you need to change the canvas to another way.

来源：https://stackoverflow.com/questions/33063213/pdf-js-with-text-selection

标签

javascript

jquery

pdf.js