I've created this demo:
http://polishwords.com.pl/dev/pdfjs/test.html
It displays one page. I would like to display all pages. One below another, or place some buttons to change page or even better load all standard controls of PDF.JS like in Firefox. How to acomplish this?
PDFJS has a member variable numPages, so you'd just iterate through them. BUT it's important to remember that getting a page in pdf.js is asynchronous, so the order wouldn't be guaranteed. So you'd need to chain them. You could do something along these lines:
var currPage = 1; //Pages are 1-based not 0-based
var numPages = 0;
var thePDF = null;
//This is where you start
PDFJS.getDocument(url).then(function(pdf) {
//Set PDFJS global object (so we can easily access in our page functions
thePDF = pdf;
//How many pages it has
numPages = pdf.numPages;
//Start with first page
pdf.getPage( 1 ).then( handlePages );
});
function handlePages(page)
{
//This gives us the page's dimensions at full scale
var viewport = page.getViewport( 1 );
//We'll create a canvas for each page to draw it on
var canvas = document.createElement( "canvas" );
canvas.style.display = "block";
var context = canvas.getContext('2d');
canvas.height = viewport.height;
canvas.width = viewport.width;
//Draw it on the canvas
page.render({canvasContext: context, viewport: viewport});
//Add it to the web page
document.body.appendChild( canvas );
//Move to next page
currPage++;
if ( thePDF !== null && currPage <= numPages )
{
thePDF.getPage( currPage ).then( handlePages );
}
}
Here's my take. Renders all pages in correct order and still works asynchronously.
<style>
#pdf-viewer {
width: 100%;
height: 100%;
background: rgba(0, 0, 0, 0.1);
overflow: auto;
}
.pdf-page-canvas {
display: block;
margin: 5px auto;
border: 1px solid rgba(0, 0, 0, 0.2);
}
</style>
<script>
url = 'https://github.com/mozilla/pdf.js/blob/master/test/pdfs/tracemonkey.pdf';
var thePdf = null;
var scale = 1;
PDFJS.getDocument(url).promise.then(function(pdf) {
thePdf = pdf;
viewer = document.getElementById('pdf-viewer');
for(page = 1; page <= pdf.numPages; page++) {
canvas = document.createElement("canvas");
canvas.className = 'pdf-page-canvas';
viewer.appendChild(canvas);
renderPage(page, canvas);
}
});
function renderPage(pageNumber, canvas) {
thePdf.getPage(pageNumber).then(function(page) {
viewport = page.getViewport({ scale: scale });
canvas.height = viewport.height;
canvas.width = viewport.width;
page.render({canvasContext: canvas.getContext('2d'), viewport: viewport});
});
}
</script>
<div id='pdf-viewer'></div>
The pdfjs-dist library contains parts for building PDF viewer. You can use PDFPageView to render all pages. Based on https://github.com/mozilla/pdf.js/blob/master/examples/components/pageviewer.html :
var url = "https://cdn.mozilla.net/pdfjs/tracemonkey.pdf";
var container = document.getElementById('container');
// Load document
PDFJS.getDocument(url).then(function (doc) {
var promise = Promise.resolve();
for (var i = 0; i < doc.numPages; i++) {
// One-by-one load pages
promise = promise.then(function (id) {
return doc.getPage(id + 1).then(function (pdfPage) {
// Add div with page view.
var SCALE = 1.0;
var pdfPageView = new PDFJS.PDFPageView({
container: container,
id: id,
scale: SCALE,
defaultViewport: pdfPage.getViewport(SCALE),
// We can enable text/annotations layers, if needed
textLayerFactory: new PDFJS.DefaultTextLayerFactory(),
annotationLayerFactory: new PDFJS.DefaultAnnotationLayerFactory()
});
// Associates the actual page with the view, and drawing it
pdfPageView.setPdfPage(pdfPage);
return pdfPageView.draw();
});
}.bind(null, i));
}
return promise;
});
#container > *:not(:first-child) {
border-top: solid 1px black;
}
<link href="https://npmcdn.com/pdfjs-dist/web/pdf_viewer.css" rel="stylesheet"/>
<script src="https://npmcdn.com/pdfjs-dist/web/compatibility.js"></script>
<script src="https://npmcdn.com/pdfjs-dist/build/pdf.js"></script>
<script src="https://npmcdn.com/pdfjs-dist/web/pdf_viewer.js"></script>
<div id="container" class="pdfViewer singlePageView"></div>
The accepted answer is not working anymore (in 2021), due to the API change for var viewport = page.getViewport( 1 ); to var viewport = page.getViewport({scale: scale});, you can try the full working html as below, just copy the content below to a html file, and open it:
<html>
<head>
<script src="https://mozilla.github.io/pdf.js/build/pdf.js"></script>
<head>
<body>
</body>
<script>
var url = 'https://raw.githubusercontent.com/mozilla/pdf.js/ba2edeae/web/compressed.tracemonkey-pldi-09.pdf';
// Loaded via <script> tag, create shortcut to access PDF.js exports.
var pdfjsLib = window['pdfjs-dist/build/pdf'];
// The workerSrc property shall be specified.
pdfjsLib.GlobalWorkerOptions.workerSrc = 'https://mozilla.github.io/pdf.js/build/pdf.worker.js';
var currPage = 1; //Pages are 1-based not 0-based
var numPages = 0;
var thePDF = null;
//This is where you start
pdfjsLib.getDocument(url).promise.then(function(pdf) {
//Set PDFJS global object (so we can easily access in our page functions
thePDF = pdf;
//How many pages it has
numPages = pdf.numPages;
//Start with first page
pdf.getPage( 1 ).then( handlePages );
});
function handlePages(page)
{
//This gives us the page's dimensions at full scale
var viewport = page.getViewport( {scale: 1.5} );
//We'll create a canvas for each page to draw it on
var canvas = document.createElement( "canvas" );
canvas.style.display = "block";
var context = canvas.getContext('2d');
canvas.height = viewport.height;
canvas.width = viewport.width;
//Draw it on the canvas
page.render({canvasContext: context, viewport: viewport});
//Add it to the web page
document.body.appendChild( canvas );
var line = document.createElement("hr");
document.body.appendChild( line );
//Move to next page
currPage++;
if ( thePDF !== null && currPage <= numPages )
{
thePDF.getPage( currPage ).then( handlePages );
}
}
</script>
</html>
The following answer is a partial answer targeting anyone trying to get a PDF.js to display a whole PDF in 2019, as the api has changed significantly. This was of course the OP's primary concern. inspiration sample code
Please take note of the following:
extra libs are being used -- Lodash (for range() function) and polyfills (for promises)....
Bootstrap is being used
<div class="row">
<div class="col-md-10 col-md-offset-1">
<div id="wrapper">
</div>
</div>
</div>
<style>
body {
background-color: #808080;
/* margin: 0; padding: 0; */
}
</style>
<link href="//cdnjs.cloudflare.com/ajax/libs/pdf.js/2.1.266/pdf_viewer.css" rel="stylesheet"/>
<script src="//cdnjs.cloudflare.com/ajax/libs/pdf.js/2.1.266/pdf.js"></script>
<script src="//cdnjs.cloudflare.com/ajax/libs/pdf.js/2.1.266/pdf_viewer.js"></script>
<script src="//cdn.polyfill.io/v2/polyfill.min.js"></script>
<script src="//cdnjs.cloudflare.com/ajax/libs/lodash.js/4.17.15/lodash.js"></script>
<script>
$(document).ready(function () {
// startup
});
'use strict';
if (!pdfjsLib.getDocument || !pdfjsViewer.PDFViewer) {
alert("Please build the pdfjs-dist library using\n" +
" `gulp dist-install`");
}
var url = '//www.pdf995.com/samples/pdf.pdf';
pdfjsLib.GlobalWorkerOptions.workerSrc =
'//cdnjs.cloudflare.com/ajax/libs/pdf.js/2.1.266/pdf.worker.js';
var loadingTask = pdfjsLib.getDocument(url);
loadingTask.promise.then(function(pdf) {
// please be aware this uses .range() function from lodash
var pagePromises = _.range(1, pdf.numPages).map(function(number) {
return pdf.getPage(number);
});
return Promise.all(pagePromises);
}).then(function(pages) {
var scale = 1.5;
var canvases = pages.forEach(function(page) {
var viewport = page.getViewport({ scale: scale, }); // Prepare canvas using PDF page dimensions
var canvas = document.createElement('canvas');
canvas.height = viewport.height;
canvas.width = viewport.width; // Render PDF page into canvas context
var canvasContext = canvas.getContext('2d');
var renderContext = {
canvasContext: canvasContext,
viewport: viewport
};
page.render(renderContext).promise.then(function() {
if (false)
return console.log('Page rendered');
});
document.getElementById('wrapper').appendChild(canvas);
});
},
function(error) {
return console.log('Error', error);
});
</script>
If you want to render all pages of pdf document in different canvases, all one by one synchronously this is kind of solution:
index.html
<!doctype html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>PDF Sample</title>
<script type="text/javascript" src="jquery.js"></script>
<script type="text/javascript" src="pdf.js"></script>
<script type="text/javascript" src="main.js">
</script>
<link rel="stylesheet" type="text/css" href="main.css">
</head>
<body id="body">
</body>
</html>
main.css
canvas {
display: block;
}
main.js
$(function() {
var filePath = "document.pdf";
function Num(num) {
var num = num;
return function () {
return num;
}
};
function renderPDF(url, canvasContainer, options) {
var options = options || {
scale: 1.5
},
func,
pdfDoc,
def = $.Deferred(),
promise = $.Deferred().resolve().promise(),
width,
height,
makeRunner = function(func, args) {
return function() {
return func.call(null, args);
};
};
function renderPage(num) {
var def = $.Deferred(),
currPageNum = new Num(num);
pdfDoc.getPage(currPageNum()).then(function(page) {
var viewport = page.getViewport(options.scale);
var canvas = document.createElement('canvas');
var ctx = canvas.getContext('2d');
var renderContext = {
canvasContext: ctx,
viewport: viewport
};
if(currPageNum() === 1) {
height = viewport.height;
width = viewport.width;
}
canvas.height = height;
canvas.width = width;
canvasContainer.appendChild(canvas);
page.render(renderContext).then(function() {
def.resolve();
});
})
return def.promise();
}
function renderPages(data) {
pdfDoc = data;
var pagesCount = pdfDoc.numPages;
for (var i = 1; i <= pagesCount; i++) {
func = renderPage;
promise = promise.then(makeRunner(func, i));
}
}
PDFJS.disableWorker = true;
PDFJS.getDocument(url).then(renderPages);
};
var body = document.getElementById("body");
renderPDF(filePath, body);
});
First of all please be aware that doing this is really not a good idea; as explained in https://github.com/mozilla/pdf.js/wiki/Frequently-Asked-Questions#allthepages
How to do it;
Use the viewer provided by mozilla;
https://mozilla.github.io/pdf.js/web/viewer.html
modify BaseViewer class, _getVisiblePages() method in viewer.js to
/* load all pages */
_getVisiblePages() {
let visible = [];
let currentPage = this._pages[this._currentPageNumber - 1];
for (let i=0; i<this.pagesCount; i++){
let aPage = this._pages[i];
visible.push({ id: aPage.id, view: aPage, });
}
return { first: currentPage, last: currentPage, views: visible, };
}
If you want to render all pages of pdf document in different canvases
<html>
<head>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>
<script src="pdf.js"></script>
<script src="jquery.js"></script>
</head>
<body>
<h1>PDF.js 'Hello, world!' example</h1>
<div id="canvas_div"></div>
<body>
<script>
// If absolute URL from the remote server is provided, configure the CORS
// header on that server.
var url = 'pdff.pdf';
// Loaded via <script> tag, create shortcut to access PDF.js exports.
var pdfjsLib = window['pdfjs-dist/build/pdf'];
// The workerSrc property shall be specified.
pdfjsLib.GlobalWorkerOptions.workerSrc = 'worker.js';
var loadingTask = pdfjsLib.getDocument(url);
loadingTask.promise.then(function(pdf) {
var __TOTAL_PAGES = pdf.numPages;
// Fetch the first page
var pageNumber = 1;
for( let i=1; i<=__TOTAL_PAGES; i+=1){
var id ='the-canvas'+i;
$('#canvas_div').append("<div style='background-color:gray;text-align: center;padding:20px;' ><canvas calss='the-canvas' id='"+id+"'></canvas></div>");
var canvas = document.getElementById(id);
//var pageNumber = 1;
renderPage(canvas, pdf, pageNumber++, function pageRenderingComplete() {
if (pageNumber > pdf.numPages) {
return;
}
// Continue rendering of the next page
renderPage(canvas, pdf, pageNumber++, pageRenderingComplete);
});
}
});
function renderPage(canvas, pdf, pageNumber, callback) {
pdf.getPage(pageNumber).then(function(page) {
var scale = 1.5;
var viewport = page.getViewport({scale: scale});
var pageDisplayWidth = viewport.width;
var pageDisplayHeight = viewport.height;
//var pageDivHolder = document.createElement();
// Prepare canvas using PDF page dimensions
//var canvas = document.createElement(id);
var context = canvas.getContext('2d');
canvas.width = pageDisplayWidth;
canvas.height = pageDisplayHeight;
// pageDivHolder.appendChild(canvas);
// Render PDF page into canvas context
var renderContext = {
canvasContext: context,
viewport: viewport
};
page.render(renderContext).promise.then(callback);
});
}
</script>
<html>
The accepted answer works perfectly for a single PDF. In my case there were multiple PDFs that I wanted to render all pages for in the same sequence of the array.
I adjusted the code so that the global variables are encapsulated in an object array as follows:
var docs = []; // Add this object array
var urls = []; // You would need an array of the URLs to start.
// Loop through each url. You will also need the index for later.
urls.forEach((url, ix) => {
//Get the document from the url.
PDFJS.getDocument(url).then(function(pdf) {
// Make new doc object and set the properties of the new document
var doc = {};
//Set PDFJS global object (so we can easily access in our page functions
doc.thePDF = pdf;
//How many pages it has
doc.numPages = pdf.numPages;
//Push the new document to the global object array
docs.push(doc);
//Start with first page -- pass through the index for the handlePages method
pdf.getPage( 1 ).then(page => handlePages(page, ix) );
});
});
function handlePages(page, ix)
{
//This gives us the page's dimensions at full scale
var viewport = page.getViewport( {scale: 1} );
//We'll create a canvas for each page to draw it on
var canvas = document.createElement( "canvas" );
canvas.style.display = "block";
var context = canvas.getContext('2d');
canvas.height = viewport.viewBox[3];
canvas.width = viewport.viewBox[2];
//Draw it on the canvas
page.render({canvasContext: context, viewport: viewport});
//Add it to an element based on the index so each document is added to its own element
document.getElementById('doc-' + ix).appendChild( canvas );
//Move to next page using the correct doc object from the docs object array
docs[ix].currPage++;
if ( docs[ix].thePDF !== null && docs[ix].currPage <= docs[ix].numPages )
{
console.log("Rendering page " + docs[ix].currPage + " of document #" + ix);
docs[ix].thePDF.getPage( docs[ix].currPage ).then(newPage => handlePages(newPage, ix) );
}
}
Because the entire operation is asynchronous, without a unique object for each document, global variables of thePDF, currPage and numPages will be overwritten when subsequent PDFs are rendered, resulting in random pages being skipped, documents entirely skipped or pages from one document being appended to the wrong document.
One last point is that if this is being done offline or without using ES6 modules, the PDFJS.getDocument(url).then() method should change to pdfjsLib.getDocument(url).promise.then().
Make it to be iterate every page how much you want.
const url = '/storage/documents/reports/AR-2020-CCBI IND.pdf';
pdfjsLib.GlobalWorkerOptions.workerSrc = '/vendor/pdfjs-dist-2.12.313/package/build/pdf.worker.js';
const loadingTask = pdfjsLib.getDocument({
url: url,
verbosity: 0
});
(async () => {
const pdf = await loadingTask.promise;
let numPages = await pdf.numPages;
if (numPages > 10) {
numPages = 10;
}
for (let i = 1; i <= numPages; i++) {
let page = await pdf.getPage(i);
let scale = 1.5;
let viewport = page.getViewport({ scale });
let outputScale = window.devicePixelRatio || 1;
let canvas = document.createElement('canvas');
let context = canvas.getContext("2d");
canvas.width = Math.floor(viewport.width * outputScale);
canvas.height = Math.floor(viewport.height * outputScale);
canvas.style.width = Math.floor(viewport.width) + "px";
canvas.style.height = Math.floor(viewport.height) + "px";
document.getElementById('canvas-column').appendChild(canvas);
let transform = outputScale !== 1
? [outputScale, 0, 0, outputScale, 0, 0]
: null;
let renderContext = {
canvasContext: context,
transform,
viewport
};
page.render(renderContext);
}
})();
Related
I'm trying to implement a "drag-to-pan" function for the pfd.js viewer.
However, this only works every other time, so that after panning around, I have to click the viewer again to make it re-render.
Here's the code:
var pdfScale = 1;
var activePdf;
var rotate = 0;
var addX = 0;
var addY = 0;
function renderPage(page) {
activePdf = page;
var canvas = document.getElementById('the-canvas');
var wrapperStyle = window.getComputedStyle(document.getElementsByClassName("canvas-wrapper")[0]);
var context = canvas.getContext('2d');
var viewport = page.getViewport(pdfScale, rotate);
canvas.height = parseInt(wrapperStyle.height);
canvas.width = parseInt(wrapperStyle.width);
viewport.viewBox[0] -= addX;
viewport.viewBox[2] -= addX;
viewport.viewBox[1] += addY;
viewport.viewBox[3] += addY;
addX = addY = 0;
// Render PDF page into canvas context
var renderContext = {
canvasContext: context,
viewport: viewport
};
var renderTask = page.render(renderContext);
}
$(document).ready(function() {
var start = [0,0];
$('#the-canvas').mousedown(function(event) {
start[0] = event.screenX;
start[1] = event.screenY;
}).mouseup(function(event) {
console.log(event);
addX = event.screenX - start[0];
addY = event.screenY - start[1];
setTimeout(function() {
renderPage(activePdf);
}, 500);
});
var url = 'http://localhost/test.pdf';
// Disable workers to avoid yet another cross-origin issue (workers need
// the URL of the script to be loaded, and dynamically loading a cross-origin
// script does not work).
PDFJS.disableWorker = true;
// The workerSrc property shall be specified.
PDFJS.workerSrc = 'build/pdf.worker.js';
// Asynchronous download of PDF
var loadingTask = PDFJS.getDocument(url);
loadingTask.promise.then(function(pdf) {
console.log('PDF loaded');
// Fetch the first page
var pageNumber = 1;
pdf.getPage(pageNumber).then(function(page) {
console.log('Page loaded');
renderPage(page);
});
}, function (reason) {
// PDF loading error
console.error(reason);
});
});
Even after adding the setTimeout, it still doesn't render correctly on the first time. How can I edit my logic to make it work?
Thanks!
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
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>
On pdf.js version 2.8.61, the checked answer does no more work, as renderTextLayer() is integrated to pdf.js, no more outside source is required, neither jQuery.
The following code will make PDF text selectable. It loads the following PDF document as example, please replace it with your own:
https://raw.githubusercontent.com/mozilla/pdf.js/ba2edeae/web/compressed.tracemonkey-pldi-09.pdf
It uses mainly two html elements:
<canvas id="the-canvas"></canvas>
<div class="textLayer"></div>
canvas for the non selectable document for display, .textLayer div for selectable text. Text on .textLayer div is all transparent, so invisible, it provides only the selection effect.
<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<meta name="viewport" content="width=device-width,initial-scale=1.0,maximum-scale=1.0,user-scalable=no">
<script src="//mozilla.github.io/pdf.js/build/pdf.js" crossorigin="anonymous"></script>
<link href="//mozilla.github.io/pdf.js/web/viewer.css" rel="stylesheet" type="text/css" />
<style type="text/css">
#the-canvas {
border: 1px solid black;
direction: ltr;
}
</style>
</head>
<body>
<h1>PDF.js Previous/Next example</h1>
<div>
<button id="prev">Previous</button>
<button id="next">Next</button>
<span>Page: <span id="page_num"></span> / <span id="page_count"></span></span>
</div>
<canvas id="the-canvas"></canvas>
<div class="textLayer"></div>
<script>
// If absolute URL from the remote server is provided, configure the CORS
// header on that server.
var url = '//raw.githubusercontent.com/mozilla/pdf.js/ba2edeae/web/compressed.tracemonkey-pldi-09.pdf';
// Loaded via <script> tag, create shortcut to access PDF.js exports.
var pdfjsLib = window['pdfjs-dist/build/pdf'];
// The workerSrc property shall be specified.
pdfjsLib.GlobalWorkerOptions.workerSrc = '//mozilla.github.io/pdf.js/build/pdf.worker.js';
var pdfDoc = null,
pageNum = 1,
pageRendering = false,
pageNumPending = null,
//scale = 0.8,
scale = 1,
canvas = document.getElementById('the-canvas'),
ctx = canvas.getContext('2d');
/**
* Get page info from document, resize canvas accordingly, and render page.
* #param num Page number.
*/
function renderPage(num) {
pageRendering = true;
// Using promise to fetch the page
pdfDoc.getPage(num).then(function(page) {
var viewport = page.getViewport({scale: scale});
canvas.height = viewport.height;
canvas.width = viewport.width;
// Render PDF page into canvas context
var renderContext = {
canvasContext: ctx,
viewport: viewport
};
var renderTask = page.render(renderContext);
// Wait for rendering to finish
renderTask.promise.then(function() {
pageRendering = false;
if (pageNumPending !== null) {
// New page rendering is pending
renderPage(pageNumPending);
pageNumPending = null;
}
}).then(function() {
// Returns a promise, on resolving it will return text contents of the page
return page.getTextContent();
}).then(function(textContent) {
// Assign CSS to the textLayer element
var textLayer = document.querySelector(".textLayer");
textLayer.style.left = canvas.offsetLeft + 'px';
textLayer.style.top = canvas.offsetTop + 'px';
textLayer.style.height = canvas.offsetHeight + 'px';
textLayer.style.width = canvas.offsetWidth + 'px';
// Pass the data to the method for rendering of text over the pdf canvas.
pdfjsLib.renderTextLayer({
textContent: textContent,
container: textLayer,
viewport: viewport,
textDivs: []
});
});
});
// Update page counters
document.getElementById('page_num').textContent = num;
}
/**
* If another page rendering in progress, waits until the rendering is
* finised. Otherwise, executes rendering immediately.
*/
function queueRenderPage(num) {
if (pageRendering) {
pageNumPending = num;
} else {
renderPage(num);
}
}
/**
* Displays previous page.
*/
function onPrevPage() {
if (pageNum <= 1) {
return;
}
pageNum--;
queueRenderPage(pageNum);
}
document.getElementById('prev').addEventListener('click', onPrevPage);
/**
* Displays next page.
*/
function onNextPage() {
if (pageNum >= pdfDoc.numPages) {
return;
}
pageNum++;
queueRenderPage(pageNum);
}
document.getElementById('next').addEventListener('click', onNextPage);
/**
* Asynchronously downloads PDF.
*/
pdfjsLib.getDocument(url).promise.then(function(pdfDoc_) {
pdfDoc = pdfDoc_;
document.getElementById('page_count').textContent = pdfDoc.numPages;
// Initial/first page rendering
renderPage(pageNum);
});
</script>
</body>
</html>
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.
I use pdf.js to show pdf files, but the result is not good, please have a look at my code.
My codes are as follows.
var aaa = function (pdf, page_number) {
pdf.getPage(page_number).then(function(page) {
var scale = 1.5;
var viewport = page.getViewport(scale);
var canvas = $('.pdf-view')[page_number-1];
var context = canvas.getContext('2d');
canvas.height = viewport.height;
canvas.width = viewport.width;
var renderContext = {
canvasContext: context,
viewport: viewport
};
page.render(renderContext);
});
};
for (var i = 1;i < 51;i++) {
aaa(pdf, i);
if (i !== 50) {
var a = '<canvas data="{{ raw_path }}" class="pdf-view hide" style="margin-bottom:10px;"></canvas>';
$('#file-view #pdf').append(a);
}
}
There is a loop, then 50 functions (aaa) execute at the same time. The effect is disastrous, and my computer gets stuck. I want to excute a function right after the last function excuted very well.
Please help me improve it. Thank a lot. (Sorry, my English is disastrous as well.)
To avoid simultaneous run of single page load and render function aaa , you should move its call to callback of the page load - .then( part so it's called recursively. And then call aaa function only once with page_number = 1.
//define page render function
var aaa = function (pdf, page_number) {
pdf.getPage(page_number).then(function(page) {
var scale = 1.5;
var viewport = page.getViewport(scale);
var canvas = $('.pdf-view')[page_number-1];
var context = canvas.getContext('2d');
canvas.height = viewport.height;
canvas.width = viewport.width;
var renderContext = {
canvasContext: context,
viewport: viewport
};
page.render(renderContext);
if (i < 50) {
//render first 50 pages but not all pages except #50
aaa(pdf, i);
i++;
}
});
};
//pre-generate 50 canvases
var docFragment = document.createDocumentFragment();
for (var i = 1;i < 51;i++) {
var c = document.createElement("canvas");
$(c).data({{ raw_path }});
$(c).addClass('pdf-view hide');
$(c).css('margin-bottom', '10px');
docfrag.appendChild(c);
}
$('#file-view #pdf').append(docfrag);
//call render
var i = 1;
aaa(pdf, i);
I use mozilla pdf.js. I have a code:
<canvas id="the-canvas"/>
function displayDocument(){
PDFJS.getDocument(numberOdDocument[attachment]).then(function (pdfDoc_) {
pdfDoc = pdfDoc_;
renderPage(pageNum);
});
}
function renderPage(num) {
pdfDoc.getPage(num).then(function(page) {
var viewport = page.getViewport(scale, rotate);
canvas.height = '900';
canvas.width = '500';
var renderContext = {
canvasContext: ctx,
viewport: viewport
};
var renderTask = page.render(renderContext);
renderTask.promise.then(function () {
pageRendering = false;
if (pageNumPending !== null) {
renderPage(pageNumPending);
pageNumPending = null;
}
});
});
}
Now i see only one page in canvas tag, but I want add scrollbar to my canvvas, and I want change page with scroll. How can I do that?
Allow scroll
First, create a parent div to encapsulate the canvas element :
<div>
<canvas id="the-canvas"/>
</div>
Then, set a fixed size with a vertical scroll
<div style="width:650px;height:600px;overflow-y:scroll;">...</div>
Finally, you can set the scale you want using the variable "scale" but keep these original lines :
function renderPage(num) {
pdfDoc.getPage(num).then(function(page) {
var viewport = page.getViewport(scale);
canvas.height = viewport.height;
canvas.width = viewport.width;
...
Render all pages
Keep in mind, that render a lot of pages will take a bit of time but here is how to do it.
Idea : you need to render each page in a separate canvas element.
First, create dynamically the canvas element with a specific id during render :
<div id="pdf-viewer"></div>
...
function renderPage(num) {
pdfDoc.getPage(num).then(function(page) {
var canvasId = 'pdf-viewer-' + num;
$('#pdf-viewer').append($('<canvas/>', {'id': canvasId}));
var canvas = document.getElementById(canvasId);
...
Finally, call renderPage() for each page
function renderAllPages() {
for (var i = 1; i <= pdfDoc.numPages; i++) {
renderPage(i);
}
}
I need to place multiple PDFs on a page determined by an AJAX response, and when all documents and pages have rendered, call window.print.
The pages (canvases) of each document are being added to a div with class 'pdfdoc' to keep the pages in order by document.
I'm new to Promises, and I'm having trouble determining when to call window.print because of the async nature. Sometimes it is being called before all the pages are available even though I'm checking for the last page of the last document in the render promise before calling it. Below is the code:
// Called on each iteration of coredatalist
var getDoc = function(count) {
PDFJS.getDocument(srcUrl).then(function(pdf) {
var currentPage = 1;
$('<div class="pdfdoc" id="doc' + count + '"></div>').appendTo('body');
getPage(pdf, currentPage, count);
});
};
// Called for each page in PDF
var getPage = function(pdf, currentPage, count) {
pdf.getPage(currentPage).then(function(page) {
var scale = 2,
viewport = page.getViewport(scale),
canvas = document.createElement('canvas'),
context = canvas.getContext('2d'),
renderContext = {
canvasContext: context,
viewport: viewport,
intent: 'print'
};
// Prepare canvas using PDF page dimensions
canvas.setAttribute('class', 'canvaspdf');
canvas.id = 'canvas' + currentPage;
canvas.height = viewport.height;
canvas.width = viewport.width;
// Render PDF page into canvas context
page.render(renderContext).then(function(page) {
$('#doc' + count).append(canvas);
if (currentPage < pdf.numPages) {
currentPage++;
getPage(pdf, currentPage, count);
} else {
if (parseInt(count) === coredatalist.length - 1) {
window.print();
}
}
});
});
};
// Iterate through JSON object from AJAX request
for (var j in coredatalist) {
if (coredatalist.hasOwnProperty(j)) {
srcUrl = coredatalist[j].props.downloaduri;
getDoc(j);
}
}
Does anyone know how to call window.print after all documents AND pages are rendered?
For anyone interested, I fulfilled my requirements by wrapping PDFJS.getDocument() inside a function with a callback 'next':
loadPdf: function (pdfUrl, pdfindex, next) {
var self = this;
PDFJS.getDocument(pdfUrl).then(function (pdf) {
var currentPage = 1;
function getPage() {
pdf.getPage(currentPage).then(function (page) {
var scale = 2,
viewport = page.getViewport(scale),
canvas = document.createElement('canvas'),
context = canvas.getContext('2d'),
renderContext = {
canvasContext: context,
viewport: viewport,
intent: 'print'
};
// Prepare canvas using PDF page dimensions
canvas.setAttribute('class', 'canvaspdf');
canvas.id = 'canvas' + currentPage + '-' + pdfindex;
canvas.height = viewport.height;
canvas.width = viewport.width;
// Render PDF page into canvas context
page.render(renderContext).then(function (page) {
document.body.appendChild(canvas);
if (currentPage < pdf.numPages) {
currentPage++;
getPage();
} else {
next();
}
});
});
}
if (currentPage < pdf.numPages) {
getPage();
}
});
}
And then calling it within the callback:
var pdfUrls = [],
next = function () {
if (pdfUrls.length === 0) {
window.print();
} else {
self.loadPdf(pdfUrls.pop(), pdfUrls.length, next);
}
};
for (var j in coredatalist) {
if (coredatalist.hasOwnProperty(j)) {
pdfUrls.push('url');
}
}
next();