extract text from pdf in Javascript
This is an ancient question, but because pdf.js has been developing over the years, I would like to give a new answer. That is, it can be done locally without involving any server or external service. The new pdf.js has a function: page.getTextContent(). You can get the text content from that. I've done it successfully with the following code.
What you get in each step is a promise. You need to code this way:
.then( function(){...})to proceed to the next step.1)
PDFJS.getDocument( data ).then( function(pdf) {2)
pdf.getPage(i).then( function(page){3)
page.getTextContent().then( function(textContent){What you finally get is an string array
textContent.bidiTexts[]. You concatenate them to get the text of 1 page. Text blocks' coordinates are used to judge whether newline or space need to be inserted. (This may not be totally robust, but from my test it seems ok.)The input parameter
dataneeds to be either a URL or ArrayBuffer type data. I used the ReadAsArrayBuffer(file) function inFileReaderAPI to get the data.
Hope this helps.
Note: According to some other user, the library has updated and caused the code to break. According to the comment by async5 below, you need to replace textContent.bidiTexts with textContent.items.
function Pdf2TextClass(){
var self = this;
this.complete = 0;
/**
*
* @param data ArrayBuffer of the pdf file content
* @param callbackPageDone To inform the progress each time
* when a page is finished. The callback function's input parameters are:
* 1) number of pages done;
* 2) total number of pages in file.
* @param callbackAllDone The input parameter of callback function is
* the result of extracted text from pdf file.
*
*/
this.pdfToText = function(data, callbackPageDone, callbackAllDone){
console.assert( data instanceof ArrayBuffer || typeof data == 'string' );
PDFJS.getDocument( data ).then( function(pdf) {
var div = document.getElementById('viewer');
var total = pdf.numPages;
callbackPageDone( 0, total );
var layers = {};
for (i = 1; i <= total; i++){
pdf.getPage(i).then( function(page){
var n = page.pageNumber;
page.getTextContent().then( function(textContent){
if( null != textContent.bidiTexts ){
var page_text = "";
var last_block = null;
for( var k = 0; k < textContent.bidiTexts.length; k++ ){
var block = textContent.bidiTexts[k];
if( last_block != null && last_block.str[last_block.str.length-1] != ' '){
if( block.x < last_block.x )
page_text += "\r\n";
else if ( last_block.y != block.y && ( last_block.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null ))
page_text += ' ';
}
page_text += block.str;
last_block = block;
}
textContent != null && console.log("page " + n + " finished."); //" content: \n" + page_text);
layers[n] = page_text + "\n\n";
}
++ self.complete;
callbackPageDone( self.complete, total );
if (self.complete == total){
window.setTimeout(function(){
var full_text = "";
var num_pages = Object.keys(layers).length;
for( var j = 1; j <= num_pages; j++)
full_text += layers[j] ;
callbackAllDone(full_text);
}, 1000);
}
}); // end of page.getTextContent().then
}); // end of page.then
} // of for
});
}; // end of pdfToText()
}; // end of class
I couldn't get gm2008's example to work (the internal data structure on pdf.js has changed apparently), so I wrote my own fully promise-based solution that doesn't use any DOM elements, queryselectors or canvas, using the updated pdf.js from the example at mozilla
It eats a file path for the upload since i'm using it with node-webkit. You need to make sure you have the cmaps downloaded and pointed somewhere and you nee pdf.js and pdf.worker.js to get this working.
/**
* Extract text from PDFs with PDF.js
* Uses the demo pdf.js from https://mozilla.github.io/pdf.js/getting_started/
*/
this.pdfToText = function(data) {
PDFJS.workerSrc = 'js/vendor/pdf.worker.js';
PDFJS.cMapUrl = 'js/vendor/pdfjs/cmaps/';
PDFJS.cMapPacked = true;
return PDFJS.getDocument(data).then(function(pdf) {
var pages = [];
for (var i = 0; i < pdf.numPages; i++) {
pages.push(i);
}
return Promise.all(pages.map(function(pageNumber) {
return pdf.getPage(pageNumber + 1).then(function(page) {
return page.getTextContent().then(function(textContent) {
return textContent.items.map(function(item) {
return item.str;
}).join(' ');
});
});
})).then(function(pages) {
return pages.join("\r\n");
});
});
}
usage:
self.pdfToText(files[0].path).then(function(result) {
console.log("PDF done!", result);
})
Here's some JavaScript code that does what you want using Pdf.js from http://hublog.hubmed.org/archives/001948.html:
var input = document.getElementById("input");
var processor = document.getElementById("processor");
var output = document.getElementById("output");
// listen for messages from the processor
window.addEventListener("message", function(event){
if (event.source != processor.contentWindow) return;
switch (event.data){
// "ready" = the processor is ready, so fetch the PDF file
case "ready":
var xhr = new XMLHttpRequest;
xhr.open('GET', input.getAttribute("src"), true);
xhr.responseType = "arraybuffer";
xhr.onload = function(event) {
processor.contentWindow.postMessage(this.response, "*");
};
xhr.send();
break;
// anything else = the processor has returned the text of the PDF
default:
output.textContent = event.data.replace(/\s+/g, " ");
break;
}
}, true);
...and here's an example:
http://git.macropus.org/2011/11/pdftotext/example/