ExternalInterface.addCallback doesnot runs well - javascript

I try make a login facebook mechanism in my flash apps.
But when I try to get the token access form callback page, the ExternalInterface.addCallback that will get and send to flash didn;t runs well.
How I can solve it?
This my code:
var accessToken:String ="";
tombol.addEventListener(MouseEvent.CLICK, onClick);
function onClick(e:MouseEvent):void{
attemptToAuthenticate();
tombol.removeEventListener(MouseEvent.CLICK, onClick);
}
function attemptToAuthenticate(...permissions):void{
var scope:String = "";
if (permissions.length > 0){
scope = "&scope=" + permissions.join(",");
}
ExternalInterface.call("window.open","https://graph.facebook.com/oauth/authorize?client_id=245127485627150&type=user_agent&redirect_uri=http://localhost/satu/callback.html"+scope,"facebookLoginWindow","height=370, width=600");
teks.text = "success get token from server fb";
ExternalInterface.addCallback("setAccessToken", setAccessToken);
ExternalInterface.call("function() {"
+ "window.setAccessToken = function(hashValue){"
+ "var satu1 = document.getElementById('satu');"
+ "satu1.setAccessToken(hashValue);"
+ "}"
+ "}");
ExternalInterface.call("window.alert", "hashValue");
teks.text += " get from flash";
}
function setAccessToken(a_hashValue:String):void{
teks.text += "setaccesstoken";
var hashParams:Array = a_hashValue.substr(1).split("&");
var hashKeyAndValue:Array;
for (var i:int = 0; i < hashParams.length; i++){
hashKeyAndValue = (hashParams[i] as String).split("=");
if (hashKeyAndValue[0] == "access_token"){
this.accessToken = hashKeyAndValue[1];
break;
}
}
this.request("me","");
}
// some code below.....

Related

Website not responding - I think due to javascript code

I'm trying to make a game in javascript and display it on my website, but the website isn't responding anymore. The internet connection is just fine.
Here is the code where I think it went wrong:
$(function(){
init();
console.log("Main Init Called")
});
function InitFilesRanksBrd() {
var index = 0;
var file = FILES.FILE_A;
var rank = RANKS.RANK_1;
var sq = SQUARES.A1;
for(index = 0; index < BRD_SQ_NUM; ++index) {
FilesBrd[index] = SQUARES.OFFBOARD;
RanksBrd[index] = SQUARES.OFFBOARD;
}
for(rank = RANKS.RANK_1; rank <= RANKS.RANK_5; ++rank) {
for(file = FILES.FILE_1; rank <= FILES.FILE_E; ++file) {
sq = FR2SQ(file,rank);
FilesBrd[sq] = file;
RanksBrd[sq] = rank;
}
}
console.log("FilesBrd[0]:" + FilesBrd[0] + " RanksBrd[0]:" + RanksBrd[0]);
console.log("FilesBrd[SQUARES.A1]:" + FilesBrd[SQUARES.A1] + " RanksBrd[SQUARES.A1]:" + RanksBrd[SQUARES.A1]);
//console.log("FilesBrd[SQUARES.C5]:" + FilesBrd[SQUARES.C5] + " RanksBrd[SQUARES.C5]:" + RanksBrd[SQUARES.C5]);
console.log(FilesBrd);
console.log(RanksBrd);
}
function init(){
console.log("init() called");
InitFilesRanksBrd();
}
In the inner for, the variable that you are comparing is rank, not file. It should be:
for(file = FILES.FILE_1; file <= FILES.FILE_E; ++file)
Because the rank variable isn't incrementing until the loop content end, but the loop content doesn't end because of the inner loop.

Cannot store a value in local storage

I have fetched a list of items from web service, now i want to store the item_name on which I have clicked. I cannot store that item name, if its "bread butter" , it stores only "bread".
What shall i do now?
<script>
var sub_catidall = [];
var sub_catnameall = [];
function selected_index(sub_cat_name_all) {
alert("selected sub category" + sub_cat_name_all);
//window.localStorage.setItem("current_sub_id_all",sub_cat_id_all);
window.localStorage.setItem("DishName", sub_cat_name_all);
window.open("MenuDetails.html", "_self");
}
function jsondata(data) {
var parsedata = JSON.parse(JSON.stringify(data));
var sub_category = parsedata["Item List"];
for (var i = 0; i < sub_category.length; i++) {
var sub_menuall = sub_category[i];
sub_catidall = sub_menuall['menuItemId'];
sub_catnameall = sub_menuall['menuItemName'];
//alert(sub_catnameall);
var id = document.createElement("table");
if ((i % 2) == 0) {
id.innerHTML += '<br><td><strong><font face="DEVROYE">' + sub_menuall['menuItemName'] + '</td></strong>';
document.getElementById("block_left").appendChild(id);
} else {
id.innerHTML += '<br><tr><td><strong><font face="DEVROYE">' + sub_menuall['menuItemName'] + '</td></strong>';
document.getElementById("block_right").appendChild(id);
}
}
}
jsonp("http://remoteaddress/hotelTab/menuitem.php?callback=jsondata&mCatId=" + window.localStorage.getItem('current_id') + "&menuCategoryId=" + window.localStorage.getItem('current_sub_id'));
</script>
DOM Storage Guide
Example
var string = 'Bread Butter';
localStorage.setItem("DishName", string);
alert(localStorage.getItem('DishName'));
On jsFiddle
I use Amplifyjs store library to access local storage.
It's simple to use/understand, works really well and it's cross browser (mobile browser as well)
Hope this Helps

jqgrid jquery set a new css class for a errors in dialog box

For checking server side validation errors, I am using "afterSubmit" property of jqGRid.
afterSubmit: checkForErrors
And my checkForErrors is something like this:
function checkForErrors(response,postdata){
var success = true;
var message = ""
var json = eval('(' + response.responseText + ')');
if(json.errors.length>0) {
success = false;
for(i=0; i < json.errors.length; i++) {
message += json.errors[i] + '<br/>';
}
}
var new_id = null;
return [success,message,new_id];
}
The only thing i need to fix is change the default error class/style used by jqgrid (ie. ui-state-error), to my custom css class. How can i do that.
Thanks!
Try this:
function checkForErrors(response,postdata){
var success = true;
var message = ""
var json = eval('(' + response.responseText + ')');
if(json.errors.length>0) {
success = false;
for(i=0; i < json.errors.length; i++) {
message += json.errors[i] + '<br/>';
}
}
var new_id = null;
//Here pass the right class name instead of ".dialog" which you are using in your code
$(".dialog").find(".ui-state-error").removeClass("ui-state-error").addClass("newClass");
return [success,message,new_id];
}

JS: Can not convert to object, childNodes related

Ok, feeling stupid here, but wondering what the problem is here exactly.
Although the function works as it should, I get this JS Error in Opera. Not sure about other browsers...
Uncaught exception: TypeError: Cannot
convert
'document.getElementById("shoutbox_area"
+ moduleId)' to object
oElement = document.getElementById("shoutbox_area"
+ moduleId).childNodes;
Here is the relevant code:
function appendShout(XMLDoc)
{
var shoutData = XMLDoc.getElementsByTagName("item");
var oElement = [];
if (shoutData.length > 0)
{
var moduleId = shoutData[0].getAttribute("moduleid");
if (shoutData[shoutData.length - 1].getAttribute("lastshout") != "undefined")
{
for (var i = 0; i < shoutData.length; i++)
if (shoutData[i].firstChild.nodeValue != 0)
document.getElementById("shoutbox_area" + moduleId).innerHTML += shoutData[i].firstChild.nodeValue;
oElement = document.getElementById("shoutbox_area" + moduleId).childNodes;
var i = oElement.length;
while (i--)
{
if (i % 2 == 0)
oElement[i].className = "windowbg2";
else
oElement[i].className = "windowbg";
}
oElement[oElement.length - 2].style.borderBottom = "1px black dashed";
}
}
}
Can someone please help me to understand why it is giving me an error here:
oElement = document.getElementById("shoutbox_area" + moduleId).childNodes;
Can I not assign an array to the childNodes?
EDIT:
This JS Error occurs when I try and delete a shout. The JS function for deleting a shout is this:
function removeShout(shout, moduleID)
{
var shoutContainer = shout.parentNode.parentNode;
var send_data = "id_shout=" + shout.id;
var url = smf_prepareScriptUrl(smf_scripturl) + "action=dream;sa=shoutbox;xml;" + "delete_shout;" + "canmod=" + canMod[moduleID] + ";" + sessVar + "=" + sessId;
sendXMLDocument(url, send_data);
var shoutID = 0;
while (shoutID !== null)
{
var shoutID = document.getElementById(shout.parentNode.id);
var moduleID = shoutID.parentNode.getAttribute("moduleid");
if (shoutID.parentNode.lastChild)
{
var url = smf_prepareScriptUrl(smf_scripturl) + "action=dream;sa=shoutbox;xml;get_shouts=" + (shoutID.parentNode.lastChild.id.replace("shout_", "") - 1) + ";membercolor=" + memberColor[moduleID] + ";maxcount=" + maxCount[moduleID] + ";shoutboxid=" + shoutboxID[moduleID] + ";textsize=" + textSize[moduleID] + ";parsebbc=" + parseBBC[moduleID] + ";moduleid=" + moduleID + ";maxcount=" + maxCount[moduleID] + ";canmod=" + canMod[moduleID] + ";" + sessVar + "=" + sessId;
getXMLDocument(url, appendShout);
}
element = shoutID.parentNode.childNodes;
var i = element.length;
while (i--)
{
if (i % 2 == 0)
element[i].className = "windowbg2";
else
element[i].className = "windowbg";
}
shoutID.parentNode.removeChild(shoutID);
}
}
Am using the following functions for the sending and getting the XMLHttpRequest as you may have noticed already in the removeShout function above:
// Load an XML document using XMLHttpRequest.
function getXMLDocument(sUrl, funcCallback)
{
if (!window.XMLHttpRequest)
return null;
var oMyDoc = new XMLHttpRequest();
var bAsync = typeof(funcCallback) != 'undefined';
var oCaller = this;
if (bAsync)
{
oMyDoc.onreadystatechange = function () {
if (oMyDoc.readyState != 4)
return;
if (oMyDoc.responseXML != null && oMyDoc.status == 200)
{
if (funcCallback.call)
{
funcCallback.call(oCaller, oMyDoc.responseXML);
}
// A primitive substitute for the call method to support IE 5.0.
else
{
oCaller.tmpMethod = funcCallback;
oCaller.tmpMethod(oMyDoc.responseXML);
delete oCaller.tmpMethod;
}
}
};
}
oMyDoc.open('GET', sUrl, bAsync);
oMyDoc.send(null);
return oMyDoc;
}
// Send a post form to the server using XMLHttpRequest.
function sendXMLDocument(sUrl, sContent, funcCallback)
{
if (!window.XMLHttpRequest)
return false;
var oSendDoc = new window.XMLHttpRequest();
var oCaller = this;
if (typeof(funcCallback) != 'undefined')
{
oSendDoc.onreadystatechange = function () {
if (oSendDoc.readyState != 4)
return;
if (oSendDoc.responseXML != null && oSendDoc.status == 200)
funcCallback.call(oCaller, oSendDoc.responseXML);
else
funcCallback.call(oCaller, false);
};
}
oSendDoc.open('POST', sUrl, true);
if ('setRequestHeader' in oSendDoc)
oSendDoc.setRequestHeader('Content-Type', 'application/x-www-form-urlencoded');
oSendDoc.send(sContent);
return true;
}
Hopefully this is good enough, you can do a view source on it to see the actual HTML, but there are attributes that get added to the Shoutbox tags at runtime so as to be XHTML compliant, etc..
Please let me know if there is anything else you need?
Thanks :)
The code is breaking because shoutID is null in the second of these two lines, the second time through the loop:
var shoutID = document.getElementById(shout.parentNode.id);
var moduleID = shoutID.parentNode.getAttribute("moduleid");
The first of those lines is strange. Why not just use var shoutID = shout.parentNode;?
Also, the moduleId attribute seems to be nowhere around.
What are you trying to achieve with the while loop?

How to extract text from a PDF in JavaScript

I wonder if is possible to get the text inside of a PDF file by using only Javascript?
If yes, can anyone show me how?
I know there are some server-side java, c#, etc libraries but I would prefer not using a server.
thanks
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.
PDFJS.getDocument( data ).then( function(pdf) {
pdf.getPage(i).then( function(page){
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 data needs to be either a URL or ArrayBuffer type data. I used the ReadAsArrayBuffer(file) function in FileReader API to get the data.
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);
})
Just leaving here a full working sample.
<html>
<head>
<script src="https://npmcdn.com/pdfjs-dist/build/pdf.js"></script>
</head>
<body>
<input id="pdffile" name="pdffile" type="file" />
<button id="btn" onclick="convert()">Process</button>
<div id="result"></div>
</body>
</html>
<script>
function convert() {
var fr=new FileReader();
var pdff = new Pdf2TextClass();
fr.onload=function(){
pdff.pdfToText(fr.result, null, (text) => { document.getElementById('result').innerText += text; });
}
fr.readAsDataURL(document.getElementById('pdffile').files[0])
}
function Pdf2TextClass() {
var self = this;
this.complete = 0;
this.pdfToText = function (data, callbackPageDone, callbackAllDone) {
console.assert(data instanceof ArrayBuffer || typeof data == 'string');
var loadingTask = pdfjsLib.getDocument(data);
loadingTask.promise.then(function (pdf) {
var total = pdf._pdfInfo.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) {
//console.log(textContent.items[0]);0
if (null != textContent.items) {
var page_text = "";
var last_block = null;
for (var k = 0; k < textContent.items.length; k++) {
var block = textContent.items[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
</script>
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/
Note: This code assumes you're using nodejs. That means you're parsing a local file instead of one from a web page since the original question doesn't explicitly ask about parsing pdfs on a web page.
#gm2008's answer was a great starting point (please read it and its comments for more info), but needed some updates (08/19) and had some unused code. I also like examples that are more full. There's more refactoring and tweaking that could be done (e.g. with await), but for now it's as close to that original answer as it could be.
As before, this uses Mozilla's PDFjs library. The npmjs package is at https://www.npmjs.com/package/pdfjs-dist.
In my experience, this doesn't do well in finding where to put spaces, but that's a problem for another time.
[Edit: I believe the update to the use of .transform has restored the whitespace as it originally behaved.]
// This file is called myPDFfileToText.js and is in the root folder
let PDFJS = require('pdfjs-dist');
let pathToPDF = 'path/to/myPDFfileToText.pdf';
let toText = Pdf2TextObj();
let onPageDone = function() {}; // don't want to do anything between pages
let onFinish = function(fullText) { console.log(fullText) };
toText.pdfToText(pathToPDF, onPageDone, onFinish);
function Pdf2TextObj() {
let self = this;
this.complete = 0;
/**
*
* #param path Path to the pdf file.
* #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.
* 3) the `page` object itself or null.
* #param callbackAllDone Called after all text has been collected. Input parameters:
* 1) full text of parsed pdf.
*
*/
this.pdfToText = function(path, callbackPageDone, callbackAllDone) {
// console.assert(typeof path == 'string');
PDFJS.getDocument(path).promise.then(function(pdf) {
let total = pdf.numPages;
callbackPageDone(0, total, null);
let pages = {};
// For some (pdf?) reason these don't all come in consecutive
// order. That's why they're stored as an object and then
// processed one final time at the end.
for (let pagei = 1; pagei <= total; pagei++) {
pdf.getPage(pagei).then(function(page) {
let pageNumber = page.pageNumber;
page.getTextContent().then(function(textContent) {
if (null != textContent.items) {
let page_text = "";
let last_item = null;
for (let itemsi = 0; itemsi < textContent.items.length; itemsi++) {
let item = textContent.items[itemsi];
// I think to add whitespace properly would be more complex and
// would require two loops.
if (last_item != null && last_item.str[last_item.str.length - 1] != ' ') {
let itemX = item.transform[5]
let lastItemX = last_item.transform[5]
let itemY = item.transform[4]
let lastItemY = last_item.transform[4]
if (itemX < lastItemX)
page_text += "\r\n";
else if (itemY != lastItemY && (last_item.str.match(/^(\s?[a-zA-Z])$|^(.+\s[a-zA-Z])$/) == null))
page_text += ' ';
} // ends if may need to add whitespace
page_text += item.str;
last_item = item;
} // ends for every item of text
textContent != null && console.log("page " + pageNumber + " finished.") // " content: \n" + page_text);
pages[pageNumber] = page_text + "\n\n";
} // ends if has items
++self.complete;
callbackPageDone(self.complete, total, page);
// If all done, put pages in order and combine all
// text, then pass that to the callback
if (self.complete == total) {
// Using `setTimeout()` isn't a stable way of making sure
// the process has finished. Watch out for missed pages.
// A future version might do this with promises.
setTimeout(function() {
let full_text = "";
let num_pages = Object.keys(pages).length;
for (let pageNum = 1; pageNum <= num_pages; pageNum++)
full_text += pages[pageNum];
callbackAllDone(full_text);
}, 1000);
}
}); // ends page.getTextContent().then
}); // ends page.then
} // ends for every page
});
}; // Ends pdfToText()
return self;
}; // Ends object factory
Run in the terminal:
node myPDFfileToText.js
Updated 02/2021
<script src="https://npmcdn.com/pdfjs-dist/build/pdf.js"></script>
<script>
function Pdf2TextClass(){
var self = this;
this.complete = 0;
this.pdfToText = function(data, callbackPageDone, callbackAllDone){
console.assert( data instanceof ArrayBuffer || typeof data == 'string' );
var loadingTask = pdfjsLib.getDocument(data);
loadingTask.promise.then(function(pdf) {
var total = pdf._pdfInfo.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){
//console.log(textContent.items[0]);0
if( null != textContent.items ){
var page_text = "";
var last_block = null;
for( var k = 0; k < textContent.items.length; k++ ){
var block = textContent.items[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] ;
console.log(full_text);
}, 1000);
}
}); // end of page.getTextContent().then
}); // end of page.then
} // of for
});
}; // end of pdfToText()
}; // end of class
var pdff = new Pdf2TextClass();
pdff.pdfToText('PDF_URL');
</script>
For all the people who actually want to use it on a node server:
/**
* Created by velten on 25.04.16.
*/
"use strict";
let pdfUrl = "http://example.com/example.pdf";
let request = require('request');
var pdfParser = require('pdf2json');
let pdfPipe = request({url: pdfUrl, encoding:null}).pipe(pdfParser);
pdfPipe.on("pdfParser_dataError", err => console.error(err) );
pdfPipe.on("pdfParser_dataReady", pdf => {
//optionally:
//let pdf = pdfParser.getMergedTextBlocksIfNeeded();
let count1 = 0;
//get text on a particular page
for (let page of pdf.formImage.Pages) {
count1 += page.Texts.length;
}
console.log(count1);
pdfParser.destroy();
});
It is possible but:
you would have to use the server anyway, there's no way you can get content of a file on user computer without transferring it to server and back
I don't thing anyone has written such library yet
So if you have some free time you can learn pdf format and write such a library yourself, or you can just use server side library of course.

Categories