I am using node-express and need to convert pdf into image in the server side.
Pdf-poppler is not working in linux and pdf-image happens to be not working as well.
Any alternate method how we can convert and save pdf to image in the backend.
Pdf-poppler use pdftocairo command provided by the poppler project. Since poppler did support Linux, you can install it by yourself.
For example, on ubuntu
apt-get install poppler-utils
then call pdftocairo command using the code below from Pdf-poppler.
const path = require('path');
const {execFile} = require('child_process');
const pdftocairoBin = '/usr/bin/pdftocairo';
const FORMATS = ['png', 'jpeg', 'tiff', 'pdf', 'ps', 'eps', 'svg'];
let defaultOptions = {
format: 'jpeg',
scale: 1024,
out_dir: null,
out_prefix: null,
page: null
};
function pdf2image(file, opts) {
return new Promise((resolve, reject) => {
opts.format = FORMATS.includes(opts.format) ? opts.format : defaultOptions.format;
opts.scale = opts.scale || defaultOptions.scale;
opts.out_dir = opts.out_dir || defaultOptions.out_dir;
opts.out_prefix = opts.out_prefix || path.dirname(file);
opts.out_prefix = opts.out_prefix || path.basename(file, path.extname(file));
opts.page = opts.page || defaultOptions.page;
let args = [];
args.push([`-${opts.format}`]);
if (opts.page) {
args.push(['-f']);
args.push([parseInt(opts.page)]);
args.push(['-l']);
args.push([parseInt(opts.page)]);
}
if (opts.scale) {
args.push(['-scale-to']);
args.push([parseInt(opts.scale)]);
}
args.push(`${file}`);
args.push(`${path.join(opts.out_dir, opts.out_prefix)}`);
execFile(pdftocairoBin, args, {
encoding: 'utf8',
maxBuffer: 5000*1024,
shell: false
}, (err, stdout, stderr) => {
if (err) {
reject(err);
}
else {
resolve(stdout);
}
});
});
};
Usage of pdf2image function
pdf2image('./input.pdf', {out_dir:'./', out_prefix:'ppp'});
may be you can try this bro:
Create an uploads folder & copy the sample.pdf file which you want to convert as png. since here I am only going to show you how to convert the pdf to png I am using the pdf as a static path you need to upload that pdf file via REST API.
Now open your app.js OR index.js file & paste the below code we are using the pdf2pic packages to covert the pdf pages to png images.
or you visit this link:
https://codinghub.medium.com/how-to-convert-pdf-file-pages-to-png-images-node-js-dccec010bf13
Related
I am trying to unzip a file called Restart.Manager.zip which contains a single item, Restart Manager.app. This code seems to unzip the file correctly but upon launching the outputted .app folder, I get an error "The application “Restart Manager” can’t be opened."
const JSZip = require('jszip');
const fs = require('fs');
const jetpack = require('fs-jetpack');
const originalFs = require('original-fs');
async function extractZip(filePath, destination) {
fs.readFile(filePath, function(err, data) {
if (!err) {
var zip = new JSZip();
zip.loadAsync(data).then(function(contents) {
Object.keys(contents.files).forEach(function(filename) {
const file = zip.file(filename);
if (file) {
file.async('nodebuffer').then(function(content) {
var dest = destination + '/' + filename;
if (filename.endsWith('.asar')) {
originalFs.writeFileSync(dest, content)
} else {
jetpack.write(dest, content);
}
});
}
});
});
}
});
};
extractZip('/Users/me/Desktop/Restart.Manager.zip', '/Users/me/Desktop')
Manually unzipping the .zip file creates a working .app so I'm not sure where the code is messing up.
Here is the file on GitHub releases for testing: https://github.com/itw-creative-works/restart-manager-download-server/releases/download/installer/Restart.Manager.zip but feel free to use your own zipped .app file (although it should probably be an Electron app in which case you can find one here https://www.electronjs.org/apps)
I have tried zipping things like a .png and it unzips fine, which makes me think it is having problems with .app files or possibly the fact that the .app contains a .asar file which Electron supposedly has problems handling when it comes to the fs module: https://github.com/electron/electron/issues/1658
I need to convert a docx file to pdf but I don't know very well nodejs, however, I know that the following can be done:
There is a project called unoconv-worker and in it, there is a part where the following line appears:
var child = spawn ('unoconv', [
'--stdout',
'--no-launch',
'--format', job.outputExtension,
job.tempPath
]);
https://github.com/koumoul-dev/unoconv-worker/blob/master/route.js
In my terminal I can convert it in the following way and it works perfectly:
unoconv -f pdf --output="something.pdf" docxtoconvert.docx
However, I would like to give you a file that I gave you the route, so I tried it this way:
var filePath = "/tmp/docxtoconvert.docx";
var child = spawn ("unoconv", [
"-f",
"pdf",
"--output",
"/tmp/something.pdf",
filePath
]);
Output:
Unoconv converter received message on stderr function () {
if (arguments.length === 0) {
var result = this.utf8Slice(0, this.length);
} else {
var result = slowToString.apply(this, arguments);
}
if (result === undefined)
throw new Error('toString failed');
return result;
}
But it has not worked. Could you help me? Thank you
Lot of wrapper modules exists for unoconv that can solve your problem.
You can try this
https://www.npmjs.com/package/unoconv
I found some repos, which do not look as they are still maintained:
https://github.com/gfloyd/node-unoconv
https://github.com/skmp/node-msoffice-pdf
...
I tried the approach with libreoffice, but the pdf output is so bad, that it is not useable (text on diff. pages etc.).
If possible I would like to avoid starting any background processes and/or saving the file on the server. Best would be solution where I can use buffers. For privacy reasons, I cannot use any external service.
doc buffer -> pdf buffer
Question:
How to convert docs to pdf in nodejs?
For those who might stumble on this question nowadays:
There is cool tool called Gotenberg — Docker-powered stateless API for converting HTML, Markdown and Office documents to PDF. It supports converting DOCs via unoconv.
And I am happen to be an author of JS/TS client for Gotenberg — gotenberg-js-client
I welcome you to use it :)
UPD:
Gotenberg has new website now — https://gotenberg.dev
While I was creating an application I need to convert the doc or docx file uploaded by a user into a pdf file for further analysis. I used npm package libreoffice-convert for this purpose. libreoffice-convert requires libreoffice to be installed on your Linux machine. Here is a sample code that I have used.
This code is written in javascript for nodejs based application.
const libre = require('libreoffice-convert');
const path = require('path');
const fs = require('fs').promises;
let lib_convert = promisify(libre.convert)
async function convert(name="myresume.docx") {
try {
let arr = name.split('.')
const enterPath = path.join(__dirname, `/public/Resume/${name}`);
const outputPath = path.join(__dirname, `/public/Resume/${arr[0]}.pdf`);
// Read file
let data = await fs.readFile(enterPath)
let done = await lib_convert(data, '.pdf', undefined)
await fs.writeFile(outputPath, done)
return { success: true, fileName: arr[0] };
} catch (err) {
console.log(err)
return { success: false }
}
}
You will get a very good quality of pdf.
To convert a document into PDF we can use Universal Office Converter (unoconv) command line utility.
It can be installed on your OS by any package manager e.g. To install it on ubuntu using apt-get
sudo apt-get install unoconv
As per documentation of unoconv
If you installed unoconv by hand, make sure you have the required LibreOffice or OpenOffice packages installed
Following example demonstrate how to invoke unoconv utility
unoconv -f pdf sample_document.py
It generates PDF document that contains content of sample_document.py
If you want to use a nodeJS program then you can invoke the command through child process
Find code below that demonstrates how to use child process for using the unoconv for creating PDF
const util = require('util');
const exec = util.promisify(require('child_process').exec);
async function createPDFExample() {
const { stdout, stderr } = await exec('unoconv -f pdf sample.js');
console.log('stdout:', stdout);
console.log('stderr:', stderr);
}
createPDFExample();
Posting a slightly modified version for excel, based upon the answer provided by #shubham singh. I tried it and it worked perfectly.
const fs = require('fs').promises;
const path = require('path');
const { promisify } = require('bluebird');
const libre = require('libreoffice-convert');
const libreConvert = promisify(libre.convert);
// get current working directory
let workDir = path.dirname(process.mainModule.filename)
// read excel file
let data = await fs.readFile(
`${workDir}/my_excel.xlsx`
);
// create pdf file from excel
let pdfFile = await libreConvert(data, '.pdf', undefined);
// write new pdf file to directory
await fs.writeFile(
`${workDir}/my_pdf.pdf`,
pdfFile
);
Docx to pdf
A library that converts docx file to pdf.
Installation:
npm install docx-pdf --save
Usage
var docxConverter = require('docx-pdf');
docxConverter('./input.docx','./output.pdf',function(err,result){
if(err){
console.log(err);
}
console.log('result'+result);
});
its basically docxConverter(inputPath,outPath,function(err,result){
if(err){
console.log(err);
}
console.log('result'+result);
});
Output should be output.pdf which will be produced on the output path your provided
I'm trying to create a simple dynamic-badge (png) to embed in static pages to let know the status of my application.
I'd like so to use an existing PNG image and write on it some text with Node.js.
I've found lot of libraries but all of them use Imagemagick or Cairo as native dependencies, I'd like to avoid to install anything else on the server.
I've then found lwip, but I can't really understand how to write text on an image with it. How can I do?
You could use Jimp. It has a print method:
var Jimp = require("jimp");
var fileName = 'test.png';
var imageCaption = 'Image caption';
var loadedImage;
Jimp.read(fileName)
.then(function (image) {
loadedImage = image;
return Jimp.loadFont(Jimp.FONT_SANS_16_BLACK);
})
.then(function (font) {
loadedImage.print(font, 10, 10, imageCaption)
.write(fileName);
})
.catch(function (err) {
console.error(err);
});
If you want to use a ttf file you can use gm
This will also align the text automatically so you don't have to keep track of your letter sizing / location.
const gm = require('gm').subClass({imageMagick: true});
gm('path/to/image.png')
.fill("#FFFFFF")
.font("./font.ttf", 20)
.drawText(15, 10, "your text", 'southeast') //can be any location
.write("./output.png", function (err) {
if (!err) console.log('done');
});
I am using wkhtmltopdf to generate pdfs in nodejs
Below is my sample code to generate pdf
var wkhtmltopdf = require('wkhtmltopdf')
, createWriteStream = require('fs').createWriteStream;
var r = wkhtmltopdf('http://www.google.com', { pageSize: 'letter' })
.pipe(createWriteStream('C:/MYUSERNAME/demo.pdf'));
r.on('close', function(){
mycallback();
});
The above code is generating corrupt pdfs. I could not figure out the issue.
Although when I generate pdfs using command prompt it is generating correctly
like when I use below code in windows command prompt
wkhtmltopdf http://www.google.com demo.pdf
I get correct pdf generated,sadly when I try to generate pdf in node environment, it generates corrupt pdfs.
Incase it helps I'm using wkhtmltopdf 0.11.0 rc2
Thanks in advance.
wkhtmltopdf for node has a bug for windows, so you can write a new one.
Like this:
function wkhtmltopdf(input, pageSize) {
var spawn = require('child_process').spawn;
var html;
var isUrl = /^(https?|file):\/\//.test(input);
if (!isUrl) {
html = input;
input = '-';
}
var args = ['wkhtmltopdf', '--quiet', '--page-size', pageSize, input, '-']
if (process.platform === 'win32') {
var child = spawn(args[0], args.slice(1));
} else {
var child = spawn('/bin/sh', ['-c', args.join(' ') + ' | cat']);
}
if (!isUrl) {
child.stdin.end(html);
}
return child.stdout;
}
// usage:
createWriteStream = require('fs').createWriteStream;
wkhtmltopdf('http://google.com/', 'letter')
.pipe(createWriteStream('demo1.pdf'));
wkhtmltopdf('<body>hello world!</body>', 'letter')
.pipe(createWriteStream('demo2.pdf'));
note: the param is now 'letter' not { pageSize: 'letter' }