pdf-stringfy

js module to extract texts from PDFs.

Installation

npm install pdf-stringfy

Basic Usage - Get all pages

const fs = require('fs');
const PdfStringfy = require('pdf-stringfy');

let dataBuffer = fs.readFileSync('path-to-pdf');

PdfStringfy(dataBuffer).then(function(data) {
	console.log(data.numpages);
	console.log(data.numrender);
	console.log(data.info);
	console.log(data.metadata); 
	console.log(data.version);
	console.log(data.text); 
});

Get only one page 35

const fs = require('fs');
const PdfStringfy = require('pdf-stringfy');

let dataBuffer = fs.readFileSync('path-to-pdf');

let options = {
    onePageOnly: 35,
};

PdfStringfy(dataBuffer, options).then(function(data) {
	console.log(data.numpages);
	console.log(data.numrender);
	console.log(data.info);
	console.log(data.metadata); 
	console.log(data.version);
	console.log(data.text);
});

Exception Handling

const fs = require('fs');
const PdfStringfy = require('pdf-stringfy');

let dataBuffer = fs.readFileSync('path-to-pdf');

PdfStringfy(dataBuffer).then(function(data) {
	console.log(data.text);
})
.catch(function(error){
	console.error("error", error.message);
})

Example

• npm run example or node example/pdf-stringfy-example.js
• Check example code. When you run the example you should have an output.txt with parsed input.pdf file.

Test

• mocha or npm test
• Check test folder.

License

MIT licensed and all it's dependencies are MIT or BSD licensed.