@mmaaikel/pdf-parse NPM

@mmaaikel/pdf-parse

Pure javascript cross-platform module to extract texts from PDFs.

Similar Packages

pdf2json buggy, no support anymore, memory leak, throws non-catchable fatal errors
j-pdfjson fork of pdf2json
pdf-parser buggy, no tests
pdfreader using pdf2json
pdf-extract not cross-platform using xpdf

Based on

https://gitlab.com/autokent/pdf-parse

Installation

npm install @mmaaikel/pdf-parse

Basic Usage - Local Files

import fs from 'fs'
import PdfParse from '@mmaaikel/pdf-parse'

let dataBuffer = fs.readFileSync('path to PDF file...');

PdfParse(dataBuffer).then(function(data) {
	// number of pages
	console.log(data.numpages);
	// number of rendered pages
	console.log(data.numrender);
	// PDF info
	console.log(data.info);
	// PDF metadata
	console.log(data.metadata); 
	// PDF.js version
	// check https://mozilla.github.io/pdf.js/getting_started/
	console.log(data.version);
	// PDF text
	console.log(data.text); 
        
});

Exception Handling

import fs from 'fs'
import PdfParse from '@mmaaikel/pdf-parse'

let dataBuffer = fs.readFileSync('path to PDF file...');

PdfParse(dataBuffer).then(function(data) {
	// use data
})
.catch(function(error){
	// handle exceptions
})

Options

const DEFAULT_OPTIONS = {
	// internal page parser callback
	// you can set this option, if you need another format except raw text
	pageRender: render_page,
	
	// max page number to parse
	max: 0,
	
	//check https://mozilla.github.io/pdf.js/getting_started/
	version: 'v1.10.100'
}