Pdf-lecture NPM

pdf-lecture

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

Installation

npm install pdf-lecture

Basic Usage - Local Files

var path = require("path");
var fs = require("fs");
var filePath = path.join(__dirname, "..your path");
var PDF = require("pdf-lecture");

PDF(filePath).then((data) => {
   console.log(data.numpages)
   console.log(data.text)
   console.log(data.pageTextArray)
});

Exception Handling

const fs = require('fs');

var filePath = path.join(__dirname, "..your path");
var PDF = require("pdf-lecture");

PDF(filePath).then(function(data) {
	// use data
})
.catch(function(error){
	// handle exceptions
})

// default render callback
function render_page(pageData) {
  let render_options = {
    normalizeWhitespace: false,
    disableCombineTextItems: false,
  };

  return pageData.getTextContent(render_options).then(function (textContent) {
    let lastY,
      text = "";
    for (let item of textContent.items) {
      if (lastY == item.transform[5] || !lastY) {
        text += item.str;
      } else {
        text += "\n" + item.str;
      }
      lastY = item.transform[5];
    }
    return text;
  });
}

let options = {
    pagerender: render_page
}

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

pdf(dataBuffer,options).then(function(data) {
	//use new format
});

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'
}