Javascript cross-platform module to extract texts from PDFs.
- 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
npm install pdf-lecture
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)
});
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
});
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'
}
If you need another format except raw text.
Max number of page to parse. If the value is less than or equal to 0, parser renders all pages.
check pdf.js
'default'
'v1.9.426'
'v1.10.100'
'v1.10.88'
'v2.0.550'
default version is v1.10.100
mozilla.github.io/pdf.js
If you find a bug or a mistake, you can help by submitting an issue to Github Repository
[MIT licensed]