xxxxxxxxxx
const pdfParse = require("pdf-parse");
const pdfFileUrl = "./inputfile.pdf";
pdfParse(pdfFileUrl).then((result) => {
console.log("Text extracted successfully");
fs.writeFileSync("output.txt" , result.text , "utf-8");
console.log("PDF data saved in file");
}).catch((err) => {
console.error(`An error occured.\n${err.message}`);
});
xxxxxxxxxx
// Installation
// npm install pdf-parse
// Basic Usage
const fs = require('fs');
const pdf = require('pdf-parse');
let dataBuffer = fs.readFileSync('path to PDF file...');
pdf(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); */
});