I can\'t find any packages to do this. I know PHP has a ton of libraries for PDFs (like http://www.fpdf.org/) but anything for Node?
you can use pdf-text for pdf files. it will extract text from a pdf into an array of text 'chunks'. Useful for doing fuzzy parsing on structured pdf text.
var pdfText = require('pdf-text')
var pathToPdf = __dirname + "/info.pdf"
pdfText(pathToPdf, function(err, chunks) {
//chunks is an array of strings
//loosely corresponding to text objects within the pdf
//for a more concrete example, view the test file in this repo
})
var fs = require('fs')
var buffer = fs.readFileSync(pathToPdf)
pdfText(buffer, function(err, chunks) {
console.log(chunks)
})
for docx files you can use mammoth, it will extract text from .docx files.
var mammoth = require("mammoth");
mammoth.extractRawText({path: "./doc.docx"})
.then(function(result){
var text = result.value; // The raw text
console.log(text);
var messages = result.messages;
})
.done();
I hope this will help.