Keyword and text summarization from url

index.js

const fs = require('fs')
const port = process.env.PORT || 5000
const express = require('express')
const app = express()
const http = require('http')
const bodyParser = require('body-parser')
const server = http.createServer(app)
const _ = require('lodash')
const textract = require('textract')
const pdf_extract = require('pdf-text-extract')
const countWords = require("count-words")
const summarizer = require('nodejs-text-summarizer')



// Express App setup
app.use(express.static(__dirname))
app.use(bodyParser.json())

app.all(['/test'], function(req, res, next) {
	var json = require('./test_keywords.json');
	// var map = json.map(r=>!~stopwords.indexOf(r));
	var map = json.filter(remove_stop_words)
	// console.log("JSON MAP", map)
	res.send('ok')
})



app.all(['/get'], function(req, res, next){
	var url = req.query.url

	!!url ? textract.fromUrl( url, function( error, text_body ) {
		// Error handling
		if (error) res.status(404).json({error: "could not read file at url", params: req.query});

		// Get keyword density
		keywords = countWords( text_body );
		text_body = text_body.split(" ").slice(0, 100).join(' ')
		// Summarize the text
		var summary = summarizer( text_body );
		var summary_keywords = countWords(summary);
		// Limit text summary to 100 words
		summary = summary.split(" ").slice(0, 100).join(' ');
		
		// Respond to client
		res.json({
			summary,
			summary_keywords,
			keywords
		})
	}) : res.status(404).json({error: "could not determine url"})
})




// Begin server
server.listen(port, () => console.log(`App running on localhost:${port}`))