Report is now in .json format

Node.js/index.js

@@ -3,21 +3,22 @@ const http = require('http')
 const fs = require('fs')
 
 async function main_loop() {
+	json_object = []
 	for (let i = 0; i < times; i++) {
 		const url = await url_generator(domains, mode, log)
 		try {
 			const response = await fetch(url)
 			console.log(`${url} exists!`)
-			fs.appendFile("JS_report.txt", "\n" + url + " | STATUS_CODE: " + String(response.statusCode), function(err) {if (err) throw err})
+			json_object.push(`{"website_url":"${url}","response_type":"SUCCESS","response_code":"${String(response.statusCode)}","response_details":"${String(response.statusMessage)}"}`)
 		}
 		catch(e) {
 			if (e.errno != 'ENOTFOUND') {
 				console.log(`${url} exists!`)
-				fs.appendFile("JS_report.txt", "\n" + url + " | ERROR_CODE: " + e.errno, function(err) {if (err) throw err})
+				json_object.push(`{"website_url":"${url}","response_type":"ERROR","response_code":"${String(e.errno)}","response_details":"${String(e.syscall)}"}`)
 			}
 		}
 	}
-	fs.appendFile("JS_report.txt", "\n---\n", function(err) {if (err) throw err})
+	fs.appendFile(report_file, '[' + String(json_object) + ']', function(err) {if (err) throw err})
 	console.log('\nFinished at ' + String(new Date().getHours()) + 'h' + String(new Date().getMinutes()) + 'm')
 }
 
@@ -35,42 +36,40 @@ function url_generator(domains, mode, log) {
 
 function fetch(url, options = {}) {
 	return new Promise((resolve, reject) => {
-		if (!url) return reject(new Error('URL was not provided'))
+		if (!url) return reject(new Error('URL was not provided')) //Cannot happen, line may end up getting removed
 
-		const { body, method = 'GET', ...restOptions } = options
+		const {body, method = 'GET', ...restOptions} = options
 		const client = url.startsWith('https') ? https : http
-		const request = client.request(url, { method, ...restOptions }, (res) => {
-			let chunks = ''
+		const request = client.request(url, {method, ...restOptions}, (res) => {
 			res.setEncoding('utf8')
+			let chunks = ''
 			res.on('data', (chunk) => {
 				chunks += chunk
 			})
 			res.on('end', () => {
-				resolve({ statusCode: res.statusCode, body: chunks })
+				resolve({statusCode: res.statusCode, statusMessage: res.statusMessage})
 			})
 		})
 		request.on('error', (err) => {
 			reject(err)
 		})
-		if (body) {
-			request.setHeader('Content-Length', body.length)
-			request.write(body)
-		}
 		request.end()
 	})
 }
 
 const times = process.argv.indexOf('-t') > -1 ? Math.round(Number(process.argv[process.argv.indexOf('-t') + 1])) : 3000
 if (isNaN(times)) return console.error("-t argument expected a number!")
-const domains = process.argv.indexOf('-d') > -1 ? process.argv[process.argv.indexOf('-d') + 1].split(',') : ['.com', '.net', '.edu', '.gov', '.cn', '.org']
+const domains = process.argv.indexOf('-d') > -1 ? process.argv[process.argv.indexOf('-d') + 1].split(',') : ['.co', '.com', '.net', '.edu', '.gov', '.cn', '.org', '.cc']
 const mode = process.argv.indexOf('-m') > -1 ? process.argv[process.argv.indexOf('-m') + 1].split(',') : ['http']
 const log = process.argv.indexOf('-l') > -1
 
+const report_file = "JS_report_" + String(new Date().getUTCDate()) + String(new Date().getHours()) + String(new Date().getMinutes()) + ".json"
+
 process.stdout.write(`\nI am going to look for images through ${times} random URLs with the following domains: `)
 console.log(domains)
 process.stdout.write("These URLs will use the following protocols: ")
 console.log(mode)
 console.log('Started at ' + String(new Date().getHours()) + 'h' + String(new Date().getMinutes()) + 'm\n')
 
-fs.appendFile("JS_report.txt", "---", function(err) {if (err) throw err})
+fs.open(report_file, "w", function(err) {if (err) throw err})
 main_loop()

Python/index.py

@@ -4,19 +4,20 @@ import datetime
 import urllib.request
 
 def main_loop():
+	json_object = []
 	for i in range(times):
 		url = url_generator(domains, log)
 		try:
 			response = urllib.request.urlopen(url)
 			print(url + " exists!")
-			f.write("\n" + url + " | STATUS_CODE: " + str(response.getcode()))
+			json_object.append('{"website_url":"' + url + '","response_type":"SUCCESS","response_code":"' + str(response.getcode()) + '","response_details":"Server seems to be ' + str(response.info()["Server"]) + '"}')
 		except Exception as e:
 			if "[Errno 11001]" in str(e): continue
-			if "[" in str(e) and "]" in str(e): e = str(e)[str(e).index("[") + 1:str(e).index("]")] + ": " + str(e)[str(e).index("]") + 2:][:-1]
 			print(url + " exists!")
-			f.write("\n" + url + " | ERROR_CODE: " + str(e))
+			err_code = str(e)[str(e).index("[") + 1:str(e).index("]")] if "[" in str(e) and "]" in str(e) else "NONE FOUND"
+			json_object.append('{"website_url":"' + url + '","response_type":"ERROR","response_code":"' + err_code + '","response_details":"' + str(e).replace("\\", "") + '"}')
 
-	f.write("\n---\n")
+	f.write(str(json_object).replace("'", ""))
 	f.close()
 	print("Finished at " + str(datetime.datetime.now().time())[0:5].replace(":", "h") + "m")
 
@@ -35,7 +36,7 @@ try:
 except:
 	print("-t argument expected a number!")
 	sys.exit()
-domains = sys.argv[sys.argv.index('-d') + 1] if '-d' in sys.argv else ['.com', '.net', '.edu', '.gov', '.cn', '.org']
+domains = sys.argv[sys.argv.index('-d') + 1] if '-d' in sys.argv else ['.co', '.com', '.net', '.edu', '.gov', '.cn', '.org', '.cc']
 mode = sys.argv[sys.argv.index('-m') + 1].split(",") if '-m' in sys.argv else ['http']
 log = '-l' in sys.argv
 
@@ -43,6 +44,5 @@ print("\nI am going to look for images through " + str(times) + " random URLs wi
 print("These URLs use the following protocols: " + str(mode))
 print("Started at " + str(datetime.datetime.now().time())[0:5].replace(":", "h") + "m")
 
-f = open("PY_report.txt", "a+")
-f.write("---")
+f = open("PY_report_" + str(datetime.datetime.now().strftime("%d%H%M")) + ".json", "a+")
 main_loop()

README.md

@@ -1,6 +1,6 @@
 # Website-Finder
 
-Website-Finder is a collection of light scripts written in various programming languages without the need for external libraries that finds websites of all sorts for you and make reports of that in the form of automatically generated text files.
+Website-Finder is a collection of light scripts written in various programming languages without the need for external libraries that finds websites of all sorts for you and make reports of that in the form of automatically generated json files.
 
 ## REQUIREMENTS
 
@@ -53,3 +53,7 @@ A: As far as I am aware, nope! However, the reports are generated differently de
 
 Q: Why does the "-m" argument defaults to "http" rather than "https"?  
 A: Requests in "http" receive more status codes than error codes compared to "https". I suspect it's because some websites don't support "https" very well, even in the current year.
+
+## TO DO
+
+Second-level domains

Ruby/index.rb

@@ -1,21 +1,23 @@
 require 'net/http'
+require 'json'
 
 def main_loop
+	json_object = []
 	TIMES.times do
 		url = url_generator(DOMAINS, MODE)
 		puts(url) if LOG
 		begin
 			response = Net::HTTP.get_response(URI(url))
 			puts("#{url} exists!")
-			File.open("RB_report.txt", 'a+') {|f| f.write("\n#{url} | STATUS_CODE: #{response.code} | DETAILS: #{response.message}")}
+			json_object << Hash["website_url" => url, "response_type" => "SUCCESS", "response_code" => response.code, "response_details" => response.message]
 		rescue Exception => e # Unlike JS/PY, the number of existing websites that raise exceptions is small
 			if e.class != SocketError
 				puts("#{url} exists!")
-				File.open("RB_report.txt", 'a+') {|f| f.write("\n#{url} | ERROR_CODE: #{e.class.to_s} | DETAILS: #{e.to_s}")}
+				json_object << Hash["website_url" => url, "response_type" => "ERROR", "response_code" => e.class.to_s, "response_details" => e.to_s]
 			end
 		end
 	end
-	File.open("RB_report.txt", 'a+') {|f| f.write("\n---\n")}
+	File.open(REPORT_FILE, 'a+') {|f| f << json_object.to_json} if json_object.any?
 	puts("Finished at #{Time.new.hour}h#{Time.new.min}m\n")
 end
 
@@ -27,13 +29,15 @@ def url_generator(domains, mode)
 end
 
 TIMES = ARGV.include?('-t') ? ARGV[ARGV.index("-t") + 1].to_i : 3000
-DOMAINS = ARGV.include?('-d') ? ARGV[ARGV.index("-d") + 1].split(",") : ['.com', '.net', '.edu', '.gov', '.cn', '.org']
+DOMAINS = ARGV.include?('-d') ? ARGV[ARGV.index("-d") + 1].split(",") : ['.co', '.com', '.net', '.edu', '.gov', '.cn', '.org', '.cc']
 MODE = ARGV.include?('-m') ? ARGV[ARGV.index("-m") + 1].split(",") : ['http']
 LOG = ARGV.index("-l").class == Integer
 
+REPORT_FILE = "RB_report_#{Time.new.day}#{Time.new.hour}#{Time.new.min}.json"
+
 puts("\nI am going to look for images through #{TIMES} random URLs with the following domains: #{DOMAINS}")
 puts("These URLs will use the following protocols: #{MODE}")
 puts("Started at #{Time.new.hour}h#{Time.new.min}m\n")
 
-File.open("RB_report.txt", 'a+') {|f| f.write("---")}
+File.open(REPORT_FILE, 'a+')
 main_loop