Last active
August 29, 2015 14:05
-
-
Save averagesecurityguy/666658c8ad41ca68ebc6 to your computer and use it in GitHub Desktop.
URL Scanner in Node
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var fs = require('fs'); | |
var readline = require('readline'); | |
var http = require('http'); | |
var timeout = 2; // Timeout in seconds. | |
var rd = readline.createInterface({ | |
input: fs.createReadStream('tenthousand_urls.txt'), | |
output: process.stdout, | |
terminal: false | |
}); | |
function processResponse(res) { | |
var code = res.statusCode; | |
var requestedHost = res.req.getHeader('host'); | |
var redirectedHost = res.headers['location']; | |
if (code >= 200 && code <= 299) { | |
console.log('2XX: ' + requestedHost); | |
} else if (code >= 300 && code <= 399) { | |
console.log('3XX: ' + requestedHost + ' -> ' + redirectedHost); | |
} else if (code >= 400 && code <= 499) { | |
console.log('4XX: ' + requestedHost); | |
} else if (code >= 500 && code <= 599) { | |
console.log('5XX: ' + requestedHost); | |
} else { | |
console.log(code + ': ' + requestedHost); | |
} | |
} | |
function getUrl(hostname, port) { | |
var options = {method: 'HEAD', hostname: hostname, port: port}; | |
var req = http.request(options); | |
req.on('response', processResponse); | |
req.on('error', function(e) {}); | |
req.setTimeout(timeout * 1000, req.abort); | |
req.end(); | |
} | |
rd.on('line', function(line) { | |
switch(line) { | |
case line[0] === '#': | |
break; | |
case line === '': | |
break; | |
case line.slice(0, 4) !== 'http': | |
break; | |
default: | |
if (line.slice(0, 5) === 'http:') { | |
getUrl(line.slice(7), 80); | |
} | |
if (line.slice(0, 5) === 'https') { | |
getUrl(line.slice(8), 443); | |
} | |
} | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment