UNPKG

sitebot

Version:

SiteBot is an event driven website crawler.

25 lines (18 loc) 565 B
const Crawler = require("sitebot") const crawler = new Crawler({ url: "http://the-internet.herokuapp.com/status_codes" }) const URLs = {} crawler.on("end", function() { console.log(URLs) }) crawler.on("response", function(queueItem, response) { if (!URLs[response.statusCode]) URLs[response.statusCode] = [] URLs[response.statusCode].push(queueItem.href) }) crawler.on("error", function(queueItem, error) { if (!URLs[error]) URLs[error] = [] URLs[error].push({ href: queueItem.href, referrer: queueItem.referrer.href }) }) crawler.start()