spiderweb

0.0.14 • Public • Published

Spiderweb

Crawl multiple domains using one or more entry URLs.

Installation

npm install spiderweb
var Spiderweb = require('spiderweb'),
	urls, options, spiderweb;

urls = ['bar.com', 'foo.bar.com'];

options = {
	strictSSL: false,
	images: true,
	excludedUrls: ['*biz.foo.com*', '*/admin/*']
};

spiderweb = new Spiderweb(urls, options);

spider.pageHandler = function(err, resp, body, entry) {
	console.log(entry.url);
	Spiderweb.prototype.pageHandler.apply(this, arguments);
}

spiderweb.start(function(err, log) {
	if (err) {
		console.log('ERROR: ', err)
	}

	if (log.length) {
		console.log('DONE: ' + log.length + ' page errors');
	}
	else {
		console.log('DONE: no errors');
	}
});

Readme

Keywords

none

Package Sidebar

Install

npm i spiderweb

Weekly Downloads

0

Version

0.0.14

License

none

Last publish

Collaborators

  • jmerrick