Error: getaddrinfo ENOTFOUND parishackers.org parishackers.org:80 - node.js

Question

Error: getaddrinfo ENOTFOUND parishackers.org parishackers.org:80 error happens.
I wrote the codes,
var Crawler = require("node-webcrawler");
var url = require('url');
var c = new Crawler({
maxConnections : 10,
// This will be called for each crawled page
callback : function (error, result, $) {
// $ is Cheerio by default
//a lean implementation of core jQuery designed specifically for the server
if(error){
console.log(error);
}else{
console.log($("title").text());
}
}
});
// Queue just one URL, with default callback
c.queue('http://www.amazon.com');
// Queue a list of URLs
c.queue(['http://www.google.com/','http://www.yahoo.com']);
// Queue URLs with custom callbacks & parameters
c.queue([{
uri: 'http://parishackers.org/',
jQuery: false,
// The global callback won't be called
callback: function (error, result) {
if(error){
console.log(error);
}else{
console.log('Grabbed', result.body.length, 'bytes');
}
}
}]);
// Queue some HTML code directly without grabbing (mostly for tests)
c.queue([{
html: '<p>This is a <strong>test</strong></p>'
}]);
but when I run the code,
Google
Yahoo
Amazon.com: Online Shopping for Electronics, Apparel, Computers, Books, DVDs & more
{ Error: getaddrinfo ENOTFOUND parishackers.org parishackers.org:80
at errnoException (dns.js:50:10)
at GetAddrInfoReqWrap.onlookup [as oncomplete] (dns.js:92:26)
code: 'ENOTFOUND',
errno: 'ENOTFOUND',
syscall: 'getaddrinfo',
hostname: 'parishackers.org',
host: 'parishackers.org',
port: 80 }
error happens. I think program scrape data part of it, but I do not know why program can do it completely. I installed library like npm install node-webcrawler. I read another site, so I think this error happens because of wrong link, right? How should I fix this? What is wrong in my code?

Answer 1

Error (getaddrinfo ENOTFOUND parishackers.org parishackers.org:80) is throwed because of invalid domain http://parishackers.org. Use valid url links, your node webcrawler will works like a charm. Modified the snippet for your reference
var Crawler = require("node-webcrawler");
var url = require('url');
var c = new Crawler({
maxConnections : 10,
// This will be called for each crawled page
callback : function (error, result, $) {
// $ is Cheerio by default
//a lean implementation of core jQuery designed specifically for the server
if(error){
console.log(error);
}else{
console.log($("title").text());
}
}
});
// Queue just one URL, with default callback
c.queue('http://www.amazon.com');
// Queue a list of URLs
c.queue(['http://www.google.com/','http://www.yahoo.com']);
// Queue URLs with custom callbacks & parameters
c.queue([{
uri: 'http://www.amazon.com',
jQuery: false,
// The global callback won't be called
callback: function (error, result) {
if(error){
console.log(error);
}else{
console.log('Grabbed', result.body.length, 'bytes');
}
}
}]);
// Queue some HTML code directly without grabbing (mostly for tests)
c.queue([{
html: '<p>This is a <strong>test</strong></p>'
}]);