how to crawl all the internal url's of a website using crawler?

Question

I wanted to use a crawler in node.js to crawl all the links in a website (internal links) and get the title of each page , i saw this plugin on npm crawler, if i check the docs there is the following example:

var Crawler = require("crawler");

var c = new Crawler({
   maxConnections : 10,
   // This will be called for each crawled page
   callback : function (error, res, done) {
       if(error){
           console.log(error);
       }else{
           var $ = res.$;
           // $ is Cheerio by default
           //a lean implementation of core jQuery designed specifically for the server
           console.log($("title").text());
       }
       done();
   }
});

// Queue just one URL, with default callback
c.queue('http://balenol.com');

But what i really want is to crawl all the internal urls in the site and is the inbuilt into this plugin or does this need to be written seperately ? i don't see any option in the plugin to visit all the links in a site , is this possible ?

Answer 1

The following snippet crawls all URLs in every URL it finds.

const Crawler = require("crawler");

let obselete = []; // Array of what was crawled already

let c = new Crawler();

function crawlAllUrls(url) {
    console.log(`Crawling ${url}`);
    c.queue({
        uri: url,
        callback: function (err, res, done) {
            if (err) throw err;
            let $ = res.$;
            try {
                let urls = $("a");
                Object.keys(urls).forEach((item) => {
                    if (urls[item].type === 'tag') {
                        let href = urls[item].attribs.href;
                        if (href && !obselete.includes(href)) {
                            href = href.trim();
                            obselete.push(href);
                            // Slow down the
                            setTimeout(function() {
                                href.startsWith('http') ? crawlAllUrls(href) : crawlAllUrls(`${url}${href}`) // The latter might need extra code to test if its the same site and it is a full domain with no URI
                            }, 5000)

                        }
                    }
                });
            } catch (e) {
                console.error(`Encountered an error crawling ${url}. Aborting crawl.`);
                done()

            }
            done();
        }
    })
}

crawlAllUrls('https://github.com/evyatarmeged/');

Answer 2

In the above code, just change the following to get the internal links of a website...

from

href.startsWith('http') ? crawlAllUrls(href) : crawlAllUrls(`${url}${href}`)

to

href.startsWith(url) ? crawlAllUrls(href) : crawlAllUrls(`${url}${href}`)