[node.js]what libraries we can use for crawling website : cheerio

I’ll use libraries which are “request” and “cheerio”.

npm install request
npm install cheerio

“request” allows us to get data from target URL.
And then, “cheerio” allows us to analyse the retrieved data with DOM. Sample is following.

#!/usr/bin/env node

var request = require("request");
var cheerio = require("cheerio");

var request_url = "http://www.google.com";

request({url: request_url}, function(error, response, body)
{
  if (!error && response.statusCode == 200) {
    $ = cheerio.load(body);

    var url = response.request.href;
    var title = $("title").text();

    console.log(url);
    console.log(title);
  } else {
    console.log(response.statusCode);
  }
});