Here are two functions that make a request for a given URL and then takes the response body (HTML) and loads it into the cheerio library:
scrapeListing.js
var fs = require('fs');
var request = require('request');
var cheerio = require('cheerio');
var Listing = require('./listingClass.js');
var url = 'http://www.google.com';
var getResponseBody = (url) => {
return new Promise((resolve, reject) => {
request({
headers: {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:24.0) Gecko/20100101 Firefox/24.0',
'Content-Type': 'application/x-www-form-urlencoded'
},
method: 'GET',
url: url
},
(err, response, body) => {
if (err) {
reject({err})
}
else {
resolve({err, response, body})
}
});
})
};
var getCheerioInstance = (html) => {
if (html){
return cheerio.load(html);
}
else throw Error('no HTML body for cheerio to load')
};
module.exports = {
getResponseBody: getResponseBody,
getCheerioInstance: getCheerioInstance
};
Here is a class for listing objects which have methods that use cheerio to parse data from HTML of the listing page.
Should the class only contain methods associated with parsing the HTML or should the class incorporate the above more general functions as methods? Or is it better still to make the above functions methods of a new class that gets the response for a URL?
listingClass.js
module.exports = class Listing {
constructor(url, location){
this.url = url;
this.location = location;
}
// example method that retrieves data from html response
getTitle(){
var title = this.html('div.js-details-column>div').contents(":not(:empty)").first().text();
this.title = title
}
}