Media title/image universal scrapper with scraperjs promised

media_scraper.js

/*
 * Bundle: Helpers - Scraper
 * Project: Readlist - Server
 * Author: Quentin de Quelen <[email protected]>
 * Copyright: 2015, Readlist
 */
 
 /*
  *
  *Need 'scraperjs & url'
  */

"use strict";

const scraperjs = require('scraperjs');
const url = require('url');


exports.scrapUrl = function(url) {
	var res = {
		"title": '',
		"image": ''
	}

	var scrapFacebook = function($) {
		return new Promise(function(resolve, reject) {
			try {
				res.title = $('meta[property="og:title"]').attr('content');
				if ($('meta[property="og:image"]').attr('content').length > 0)
					res.image = $('meta[property="og:image"]').attr('content');
				reject();
			} catch (err) {
				resolve($);
			}
		});
	};

	var scrapTwitter = function($) {
		return new Promise(function(resolve, reject) {
			try {
				res.title = $('meta[property="twitter:title"]').attr('content');
				if ($('meta[property="twitter:image"]').attr('content').length > 0)
					res.image = $('meta[property="twitter:image"]').attr('content');
				reject();
			} catch (err) {
				resolve($);
			}
		});
	};

	var scrapArticleH1 = function($) {
		return new Promise(function(resolve, reject) {
			try {
				res.title = $('.article h1').text();
				res.image = $('.article img').attr("src");
				if (res.title.length == 0) resolve($);
				else reject();
			} catch (err) {
				resolve($);
			}
		});
	};

	var scrapArticleH2 = function($) {
		return new Promise(function(resolve, reject) {
			try {
				res.title = $('article h2').text();
				res.image = $('article img').attr("src");
				if (res.title.length == 0) resolve($);
				else reject();
			} catch (err) {
				resolve($);
			}
		});
	};

	var scrapMainH2 = function($) {
		return new Promise(function(resolve, reject) {
			try {
				res.title = $('#main h2').text();
				res.image = $('#main img').attr("src");
				if (res.title.length == 0) resolve($);
				else reject();
			} catch (err) {
				resolve($);
			}
		});
	};

	return new Promise(function(resolve, reject) {
		scraperjs.StaticScraper.create(url)
			.scrape(function($) {
				scrapFacebook($)
					.then(scrapFacebook)
					.then(scrapTwitter)
					.then(scrapArticleH1)
					.then(scrapArticleH2)
					.then(scrapMainH2)
					.then(function($) {
						reject("Article not found");
					})
					.catch(function() {
						resolve(res);
					});
			});
	});
};