mercury-parser/src/extractors/custom/www.fortinet.com/index.test.js

import assert from 'assert';
import URL from 'url';
import cheerio from 'cheerio';

import Mercury from 'mercury';
import getExtractor from 'extractors/get-extractor';
import { excerptContent } from 'utils/text';

const fs = require('fs');

describe('WwwFortinetComExtractor', () => {
  describe('initial test case', () => {
    let result;
    let url;
    beforeAll(() => {
      url =
        'https://www.fortinet.com/blog/threat-research/defeating-an-android-packer-with-frida.html';
      const html = fs.readFileSync(
        './fixtures/www.fortinet.com/1546954846985.html'
      );
      result = Mercury.parse(url, { html, fallback: false });
    });

    it('is selected properly', () => {
      // This test should be passing by default.
      // It sanity checks that the correct parser
      // is being selected for URLs from this domain
      const extractor = getExtractor(url);
      assert.equal(extractor.domain, URL.parse(url).hostname);
    });

    it('returns the title', async () => {
      // To pass this test, fill out the title selector
      // in ./src/extractors/custom/www.fortinet.com/index.js.
      const { title } = await result;

      // Update these values with the expected values from
      // the article.
      assert.equal(
        title,
        'How-to Guide: Defeating an Android Packer with FRIDA'
      );
    });

    it('returns the author', async () => {
      // To pass this test, fill out the author selector
      // in ./src/extractors/custom/www.fortinet.com/index.js.
      const { author } = await result;

      // Update these values with the expected values from
      // the article.
      assert.equal(author, 'Dario Durando');
    });

    it('returns the date_published', async () => {
      // To pass this test, fill out the date_published selector
      // in ./src/extractors/custom/www.fortinet.com/index.js.
      const { date_published } = await result;

      // Update these values with the expected values from
      // the article.
      assert.equal(date_published, '2018-11-02T07:00:00.000Z');
    });

    it('returns the lead_image_url', async () => {
      // To pass this test, fill out the lead_image_url selector
      // in ./src/extractors/custom/www.fortinet.com/index.js.
      const { lead_image_url } = await result;

      // Update these values with the expected values from
      // the article.
      assert.equal(
        lead_image_url,
        'https://www.fortinet.com/content/dam/fortinet-blog/article-images/defeating_an_android_packer_with_frida/frida_02.png'
      );
    });

    it('returns the content', async () => {
      // To pass this test, fill out the content selector
      // in ./src/extractors/custom/www.fortinet.com/index.js.
      // You may also want to make use of the clean and transform
      // options.
      const { content } = await result;

      const $ = cheerio.load(content || '');

      const first13 = excerptContent(
        $('*')
          .first()
          .text(),
        13
      );

      // Update these values with the expected values from
      // the article.
      assert.equal(
        first13,
        'A FortiGuard Labs How-To Guide for Cybersecurity Threat Researchers Here at FortiGuard Labs'
      );
    });

    it('converts lazy-loaded noscript images to figures', async () => {
      const { content } = await result;

      const $ = cheerio.load(content || '');

      const $lazyImages = $('noscript img');
      const $figures = $('figure img');

      // there were six lazy-loaded images
      // noscript tags should be replaced by figures
      assert.equal($lazyImages.length, 0);
      assert.equal($figures.length, 6);
    });
  });
});