mercury-parser/src/extractors/custom/www.al.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('WwwAlComExtractor', () => {
  describe('initial test case', () => {
    let result;
    let url;
    beforeAll(() => {
      url =
        'http://www.al.com/news/birmingham/index.ssf/2016/12/two_arrested_in_multi-state_de.html#incart_river_home';
      const html = fs.readFileSync('./fixtures/www.al.com/1482445422101.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.al.com/index.js.
      const { title } = await result;

      // Update these values with the expected values from
      // the article.
      assert.equal(
        title,
        'Two arrested in multi-state debit card skimming scheme'
      );
    });

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

      // Update these values with the expected values from
      // the article.
      assert.equal(author, 'Mike Cason | mcason@al.com');
    });

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

      // Update these values with the expected values from
      // the article.
      assert.equal(date_published, '2016-12-22T19:47:00.000Z');
    });

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

      // Update these values with the expected values from
      // the article.
      assert.equal(
        lead_image_url,
        'http://image.al.com/home/bama-media/width620/img/news_birmingham_impact/photo/21753198-standard.jpg'
      );
    });

    it('returns the content', async () => {
      // To pass this test, fill out the content selector
      // in ./src/extractors/custom/www.al.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,
        "Jake Frith, special agent with the Alabama Attorney General's office, talks about an"
      );
    });
  });
});