You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
113 lines
3.6 KiB
JavaScript
113 lines
3.6 KiB
JavaScript
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('WwwCnetComExtractor', () => {
|
|
describe('initial test case', () => {
|
|
let result;
|
|
let url;
|
|
beforeAll(() => {
|
|
url =
|
|
'https://www.cnet.com/news/seven-mobile-trends-to-look-for-in-2017/';
|
|
const html = fs.readFileSync(
|
|
'./fixtures/www.cnet.com/1482428196806.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.cnet.com/index.js.
|
|
const { title } = await result;
|
|
|
|
// Update these values with the expected values from
|
|
// the article.
|
|
assert.equal(title, 'Seven mobile trends to look for in 2017');
|
|
});
|
|
|
|
it('returns the author', async () => {
|
|
// To pass this test, fill out the author selector
|
|
// in ./src/extractors/custom/www.cnet.com/index.js.
|
|
const { author } = await result;
|
|
|
|
// Update these values with the expected values from
|
|
// the article.
|
|
assert.equal(author, 'Marguerite Reardon');
|
|
});
|
|
|
|
it('returns the date_published', async () => {
|
|
// To pass this test, fill out the date_published selector
|
|
// in ./src/extractors/custom/www.cnet.com/index.js.
|
|
const { date_published } = await result;
|
|
|
|
// Update these values with the expected values from
|
|
// the article.
|
|
assert.equal(date_published, '2016-12-22T13:00:00.000Z');
|
|
});
|
|
|
|
it('returns the dek', async () => {
|
|
// To pass this test, fill out the dek selector
|
|
// in ./src/extractors/custom/www.cnet.com/index.js.
|
|
const { dek } = await result;
|
|
|
|
// Update these values with the expected values from
|
|
// the article.
|
|
assert.equal(
|
|
dek,
|
|
'An anti-regulation, pro-dealmaking US president could make for an interesting year for wireless and broadband companies.'
|
|
);
|
|
});
|
|
|
|
it('returns the lead_image_url', async () => {
|
|
// To pass this test, fill out the lead_image_url selector
|
|
// in ./src/extractors/custom/www.cnet.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://cnet2.cbsistatic.com/img/eW0A_hGjyVcT0oRB_23SDCOdEGU=/670x503/2016/12/16/48966e5f-87df-4915-ad68-ed70cdd37fdd/gettyimages-537252007.jpg'
|
|
);
|
|
});
|
|
|
|
it('returns the content', async () => {
|
|
// To pass this test, fill out the content selector
|
|
// in ./src/extractors/custom/www.cnet.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,
|
|
'Faster networks, more "free data" and a dismantling of net neutrality rules could'
|
|
);
|
|
});
|
|
});
|
|
});
|