|
|
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('PagesixComExtractor', () => {
|
|
|
describe('initial test case', () => {
|
|
|
let result;
|
|
|
let url;
|
|
|
beforeAll(() => {
|
|
|
url =
|
|
|
'http://pagesix.com/2016/12/19/sofia-vergara-and-nick-loebs-embryo-drama-taking-a-detour/';
|
|
|
const html = fs.readFileSync('./fixtures/pagesix.com/1482254007534.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/pagesix.com/index.js.
|
|
|
const { title } = await result;
|
|
|
|
|
|
// Update these values with the expected values from
|
|
|
// the article.
|
|
|
assert.equal(
|
|
|
title,
|
|
|
'Sofía Vergara and Nick Loeb’s embryo drama taking a detour'
|
|
|
);
|
|
|
});
|
|
|
|
|
|
it('returns the author', async () => {
|
|
|
// To pass this test, fill out the author selector
|
|
|
// in ./src/extractors/custom/pagesix.com/index.js.
|
|
|
const { author } = await result;
|
|
|
|
|
|
// Update these values with the expected values from
|
|
|
// the article.
|
|
|
assert.equal(author, 'Oli Coleman');
|
|
|
});
|
|
|
|
|
|
it('returns the date_published', async () => {
|
|
|
// To pass this test, fill out the date_published selector
|
|
|
// in ./src/extractors/custom/pagesix.com/index.js.
|
|
|
const { date_published } = await result;
|
|
|
|
|
|
// Update these values with the expected values from
|
|
|
// the article.
|
|
|
assert.equal(date_published, '2016-12-20T00:08:44.000Z');
|
|
|
});
|
|
|
|
|
|
it('returns the lead_image_url', async () => {
|
|
|
// To pass this test, fill out the lead_image_url selector
|
|
|
// in ./src/extractors/custom/pagesix.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://nyppagesix.files.wordpress.com/2016/12/sofia-vergara4.jpg?quality=90&strip=all&w=1200'
|
|
|
);
|
|
|
});
|
|
|
|
|
|
it('returns the content', async () => {
|
|
|
// To pass this test, fill out the content selector
|
|
|
// in ./src/extractors/custom/pagesix.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,
|
|
|
'Nick Loeb and Sofia Vergara Shutterstock / Getty Images (Composite) In the latest'
|
|
|
);
|
|
|
});
|
|
|
});
|
|
|
});
|