|
|
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');
|
|
|
|
|
|
// Rename CustomExtractor
|
|
|
describe('PoliticoExtractor', () => {
|
|
|
describe('initial test case', () => {
|
|
|
let result;
|
|
|
let url;
|
|
|
beforeAll(() => {
|
|
|
url =
|
|
|
'http://www.politico.com/story/2016/10/who-will-win-the-vp-debate-229079?lo=ut_a1';
|
|
|
const html = fs.readFileSync(
|
|
|
'./fixtures/www.politico.com/1475617690069.html'
|
|
|
);
|
|
|
result = Mercury.parse(url, html, { fallback: false });
|
|
|
});
|
|
|
|
|
|
it('is selected properly', async () => {
|
|
|
// To pass this test, rename your extractor in
|
|
|
// ./src/extractors/custom/www.politico.com/index.js
|
|
|
// (e.g., CustomExtractor => NYTimesExtractor)
|
|
|
// then add your new extractor to
|
|
|
// src/extractors/all.js
|
|
|
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.politico.com/index.js.
|
|
|
const { title } = await result;
|
|
|
|
|
|
// Update these values with the expected values from
|
|
|
// the article.
|
|
|
assert.equal(title, 'Insiders: Trump will sink Pence in VP debate');
|
|
|
});
|
|
|
|
|
|
it('returns the author', async () => {
|
|
|
// To pass this test, fill out the author selector
|
|
|
// in ./src/extractors/custom/www.politico.com/index.js.
|
|
|
const { author } = await result;
|
|
|
|
|
|
// Update these values with the expected values from
|
|
|
// the article.
|
|
|
assert.equal(author, 'Steven Shepard');
|
|
|
});
|
|
|
|
|
|
it('returns the date_published', async () => {
|
|
|
// To pass this test, fill out the date_published selector
|
|
|
// in ./src/extractors/custom/www.politico.com/index.js.
|
|
|
const { date_published } = await result;
|
|
|
|
|
|
// Update these values with the expected values from
|
|
|
// the article.
|
|
|
assert.equal(date_published, '2016-10-04T09:07:00.000Z');
|
|
|
});
|
|
|
|
|
|
it('returns the lead_image_url', async () => {
|
|
|
// To pass this test, fill out the lead_image_url selector
|
|
|
// in ./src/extractors/custom/www.politico.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://static.politico.com/0f/e7/5ee9a89044d1a01f74140bcd5b9e/caucus-vp-preview.jpg'
|
|
|
);
|
|
|
});
|
|
|
|
|
|
it('returns the content', async () => {
|
|
|
// To pass this test, fill out the content selector
|
|
|
// in ./src/extractors/custom/www.politico.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,
|
|
|
'Tim Kaine isn’t Mike Pence’s only opponent Tuesday night in the only debate'
|
|
|
);
|
|
|
});
|
|
|
});
|
|
|
});
|