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('WwwNjComExtractor', () => { describe('initial test case', () => { let result; let url; beforeAll(() => { url = 'http://www.nj.com/essex/index.ssf/2016/12/man_sentenced_for_stealing_millions_from_nj_atms_i.html#incart_river_home'; const html = fs.readFileSync('./fixtures/www.nj.com/1481666201503.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.nj.com/index.js. const { title } = await result; // Update these values with the expected values from // the article. assert.equal( title, 'Man sentenced for stealing millions in elaborate N.J. ATM skimming scheme' ); }); it('returns the author', async () => { // To pass this test, fill out the author selector // in ./src/extractors/custom/www.nj.com/index.js. const { author } = await result; // Update these values with the expected values from // the article. assert.equal(author, 'Rajeev Dhir | NJ Advance Media for NJ.com'); }); it('returns the date_published', async () => { // To pass this test, fill out the date_published selector // in ./src/extractors/custom/www.nj.com/index.js. const { date_published } = await result; // Update these values with the expected values from // the article. assert.equal(date_published, '2016-12-13T21:51:00.000Z'); }); it('returns the lead_image_url', async () => { // To pass this test, fill out the lead_image_url selector // in ./src/extractors/custom/www.nj.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.nj.com/home/njo-media/width620/img/njcom_photos/photo/2016/12/08/21671718-large.png' ); }); it('returns the content', async () => { // To pass this test, fill out the content selector // in ./src/extractors/custom/www.nj.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, 'NEWARK -- A Romanian native was sentenced to 57 months on Tuesday for' ); }); }); });