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('WwwQdailyComExtractor', () => { describe('initial test case', () => { let result; let url; beforeAll(() => { url = 'http://www.qdaily.com/articles/38282.html'; const html = fs.readFileSync( './fixtures/www.qdaily.com/1488417691505.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.qdaily.com/index.js. const { title } = await result; // Update these values with the expected values from // the article. assert.equal(title, '这个约会软件,想用你和对方的相似好恶来帮你找对象'); }); it('returns the author', async () => { // To pass this test, fill out the author selector // in ./src/extractors/custom/www.qdaily.com/index.js. const { author } = await result; // Update these values with the expected values from // the article. assert.equal(author, '谢若含'); }); it('returns the date_published', async () => { // To pass this test, fill out the date_published selector // in ./src/extractors/custom/www.qdaily.com/index.js. const { date_published } = await result; // Update these values with the expected values from // the article. assert.equal(date_published, '2017-03-01T06:27:02.000Z'); }); it('returns the dek', async () => { // To pass this test, fill out the dek selector // in ./src/extractors/custom/www.qdaily.com/index.js. const { dek } = await result; // Update these values with the expected values from // the article. assert.equal(dek, '人们对于讨厌的事物总是能很有共同话题...'); }); it('returns the lead_image_url', async () => { // To pass this test, fill out the lead_image_url selector // in ./src/extractors/custom/www.qdaily.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://img.qdaily.com/article/article_show/20170228225314Dh4XvM63TzkWPNHJ.png?imageMogr2/auto-orient/thumbnail/!755x450r/gravity/Center/crop/755x450/quality/85/format/jpg/ignore-error/1' ); }); it('returns the content', async () => { // To pass this test, fill out the content selector // in ./src/extractors/custom/www.qdaily.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 first3 = excerptContent( $('*') .first() .text(), 3 ); // Update these values with the expected values from // the article. assert.equal( first3, '无法忍受乡村音乐? 对某某明星迷之厌恶? 讨厌特朗普?不爱自拍?' ); }); }); });