feat: add fastcompany custom parser (#191)
* feat: add fastcompany custom parser * fix: eslint error * fix: test for date_published * feat: add fastcompany custom parser * fix: eslint error * fix: test for date_published * fix: fs importpull/188/head^2
parent
199fe70b03
commit
9b36003b62
File diff suppressed because one or more lines are too long
@ -0,0 +1,39 @@
|
||||
export const WwwFastcompanyComExtractor = {
|
||||
domain: 'www.fastcompany.com',
|
||||
|
||||
title: {
|
||||
selectors: [
|
||||
'h1',
|
||||
],
|
||||
},
|
||||
|
||||
author: {
|
||||
selectors: [
|
||||
'.post__by',
|
||||
],
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: [
|
||||
['meta[name="article:published_time"]', 'value'],
|
||||
],
|
||||
},
|
||||
|
||||
dek: {
|
||||
selectors: [
|
||||
'.post__deck',
|
||||
],
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [
|
||||
['meta[name="og:image"]', 'value'],
|
||||
],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: [
|
||||
'.post__article',
|
||||
],
|
||||
},
|
||||
};
|
@ -0,0 +1,98 @@
|
||||
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('WwwFastcompanyComExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url =
|
||||
'https://www.fastcompany.com/3067012/the-only-five-email-folders-your-inbox-will-ever-need';
|
||||
const html =
|
||||
fs.readFileSync('./fixtures/www.fastcompany.com/1547124373499.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.fastcompany.com/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(title, 'The Only Five Email Folders Your Inbox Will Ever Need');
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/www.fastcompany.com/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(author, 'Zach Hanlon');
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/www.fastcompany.com/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, '2017-01-09T05:00:00.000Z');
|
||||
});
|
||||
|
||||
it('returns the dek', async () => {
|
||||
// To pass this test, fill out the dek selector
|
||||
// in ./src/extractors/custom/www.fastcompany.com/index.js.
|
||||
const { dek } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(dek, 'Stop “organizing” your emails by subject and start thinking of them in terms of deadlines.');
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/www.fastcompany.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://images.fastcompany.net/image/upload/w_1280,f_auto,q_auto,fl_lossy/fc/3067012-poster-p-1-the-only-five-email-folders-your-inbox-will-ever-need.jpg');
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/www.fastcompany.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, 'For years, my approach to email was like slaying a hydra. For every');
|
||||
});
|
||||
});
|
||||
});
|
Loading…
Reference in New Issue