feat: hellogiggles parser (#107)

Looks good to me!
pull/75/head
Janet 8 years ago committed by Zachary Golba
parent 11ad7b9a92
commit aff651c2d8

File diff suppressed because one or more lines are too long

@ -0,0 +1,45 @@
export const HellogigglesComExtractor = {
domain: 'hellogiggles.com',
title: {
selectors: [
'.title',
],
},
author: {
selectors: [
'.author-link',
],
},
date_published: {
selectors: [
['meta[name="article:published_time"]', 'value'],
],
},
lead_image_url: {
selectors: [
['meta[name="og:image"]', 'value'],
],
},
content: {
selectors: [
'.entry-content',
],
// Is there anything in the content you selected that needs transformed
// before it's consumable content? E.g., unusual lazy loaded images
transforms: {
},
// Is there anything that is in the result that shouldn't be?
// The clean selectors will remove anything that matches from
// the result
clean: [
],
},
};

@ -0,0 +1,87 @@
import assert from 'assert';
import fs from 'fs';
import URL from 'url';
import cheerio from 'cheerio';
import Mercury from 'mercury';
import getExtractor from 'extractors/get-extractor';
import { excerptContent } from 'utils/text';
describe('HellogigglesComExtractor', () => {
describe('initial test case', () => {
let result;
let url;
beforeAll(() => {
url =
'http://hellogiggles.com/comfy-chic-holiday-outfit-illustrated/';
const html =
fs.readFileSync('./fixtures/hellogiggles.com/1482437663500.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/hellogiggles.com/index.js.
const { title } = await result;
// Update these values with the expected values from
// the article.
assert.equal(title, 'Your comfy-chic holiday outfit, illustrated');
});
it('returns the author', async () => {
// To pass this test, fill out the author selector
// in ./src/extractors/custom/hellogiggles.com/index.js.
const { author } = await result;
// Update these values with the expected values from
// the article.
assert.equal(author, 'Cindy Mangomini');
});
it('returns the date_published', async () => {
// To pass this test, fill out the date_published selector
// in ./src/extractors/custom/hellogiggles.com/index.js.
const { date_published } = await result;
// Update these values with the expected values from
// the article.
assert.equal(date_published, '2016-12-22T00:05:23.000Z');
});
it('returns the lead_image_url', async () => {
// To pass this test, fill out the lead_image_url selector
// in ./src/extractors/custom/hellogiggles.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://images.hellogiggles.com/uploads/2016/12/21073729/HG-Xmas-NY-Cindy-Mangomini1.jpg');
});
it('returns the content', async () => {
// To pass this test, fill out the content selector
// in ./src/extractors/custom/hellogiggles.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, 'Its almost that time! The time to quietly panic and throw all the');
});
});
});

@ -41,6 +41,7 @@ export * from './uproxx.com';
export * from './www.eonline.com';
export * from './www.miamiherald.com';
export * from './www.refinery29.com';
export * from './hellogiggles.com';
export * from './thoughtcatalog.com';
export * from './www.nj.com';
export * from './www.inquisitr.com';

Loading…
Cancel
Save