feat: Ladbible.com extractor (#624)
* Ladbible.com extractors and test * CircleCI says timezone needs to be Europe/London aka BST Co-authored-by: Postlight Bot <adam.pash+postlight-bot@postlight.com> Co-authored-by: Jad Termsani <32297675+JadTermsani@users.noreply.github.com>pull/631/head
parent
30d6f472ee
commit
8c9982247b
File diff suppressed because one or more lines are too long
@ -0,0 +1,31 @@
|
||||
export const WwwLadbibleComExtractor = {
|
||||
domain: 'www.ladbible.com',
|
||||
|
||||
title: {
|
||||
selectors: ['h1'],
|
||||
},
|
||||
|
||||
author: {
|
||||
selectors: ['[class*=Byline]'],
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: ['time'],
|
||||
timezone: 'Europe/London',
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [['meta[name="og:image"]', 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['[class*=ArticleContainer]'],
|
||||
clean: [
|
||||
'time',
|
||||
'source',
|
||||
'a[href^="https://www.ladbible.com/"]',
|
||||
'picture',
|
||||
'[class*=StyledCardBlock]',
|
||||
],
|
||||
},
|
||||
};
|
@ -0,0 +1,102 @@
|
||||
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('WwwLadbibleComExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url =
|
||||
'https://www.ladbible.com/news/latest-aussie-government-sparks-fury-over-graphic-and-confronting-covid-19-ad-20210711';
|
||||
const html = fs.readFileSync(
|
||||
'./fixtures/www.ladbible.com/1626477326151.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.ladbible.com/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
title,
|
||||
`Aussie Government Sparks Fury Over 'Graphic' And Confronting Covid-19 Ad`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/www.ladbible.com/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(author, 'Stewart Perrie');
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/www.ladbible.com/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, '2021-07-11T21:00:00.000Z');
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/www.ladbible.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://www.ladbible.com/cdn-cgi/image/width=1200,quality=70,format=jpeg,fit=cover,dpr=1/https%3A%2F%2Fs3-images.ladbible.com%2Fs3%2Fcontent%2F788d729460eb11aa5ceadb28b93c0f8a.png`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/www.ladbible.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,
|
||||
'The Australian government has copped backlash for publishing a confronting and graphic advertisement'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
Loading…
Reference in New Issue