feat: add postlight.com custom extractor (#695)

pull/696/head
Sarah Doire 2 years ago committed by GitHub
parent 39b9ff55c4
commit 8ca8a5f7e5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

2
.gitignore vendored

@ -11,3 +11,5 @@ dist/mercury_test.js.map
dist/mercury_test.web.js
tmp/artifacts
test-output.json
.tool-versions
.yarnrc.yml

32
dist/mercury.js vendored

@ -6139,6 +6139,35 @@ var SpektrumExtractor = {
}
};
var PostlightComExtractor = {
domain: 'postlight.com',
title: {
selectors: [['meta[name="og:title"]', 'value']]
},
author: {
selectors: [['meta[name="parsely-author"]', 'value']]
},
date_published: {
selectors: [['meta[name="article:published_time"]', 'value']]
},
dek: {
selectors: ['h2.single-hero__abstract']
},
lead_image_url: {
selectors: [['meta[name="og:image"]', 'value']]
},
content: {
selectors: ['article.body'],
// 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: ['section.pl-post-link']
}
};
var CustomExtractors = /*#__PURE__*/Object.freeze({
@ -6285,7 +6314,8 @@ var CustomExtractors = /*#__PURE__*/Object.freeze({
WwwEngadgetComExtractor: WwwEngadgetComExtractor,
ArstechnicaComExtractor: ArstechnicaComExtractor,
WwwNdtvComExtractor: WwwNdtvComExtractor,
SpektrumExtractor: SpektrumExtractor
SpektrumExtractor: SpektrumExtractor,
PostlightComExtractor: PostlightComExtractor
});
var Extractors = _Object$keys(CustomExtractors).reduce(function (acc, key) {

File diff suppressed because one or more lines are too long

@ -142,3 +142,4 @@ export * from './www.engadget.com';
export * from './arstechnica.com';
export * from './www.ndtv.com';
export * from './www.spektrum.de';
export * from './postlight.com';

@ -0,0 +1,36 @@
export const PostlightComExtractor = {
domain: 'postlight.com',
title: {
selectors: [['meta[name="og:title"]', 'value']],
},
author: {
selectors: [['meta[name="parsely-author"]', 'value']],
},
date_published: {
selectors: [['meta[name="article:published_time"]', 'value']],
},
dek: {
selectors: ['h2.single-hero__abstract'],
},
lead_image_url: {
selectors: [['meta[name="og:image"]', 'value']],
},
content: {
selectors: ['article.body'],
// 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: ['section.pl-post-link'],
},
};

@ -0,0 +1,111 @@
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('PostlightComExtractor', () => {
describe('initial test case', () => {
let result;
let url;
beforeAll(() => {
url = 'https://postlight.com/insights/three-ways-to-be-the-thermostat';
const html = fs.readFileSync(
'./fixtures/postlight.com/1664999338243.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/postlight.com/index.js.
const { title } = await result;
// Update these values with the expected values from
// the article.
assert.equal(title, `Three Ways to Be the Thermostat`);
});
it('returns the author', async () => {
// To pass this test, fill out the author selector
// in ./src/extractors/custom/postlight.com/index.js.
const { author } = await result;
// Update these values with the expected values from
// the article.
assert.equal(author, 'Gina Trapani');
});
it('returns the date_published', async () => {
// To pass this test, fill out the date_published selector
// in ./src/extractors/custom/postlight.com/index.js.
const { date_published } = await result;
// Update these values with the expected values from
// the article.
assert.equal(date_published, `2022-10-05T16:00:00.000Z`);
});
it('returns the dek', async () => {
// To pass this test, fill out the dek selector
// in ./src/extractors/custom/postlight.com/index.js.
const { dek } = await result;
// Update these values with the expected values from
// the article.
assert.equal(
dek,
'Great leaders set the temperature, especially when stress is high.'
);
});
it('returns the lead_image_url', async () => {
// To pass this test, fill out the lead_image_url selector
// in ./src/extractors/custom/postlight.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://postlight.com/wp-content/uploads/2022/09/Be-The-Thermostat-1200-1.png?fit=1200%2C675`
);
});
it('returns the content', async () => {
// To pass this test, fill out the content selector
// in ./src/extractors/custom/postlight.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,
'One of the best pieces of advice Ive ever received is: “Be the'
);
});
});
});
Loading…
Cancel
Save