feat: add wired.jp custom parser (#409)
* feat: add wired.jp custom parser * fix: author test * fix: date_published selector * test: fix dek and contest * test: fix content (without clean dek)pull/410/head^2
parent
0b36c96de0
commit
77e3bc00e2
File diff suppressed because one or more lines are too long
@ -0,0 +1,40 @@
|
||||
import URL from 'url';
|
||||
|
||||
export const WiredJpExtractor = {
|
||||
domain: 'wired.jp',
|
||||
|
||||
title: {
|
||||
selectors: ['h1.post-title'],
|
||||
},
|
||||
|
||||
author: {
|
||||
selectors: ['p[itemprop="author"]'],
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: [['time', 'datetime']],
|
||||
},
|
||||
|
||||
dek: {
|
||||
selectors: ['.post-intro'],
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [['meta[name="og:image"]', 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['article.article-detail'],
|
||||
|
||||
transforms: {
|
||||
'img[data-original]': $node => {
|
||||
const dataOriginal = $node.attr('data-original');
|
||||
const src = $node.attr('src');
|
||||
const url = URL.resolve(src, dataOriginal);
|
||||
$node.attr('src', url);
|
||||
},
|
||||
},
|
||||
|
||||
clean: ['.post-category', 'time', 'h1.post-title', '.social-area-syncer'],
|
||||
},
|
||||
};
|
@ -0,0 +1,118 @@
|
||||
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('WiredJpExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url = 'https://wired.jp/2019/04/25/helvetica-now/';
|
||||
const html = fs.readFileSync('./fixtures/wired.jp/1556585529692.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/wired.jp/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
title,
|
||||
`あの有名フォント「Helvetica」は、こうしてデジタル時代に生まれ変わった`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/wired.jp/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
author,
|
||||
'TEXT BY ARIELLE PARDES\nTRANSLATION BY CHIHIRO OKA WIRED(US)'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/wired.jp/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, `2019-04-25T16:00:25.000Z`);
|
||||
});
|
||||
|
||||
it('returns the dek', async () => {
|
||||
// To pass this test, fill out the dek selector
|
||||
// in ./src/extractors/custom/wired.jp/index.js.
|
||||
const { dek } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
dek,
|
||||
'世界で最も多く使われているであろうフォントのひとつ「Helvetica」が、このほどリニューアルを遂げた。まるで水のように生活に浸透しているフォントのデザインは、いかに伝統を守りながら、デジタル時代に合わせて最適化されたのか。'
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/wired.jp/index.js.
|
||||
const { lead_image_url } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
lead_image_url,
|
||||
`https://wired.jp/wp-content/uploads/2019/04/190315_Helvetica_Now_Device_AS-1024x768.jpg`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/wired.jp/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(),
|
||||
1
|
||||
);
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
first13,
|
||||
'世界で最も多く使われているであろうフォントのひとつ「Helvetica」が、このほどリニューアルを遂げた。まるで水のように生活に浸透しているフォントのデザインは、いかに伝統を守りながら、デジタル時代に合わせて最適化されたのか。'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
Loading…
Reference in New Issue