feat: add buzzap.jp custom parser (#351)
parent
f3a7e393a3
commit
21f7de70c1
File diff suppressed because one or more lines are too long
@ -0,0 +1,29 @@
|
||||
export const BuzzapJpExtractor = {
|
||||
domain: 'buzzap.jp',
|
||||
|
||||
title: {
|
||||
selectors: ['h1.entry-title'],
|
||||
},
|
||||
|
||||
author: null,
|
||||
|
||||
date_published: {
|
||||
selectors: [['time.entry-date', 'datetime']],
|
||||
},
|
||||
|
||||
dek: null,
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [['meta[name="og:image"]', 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['div.ctiframe'],
|
||||
|
||||
defaultCleaner: false,
|
||||
|
||||
transforms: {},
|
||||
|
||||
clean: [],
|
||||
},
|
||||
};
|
@ -0,0 +1,109 @@
|
||||
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('BuzzapJpExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url = 'https://buzzap.jp/news/20190302-reduced-tax-rate-benefit/';
|
||||
const html = fs.readFileSync('./fixtures/buzzap.jp/1551497136221.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/buzzap.jp/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
title,
|
||||
`【?】「消費増税の軽減税率は高所得者ほどお得!」総務省が謎仕様であることを認める`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/buzzap.jp/index.js.
|
||||
const { author } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(author, null);
|
||||
});
|
||||
|
||||
it('returns the date_published', async () => {
|
||||
// To pass this test, fill out the date_published selector
|
||||
// in ./src/extractors/custom/buzzap.jp/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, `2019-03-02T09:18:32.000Z`);
|
||||
});
|
||||
|
||||
it('returns the dek', async () => {
|
||||
// To pass this test, fill out the dek selector
|
||||
// in ./src/extractors/custom/buzzap.jp/index.js.
|
||||
const { dek } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(dek, null);
|
||||
});
|
||||
|
||||
it('returns the lead_image_url', async () => {
|
||||
// To pass this test, fill out the lead_image_url selector
|
||||
// in ./src/extractors/custom/buzzap.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://buzzap.net/images/2018/11/29/consumption-tax-opportunistic-price-hike/top.jpg`
|
||||
);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/buzzap.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,
|
||||
'家計の負担を和らげるための軽減税率のはずでしたが、低所得者ほど恩恵が薄いことを総務省が公式に認めました。詳細は以下から。'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
Loading…
Reference in New Issue