feat: add phpspot.org custom parser (#369)
* feat: add phpspot.org custom parser * fix: date_published selectorpull/368/head^2
parent
ca47f9c7a7
commit
ce5cd2dd0d
File diff suppressed because one or more lines are too long
@ -0,0 +1,29 @@
|
||||
export const PhpspotOrgExtractor = {
|
||||
domain: 'phpspot.org',
|
||||
|
||||
title: {
|
||||
selectors: ['h3.hl'],
|
||||
},
|
||||
|
||||
author: null,
|
||||
|
||||
date_published: {
|
||||
selectors: ['h4.hl'],
|
||||
format: 'YYYY年MM月DD日',
|
||||
timezone: 'Asia/Tokyo',
|
||||
},
|
||||
|
||||
dek: null,
|
||||
|
||||
lead_image_url: null,
|
||||
|
||||
content: {
|
||||
selectors: ['div.entrybody'],
|
||||
|
||||
defaultCleaner: false,
|
||||
|
||||
transforms: {},
|
||||
|
||||
clean: [],
|
||||
},
|
||||
};
|
@ -0,0 +1,106 @@
|
||||
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('PhpspotOrgExtractor', () => {
|
||||
describe('initial test case', () => {
|
||||
let result;
|
||||
let url;
|
||||
beforeAll(() => {
|
||||
url = 'http://phpspot.org/blog/archives/2019/04/treeviz.html';
|
||||
const html = fs.readFileSync('./fixtures/phpspot.org/1554622277068.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/phpspot.org/index.js.
|
||||
const { title } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(title, `マインドマップ風のツリーを描画できる「Treeviz」`);
|
||||
});
|
||||
|
||||
it('returns the author', async () => {
|
||||
// To pass this test, fill out the author selector
|
||||
// in ./src/extractors/custom/phpspot.org/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/phpspot.org/index.js.
|
||||
const { date_published } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(date_published, '2019-04-03T15:00:00.000Z');
|
||||
});
|
||||
|
||||
it('returns the dek', async () => {
|
||||
// To pass this test, fill out the dek selector
|
||||
// in ./src/extractors/custom/phpspot.org/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/phpspot.org/index.js.
|
||||
const { lead_image_url } = await result;
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(lead_image_url, null);
|
||||
});
|
||||
|
||||
it('returns the content', async () => {
|
||||
// To pass this test, fill out the content selector
|
||||
// in ./src/extractors/custom/phpspot.org/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(),
|
||||
2
|
||||
);
|
||||
|
||||
// Update these values with the expected values from
|
||||
// the article.
|
||||
assert.equal(
|
||||
first13,
|
||||
'Treeviz マインドマップ風のツリーを描画できる「Treeviz」'
|
||||
);
|
||||
});
|
||||
});
|
||||
});
|
Loading…
Reference in New Issue