feat: add www.infoq.com custom parser (#368)

* feat: add www.infoq.com custom parser

* fix: date_published selector

src/extractors/custom/index.js

@@ -106,3 +106,4 @@ export * from './jvndb.jvn.jp';
 export * from './genius.com';
 export * from './www.jnsa.org';
 export * from './phpspot.org';
+export * from './www.infoq.com';

src/extractors/custom/www.infoq.com/index.js

@@ -0,0 +1,35 @@
+export const WwwInfoqComExtractor = {
+  domain: 'www.infoq.com',
+
+  title: {
+    selectors: ['h1.heading'],
+  },
+
+  author: {
+    selectors: ['div.widget.article__authors'],
+  },
+
+  date_published: {
+    selectors: ['.article__readTime.date'],
+    format: 'YYYY年MM月DD日',
+    timezone: 'Asia/Tokyo',
+  },
+
+  dek: {
+    selectors: [['meta[name="og:description"]', 'value']],
+  },
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']],
+  },
+
+  content: {
+    selectors: ['div.article__data'],
+
+    defaultCleaner: false,
+
+    transforms: {},
+
+    clean: [],
+  },
+};

src/extractors/custom/www.infoq.com/index.test.js

@@ -0,0 +1,114 @@
+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('WwwInfoqComExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url = 'https://www.infoq.com/jp/news/2019/02/chrome-never-slow-mode';
+      const html = fs.readFileSync(
+        './fixtures/www.infoq.com/1554555811551.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.itmedia.co.jp/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(title, `Google ChromeのNever-Slow Mode`);
+    });
+
+    it('returns the author', async () => {
+      // To pass this test, fill out the author selector
+      // in ./src/extractors/custom/www.itmedia.co.jp/index.js.
+      const { author } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(author, '作者： Diogo Carleto 翻訳者 中村 真子');
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/www.itmedia.co.jp/index.js.
+      const { date_published } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(date_published, '2019-02-26T15:00:00.000Z');
+    });
+
+    it('returns the dek', async () => {
+      // To pass this test, fill out the dek selector
+      // in ./src/extractors/custom/www.itmedia.co.jp/index.js.
+      const { dek } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        dek,
+        'GoogleはNever-Slow Modeと呼ばれるプロトタイプ機能に取り組んでいる。このプロトタイプ機能はChromium プロジェクトでコミット作業進行中であり、ユーザーエクスペリエンスの向上、一貫性のある迅速なブラウジングの提供を目的としている。'
+      );
+    });
+
+    it('returns the lead_image_url', async () => {
+      // To pass this test, fill out the lead_image_url selector
+      // in ./src/extractors/custom/www.itmedia.co.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://cdn.infoq.com/statics_s2_20190403-0313/styles/i/logo-big.jpg`
+      );
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/www.itmedia.co.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(),
+        2
+      );
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        first13,
+        '原文(投稿日：2019/02/16)へのリンク GoogleはNever-Slow'
+      );
+    });
+  });
+});