feat: add www.lifehacker.jp custom parser (#403)

src/extractors/custom/index.js

@@ -117,3 +117,4 @@ export * from './japan.cnet.com';
 export * from './deadline.com';
 export * from './www.gizmodo.jp';
 export * from './getnews.jp';
+export * from './www.lifehacker.jp';

src/extractors/custom/www.lifehacker.jp/index.js

@@ -0,0 +1,34 @@
+export const WwwLifehackerJpExtractor = {
+  domain: 'www.lifehacker.jp',
+
+  title: {
+    selectors: ['h1.lh-summary-title'],
+  },
+
+  author: {
+    selectors: ['p.lh-entryDetailInner--credit'],
+  },
+
+  date_published: {
+    selectors: [['div.lh-entryDetail-header time', 'datetime']],
+  },
+
+  dek: null,
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']],
+  },
+
+  content: {
+    selectors: ['div.lh-entryDetail-body'],
+
+    transforms: {
+      'img.lazyload': $node => {
+        const src = $node.attr('src');
+        $node.attr('src', src.replace(/^.*=%27/, '').replace(/%27;$/, ''));
+      },
+    },
+
+    clean: ['p.lh-entryDetailInner--credit'],
+  },
+};

src/extractors/custom/www.lifehacker.jp/index.test.js

@@ -0,0 +1,115 @@
+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('WwwLifehackerJpExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url =
+        'https://www.lifehacker.jp/2019/03/amazon-fine-newspaper-stocker.html';
+      const html = fs.readFileSync(
+        './fixtures/www.lifehacker.jp/1555841834276.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.lifehacker.jp/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        title,
+        `ファインの新聞ストッカーは引越しにも使える！ 家具の固定も簡単`
+      );
+    });
+
+    it('returns the author', async () => {
+      // To pass this test, fill out the author selector
+      // in ./src/extractors/custom/www.lifehacker.jp/index.js.
+      const { author } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(author, '島津健吾');
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/www.lifehacker.jp/index.js.
+      const { date_published } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(date_published, `2019-03-08T04:00:00.000Z`);
+    });
+
+    it('returns the dek', async () => {
+      // To pass this test, fill out the dek selector
+      // in ./src/extractors/custom/www.lifehacker.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/www.lifehacker.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://assets.media-platform.com/lifehacker/dist/images/2019/02/28/%E3%82%B9%E3%82%AF%E3%83%AA%E3%83%BC%E3%83%B3%E3%82%B7%E3%83%A7%E3%83%83%E3%83%882019-02-2810.48.32-w960.jpg`
+      );
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/www.lifehacker.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,
+        'Image: Amazon.co.jpついつい溜めてしまい、気がつくとかさばって捨てるのにも苦労する新聞紙。そんな新聞紙を捨てる時には、ファインの｢新聞ストッカー｣が役に立ちます。新聞紙を簡単に、くるくるっとテープでまけちゃうんです。Image:'
+      );
+    });
+  });
+});