feat: add www.gizmodo.jp custom parser (#400)

src/extractors/custom/index.js

@@ -115,3 +115,4 @@ export * from './bookwalker.jp';
 export * from './www.yomiuri.co.jp';
 export * from './japan.cnet.com';
 export * from './deadline.com';
+export * from './www.gizmodo.jp';

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

@@ -0,0 +1,34 @@
+export const WwwGizmodoJpExtractor = {
+  domain: 'www.gizmodo.jp',
+
+  title: {
+    selectors: ['h1.p-post-title'],
+  },
+
+  author: {
+    selectors: ['li.p-post-AssistAuthor'],
+  },
+
+  date_published: {
+    selectors: [['li.p-post-AssistTime time', 'datetime']],
+  },
+
+  dek: null,
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']],
+  },
+
+  content: {
+    selectors: ['article.p-post'],
+
+    transforms: {
+      'img.p-post-thumbnailImage': $node => {
+        const src = $node.attr('src');
+        $node.attr('src', src.replace(/^.*=%27/, '').replace(/%27;$/, ''));
+      },
+    },
+
+    clean: ['h1.p-post-title', 'ul.p-post-Assist'],
+  },
+};

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

@@ -0,0 +1,111 @@
+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('WwwGizmodoJpExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url = 'https://www.gizmodo.jp/2019/04/suica-gashapon-bandai.html';
+      const html = fs.readFileSync(
+        './fixtures/www.gizmodo.jp/1555839535234.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.gizmodo.jp/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        title,
+        `Suicaでガシャれる。電子マネー対応ガシャポンが稼働開始`
+      );
+    });
+
+    it('returns the author', async () => {
+      // To pass this test, fill out the author selector
+      // in ./src/extractors/custom/www.gizmodo.jp/index.js.
+      const { author } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(author, '小暮ひさのり');
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/www.gizmodo.jp/index.js.
+      const { date_published } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(date_published, `2019-04-19T11:00:00.000Z`);
+    });
+
+    it('returns the dek', async () => {
+      // To pass this test, fill out the dek selector
+      // in ./src/extractors/custom/www.gizmodo.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.gizmodo.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/gizmodo/dist/images/2019/04/18/190418gak00-w960.jpg`
+      );
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/www.gizmodo.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, 'Image:');
+    });
+  });
+});