feat: add weekly.ascii.jp custom parser (#401)

* feat: add weekly.ascii.jp custom parser

* fix: title and date_published selector

src/extractors/custom/index.js

@@ -121,3 +121,4 @@ export * from './www.lifehacker.jp';
 export * from './sect.iij.ad.jp';
 export * from './www.oreilly.co.jp';
 export * from './www.ipa.go.jp';
+export * from './weekly.ascii.jp';

src/extractors/custom/weekly.ascii.jp/index.js

@@ -0,0 +1,29 @@
+export const WeeklyAsciiJpExtractor = {
+  domain: 'weekly.ascii.jp',
+
+  title: {
+    selectors: ['h1[itemprop="headline"]'],
+  },
+
+  author: {
+    selectors: ['p.author'],
+  },
+
+  date_published: {
+    selectors: [['meta[name="odate"]', 'value']],
+  },
+
+  dek: null,
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']],
+  },
+
+  content: {
+    selectors: ['div.article'],
+
+    transforms: {},
+
+    clean: [],
+  },
+};

src/extractors/custom/weekly.ascii.jp/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('WeeklyAsciiJpExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url = 'https://weekly.ascii.jp/elem/000/000/428/428292/';
+      const html = fs.readFileSync(
+        './fixtures/weekly.ascii.jp/1555849300154.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/weekly.ascii.jp/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        title,
+        `普通に使える手のひらサイズの超小型スマホ「Palm Phone」の実機チェック`
+      );
+    });
+
+    it('returns the author', async () => {
+      // To pass this test, fill out the author selector
+      // in ./src/extractors/custom/weekly.ascii.jp/index.js.
+      const { author } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(author, `文●オカモト／ASCII編集部`);
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/weekly.ascii.jp/index.js.
+      const { date_published } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(date_published, '2019-04-21T03:00:00.000Z');
+    });
+
+    it('returns the dek', async () => {
+      // To pass this test, fill out the dek selector
+      // in ./src/extractors/custom/weekly.ascii.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/weekly.ascii.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://ascii.jp/elem/000/001/848/1848427/00-01_1024x1024.jpg`
+      );
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/weekly.ascii.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,
+        'FOXが国内販売代理店となり、同社ECサイトやプラススタイルのほか、ヨドバシカメラ、ビックカメラ、Amazon.co.jpなどで、24日から販売される手のひらサイズのAndroidスマートフォン「Palm'
+      );
+    });
+  });
+});