feat: add takagi-hiromitsu.jp custom parser (#364)

src/extractors/custom/index.js

@@ -110,3 +110,4 @@ export * from './www.infoq.com';
 export * from './www.moongift.jp';
 export * from './www.itmedia.co.jp';
 export * from './www.publickey1.jp';
+export * from './takagi-hiromitsu.jp';

src/extractors/custom/takagi-hiromitsu.jp/index.js

@@ -0,0 +1,29 @@
+export const TakagihiromitsuJpExtractor = {
+  domain: 'takagi-hiromitsu.jp',
+
+  title: {
+    selectors: ['h3'],
+  },
+
+  author: {
+    selectors: [['meta[name="author"]', 'value']],
+  },
+
+  date_published: {
+    selectors: [['meta[http-equiv="Last-Modified"]', 'value']],
+  },
+
+  dek: null,
+
+  lead_image_url: null,
+
+  content: {
+    selectors: ['div.body'],
+
+    defaultCleaner: false,
+
+    transforms: {},
+
+    clean: [],
+  },
+};

src/extractors/custom/takagi-hiromitsu.jp/index.test.js

@@ -0,0 +1,110 @@
+import assert from 'assert';
+import URL from 'url';
+import cheerio from 'cheerio';
+import moment from 'moment';
+
+import Mercury from 'mercury';
+import getExtractor from 'extractors/get-extractor';
+import { excerptContent } from 'utils/text';
+
+const fs = require('fs');
+
+describe('TakagihiromitsuJpExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url = 'http://takagi-hiromitsu.jp/diary/20190211.html';
+      const html = fs.readFileSync(
+        './fixtures/takagi-hiromitsu.jp/1551506427717.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/takagi-hiromitsu.jp/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        title,
+        `■ 改正NICT法がプチ炎上、工場出荷時共通初期パスワードが識別符号に当たらないことが理解されていない`
+      );
+    });
+
+    it('returns the author', async () => {
+      // To pass this test, fill out the author selector
+      // in ./src/extractors/custom/takagi-hiromitsu.jp/index.js.
+      const { author } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(author, '高木浩光');
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/takagi-hiromitsu.jp/index.js.
+      const { date_published } = await result;
+      const newDatePublished = moment(date_published).format();
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(newDatePublished.split('T')[0], '2019-02-17');
+    });
+
+    it('returns the dek', async () => {
+      // To pass this test, fill out the dek selector
+      // in ./src/extractors/custom/takagi-hiromitsu.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/takagi-hiromitsu.jp/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/takagi-hiromitsu.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, '先月のこと、NHKニュースが「総務省');
+    });
+  });
+});