feat: add scan.netsecurity.ne.jp custom parser (#347)

src/extractors/custom/index.js

@@ -101,3 +101,4 @@ export * from './buzzap.jp';
 export * from './www.asahi.com';
 export * from './www.sanwa.co.jp';
 export * from './www.elecom.co.jp';
+export * from './scan.netsecurity.ne.jp';

src/extractors/custom/scan.netsecurity.ne.jp/index.js

@@ -0,0 +1,31 @@
+export const ScanNetsecurityNeJpExtractor = {
+  domain: 'scan.netsecurity.ne.jp',
+
+  title: {
+    selectors: ['header.arti-header h1.head'],
+  },
+
+  author: null,
+
+  date_published: {
+    selectors: [['meta[name="article:modified_time"]', 'value']],
+  },
+
+  dek: {
+    selectors: ['header.arti-header p.arti-summary'],
+  },
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']],
+  },
+
+  content: {
+    selectors: ['div.arti-content.arti-content--thumbnail'],
+
+    defaultCleaner: false,
+
+    transforms: {},
+
+    clean: ['aside.arti-giga'],
+  },
+};

src/extractors/custom/scan.netsecurity.ne.jp/index.test.js

@@ -0,0 +1,117 @@
+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('ScanNetsecurityNeJpExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url = 'https://scan.netsecurity.ne.jp/article/2019/03/05/42049.html';
+      const html = fs.readFileSync(
+        './fixtures/scan.netsecurity.ne.jp/1551788723281.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/scan.netsecurity.ne.jp/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        title,
+        `パスワードロック未実施のUSBメモリを電車内で紛失の可能性（阪南大学）`
+      );
+    });
+
+    it('returns the author', async () => {
+      // To pass this test, fill out the author selector
+      // in ./src/extractors/custom/scan.netsecurity.ne.jp/index.js.
+      const { author } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(author, null);
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/scan.netsecurity.ne.jp/index.js.
+      const { date_published } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(date_published, `2019-03-04T23:15:11.000Z`);
+    });
+
+    it('returns the dek', async () => {
+      // To pass this test, fill out the dek selector
+      // in ./src/extractors/custom/scan.netsecurity.ne.jp/index.js.
+      const { dek } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        dek,
+        '阪南大学は3月4日、同学の専任教員が学生情報等を保存したUSBメモリを紛失したことが判明したと発表した。'
+      );
+    });
+
+    it('returns the lead_image_url', async () => {
+      // To pass this test, fill out the lead_image_url selector
+      // in ./src/extractors/custom/scan.netsecurity.ne.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://scan.netsecurity.ne.jp/imgs/ogp_f/26698.jpg`
+      );
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/scan.netsecurity.ne.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,
+        '公式サイト リリース（個人情報を含むUSBメモリ紛失のお詫びとお知らせ）'
+      );
+    });
+  });
+});