feat: add deadline.com custom parser (#383)

* feat: add deadline.com custom parser

* fix: timezone

* fix: date_published selectors

* fix: title and author selector

* test: transform .embed-twitter

* fix: regenerate the fixture and fix content selector

src/extractors/custom/deadline.com/index.js

@@ -0,0 +1,34 @@
+export const DeadlineComExtractor = {
+  domain: 'deadline.com',
+
+  title: {
+    selectors: ['h1'],
+  },
+
+  author: {
+    selectors: ['section.author h3'],
+  },
+
+  date_published: {
+    selectors: [['meta[name="article:published_time"]', 'value']],
+  },
+
+  dek: null,
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']],
+  },
+
+  content: {
+    selectors: ['div.a-article-grid__main.pmc-a-grid article.pmc-a-grid-item'],
+
+    transforms: {
+      '.embed-twitter': $node => {
+        const innerHtml = $node.html();
+        $node.replaceWith(innerHtml);
+      },
+    },
+
+    clean: [],
+  },
+};

src/extractors/custom/deadline.com/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('DeadlineComExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url =
+        'https://deadline.com/2019/04/donald-trump-boeing-max-737-rebrand-advice-twitter-1202595880/';
+      const html = fs.readFileSync(
+        './fixtures/deadline.com/1556104756617.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/deadline.com/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        title.split('Twitter')[0],
+        `Donald Trump Advises Boeing To Rebrand Max 737, Tweeting “But What The Hell Do I Know?”; `
+      );
+    });
+
+    it('returns the author', async () => {
+      // To pass this test, fill out the author selector
+      // in ./src/extractors/custom/deadline.com/index.js.
+      const { author } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(author, 'Lisa de Moraes');
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/deadline.com/index.js.
+      const { date_published } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(date_published, `2019-04-15T13:18:34.000Z`);
+    });
+
+    it('returns the dek', async () => {
+      // To pass this test, fill out the dek selector
+      // in ./src/extractors/custom/deadline.com/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/deadline.com/index.js.
+      const { lead_image_url } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        lead_image_url,
+        `https://pmcdeadline2.files.wordpress.com/2019/01/donald-trump-2.jpg?w=1024`
+      );
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/deadline.com/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(),
+        13
+      );
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        first13,
+        'Andrew Harnik/AP/Shutterstock Twitter erupted Monday morning when President Donald Trump shared his branding'
+      );
+    });
+  });
+});

src/extractors/custom/index.js

@@ -114,3 +114,4 @@ export * from './takagi-hiromitsu.jp';
 export * from './bookwalker.jp';
 export * from './www.yomiuri.co.jp';
 export * from './japan.cnet.com';
+export * from './deadline.com';