feat: inquisitor parser (#72)

src/extractors/custom/index.js

@@ -38,3 +38,4 @@ export * from './uproxx.com';
 export * from './www.eonline.com';
 export * from './www.miamiherald.com';
 export * from './www.refinery29.com';
+export * from './www.inquisitr.com';

src/extractors/custom/www.inquisitr.com/index.js

@@ -0,0 +1,48 @@
+export const WwwInquisitrComExtractor = {
+  domain: 'www.inquisitr.com',
+
+  title: {
+    selectors: [
+      'h1.entry-title.story--header--title',
+    ],
+  },
+
+  author: {
+    selectors: [
+      'div.story--header--author',
+    ],
+  },
+
+  date_published: {
+    selectors: [
+      ['meta[name="datePublished"]', 'value'],
+    ],
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+    ],
+  },
+
+  content: {
+    selectors: [
+      'article.story',
+      '.entry-content.',
+    ],
+
+    // Is there anything in the content you selected that needs transformed
+    // before it's consumable content? E.g., unusual lazy loaded images
+    transforms: {
+    },
+
+    // Is there anything that is in the result that shouldn't be?
+    // The clean selectors will remove anything that matches from
+    // the result
+    clean: [
+      '.post-category',
+      '.story--header--socials',
+      '.story--header--content',
+    ],
+  },
+};

src/extractors/custom/www.inquisitr.com/index.test.js

@@ -0,0 +1,87 @@
+import assert from 'assert';
+import fs from 'fs';
+import URL from 'url';
+import cheerio from 'cheerio';
+
+import Mercury from 'mercury';
+import getExtractor from 'extractors/get-extractor';
+import { excerptContent } from 'utils/text';
+
+describe('WwwInquisitrComExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url =
+        'http://www.inquisitr.com/3790467/donald-trump-intelligence-briefings-security-president-elect-smart-mike-pence/';
+      const html =
+        fs.readFileSync('./fixtures/www.inquisitr.com/1481665067498.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.inquisitr.com/index.js.
+      const { title } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(title, 'Donald Trump Has Skipped Nearly All Intelligence Briefings? President-Elect’s Reasoning Is ‘Well, I Get It When I Need It’');
+    });
+
+    it('returns the author', async () => {
+    // To pass this test, fill out the author selector
+    // in ./src/extractors/custom/www.inquisitr.com/index.js.
+      const { author } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(author, 'Patrick Frye');
+    });
+
+    it('returns the date_published', async () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/www.inquisitr.com/index.js.
+      const { date_published } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(date_published, '2016-12-12T16:07:20.000Z');
+    });
+
+    it('returns the lead_image_url', async () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/www.inquisitr.com/index.js.
+      const { lead_image_url } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(lead_image_url, 'http://cdn.inquisitr.com/wp-content/uploads/2016/12/Donald_Trump_Annual_President_Salary-1-900x440.jpg');
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/www.inquisitr.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, 'Republican President-elect Donald Trump is facing increasing scrutiny for blowing-off security and intelligence');
+    });
+  });
+});