feat: observer parser (#91)

no problems

src/extractors/custom/index.js

@@ -30,6 +30,7 @@ export * from './www.sbnation.com';
 export * from './www.bloomberg.com';
 export * from './www.bustle.com';
 export * from './www.vox.com';
+export * from './observer.com';
 export * from './people.com';
 export * from './www.usmagazine.com';
 export * from './www.rollingstone.com';

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

@@ -0,0 +1,52 @@
+export const ObserverComExtractor = {
+  domain: 'observer.com',
+
+  title: {
+    selectors: [
+      'h1.entry-title',
+    ],
+  },
+
+  author: {
+    selectors: [
+      '.author',
+      '.vcard',
+    ],
+  },
+
+  date_published: {
+    selectors: [
+      ['meta[name="article:published_time"]', 'value'],
+    ],
+  },
+
+  dek: {
+    selectors: [
+      'h2.dek',
+    ],
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+    ],
+  },
+
+  content: {
+    selectors: [
+      'div.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: [
+
+    ],
+  },
+};

src/extractors/custom/observer.com/index.test.js

@@ -0,0 +1,97 @@
+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('ObserverComExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url =
+        'http://observer.com/2016/12/archaeologists-just-discovered-a-2500-year-old-lost-city-atop-a-greek-mountain-peak/';
+      const html =
+        fs.readFileSync('./fixtures/observer.com/1481925269939.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/observer.com/index.js.
+      const { title } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(title, 'Archaeologists Just Discovered a 2,500-Year-Old Lost City Atop a Greek Mountain Peak');
+    });
+
+    it('returns the author', async () => {
+    // To pass this test, fill out the author selector
+    // in ./src/extractors/custom/observer.com/index.js.
+      const { author } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(author, 'Sage Lazzaro');
+    });
+
+    it('returns the date_published', async () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/observer.com/index.js.
+      const { date_published } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(date_published, '2016-12-16T17:21:02.000Z');
+    });
+
+    it('returns the dek', async () => {
+    // To pass this test, fill out the dek selector
+    // in ./src/extractors/custom/observer.com/index.js.
+      const { dek } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(dek, '\'The fact that nobody has never explored the hill before is a mystery\'');
+    });
+
+    it('returns the lead_image_url', async () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/observer.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://i0.wp.com/nyoobserver.files.wordpress.com/2016/12/extra_large-1481648730-cover-image-2.jpg?quality=80&strip&ssl=1');
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/observer.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, 'The city’s acropolis is barely visible during a cloudy day on the Thessalian');
+    });
+  });
+});