feat: miami herald parser (#69)

Author: janetleekim

fixtures/www.miamiherald.com/1481571585318.html

@@ -36,3 +36,4 @@ export * from './www.rollingstone.com';
 export * from './247sports.com';
 export * from './uproxx.com';
 export * from './www.eonline.com';
+export * from './www.miamiherald.com';

src/extractors/custom/index.js

@@ -0,0 +1,41 @@
+export const WwwMiamiheraldComExtractor = {
+  domain: 'www.miamiherald.com',
+
+  title: {
+    selectors: [
+      'h1.title',
+    ],
+  },
+
+  date_published: {
+    selectors: [
+      'p.published-date',
+    ],
+
+    timezone: 'America/New_York',
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+    ],
+  },
+
+  content: {
+    selectors: [
+      'div.dateline-storybody',
+    ],
+
+    // 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/www.miamiherald.com/index.js

@@ -0,0 +1,77 @@
+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('WwwMiamiheraldComExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url =
+        'http://www.miamiherald.com/news/business/biz-monday/article120329158.html';
+      const html =
+        fs.readFileSync('./fixtures/www.miamiherald.com/1481571585318.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.miamiherald.com/index.js.
+      const { title } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(title, 'From Metrorail to bike paths, this is what CEOs think of public transit');
+    });
+
+    it('returns the date_published', async () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/www.miamiherald.com/index.js.
+      const { date_published } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(date_published, '2016-12-12T12:00:00.000Z');
+    });
+
+    it('returns the lead_image_url', async () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/www.miamiherald.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://www.miamiherald.com/news/local/community/miami-dade/5sz3wg/picture119645963/ALTERNATES/LANDSCAPE_1140/MGB19%20Metrorail%20News%20rk%20(2)');
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/www.miamiherald.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, 'This week’s question: When is the last time you took public transportation to');
+    });
+  });
+});