feat: npr parser (#86)

* feat: npr parser

Lead image appears in preview, but the test fails for some reason.

AssertionError: null ==
'https://media.npr.org/assets/img/2016/12/15/gettyimages-540681598_wide-
8b160732b96c083dc115134c3c019f3ac73586ba.jpg?s=1400'

Looks okay otherwise.

* feat: transformed figures/figcaptions, improved date_published and
addressed NPR's bad image metadata

src/extractors/custom/index.js

@@ -29,6 +29,7 @@ export * from './www.theguardian.com';
 export * from './www.sbnation.com';
 export * from './www.bloomberg.com';
 export * from './www.bustle.com';
+export * from './www.npr.org';
 export * from './www.recode.net';
 export * from './qz.com';
 export * from './www.dmagazine.com';

src/extractors/custom/www.npr.org/index.js

@@ -0,0 +1,50 @@
+export const WwwNprOrgExtractor = {
+  domain: 'www.npr.org',
+
+  title: {
+    selectors: [
+      'h1',
+      '.storytitle',
+    ],
+  },
+
+  author: {
+    selectors: [
+      'p.byline__name.byline__name--block',
+    ],
+  },
+
+  date_published: {
+    selectors: [
+      ['.dateblock time[datetime]', 'datetime'],
+      ['meta[name="date"]', 'value'],
+    ],
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+      ['meta[name="twitter:image:src"]', 'value'],
+    ],
+  },
+
+  content: {
+    selectors: [
+      '.storytext',
+    ],
+
+    // Is there anything in the content you selected that needs transformed
+    // before it's consumable content? E.g., unusual lazy loaded images
+    transforms: {
+      '.bucketwrap.image': 'figure',
+      '.bucketwrap.image .credit-caption': 'figcaption',
+    },
+
+    // Is there anything that is in the result that shouldn't be?
+    // The clean selectors will remove anything that matches from
+    // the result
+    clean: [
+      'div.enlarge_measure',
+    ],
+  },
+};

src/extractors/custom/www.npr.org/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('WwwNprOrgExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url =
+        'http://www.npr.org/sections/thetwo-way/2016/12/15/505723552/jury-finds-dylann-roof-guilty-in-s-c-church-shooting';
+      const html =
+        fs.readFileSync('./fixtures/www.npr.org/1481842125199.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.npr.org/index.js.
+      const { title } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(title, 'Jury Finds Dylann Roof Guilty In S.C. Church Shooting');
+    });
+
+    it('returns the author', async () => {
+    // To pass this test, fill out the author selector
+    // in ./src/extractors/custom/www.npr.org/index.js.
+      const { author } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(author, 'Rebecca Hersher');
+    });
+
+    it('returns the date_published', async () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/www.npr.org/index.js.
+      const { date_published } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(date_published, '2016-12-15T20:33:00.000Z');
+    });
+
+    it('returns the lead_image_url', async () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/www.npr.org/index.js.
+      const { lead_image_url } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(lead_image_url, 'https://media.npr.org/assets/img/2016/12/15/ap_16342669033405_wide-e76ba54ba052acbbbe4b9bd73bd429e8d5ca58c7.jpg?s=1400');
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/www.npr.org/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, 'Dylann Roof is escorted from the Shelby Police Department in Shelby, N.C., on');
+    });
+  });
+});