feat: pagesix parser

src/extractors/custom/index.js

@@ -37,6 +37,7 @@ export * from './www.reuters.com';
 export * from './mashable.com';
 export * from './www.chicagotribune.com';
 export * from './www.vox.com';
+export * from './pagesix.com';
 export * from './www.thepoliticalinsider.com';
 export * from './www.mentalfloss.com';
 export * from './abcnews.go.com';

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

@@ -0,0 +1,67 @@
+export const PagesixComExtractor = {
+  domain: 'pagesix.com',
+
+  supportedDomains: [
+    'nypost.com',
+  ],
+
+  title: {
+    selectors: [
+      'h1 a',
+    ],
+  },
+
+  author: {
+    selectors: [
+      '.byline',
+    ],
+  },
+
+  date_published: {
+    selectors: [
+      ['meta[name="article:published_time"]', 'value'],
+    ],
+  },
+
+  dek: {
+    selectors: [
+      ['meta[name="description"]', 'value'],
+    ],
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+    ],
+  },
+
+  content: {
+    selectors: [
+      '.article-header',
+    ],
+
+    // Is there anything in the content you selected that needs transformed
+    // before it's consumable content? E.g., unusual lazy loaded images
+    transforms: {
+      '#featured-image-wrapper': ($node) => {
+        const sourceSet = $node.find('source').first().attr('srcset');
+        const largestImg = sourceSet.split(' ')[0];
+        $node.replaceWith(`<img src="${largestImg}" />`);
+      },
+    },
+
+    // Is there anything that is in the result that shouldn't be?
+    // The clean selectors will remove anything that matches from
+    // the result
+    clean: [
+      '.flag-region',
+      'h1',
+      '.author-byline',
+      '.byline-date',
+      '.double-rule',
+      '.in-line-column',
+      '.modal-trigger',
+      '.wp-caption-text',
+    ],
+  },
+};

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

@@ -0,0 +1,88 @@
+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('PagesixComExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url =
+        'http://pagesix.com/2016/12/19/sofia-vergara-and-nick-loebs-embryo-drama-taking-a-detour/';
+      const html =
+        fs.readFileSync('./fixtures/pagesix.com/1482254007534.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/pagesix.com/index.js.
+      const { title } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(title, 'Sofía Vergara and Nick Loeb’s embryo drama taking a detour');
+    });
+
+    it('returns the author', async () => {
+    // To pass this test, fill out the author selector
+    // in ./src/extractors/custom/pagesix.com/index.js.
+      const { author } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(author, 'Oli Coleman');
+    });
+
+    it('returns the date_published', async () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/pagesix.com/index.js.
+      const { date_published } = await result;
+
+    // Update these values with the expected values from
+    // the article.
+      assert.equal(date_published, '2016-12-20T00:08:44.000Z');
+    });
+
+    it('returns the lead_image_url', async () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/pagesix.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://nyppagesix.files.wordpress.com/2016/12/sofia-vergara4.jpg?quality=90&strip=all&w=1200');
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/pagesix.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, 'In the latest twist in the wild battle over Sofía Vergara and Nick');
+    });
+  });
+});