feat: Add a custom extractor for www.ndtv.com. (#554)

* feat:Add a custom extractor for ma.ttias.be.

When parsing content for cron.weekly issues, such as the one at https://ma.ttias.be/cronweekly/issue-130/, Mercury Parser would remove headings and ordered lists that were part of the content. This resolves that as follows:

* Remove "id" attributes from "h1" and "h2" elements. Those attributes would result in the elements having a low weight.
* Since Mercury Parser demotes "h1" elements to "h2", demote "h2" elements to "h3".
* Add class="entry-content-asset" to "ul" elements to avoid them being removed.

* removed redundant comment.

* feat: Add a custom extractor for engadget.com.

* feat: Add a custom extractor for www.ndtv.com.

* Works, but I need to figure how to make pagination work correctly.

* fixed pagination - would only retrieve first or second page because we would send contentOnly: true on subsequent pages (page 2).
removed failover: true from preview.

* rolled back { fallback: false } option removal

* Clarified comments.

* rolling back yarn.lock changes

Co-authored-by: John Holdun <[email protected]>

Author: jbrayton

fixtures/www.ndtv.com/1587821636077.html

@@ -140,3 +140,4 @@ export * from './www.abendblatt.de';
 export * from './www.gruene.de';
 export * from './www.engadget.com';
 export * from './arstechnica.com';
+export * from './www.ndtv.com';

src/extractors/custom/index.js

@@ -0,0 +1,54 @@
+export const WwwNdtvComExtractor = {
+  domain: 'www.ndtv.com',
+
+  title: {
+    selectors: [['meta[name="og:title"]', 'value'], 'h1.entry-title'],
+  },
+
+  author: {
+    selectors: ['span[itemprop="author"] span[itemprop="name"]'],
+  },
+
+  date_published: {
+    selectors: [['span[itemprop="dateModified"]', 'content']],
+  },
+
+  dek: {
+    selectors: ['h2'],
+  },
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']],
+  },
+
+  content: {
+    selectors: ['div[itemprop="articleBody"]'],
+
+    // Is there anything in the content you selected that needs transformed
+    // before it's consumable content? E.g., unusual lazy loaded images
+    transforms: {
+      // This site puts a dateline in a 'b' above the first paragraph, and then somehow
+      // blends it into the first paragraph with CSS. This transform moves the dateline
+      // to the first paragraph.
+      '.place_cont': $node => {
+        if (!$node.parents('p').length) {
+          const nextSibling = $node.next('p');
+          if (nextSibling) {
+            $node.remove();
+            nextSibling.prepend($node);
+          }
+        }
+      },
+    },
+
+    // Is there anything that is in the result that shouldn't be?
+    // The clean selectors will remove anything that matches from
+    // the result
+    clean: [
+      '.highlghts_Wdgt',
+      '.ins_instory_dv_caption',
+      'input',
+      '._world-wrapper .mt20',
+    ],
+  },
+};

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

@@ -0,0 +1,120 @@
+import assert from 'assert';
+import URL from 'url';
+import cheerio from 'cheerio';
+
+import Mercury from 'mercury';
+import getExtractor from 'extractors/get-extractor';
+import { excerptContent } from 'utils/text';
+
+const fs = require('fs');
+
+describe('WwwNdtvComExtractor', () => {
+  describe('initial test case', () => {
+    let result;
+    let url;
+    beforeAll(() => {
+      url =
+        'https://www.ndtv.com/india-news/coronavirus-us-president-donald-trump-says-there-may-be-retaliation-if-india-doesnt-clear-export-of-2207327';
+      const html = fs.readFileSync(
+        './fixtures/www.ndtv.com/1587821636077.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.ndtv.com/index.js.
+      const { title } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        title,
+        `COVID-19: Trump Talks "Retaliation" If India Rejects Export Of Key Drug`
+      );
+    });
+
+    it('returns the author', async () => {
+      // To pass this test, fill out the author selector
+      // in ./src/extractors/custom/www.ndtv.com/index.js.
+      const { author } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(author, 'Swati Bhasin');
+    });
+
+    it('returns the date_published', async () => {
+      // To pass this test, fill out the date_published selector
+      // in ./src/extractors/custom/www.ndtv.com/index.js.
+      const { date_published } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(date_published, '2020-04-07T10:19:34.000Z');
+    });
+
+    it('returns the dek', async () => {
+      // To pass this test, fill out the dek selector
+      // in ./src/extractors/custom/www.ndtv.com/index.js.
+      const { dek } = await result;
+
+      // Update these values with the expected values from
+      // the article.
+      assert.equal(
+        dek,
+        'Amid rising pressure, the government is likely to take a decision on the matter today and clear the move after calculating sufficient stocks for the country, sources have told NDTV.'
+      );
+    });
+
+    it('returns the lead_image_url', async () => {
+      // To pass this test, fill out the lead_image_url selector
+      // in ./src/extractors/custom/www.ndtv.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://c.ndtvimg.com/2020-04/u9vkhue_donald-trump-white-house-afp_625x300_04_April_20.jpg`
+      );
+    });
+
+    it('returns the content', async () => {
+      // To pass this test, fill out the content selector
+      // in ./src/extractors/custom/www.ndtv.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,
+        'Washington/ New Delhi: US President Donald Trump has said "there may be retaliation"'
+      );
+
+      // Confirm that the dateline is moved.
+      const dateline = $('.place_cont');
+      assert.equal(dateline.length, 1);
+      assert.equal(dateline.get(0).parent.tagName, 'p');
+    });
+  });
+});