Merge pull request #8 from postlight/feat-buzzfeed-extractor

feat: added incomplete buzzfeed extractor

dist/mercury.js

@@ -758,6 +758,49 @@ var YahooExtractor = {
   excerpt: null
 };
 
+// Rename CustomExtractor
+// to fit your publication
+// (e.g., NYTimesExtractor)
+var BuzzfeedExtractor = {
+  domain: 'www.buzzfeed.com',
+  title: {
+    selectors: ['h1[id="post-title"]']
+  },
+
+  author: {
+    selectors: ['a[data-action="user/username"]', 'byline__author']
+  },
+
+  content: {
+    selectors: ['#buzz_sub_buzz', '.bf_dom', 'div[rel:gt_cat="[ttp]: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: []
+  },
+
+  date_published: {
+    selectors: ['.buzz-datetime']
+  },
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']]
+  },
+
+  dek: {
+    selectors: [['meta[name="description"]', 'value']]
+  },
+
+  next_page_url: null,
+
+  excerpt: null
+};
+
 var Extractors = {
   'nymag.com': NYMagExtractor,
   'blogspot.com': BloggerExtractor,
@@ -768,7 +811,8 @@ var Extractors = {
   'www.newyorker.com': NewYorkerExtractor,
   'www.wired.com': WiredExtractor,
   'www.msn.com': MSNExtractor,
-  'www.yahoo.com': YahooExtractor
+  'www.yahoo.com': YahooExtractor,
+  'www.buzzfeed.com': BuzzfeedExtractor
 
 };
 

src/extractors/all.js

@@ -8,6 +8,7 @@ import { NewYorkerExtractor } from './custom/www.newyorker.com';
 import { WiredExtractor } from './custom/www.wired.com';
 import { MSNExtractor } from './custom/www.msn.com';
 import { YahooExtractor } from './custom/www.yahoo.com';
+import { BuzzfeedExtractor } from './custom/www.buzzfeed.com';
 
 
 const Extractors = {
@@ -21,6 +22,7 @@ const Extractors = {
   'www.wired.com': WiredExtractor,
   'www.msn.com': MSNExtractor,
   'www.yahoo.com': YahooExtractor,
+  'www.buzzfeed.com': BuzzfeedExtractor,
 
 };
 

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

@@ -0,0 +1,62 @@
+// Rename CustomExtractor
+// to fit your publication
+// (e.g., NYTimesExtractor)
+export const BuzzfeedExtractor = {
+  domain: 'www.buzzfeed.com',
+  title: {
+    selectors: [
+      'h1[id="post-title"]',
+      // enter title selectors
+    ],
+  },
+
+  author: {
+    selectors: [
+      'a[data-action="user/username"]', 'byline__author',
+      // enter author selectors
+    ],
+  },
+
+  content: {
+    selectors: [
+      '#buzz_sub_buzz', '.bf_dom', 'div[rel:gt_cat="[ttp]:content"]',
+
+      // enter content selectors
+    ],
+
+    // 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: [
+
+    ],
+  },
+
+  date_published: {
+    selectors: [
+      '.buzz-datetime',
+      // enter author selectors
+    ],
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+    ],
+  },
+
+  dek: {
+    selectors: [
+      ['meta[name="description"]', 'value'],
+    ],
+  },
+
+  next_page_url: null,
+
+  excerpt: null,
+};

src/extractors/custom/www.buzzfeed.com/index.test.js

@@ -0,0 +1,134 @@
+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';
+
+// Rename CustomExtractor
+describe('BuzzfeedExtractor', () => {
+  it('is selected properly', () => {
+    // To pass this test, rename your extractor in
+    // ./src/extractors/custom/www.buzzfeed.com/index.js
+    // (e.g., CustomExtractor => NYTimesExtractor)
+    // then add your new extractor to
+    // src/extractors/all.js
+    const url =
+      'https://www.buzzfeed.com/ikrd/people-are-calling-out-this-edited-picture-of-demi-lovato-fo';
+    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.buzzfeed.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.buzzfeed.com/1475531975121.html');
+    const articleUrl =
+      'https://www.buzzfeed.com/ikrd/people-are-calling-out-this-edited-picture-of-demi-lovato-fo';
+
+    const { title } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(title, 'People Are Calling Out This Edited Picture Of Demi Lovato For Body-Shaming Her');
+  });
+
+
+  it('returns the author', ((async)) () => {
+    // To pass this test, fill out the author selector
+    // in ./src/extractors/custom/www.buzzfeed.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.buzzfeed.com/1475531975121.html');
+    const articleUrl =
+      'https://www.buzzfeed.com/ikrd/people-are-calling-out-this-edited-picture-of-demi-lovato-fo';
+
+    const { author } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(author, 'Ikran Dahir');
+  });
+
+
+  it('returns the date_published', ((async)) () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/www.buzzfeed.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.buzzfeed.com/1475531975121.html');
+    const articleUrl =
+      'https://www.buzzfeed.com/ikrd/people-are-calling-out-this-edited-picture-of-demi-lovato-fo';
+
+    const { date_published } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(date_published, ' ');
+  });
+
+
+  it('returns the dek', ((async)) () => {
+    // To pass this test, fill out the dek selector
+    // in ./src/extractors/custom/www.buzzfeed.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.buzzfeed.com/1475531975121.html');
+    const articleUrl =
+      'https://www.buzzfeed.com/ikrd/people-are-calling-out-this-edited-picture-of-demi-lovato-fo';
+
+    const { dek } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(dek, 'Lovato said: "Is that how my boobs should look?"..');
+  });
+
+
+  it('returns the lead_image_url', ((async)) () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/www.buzzfeed.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.buzzfeed.com/1475531975121.html');
+    const articleUrl =
+      'https://www.buzzfeed.com/ikrd/people-are-calling-out-this-edited-picture-of-demi-lovato-fo';
+
+    const { lead_image_url } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(lead_image_url, 'https://img.buzzfeed.com/buzzfeed-static/static/2016-10/3/12/social_promotion/buzzfeed-prod-fastlane01/facebook-social-promotion-17757-1475512210-1.jpg');
+  });
+
+
+  it('returns the content', ((async)) () => {
+    // To pass this test, fill out the content selector
+    // in ./src/extractors/custom/www.buzzfeed.com/index.js.
+    // You may also want to make use of the clean and transform
+    // options.
+    const html =
+      fs.readFileSync('./fixtures/www.buzzfeed.com/1475531975121.html');
+    const url =
+      'https://www.buzzfeed.com/ikrd/people-are-calling-out-this-edited-picture-of-demi-lovato-fo';
+
+    const { content } =
+      await Mercury.parse(url, html, { fallback: false });
+
+    const $ = cheerio.load(content || '');
+
+    const first13 = $('*').first()
+                          .text()
+                          .trim()
+                          .split(/\s+/)
+                          .slice(0, 13)
+                          .join(' ');
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(first13, 'A few months ago, Vladimir Serbanescu, a 17-year-old artist from Romania, drew this');
+  });
+});