Merge pull request #9 from postlight/feat-wikia-extractor

feat: added wikia extractor

dist/mercury.js

@@ -772,7 +772,9 @@ var BuzzfeedExtractor = {
   },
 
   content: {
-    selectors: ['#buzz_sub_buzz', '.bf_dom', 'div[rel:gt_cat="[ttp]:content"]'],
+    selectors: [
+      // 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
@@ -801,6 +803,49 @@ var BuzzfeedExtractor = {
   excerpt: null
 };
 
+// Rename CustomExtractor
+// to fit your publication
+// (e.g., NYTimesExtractor)
+var WikiaExtractor = {
+  domain: 'fandom.wikia.com',
+  title: {
+    selectors: ['h1.entry-title']
+  },
+
+  author: {
+    selectors: ['.author vcard', '.fn']
+  },
+
+  content: {
+    selectors: ['.grid-content', '.entry-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: [['meta[name="article:published_time"]', 'value']]
+  },
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']]
+  },
+
+  dek: {
+    selectors: [['meta[name="og:description"]', 'value']]
+  },
+
+  next_page_url: null,
+
+  excerpt: null
+};
+
 var Extractors = {
   'nymag.com': NYMagExtractor,
   'blogspot.com': BloggerExtractor,
@@ -812,7 +857,8 @@ var Extractors = {
   'www.wired.com': WiredExtractor,
   'www.msn.com': MSNExtractor,
   'www.yahoo.com': YahooExtractor,
-  'www.buzzfeed.com': BuzzfeedExtractor
+  'www.buzzfeed.com': BuzzfeedExtractor,
+  'fandom.wikia.com': WikiaExtractor
 
 };
 

src/extractors/all.js

@@ -9,6 +9,7 @@ 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';
+import { WikiaExtractor } from './custom/fandom.wikia.com';
 
 
 const Extractors = {
@@ -23,6 +24,7 @@ const Extractors = {
   'www.msn.com': MSNExtractor,
   'www.yahoo.com': YahooExtractor,
   'www.buzzfeed.com': BuzzfeedExtractor,
+  'fandom.wikia.com': WikiaExtractor,
 
 };
 

src/extractors/custom/fandom.wikia.com/index.js

@@ -0,0 +1,61 @@
+// Rename CustomExtractor
+// to fit your publication
+// (e.g., NYTimesExtractor)
+export const WikiaExtractor = {
+  domain: 'fandom.wikia.com',
+  title: {
+    selectors: [
+      'h1.entry-title',
+      // enter title selectors
+    ],
+  },
+
+  author: {
+    selectors: [
+      '.author vcard', '.fn',
+      // enter author selectors
+    ],
+  },
+
+  content: {
+    selectors: [
+      '.grid-content',
+      '.entry-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: [
+      ['meta[name="article:published_time"]', 'value'],
+    ],
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+    ],
+  },
+
+  dek: {
+    selectors: [
+      ['meta[name="og:description"]', 'value'],
+    ],
+  },
+
+  next_page_url: null,
+
+  excerpt: null,
+};

src/extractors/custom/fandom.wikia.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('WikiaExtractor', () => {
+  it('is selected properly', () => {
+    // To pass this test, rename your extractor in
+    // ./src/extractors/custom/fandom.wikia.com/index.js
+    // (e.g., CustomExtractor => NYTimesExtractor)
+    // then add your new extractor to
+    // src/extractors/all.js
+    const url =
+      'http://fandom.wikia.com/articles/box-office-good-peculiar';
+    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/fandom.wikia.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/fandom.wikia.com/1475595373938.html');
+    const articleUrl =
+      'http://fandom.wikia.com/articles/box-office-good-peculiar';
+
+    const { title } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(title, 'Box Office: It’s Good to Be ‘Peculiar’');
+  });
+
+
+  it('returns the author', ((async)) () => {
+    // To pass this test, fill out the author selector
+    // in ./src/extractors/custom/fandom.wikia.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/fandom.wikia.com/1475595373938.html');
+    const articleUrl =
+      'http://fandom.wikia.com/articles/box-office-good-peculiar';
+
+    const { author } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(author, 'Drew Dietsch');
+  });
+
+
+  it('returns the date_published', ((async)) () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/fandom.wikia.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/fandom.wikia.com/1475595373938.html');
+    const articleUrl =
+      'http://fandom.wikia.com/articles/box-office-good-peculiar';
+
+    const { date_published } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(date_published, '2016-10-03T02:30:57.000Z');
+  });
+
+
+  it('returns the dek', ((async)) () => {
+    // To pass this test, fill out the dek selector
+    // in ./src/extractors/custom/fandom.wikia.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/fandom.wikia.com/1475595373938.html');
+    const articleUrl =
+      'http://fandom.wikia.com/articles/box-office-good-peculiar';
+
+    const { dek } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(dek, 'Tim Burton once again claimed the top spot at the box office. Miss Peregrine’s Home for Peculiar Children secured a respectable #1 showing and may have some staying power in the coming weeks. All in all, it’s not a huge win but it’s good enough. Meanwhile, Deepwater Horizon performed about as well as expected. Seeing as how […]');
+  });
+
+
+  it('returns the lead_image_url', ((async)) () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/fandom.wikia.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/fandom.wikia.com/1475595373938.html');
+    const articleUrl =
+      'http://fandom.wikia.com/articles/box-office-good-peculiar';
+
+    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, 'http://fandom.wikia.com/wp-content/uploads/2016/10/box-office-peculiar-feature-hero.jpg');
+  });
+
+
+  it('returns the content', ((async)) () => {
+    // To pass this test, fill out the content selector
+    // in ./src/extractors/custom/fandom.wikia.com/index.js.
+    // You may also want to make use of the clean and transform
+    // options.
+    const html =
+      fs.readFileSync('./fixtures/fandom.wikia.com/1475595373938.html');
+    const url =
+      'http://fandom.wikia.com/articles/box-office-good-peculiar';
+
+    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, 'Tim Burton once again claimed the top spot at the box office. Miss');
+  });
+});