Merge pull request #10 from postlight/feat-littlethings-extractor

feat: added littlethings extractor

dist/mercury.js

@@ -846,6 +846,41 @@ var WikiaExtractor = {
   excerpt: null
 };
 
+// Rename CustomExtractor
+// to fit your publication
+// (e.g., NYTimesExtractor)
+var LittleThingsExtractor = {
+  domain: 'www.littlethings.com',
+  title: {
+    selectors: ['h1.post-title']
+  },
+
+  author: {
+    selectors: [['meta[name="author"]', 'value']]
+  },
+
+  content: {
+    selectors: [
+    // enter content selectors
+    '.mainContentIntro', '.content-wrapper'],
+
+    // 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: []
+  },
+
+  lead_image_url: null,
+
+  next_page_url: null,
+
+  excerpt: null
+};
+
 var Extractors = {
   'nymag.com': NYMagExtractor,
   'blogspot.com': BloggerExtractor,
@@ -858,7 +893,8 @@ var Extractors = {
   'www.msn.com': MSNExtractor,
   'www.yahoo.com': YahooExtractor,
   'www.buzzfeed.com': BuzzfeedExtractor,
-  'fandom.wikia.com': WikiaExtractor
+  'fandom.wikia.com': WikiaExtractor,
+  'www.littlethings.com': LittleThingsExtractor
 
 };
 

src/extractors/all.js

@@ -10,6 +10,7 @@ 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';
+import { LittleThingsExtractor } from './custom/www.littlethings.com';
 
 
 const Extractors = {
@@ -25,6 +26,7 @@ const Extractors = {
   'www.yahoo.com': YahooExtractor,
   'www.buzzfeed.com': BuzzfeedExtractor,
   'fandom.wikia.com': WikiaExtractor,
+  'www.littlethings.com': LittleThingsExtractor,
 
 };
 

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

@@ -0,0 +1,49 @@
+// Rename CustomExtractor
+// to fit your publication
+// (e.g., NYTimesExtractor)
+export const LittleThingsExtractor = {
+  domain: 'www.littlethings.com',
+  title: {
+    selectors: [
+      'h1.post-title',
+      // enter title selectors
+    ],
+  },
+
+  author: {
+    selectors: [
+      ['meta[name="author"]', 'value'],
+      // enter author selectors
+    ],
+  },
+
+  content: {
+    selectors: [
+      // enter content selectors
+      '.mainContentIntro',
+      '.content-wrapper',
+    ],
+
+    // 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: [
+
+    ],
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+    ],
+  },
+
+  next_page_url: null,
+
+  excerpt: null,
+};

src/extractors/custom/www.littlethings.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('LittleThingsExtractor', () => {
+  it('is selected properly', () => {
+    // To pass this test, rename your extractor in
+    // ./src/extractors/custom/www.littlethings.com/index.js
+    // (e.g., CustomExtractor => NYTimesExtractor)
+    // then add your new extractor to
+    // src/extractors/all.js
+    const url =
+      'http://www.littlethings.com/diy-pineapple-lamp/';
+    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.littlethings.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.littlethings.com/1475605036506.html');
+    const articleUrl =
+      'http://www.littlethings.com/diy-pineapple-lamp/';
+
+    const { title } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(title, 'Snip The Stems Off Plastic Spoons To Make A Quirky Pineapple Lamp');
+  });
+
+
+  it('returns the author', ((async)) () => {
+    // To pass this test, fill out the author selector
+    // in ./src/extractors/custom/www.littlethings.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.littlethings.com/1475605036506.html');
+    const articleUrl =
+      'http://www.littlethings.com/diy-pineapple-lamp/';
+
+    const { author } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(author, 'Laura Caseley');
+  });
+
+
+  it('returns the date_published', ((async)) () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/www.littlethings.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.littlethings.com/1475605036506.html');
+    const articleUrl =
+      'http://www.littlethings.com/diy-pineapple-lamp/';
+
+    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.littlethings.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.littlethings.com/1475605036506.html');
+    const articleUrl =
+      'http://www.littlethings.com/diy-pineapple-lamp/';
+
+    const { dek } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(dek, '');
+  });
+
+
+  it('returns the lead_image_url', ((async)) () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/www.littlethings.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.littlethings.com/1475605036506.html');
+    const articleUrl =
+      'http://www.littlethings.com/diy-pineapple-lamp/';
+
+    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://cdn1.littlethings.com/app/uploads/2016/09/pineapple-b-thumb-1.jpg');
+  });
+
+
+  it('returns the content', ((async)) () => {
+    // To pass this test, fill out the content selector
+    // in ./src/extractors/custom/www.littlethings.com/index.js.
+    // You may also want to make use of the clean and transform
+    // options.
+    const html =
+      fs.readFileSync('./fixtures/www.littlethings.com/1475605036506.html');
+    const url =
+      'http://www.littlethings.com/diy-pineapple-lamp/';
+
+    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, 'Every room needs light, and so lamps are pretty much a necessity for');
+  });
+});