Fix extension bugs (#23)

* feat: cleaning supplemental elements in nytimes (visible in web only)

closes https://github.com/postlight/mercury-reader-chrome-extension/issues/102

* wip

* fix: more generous date published bits

* feat: added washington post extractor (including figure transforms)

closes https://github.com/postlight/mercury-reader-chrome-extension/issues/100

* feat: cleaning zoom lightbox from gizmodo/kinja

* lint fix

dist/mercury.js

@@ -2060,7 +2060,7 @@ var NYTimesExtractor = {
       }
     },
 
-    clean: ['.ad', 'header#story-header', '.story-body-1 .lede.video', '.visually-hidden', '#newsletter-promo', '.promo', '.comments-button', '.hidden', '.comments']
+    clean: ['.ad', 'header#story-header', '.story-body-1 .lede.video', '.visually-hidden', '#newsletter-promo', '.promo', '.comments-button', '.hidden', '.comments', '.supplemental', '.nocontent']
   },
 
   date_published: null,
@@ -2739,6 +2739,53 @@ var WwwTmzComExtractor = {
   }
 };
 
+var WwwWashingtonpostComExtractor = {
+  domain: 'www.washingtonpost.com',
+
+  title: {
+    selectors: ['h1', '#topper-headline-wrapper']
+  },
+
+  author: {
+    selectors: ['.pb-byline']
+  },
+
+  date_published: {
+    selectors: [['.pb-timestamp[itemprop="datePublished"]', 'content']]
+  },
+
+  dek: {
+    selectors: [['meta[name="og:description"]', 'value']]
+  },
+
+  lead_image_url: {
+    selectors: [['meta[name="og:image"]', 'value']]
+  },
+
+  content: {
+    selectors: ['.article-body'],
+
+    // Is there anything in the content you selected that needs transformed
+    // before it's consumable content? E.g., unusual lazy loaded images
+    transforms: {
+      'div.inline-content': function divInlineContent($node) {
+        if ($node.has('img,iframe,video').length > 0) {
+          return 'figure';
+        }
+
+        $node.remove();
+        return null;
+      },
+      '.pb-caption': 'figcaption'
+    },
+
+    // Is there anything that is in the result that shouldn't be?
+    // The clean selectors will remove anything that matches from
+    // the result
+    clean: ['.interstitial-link']
+  }
+};
+
 
 
 var CustomExtractors = Object.freeze({
@@ -2760,7 +2807,8 @@ var CustomExtractors = Object.freeze({
 	BroadwayWorldExtractor: BroadwayWorldExtractor,
 	ApartmentTherapyExtractor: ApartmentTherapyExtractor,
 	MediumExtractor: MediumExtractor,
-	WwwTmzComExtractor: WwwTmzComExtractor
+	WwwTmzComExtractor: WwwTmzComExtractor,
+	WwwWashingtonpostComExtractor: WwwWashingtonpostComExtractor
 });
 
 var Extractors = _Object$keys(CustomExtractors).reduce(function (acc, key) {
@@ -2802,7 +2850,8 @@ var months = ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oc
 var allMonths = months.join('|');
 var timestamp1 = '[0-9]{1,2}:[0-9]{2,2}( ?[ap].?m.?)?';
 var timestamp2 = '[0-9]{1,2}[/-][0-9]{1,2}[/-][0-9]{2,4}';
-var SPLIT_DATE_STRING = new RegExp('(' + timestamp1 + ')|(' + timestamp2 + ')|([0-9]{1,4})|(' + allMonths + ')', 'ig');
+var timestamp3 = '-[0-9]{3,4}$';
+var SPLIT_DATE_STRING = new RegExp('(' + timestamp1 + ')|(' + timestamp2 + ')|(' + timestamp3 + ')|([0-9]{1,4})|(' + allMonths + ')', 'ig');
 
 // CLEAN TITLE CONSTANTS
 // A regular expression that will match separating characters on a

src/cleaners/constants.js

@@ -48,8 +48,9 @@ const months = [
 const allMonths = months.join('|');
 const timestamp1 = '[0-9]{1,2}:[0-9]{2,2}( ?[ap].?m.?)?';
 const timestamp2 = '[0-9]{1,2}[/-][0-9]{1,2}[/-][0-9]{2,4}';
+const timestamp3 = '-[0-9]{3,4}$';
 export const SPLIT_DATE_STRING =
-  new RegExp(`(${timestamp1})|(${timestamp2})|([0-9]{1,4})|(${allMonths})`, 'ig');
+  new RegExp(`(${timestamp1})|(${timestamp2})|(${timestamp3})|([0-9]{1,4})|(${allMonths})`, 'ig');
 
 // CLEAN TITLE CONSTANTS
 // A regular expression that will match separating characters on a

src/cleaners/date-published.test.js

@@ -58,4 +58,11 @@ describe('cleanDateString(dateString)', () => {
     const date1 = cleanDateString('This page was last modified on 15 April 2016, at 10:59.');
     assert.equal(date1, '15 Apr 2016 10:59');
   });
+
+  it('massages the T out', () => {
+    // The JS date parser is forgiving, but
+    // it needs am/pm separated from a time
+    const date1 = cleanDateString('2016-11-22T08:57-500');
+    assert.equal(date1, '2016 11 22 08:57 -500');
+  });
 });

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

@@ -41,6 +41,8 @@ export const DeadspinExtractor = {
     // The clean selectors will remove anything that matches from
     // the result
     clean: [
+      '.magnifier',
+      '.lightbox',
     ],
   },
 

src/extractors/custom/index.js

@@ -17,3 +17,4 @@ export * from './www.broadwayworld.com';
 export * from './www.apartmenttherapy.com';
 export * from './medium.com';
 export * from './www.tmz.com';
+export * from './www.washingtonpost.com';

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

@@ -51,6 +51,8 @@ export const NYTimesExtractor = {
       '.comments-button',
       '.hidden',
       '.comments',
+      '.supplemental',
+      '.nocontent',
     ],
   },
 

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

@@ -0,0 +1,61 @@
+export const WwwWashingtonpostComExtractor = {
+  domain: 'www.washingtonpost.com',
+
+  title: {
+    selectors: [
+      'h1',
+      '#topper-headline-wrapper',
+    ],
+  },
+
+  author: {
+    selectors: [
+      '.pb-byline',
+    ],
+  },
+
+  date_published: {
+    selectors: [
+      ['.pb-timestamp[itemprop="datePublished"]', 'content'],
+    ],
+  },
+
+  dek: {
+    selectors: [
+      ['meta[name="og:description"]', 'value'],
+    ],
+  },
+
+  lead_image_url: {
+    selectors: [
+      ['meta[name="og:image"]', 'value'],
+    ],
+  },
+
+  content: {
+    selectors: [
+      '.article-body',
+    ],
+
+    // Is there anything in the content you selected that needs transformed
+    // before it's consumable content? E.g., unusual lazy loaded images
+    transforms: {
+      'div.inline-content': ($node) => {
+        if ($node.has('img,iframe,video').length > 0) {
+          return 'figure';
+        }
+
+        $node.remove();
+        return null;
+      },
+      '.pb-caption': 'figcaption',
+    },
+
+    // Is there anything that is in the result that shouldn't be?
+    // The clean selectors will remove anything that matches from
+    // the result
+    clean: [
+      '.interstitial-link',
+    ],
+  },
+};

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

@@ -0,0 +1,122 @@
+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('WwwWashingtonpostComExtractor', () => {
+  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 url =
+      'https://www.washingtonpost.com/politics/trump-foundation-apparently-admits-to-violating-ban-on-self-dealing-new-filing-to-irs-shows/2016/11/22/893f6508-b0a9-11e6-8616-52b15787add0_story.html';
+    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.washingtonpost.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.washingtonpost.com/1480364838420.html');
+    const articleUrl =
+      'https://www.washingtonpost.com/politics/trump-foundation-apparently-admits-to-violating-ban-on-self-dealing-new-filing-to-irs-shows/2016/11/22/893f6508-b0a9-11e6-8616-52b15787add0_story.html';
+
+    const { title } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(title, 'Trump Foundation admits to violating ban on ‘self-dealing,’ new filing to IRS shows');
+  });
+
+  it('returns the author', async () => {
+    // To pass this test, fill out the author selector
+    // in ./src/extractors/custom/www.washingtonpost.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.washingtonpost.com/1480364838420.html');
+    const articleUrl =
+      'https://www.washingtonpost.com/politics/trump-foundation-apparently-admits-to-violating-ban-on-self-dealing-new-filing-to-irs-shows/2016/11/22/893f6508-b0a9-11e6-8616-52b15787add0_story.html';
+
+    const { author } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(author, 'David A. Fahrenthold');
+  });
+
+  it('returns the date_published', async () => {
+    // To pass this test, fill out the date_published selector
+    // in ./src/extractors/custom/www.washingtonpost.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.washingtonpost.com/1480364838420.html');
+    const articleUrl =
+      'https://www.washingtonpost.com/politics/trump-foundation-apparently-admits-to-violating-ban-on-self-dealing-new-filing-to-irs-shows/2016/11/22/893f6508-b0a9-11e6-8616-52b15787add0_story.html';
+
+    const { date_published } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(date_published, '2016-11-22T13:57:00.000Z');
+  });
+
+  it('returns the dek', async () => {
+    // To pass this test, fill out the dek selector
+    // in ./src/extractors/custom/www.washingtonpost.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.washingtonpost.com/1480364838420.html');
+    const articleUrl =
+      'https://www.washingtonpost.com/politics/trump-foundation-apparently-admits-to-violating-ban-on-self-dealing-new-filing-to-irs-shows/2016/11/22/893f6508-b0a9-11e6-8616-52b15787add0_story.html';
+
+    const { dek } =
+      await Mercury.parse(articleUrl, html, { fallback: false });
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(dek, 'The foundation checked “yes” on the form for 2015 when asked whether it had transferred “income or assets to a disqualified person.”');
+  });
+
+  it('returns the lead_image_url', async () => {
+    // To pass this test, fill out the lead_image_url selector
+    // in ./src/extractors/custom/www.washingtonpost.com/index.js.
+    const html =
+      fs.readFileSync('./fixtures/www.washingtonpost.com/1480364838420.html');
+    const articleUrl =
+      'https://www.washingtonpost.com/politics/trump-foundation-apparently-admits-to-violating-ban-on-self-dealing-new-filing-to-irs-shows/2016/11/22/893f6508-b0a9-11e6-8616-52b15787add0_story.html';
+
+    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.washingtonpost.com/rf/image_1484w/2010-2019/WashingtonPost/2016/11/01/Others/Images/2016-11-01/Trump-HomeSafe-News-131478026931.jpg');
+  });
+
+  it('returns the content', async () => {
+    // To pass this test, fill out the content selector
+    // in ./src/extractors/custom/www.washingtonpost.com/index.js.
+    // You may also want to make use of the clean and transform
+    // options.
+    const html =
+      fs.readFileSync('./fixtures/www.washingtonpost.com/1480364838420.html');
+    const url =
+      'https://www.washingtonpost.com/politics/trump-foundation-apparently-admits-to-violating-ban-on-self-dealing-new-filing-to-irs-shows/2016/11/22/893f6508-b0a9-11e6-8616-52b15787add0_story.html';
+
+    const { content } =
+      await Mercury.parse(url, html, { fallback: false });
+
+    const $ = cheerio.load(content || '');
+
+    const first13 = excerptContent($('*').first().text(), 13);
+
+    // Update these values with the expected values from
+    // the article.
+    assert.equal(first13, 'Painter Michael Israel, left, poses with Donald and Melania Trump in 2007 at');
+  });
+});