Add missing files

packages/content-handler/src/index.ts

@@ -36,6 +36,7 @@ import { TwitterHandler } from './websites/twitter-handler'
 import { WeixinQqHandler } from './websites/weixin-qq-handler'
 import { WikipediaHandler } from './websites/wikipedia-handler'
 import { YoutubeHandler } from './websites/youtube-handler'
+import { TheAtlanticHandler } from './websites/the-atlantic-handler'
 
 const validateUrlString = (url: string): boolean => {
   const u = new URL(url)
@@ -56,6 +57,7 @@ const validateUrlString = (url: string): boolean => {
 }
 
 const contentHandlers: ContentHandler[] = [
+  new TheAtlanticHandler(),
   new AppleNewsHandler(),
   new BloombergHandler(),
   new DerstandardHandler(),

packages/content-handler/test/the-atlantic-handler.test.ts

@@ -0,0 +1,42 @@
+import { TheAtlanticHandler } from '../src/websites/the-atlantic-handler'
+import fs from 'fs';
+import nock from 'nock'
+
+describe('Testing the atlantic opening', () => {
+  const load = (path: string): string => {
+    return fs.readFileSync(path, 'utf8')
+  }
+  
+  
+  before(() => {
+    const html = load('./test/data/the-atlantic-article.html');
+    nock('https://theatlantic.com').get('/article/').reply(200, html)
+  })
+
+  it('should parse the title of the atlantic article.', async () => {
+    const response = await new TheAtlanticHandler().preHandle(
+      'https://theatlantic.com/article/'
+    );
+
+    // We grab the title from the doucment. 
+    expect(response.title).not.toBeFalsy()
+  })
+
+  it('should remove the article section, and replace it with a parseable div', async () => {
+    const response = await new TheAtlanticHandler().preHandle(
+      'https://theatlantic.com/article/'
+    );
+
+    // We grab the title from the doucment. 
+    expect(response.dom?.querySelector('[data-event-module="article body"]')).toBeEmptyDOMElement()
+  });
+
+  it ('should append a new div, and add the article content inside', () => { 
+    const response = await new TheAtlanticHandler().preHandle(
+      'https://theatlantic.com/article/'
+    );
+
+    // We grab the title from the doucment. 
+    expect(response.dom?.getElementById('prehandled')).not.toBeEmptyDOMElement()
+  })
+})

packages/puppeteer-parse/index.js

@@ -14,7 +14,7 @@ const signToken = promisify(jwt.sign);
 const os = require('os');
 const { Storage } = require('@google-cloud/storage');
 const { parseHTML } = require('linkedom');
-const { preHandleContent, preParseContent } = require('../content-handler/src/index');
+const { preHandleContent, preParseContent } = require("@omnivore/content-handler");
 const { Readability } = require("@omnivore/readability");
 
 const puppeteer = require('puppeteer-extra');