feat: getExtractor returns generic extractor

read

@@ -1,7 +1,9 @@
 #!/usr/bin/env node
+var fs = require('fs')
 var Iris = require('./dist/bundle')
 
 var url = process.argv[2]
-var result = Iris.parse(url).then(function(result) {
+var html = fs.readFileSync('../file.html', 'utf8')
+var result = Iris.parse(url, html).then(function(result) {
   console.log(result.content)
 })

src/extractor/all.js

@@ -0,0 +1,7 @@
+import GenericExtractor from './generic'
+
+const Extractors = {
+  '*': GenericExtractor
+}
+
+export default Extractors

src/extractor/generic/index.js

@@ -8,6 +8,9 @@ import GenericDekExtractor from './dek/extractor'
 import GenericLeadImageUrlExtractor from './lead-image-url/extractor'
 
 const GenericExtractor = {
+  // This extractor is the default for all domains
+  domain: '*',
+
   parse: (url, html, $) => {
     if (html) {
       $ = cheerio.load(html)

src/extractor/get-extractor.js

@@ -0,0 +1,10 @@
+import URL from 'url'
+
+import Extractors from './all'
+
+export default function getExtractor(url) {
+  const parsedUrl = URL.parse(url)
+  const { hostname } = parsedUrl
+
+  return Extractors[hostname] || Extractors['*']
+}

src/extractor/get-extractor.test.js

@@ -0,0 +1,11 @@
+import assert from 'assert'
+
+import getExtractor from './get-extractor'
+
+describe('getExtractor(url)', () => {
+  it('returns GenericExtractor if no custom extractor is found', () => {
+    const extractor = getExtractor('http://example.com')
+
+    assert.equal(extractor.domain, '*')
+  })
+})

src/extractor/index.js

@@ -0,0 +1,5 @@
+const Extractor = {
+
+}
+
+export default Extractor