indix · TheDahv · Mar 7, 2019 · Mar 7, 2019 · Mar 8, 2019
diff --git a/README.md b/README.md
@@ -115,6 +115,24 @@ Our `parsed` object should look like -
 
 The `parsed` object includes four objects - `microdata`, `rdfa`, `jsonld` and `metatags`. Since the above HTML does not have any information encoded in `rdfa` and `jsonld`, those two objects are empty.
 
+#### [Errors](#errors)
+
+There is no guarantee against malformed content when working with live pages on
+the Internet. This is especially true when webmasters attempt to work with
+JSON-LD. You can expect to parse a page with malformed content at some point.
+
+In the case of JSON-LD, the parser will accumulate any parse errors encountered
+in an `errors` array if at least one was encountered. Note, they will be full
+Node.js error objects, so be prepared to pull off the data you need.
+
+```js
+const parsed = WAE().parse(whatWereTheyThinkingHTML)
+const parseErrors = parsed.jsonld.errors(err => err.message)
+```
+
+Clients can take advantage of checking for the presence of the `errors` property
+and respond accordingly.
+
 ## Caveat
 
 I wouldn't call it a caveat but rather the parser is strict by design. It might not parse like expected if the HTML isn't encoded correctly, so one might assume the parser is broken.

diff --git a/src/parsers/jsonld-parser.js b/src/parsers/jsonld-parser.js
@@ -17,6 +17,8 @@ export default function (html, config = {}) {
         jsonldData[type].push(obj)
       })
     } catch (e) {
+      if (!('errors' in jsonldData)) { jsonldData.errors = [] }
+      jsonldData.errors.push(e)
       console.log(`Error in jsonld parse - ${e}`)
     }
   })

diff --git a/test/resources/expectedErrors.json b/test/resources/expectedErrors.json
@@ -0,0 +1,6 @@
+{
+  "jsonld": [
+    "Unexpected end of JSON input",
+    "Unexpected token ' in JSON at position 11"
+  ]
+}
diff --git a/test/resources/testErrorPage.html b/test/resources/testErrorPage.html
@@ -0,0 +1,140 @@
+<!-- Example of incomplete JSON object -->
+<script type="application/ld+json">
+{
+  "@context": "http://schema.org/",
+  "@type": "Product",
+  "name": "Executive Anvil",
+  "image": "http://www.example.com/anvil_executive.jpg",
+  "description": "Sleeker than ACME's Classic Anvil, the Executive Anvil is perfect for the business traveler looking for something to drop from a height.",
+  "mpn": "925872",
+  "brand": {
+    "@type": "Thing",
+    "name": "ACME"
+  },
+  "aggregateRating": {
+    "@type": "AggregateRating",
+    "ratingValue": "4.4",
+    "reviewCount": "89"
+  },
+
+</script>
+<!-- Example of JSON with single instead of double-quotes -->
+<script type="application/ld+json">
+[
+  {
+    '@context':'http://schema.org',
+    '@type':'TheaterEvent',
+    'name':'Random Theater Show #1',
+    'startDate':'2016-12-15T19:30:00-06:00',
+    'location':{
+      '@type':'Place',
+      'name':'Theatre'
+    }
+  },
+  {
+    '@context':'http://schema.org',
+    '@type':'TheaterEvent',
+    'name':'Random Theater Show #2',
+    'startDate':'2016-12-16T19:30:00-06:00',
+    'location':{
+      '@type':'Place',
+      'name':'Theatre'
+    }
+  }
+]
+</script>
+<div itemscope itemtype="http://schema.org/Product">
+  <span itemprop="brand">ACME</span>
+  <span itemprop="name">Executive Anvil</span>
+  <img itemprop="image" src="anvil_executive.jpg" alt="Executive Anvil logo" />
+  <span itemprop="description">Sleeker than ACME's Classic Anvil, the
+    Executive Anvil is perfect for the business traveler
+    looking for something to drop from a height.
+  </span>
+  Product #: <span itemprop="mpn">925872</span>
+  <span itemprop="aggregateRating" itemscope itemtype="http://schema.org/AggregateRating">
+    <span itemprop="ratingValue">4.4</span> stars, based on <span itemprop="reviewCount">89
+      </span> reviews
+  </span>
+
+  <span itemprop="offers" itemscope itemtype="http://schema.org/Offer">
+    Regular price: $179.99
+    <meta itemprop="priceCurrency" content="USD" />
+    $<span itemprop="price">119.99</span>
+    (Sale ends <time itemprop="priceValidUntil" datetime="2020-11-05">
+      5 November!</time>)
+    Available from: <span itemprop="seller" itemscope itemtype="http://schema.org/Organization">
+                      <span itemprop="name">Executive Objects</span>
+                    </span>
+    Condition: <link itemprop="itemCondition" href="http://schema.org/UsedCondition"/>Previously owned,
+      in excellent condition
+    <link itemprop="availability" href="http://schema.org/InStock"/>In stock! Order now!</span>
+  </span>
+</div>
+<!-- example from http://schema.org/Recipe -->
+<div itemscope itemtype="http://schema.org/Recipe">
+  <span itemprop="name">Mom's World Famous Banana Bread</span>
+  By <span itemprop="author">John Smith</span>,
+  <meta itemprop="datePublished" content="2009-05-08">May 8, 2009
+  <meta http-equiv="refresh" content="30">
+  <img itemprop="image" src="bananabread.jpg"
+       alt="Banana bread on a plate" />
+  <span itemprop="description">This classic banana bread recipe comes
+  from my mom -- the walnuts add a nice texture and flavor to the banana
+  bread.</span>
+  Prep Time: <meta itemprop="prepTime" content="PT15M">15 minutes
+  Cook time: <meta itemprop="cookTime" content="PT1H">1 hour
+  Yield: <span itemprop="recipeYield">1 loaf</span>
+  Tags: <link itemprop="suitableForDiet" href="http://schema.org/LowFatDiet" />Low fat
+  <div itemprop="nutrition"
+       itemscope itemtype="http://schema.org/NutritionInformation">
+    Nutrition facts:
+    <span itemprop="calories">240 calories</span>,
+    <span itemprop="fatContent">9 grams fat</span>
+  </div>
+  Ingredients:
+  - <span itemprop="recipeIngredient">3 or 4 ripe bananas, smashed</span>
+  - <span itemprop="recipeIngredient">1 egg</span>
+  - <span itemprop="recipeIngredient">3/4 cup of sugar</span>
+  ...
+  Instructions:
+  <span itemprop="recipeInstructions">
+  Preheat the oven to 350 degrees. Mix in the ingredients in a bowl. Add
+  the flour last. Pour the mixture into a loaf pan and bake for one hour.
+  </span>
+  140 comments:
+  <div itemprop="interactionStatistic" itemscope itemtype="http://schema.org/InteractionCounter">
+    <meta itemprop="interactionType" content="http://schema.org/CommentAction" />
+    <meta itemprop="userInteractionCount" content="140" />
+  </div>
+  From Janel, May 5 -- thank you, great recipe!
+  ...
+</div>
+<div vocab="http://schema.org/" typeof="Product">
+  <span property="brand">ACME</span>
+  <span property="name">Executive Anvil</span>
+  <img propertyu="image" src="anvil_executive.jpg" alt="Executive Anvil logo" />
+  <span property="description">Sleeker than ACME's Classic Anvil, the
+    Executive Anvil is perfect for the business traveler
+    looking for something to drop from a height.
+  </span>
+  Product #: <span property="mpn">925872</span>
+  <span property="aggregateRating" typeof="AggregateRating">
+    <span property="ratingValue">4.4</span> stars, based on <span property="reviewCount">89
+      </span> reviews
+  </span>
+
+  <span property="offers" typeof="Offer">
+    Regular price: $179.99
+    <meta property="priceCurrency" content="USD" />
+    $<span property="price">119.99</span>
+    (Sale ends <time property="priceValidUntil" datetime="2020-11-05">
+      5 November!</time>)
+    Available from: <span property="seller" typeof="Organization">
+                      <span property="name">Executive Objects</span>
+                    </span>
+    Condition: <link property="itemCondition" href="http://schema.org/UsedCondition"/>Previously owned,
+      in excellent condition
+    <link property="availability" content="http://schema.org/InStock"/>In stock! Order now!</span>
+  </span>
+</div>
diff --git a/test/test.js b/test/test.js
@@ -7,6 +7,8 @@ import WAE from '../src'
 const fileReader = (fileName) => fs.readFileSync(fileName, { encoding: 'utf-8' })
 const expectedResult = JSON.parse(fileReader('test/resources/expectedResult.json'))
 const testPage = fileReader('test/resources/testPage.html')
+const testErrorPage = fileReader('test/resources/testErrorPage.html')
+const expectedErrors = JSON.parse(fileReader('test/resources/expectedErrors.json'))
 const { microdata, rdfa, metatags, jsonld } = WAE().parse(testPage)
 
 describe('Web Auto Extractor', function () {
@@ -25,4 +27,15 @@ describe('Web Auto Extractor', function () {
   it('should find embedded meta tags', function () {
     assert.deepEqual(metatags, expectedResult.metatags)
   })
+
+  describe('when there are parse errors', function () {
+    const { jsonld } = WAE().parse(testErrorPage)
+
+    it('should save jsonld parse errors', function () {
+      assert.equal(
+        jsonld.errors.length,
+        expectedErrors.jsonld.length
+      )
+    })
+  })
 })