grangier#173 - authors extraction test case

Xavier Grangier · Xavier Grangier · commit 321fb86e0938 · 2014-12-30T01:05:04.000+01:00
diff --git a/tests/data/extractors/test_author_schema.html b/tests/data/extractors/test_author_schema.html
@@ -0,0 +1,12 @@
+<html>
+    <body>
+        <p class="byline-dateline">
+            <span class="byline" itemprop="author creator" itemscope="" itemtype="http://schema.org/Person" itemid="http://topics.nytimes.com/top/reference/timestopics/people/s/kevin_sack/index.html">By <a href="http://topics.nytimes.com/top/reference/timestopics/people/s/kevin_sack/index.html" rel="author" title="More Articles by KEVIN SACK"><span class="byline-author" data-byline-name="KEVIN SACK" itemprop="name" data-twitter-handle="ksacknyt">KEVIN SACK</span></a>, </span><span class="byline" itemprop="author creator" itemscope="" itemtype="http://schema.org/Person" itemid="http://topics.nytimes.com/top/reference/timestopics/people/f/sheri_fink/index.html"><a href="http://topics.nytimes.com/top/reference/timestopics/people/f/sheri_fink/index.html" rel="author" title="More Articles by SHERI FINK"><span class="byline-author" data-byline-name="SHERI FINK" itemprop="name">SHERI FINK</span></a>, </span><span class="byline" itemprop="author creator" itemscope="" itemtype="http://schema.org/Person" itemid="http://topics.nytimes.com/top/reference/timestopics/people/b/pam_belluck/index.html"><a href="http://topics.nytimes.com/top/reference/timestopics/people/b/pam_belluck/index.html" rel="author" title="More Articles by PAM BELLUCK"><span class="byline-author" data-byline-name="PAM BELLUCK" itemprop="name">PAM BELLUCK</span></a> and </span><span class="byline" itemprop="author creator" itemscope="" itemtype="http://schema.org/Person" itemid="http://topics.nytimes.com/top/reference/timestopics/people/n/adam_nossiter/index.html"><a href="http://topics.nytimes.com/top/reference/timestopics/people/n/adam_nossiter/index.html" rel="author" title="More Articles by ADAM NOSSITER"><span class="byline-author" data-byline-name="ADAM NOSSITER" itemprop="name">ADAM NOSSITER</span></a></span>
+        </p>
+        <div itemprop="articleBody">
+            <p>
+              TextNode 1 - The Scala supported IDE is one of the few pain points of developers who want to start using Scala in their Java project. On existing long term project developed by a team its hard to step in and introduce a new language that is not supported by the existing IDE. On way to go about it is to hid the fact that you use Scala from the Java world by using one way dependency injection. Still, if you wish to truly absorb Scala into your existing java environment then you'll soon introduced cross language dependencies.
+            </p>
+        </div>
+    </body>
+</html>
diff --git a/tests/data/extractors/test_author_schema.json b/tests/data/extractors/test_author_schema.json
@@ -0,0 +1,11 @@
+{
+    "url": "http://exemple.com/tweet/", 
+    "expected": {
+        "authors": [
+            "KEVIN SACK", 
+            "ADAM NOSSITER", 
+            "PAM BELLUCK", 
+            "SHERI FINK"
+        ]
+    }
+}
diff --git a/tests/extractors.py b/tests/extractors.py
@@ -448,6 +448,14 @@ def test_tweet(self):
         self.assertEqual(number_tweets, expected_number_tweets)
 
 
+class TestArticleAuthor(TestExtractionBase):
+
+    def test_author_schema(self):
+        article = self.getArticle()
+        fields = ['authors']
+        self.runArticleAssertions(article=article, fields=fields)
+
+
 class TestArticleTags(TestExtractionBase):
 
     def test_tags_kexp(self):
