Fix: Readability.published_at and Readability.title works as expected (#60)

Author: vkryukov

lib/readability.ex

@@ -152,7 +152,7 @@ defmodule Readability do
   @spec title(binary | html_tree) :: binary
   def title(raw_html) when is_binary(raw_html) do
     raw_html
-    |> Floki.parse_document()
+    |> Floki.parse_document!()
     |> title
   end
 
@@ -183,7 +183,7 @@ defmodule Readability do
   @spec published_at(binary | html_tree) :: %DateTime{} | %Date{} | nil
   def published_at(raw_html) when is_binary(raw_html) do
     raw_html
-    |> Floki.parse_document()
+    |> Floki.parse_document!()
     |> published_at()
   end
 

test/readability/author_finder_test.exs

@@ -3,23 +3,35 @@ defmodule Readability.AuthoFinderTest do
 
   alias Readability.AuthorFinder
 
+  defp test_fixture(file_name, expected_authors) do
+    html = TestHelper.read_fixture(file_name)
+    assert Readability.authors(html) == expected_authors
+
+    parsed_html = TestHelper.read_parse_fixture(file_name)
+    assert AuthorFinder.find(parsed_html) == expected_authors
+  end
+
   test "extracting bbc format author" do
-    html = TestHelper.read_parse_fixture("bbc.html")
-    assert AuthorFinder.find(html) == ["BBC News"]
+    test_fixture("bbc.html", ["BBC News"])
   end
 
   test "extracting buzzfeed format author" do
-    html = TestHelper.read_parse_fixture("buzzfeed.html")
-    assert AuthorFinder.find(html) == ["Salvador Hernandez", "Hamza Shaban"]
+    test_fixture("buzzfeed.html", ["Salvador Hernandez", "Hamza Shaban"])
   end
 
   test "extracting medium format author" do
-    html = TestHelper.read_parse_fixture("medium.html")
-    assert AuthorFinder.find(html) == ["Ken Mazaika"]
+    test_fixture("medium.html", ["Ken Mazaika"])
   end
 
   test "extracting nytimes format author" do
-    html = TestHelper.read_parse_fixture("nytimes.html")
-    assert AuthorFinder.find(html) == ["Judith H. Dobrzynski"]
+    test_fixture("nytimes.html", ["Judith H. Dobrzynski"])
   end
+
+  test "extracting pubmed format author" do
+    test_fixture("pubmed.html", ["Meno H ", "et al."])
+  end
+
+  # test "extracting elixir format author" do
+  #   test_fixture("elixir.html", ["José Valim"])
+  # end
 end

test/readability/published_at_finder_test.exs

@@ -3,31 +3,30 @@ defmodule Readability.PublishedAtFinderTest do
 
   alias Readability.PublishedAtFinder
 
-  test "extracting bbc format published at" do
-    html = TestHelper.read_parse_fixture("bbc.html")
+  defp test_fixture(file_name, expected_published_at) do
+    html = TestHelper.read_fixture(file_name)
+    assert Readability.published_at(html) == expected_published_at
+    parsed_html = TestHelper.read_parse_fixture(file_name)
+    assert PublishedAtFinder.find(parsed_html) == expected_published_at
+  end
 
-    assert PublishedAtFinder.find(html) == nil
+  test "extracting bbc format published at" do
+    test_fixture("bbc.html", nil)
   end
 
   test "extracting buzzfeed format published at" do
-    html = TestHelper.read_parse_fixture("buzzfeed.html")
-
-    assert PublishedAtFinder.find(html) == nil
+    test_fixture("buzzfeed.html", nil)
   end
 
   test "extracting elixir format published at" do
-    html = TestHelper.read_parse_fixture("elixir.html")
-
-    assert PublishedAtFinder.find(html) == nil
+    test_fixture("elixir.html", nil)
   end
 
   test "extracting medium format published at" do
-    html = TestHelper.read_parse_fixture("medium.html")
-    assert PublishedAtFinder.find(html) == ~U[2015-01-31 22:58:05.645Z]
+    test_fixture("medium.html", ~U[2015-01-31 22:58:05.645Z])
   end
 
   test "extracting nytimes format published at" do
-    html = TestHelper.read_parse_fixture("nytimes.html")
-    assert PublishedAtFinder.find(html) == ~D[2016-03-16]
+    test_fixture("nytimes.html", ~D[2016-03-16])
   end
 end

test/readability/title_finder_test.exs

@@ -25,6 +25,22 @@ defmodule Readability.TitleFinderTest do
     assert title == "og title"
   end
 
+  test "extracts most proper title from an html string" do
+    assert Readability.title(@html) == "og title"
+  end
+
+  test "extracts regular title from an html string" do
+    html = """
+    <html>
+      <head>
+        <title>Tag title - test</title>
+      </head>
+    </html>
+    """
+
+    assert Readability.title(html) == "Tag title"
+  end
+
   test "extract og title" do
     title = Readability.TitleFinder.og_title(@html_tree)
     assert title == "og title"