diff --git a/lib/readability/helper.ex b/lib/readability/helper.ex index 9861143..7562dbc 100644 --- a/lib/readability/helper.ex +++ b/lib/readability/helper.ex @@ -111,6 +111,7 @@ defmodule Readability.Helper do |> transform_img_paths(opts[:url]) |> Floki.parse() |> Floki.filter_out(:comment) + |> remove_tag(fn {tag, _, _} -> is_atom(tag) end) end # Turn relative `img` tag paths into absolute if possible diff --git a/test/readability/helper_test.exs b/test/readability/helper_test.exs index a0a60b2..dd85b59 100644 --- a/test/readability/helper_test.exs +++ b/test/readability/helper_test.exs @@ -50,6 +50,15 @@ defmodule Readability.HelperTest do assert result == 5 end + test "strips out special case tags" do + expected_html = + "

Hello

" + |> Helper.normalize() + |> Floki.raw_html() + + assert expected_html == "

Hello

" + end + test "transform img relative paths into absolute" do foo_url = "https://example.org/images/foo.png" bar_url_http = "http://example.org/images/bar.png"