meta tag parser respect first title header
This commit is contained in:
parent
d9cb8acd3e
commit
7bd4c14581
@ -48,6 +48,6 @@ defp maybe_put_title(meta, html) when meta != %{} do
|
||||
defp maybe_put_title(meta, _), do: meta
|
||||
|
||||
defp get_page_title(html) do
|
||||
Floki.find(html, "title") |> Floki.text()
|
||||
Floki.find(html, "title") |> List.first() |> Floki.text()
|
||||
end
|
||||
end
|
||||
|
2895
test/fixtures/margaret-corbin-grave-west-point.html
vendored
Normal file
2895
test/fixtures/margaret-corbin-grave-west-point.html
vendored
Normal file
File diff suppressed because it is too large
Load Diff
@ -66,4 +66,23 @@ test "parses twitter card with name & property attributes" do
|
||||
"https://www.nytimes.com/2019/08/01/nyregion/nypd-facial-recognition-children-teenagers.html"
|
||||
}}
|
||||
end
|
||||
|
||||
test "respect only first title tag on the page" do
|
||||
image_path =
|
||||
"https://assets.atlasobscura.com/media/W1siZiIsInVwbG9hZHMvYXNzZXRzLzkwYzgyMzI4LThlMDUtNGRiNS05MDg3LTUzMGUxZTM5N2RmMmVkOTM5ZDM4MGM4OTIx" <>
|
||||
"YTQ5MF9EQVIgZXhodW1hdGlvbiBvZiBNYXJnYXJldCBDb3JiaW4gZ3JhdmUgMTkyNi5qcGciXSxbInAiLCJjb252ZXJ0IiwiIl0sWyJwIiwiY29udmVydCIsIi1xdWFsaXR5IDgxIC1hdXRvLW9" <>
|
||||
"yaWVudCJdLFsicCIsInRodW1iIiwiNjAweD4iXV0/DAR%20exhumation%20of%20Margaret%20Corbin%20grave%201926.jpg"
|
||||
|
||||
html = File.read!("test/fixtures/margaret-corbin-grave-west-point.html")
|
||||
|
||||
assert TwitterCard.parse(html, %{}) ==
|
||||
{:ok,
|
||||
%{
|
||||
site: "@atlasobscura",
|
||||
title:
|
||||
"The Missing Grave of Margaret Corbin, Revolutionary War Veteran - Atlas Obscura",
|
||||
card: "summary_large_image",
|
||||
image: image_path
|
||||
}}
|
||||
end
|
||||
end
|
||||
|
Loading…
Reference in New Issue
Block a user