X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fweb%2Frich_media%2Fparser.ex;h=0779065ee1bc9c00e2ddb54f7b3e8c28d9920551;hb=5ad54d1bd556f3dc957aa1d2ebe6314618e75399;hp=185156375fa36ed69d7d277a76c9a81d96b8f5e4;hpb=a00aab340275036858aecfef16b719abde3276c6;p=akkoma
diff --git a/lib/pleroma/web/rich_media/parser.ex b/lib/pleroma/web/rich_media/parser.ex
index 185156375..0779065ee 100644
--- a/lib/pleroma/web/rich_media/parser.ex
+++ b/lib/pleroma/web/rich_media/parser.ex
@@ -1,5 +1,5 @@
# Pleroma: A lightweight social networking server
-# Copyright © 2017-2019 Pleroma Authors
+# Copyright © 2017-2020 Pleroma Authors
# SPDX-License-Identifier: AGPL-3.0-only
defmodule Pleroma.Web.RichMedia.Parser do
@@ -81,15 +81,19 @@ defmodule Pleroma.Web.RichMedia.Parser do
{:ok, %Tesla.Env{body: html}} = Pleroma.HTTP.get(url, [], adapter: @hackney_options)
html
+ |> parse_html()
|> maybe_parse()
+ |> Map.put(:url, url)
|> clean_parsed_data()
|> check_parsed_data()
rescue
e ->
- {:error, "Parsing error: #{inspect(e)}"}
+ {:error, "Parsing error: #{inspect(e)} #{inspect(__STACKTRACE__)}"}
end
end
+ defp parse_html(html), do: Floki.parse_document!(html)
+
defp maybe_parse(html) do
Enum.reduce_while(parsers(), %{}, fn parser, acc ->
case parser.parse(html, acc) do
@@ -99,7 +103,8 @@ defmodule Pleroma.Web.RichMedia.Parser do
end)
end
- defp check_parsed_data(%{title: title} = data) when is_binary(title) and byte_size(title) > 0 do
+ defp check_parsed_data(%{title: title} = data)
+ when is_binary(title) and byte_size(title) > 0 do
{:ok, data}
end