X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fweb%2Frich_media%2Fparser.ex;h=0779065ee1bc9c00e2ddb54f7b3e8c28d9920551;hb=dfd2c741849e9afaf35e3ddbecbb50feb47f5d22;hp=b69b2be610a6383ed5f5c97a92f3db4c0fe3ea02;hpb=93df0796f05eff382301de91fb268bb4bc3c3379;p=akkoma diff --git a/lib/pleroma/web/rich_media/parser.ex b/lib/pleroma/web/rich_media/parser.ex index b69b2be61..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 @@ -55,8 +55,8 @@ defmodule Pleroma.Web.RichMedia.Parser do ttl_setters: [MyModule] """ def set_ttl_based_on_image({:ok, data}, url) do - with {:ok, nil} <- Cachex.ttl(:rich_media_cache, url) do - ttl = get_ttl_from_image(data, url) + with {:ok, nil} <- Cachex.ttl(:rich_media_cache, url), + ttl when is_number(ttl) <- get_ttl_from_image(data, url) do Cachex.expire_at(:rich_media_cache, url, ttl * 1000) {:ok, data} else @@ -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