1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
|
# Pleroma: A lightweight social networking server
# Copyright _ 2017-2020 Pleroma Authors <https://pleroma.social/>
# SPDX-License-Identifier: AGPL-3.0-only
defmodule Pleroma.Web.RichMedia.Helpers do
alias Pleroma.Activity
alias Pleroma.Config
alias Pleroma.HTML
alias Pleroma.Object
alias Pleroma.Web.RichMedia.Parser
@rich_media_options [
pool: :media,
max_body: 2_000_000
]
@spec validate_page_url(URI.t() | binary()) :: :ok | :error
defp validate_page_url(page_url) when is_binary(page_url) do
validate_tld = Pleroma.Config.get([Pleroma.Formatter, :validate_tld])
page_url
|> Linkify.Parser.url?(validate_tld: validate_tld)
|> parse_uri(page_url)
end
defp validate_page_url(%URI{host: host, scheme: "https", authority: authority})
when is_binary(authority) do
cond do
host in Config.get([:rich_media, :ignore_hosts], []) ->
:error
get_tld(host) in Config.get([:rich_media, :ignore_tld], []) ->
:error
true ->
:ok
end
end
defp validate_page_url(_), do: :error
defp parse_uri(true, url) do
url
|> URI.parse()
|> validate_page_url
end
defp parse_uri(_, _), do: :error
defp get_tld(host) do
host
|> String.split(".")
|> Enum.reverse()
|> hd
end
def fetch_data_for_object(object) do
with true <- Config.get([:rich_media, :enabled]),
false <- object.data["sensitive"] || false,
{:ok, page_url} <-
HTML.extract_first_external_url_from_object(object),
:ok <- validate_page_url(page_url),
{:ok, rich_media} <- Parser.parse(page_url) do
%{page_url: page_url, rich_media: rich_media}
else
_ -> %{}
end
end
def fetch_data_for_activity(%Activity{data: %{"type" => "Create"}} = activity) do
with true <- Config.get([:rich_media, :enabled]),
%Object{} = object <- Object.normalize(activity) do
fetch_data_for_object(object)
else
_ -> %{}
end
end
def fetch_data_for_activity(_), do: %{}
def perform(:fetch, %Activity{} = activity) do
fetch_data_for_activity(activity)
:ok
end
def rich_media_get(url) do
headers = [{"user-agent", Pleroma.Application.user_agent() <> "; Bot"}]
options =
if Application.get_env(:tesla, :adapter) == Tesla.Adapter.Hackney do
Keyword.merge(@rich_media_options,
recv_timeout: 2_000,
with_body: true
)
else
@rich_media_options
end
head_check =
case Pleroma.HTTP.head(url, headers, adapter: options) do
# If the HEAD request didn't reach the server for whatever reason,
# we assume the GET that comes right after won't either
{:error, _} = e ->
e
{:ok, %Tesla.Env{status: 200, headers: headers}} ->
with :ok <- check_content_type(headers),
:ok <- check_content_length(headers),
do: :ok
_ ->
:ok
end
with :ok <- head_check, do: Pleroma.HTTP.get(url, headers, adapter: options)
end
defp check_content_type(headers) do
case List.keyfind(headers, "content-type", 0) do
{_, content_type} ->
case Plug.Conn.Utils.media_type(content_type) do
{:ok, "text", "html", _} -> :ok
_ -> {:error, {:content_type, content_type}}
end
_ ->
:ok
end
end
@max_body @rich_media_options[:max_body]
defp check_content_length(headers) do
case List.keyfind(headers, "content-length", 0) do
{_, maybe_content_length} ->
case Integer.parse(maybe_content_length) do
{content_length, ""} when content_length <= @max_body -> :ok
{_, ""} -> {:error, :body_too_large}
_ -> :ok
end
_ ->
:ok
end
end
end
|
