From f2eec71ec5debc0cb3c6ffbbd0a336ebd4e73fa4 Mon Sep 17 00:00:00 2001
From: Chaska <166928710+chaskayote@users.noreply.github.com>
Date: Tue, 23 Apr 2024 01:08:00 -0500
Subject: [PATCH] Trying to add Pixiv scraper
---
lib/philomena/scrapers.ex | 1 +
lib/philomena/scrapers/pixiv.ex | 35 +++++++++++++++++++++++++++++++++
2 files changed, 36 insertions(+)
create mode 100644 lib/philomena/scrapers/pixiv.ex
diff --git a/lib/philomena/scrapers.ex b/lib/philomena/scrapers.ex
index d0ac22ae..fe8657f2 100644
--- a/lib/philomena/scrapers.ex
+++ b/lib/philomena/scrapers.ex
@@ -7,6 +7,7 @@ defmodule Philomena.Scrapers do
Philomena.Scrapers.Inkbunny,
Philomena.Scrapers.E621,
Philomena.Scrapers.Furaffinity,
+ Philomena.Scrapers.Pixiv,
Philomena.Scrapers.Raw
]
diff --git a/lib/philomena/scrapers/pixiv.ex b/lib/philomena/scrapers/pixiv.ex
new file mode 100644
index 00000000..fbb2e24c
--- /dev/null
+++ b/lib/philomena/scrapers/pixiv.ex
@@ -0,0 +1,35 @@
+defmodule Philomena.Scrapers.Pixiv do
+ @url_regex ~r|\Ahttps?://pixiv\.net/en/artworks/([0-9]+)|
+
+ @spec can_handle?(URI.t(), String.t()) :: true | false
+ def can_handle?(_uri, url) do
+ String.match?(url, @url_regex)
+ end
+
+ def scrape(_uri, url) do
+ [_, submission_id] = Regex.run(@url_regex, url, capture: :all)
+ api_url = "https://www.pixiv.net/touch/ajax/illust/details?illust_id=#{submission_id}"
+ {:ok, %Tesla.Env{status: 200, body: body}} = Philomena.Http.get(api_url)
+
+ submission = Jason.decode!(body)
+
+ description = submission["illust_details"]["comment"]
+ |> HtmlSanitizeEx.strip_tags()
+ |> String.replace(~r/ +/, " ")
+ |> String.replace(~r/\n \n +/, "\n")
+ |> String.replace(~r/\n /, "\n")
+ |> String.trim()
+
+ %{
+ source_url: url,
+ author_name: submission["author_details"]["user_account"],
+ description: description,
+ images: [
+ %{
+ url: "#{submission["illust_details"]["manga_a"]["url_big"]}",
+ camo_url: Camo.Image.image_url(submission["illust_details"]["manga_a"]["url"])
+ }
+ ]
+ }
+ end
+end