From 9af933421359c73339fe52506eb6387092d9cda1 Mon Sep 17 00:00:00 2001 From: Chaska <166928710+chaskayote@users.noreply.github.com> Date: Mon, 29 Apr 2024 00:36:08 -0500 Subject: [PATCH] Adding Furbooru --- lib/philomena/scrapers.ex | 1 + lib/philomena/scrapers/furbooru.ex | 30 ++++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) create mode 100644 lib/philomena/scrapers/furbooru.ex diff --git a/lib/philomena/scrapers.ex b/lib/philomena/scrapers.ex index 9cdd578f..5927d667 100644 --- a/lib/philomena/scrapers.ex +++ b/lib/philomena/scrapers.ex @@ -9,6 +9,7 @@ defmodule Philomena.Scrapers do Philomena.Scrapers.Furaffinity, Philomena.Scrapers.Pixiv, Philomena.Scrapers.Derpibooru, + Philomena.Scrapers.Furbooru, Philomena.Scrapers.Raw ] diff --git a/lib/philomena/scrapers/furbooru.ex b/lib/philomena/scrapers/furbooru.ex new file mode 100644 index 00000000..cb315c8d --- /dev/null +++ b/lib/philomena/scrapers/furbooru.ex @@ -0,0 +1,30 @@ +defmodule Philomena.Scrapers.Furbooru do + @url_regex ~r|\Ahttps?://furbooru\.org/images/([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://furbooru.org/api/v1/json/images/#{submission_id}" + {:ok, %Tesla.Env{status: 200, body: body}} = Philomena.Http.get(api_url) + + json = Jason.decode!(body) + submission = json["image"] + + tags = submission["tags"] + + %{ + source_url: url, + tags: tags, + sources: submission["source_url"], + description: submission["description"], + images: [%{ + url: "#{submission["representations"]["full"]}", + camo_url: Camo.Image.image_url(submission["representations"]["medium"]) + }] + } + end +end \ No newline at end of file