3aa5cab2aa
`normalize_for_source` was used to convert image URLs to page URLs when displaying sources on the post show page. Move all the code for converting image URLs to page URLs from `Sources::Strategies#normalize_for_source` to `Source::URL#page_url`. Before we had to be very careful in source strategies not to make any network calls in `normalize_for_source`, since it was used in the view for the post show page. Now all the code for generating page URLs is isolated in Source::URL, which makes source strategies simpler. It also makes it easier to check if a source is an image URL or page URL, and if the image URL is convertible to a page URL, which will make autotagging bad_link or bad_source feasible. Finally, this fixes it to generate better page URLs in a handful of cases: * https://www.artstation.com/artwork/qPVGP instead of https://anubis1982918.artstation.com/projects/qPVGP * https://yande.re/post/show?md5=b4b1d11facd1700544554e4805d47bb6s instead of https://yande.re/post?tags=md5:b4b1d11facd1700544554e4805d47bb6 * http://gallery.minitokyo.net/view/365677 instead of http://gallery.minitokyo.net/download/365677 * https://valkyriecrusade.fandom.com/wiki/File:Crimson_Hatsune_H.png instead of https://valkyriecrusade.wikia.com/wiki/File:Crimson_Hatsune_H.png * https://rule34.paheal.net/post/view/852405 instead of https://rule34.paheal.net/post/list/md5:854806addcd3b1246424e7cea49afe31/1
102 lines
2.5 KiB
Ruby
102 lines
2.5 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
# @see Source::URL::ArtStation
|
|
module Sources::Strategies
|
|
class ArtStation < Base
|
|
def match?
|
|
Source::URL::ArtStation === parsed_url
|
|
end
|
|
|
|
def image_urls
|
|
if parsed_url.image_url?
|
|
[asset_url(url)]
|
|
else
|
|
image_urls_from_api
|
|
end
|
|
end
|
|
|
|
def page_url
|
|
return nil if project_id.blank?
|
|
|
|
if artist_name.present?
|
|
"https://#{artist_name}.artstation.com/projects/#{project_id}"
|
|
else
|
|
"https://www.artstation.com/artwork/#{project_id}"
|
|
end
|
|
end
|
|
|
|
def profile_url
|
|
return nil if artist_name.blank?
|
|
"https://www.artstation.com/#{artist_name}"
|
|
end
|
|
|
|
def artist_name
|
|
artist_name_from_url || api_response.dig(:user, :username)
|
|
end
|
|
|
|
def artist_commentary_title
|
|
api_response[:title]
|
|
end
|
|
|
|
def artist_commentary_desc
|
|
api_response[:description]
|
|
end
|
|
|
|
def dtext_artist_commentary_desc
|
|
ActionView::Base.full_sanitizer.sanitize(artist_commentary_desc)
|
|
end
|
|
|
|
def tags
|
|
api_response[:tags].to_a.map do |tag|
|
|
[tag, "https://www.artstation.com/search?q=" + CGI.escape(tag)]
|
|
end
|
|
end
|
|
|
|
def image_urls_from_api
|
|
api_response[:assets].to_a.map do |asset|
|
|
if asset[:asset_type] == "image"
|
|
asset_url(asset[:image_url])
|
|
elsif asset[:asset_type] == "video_clip"
|
|
next # XXX Skip for now; actually downloading these videos requires bypassing a Cloudflare captcha.
|
|
|
|
url = Nokogiri::HTML5.parse(asset[:player_embedded]).at("iframe").attr("src")
|
|
next if url.nil?
|
|
|
|
response = http.cache(1.minute).get(url)
|
|
next if response.status != 200
|
|
|
|
response.parse.at("video source").attr("src")
|
|
end
|
|
end.compact
|
|
end
|
|
|
|
def artist_name_from_url
|
|
parsed_url.username || parsed_referer&.username
|
|
end
|
|
|
|
def project_id
|
|
parsed_url.work_id || parsed_referer&.work_id
|
|
end
|
|
|
|
def api_response
|
|
return {} if project_id.blank?
|
|
|
|
resp = http.cache(1.minute).get("https://www.artstation.com/projects/#{project_id}.json")
|
|
return {} if resp.code != 200
|
|
|
|
resp.parse.with_indifferent_access
|
|
end
|
|
memoize :api_response
|
|
|
|
def asset_url(url)
|
|
parsed_url = Source::URL.parse(url)
|
|
|
|
image_sizes = %w[original 4k large medium small]
|
|
urls = image_sizes.map { |size| parsed_url.full_image_url(size) }
|
|
|
|
chosen_url = urls.find { |url| http_exists?(url) }
|
|
chosen_url || url
|
|
end
|
|
end
|
|
end
|