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
79 lines
1.8 KiB
Ruby
79 lines
1.8 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
# @see Source::URL::HentaiFoundry
|
|
module Sources
|
|
module Strategies
|
|
class HentaiFoundry < Base
|
|
def match?
|
|
Source::URL::HentaiFoundry === parsed_url
|
|
end
|
|
|
|
def image_urls
|
|
image = page&.search("#picBox img")
|
|
|
|
return [] unless image
|
|
|
|
image.to_a.map { |img| URI.join(page_url, img["src"]).to_s }
|
|
end
|
|
|
|
def page_url
|
|
return nil if illust_id.blank?
|
|
|
|
if artist_name.blank?
|
|
"https://www.hentai-foundry.com/pic-#{illust_id}"
|
|
else
|
|
"https://www.hentai-foundry.com/pictures/user/#{artist_name}/#{illust_id}"
|
|
end
|
|
end
|
|
|
|
def page
|
|
return nil if page_url.blank?
|
|
|
|
response = http.cache(1.minute).get("#{page_url}?enterAgree=1")
|
|
return nil unless response.status == 200
|
|
|
|
response.parse
|
|
end
|
|
|
|
def tags
|
|
tags = page&.search(".boxbody [rel='tag']") || []
|
|
|
|
tags.map do |tag|
|
|
[tag.text, URI.join(page_url, tag.attr("href")).to_s]
|
|
end
|
|
end
|
|
|
|
def artist_name
|
|
parsed_url.username || parsed_referer&.username
|
|
end
|
|
|
|
def canonical_url
|
|
image_urls.first
|
|
end
|
|
|
|
def profile_url
|
|
return nil if artist_name.blank?
|
|
"https://www.hentai-foundry.com/user/#{artist_name}"
|
|
end
|
|
|
|
def artist_commentary_title
|
|
page&.search("#picBox .imageTitle")&.text
|
|
end
|
|
|
|
def artist_commentary_desc
|
|
page&.search("#descriptionBox .picDescript")&.to_html
|
|
end
|
|
|
|
def dtext_artist_commentary_desc
|
|
DText.from_html(artist_commentary_desc).gsub(/\A[[:space:]]+|[[:space:]]+\z/, "").gsub(/\n+/, "\n")
|
|
end
|
|
|
|
def illust_id
|
|
parsed_url.work_id || parsed_referer&.work_id
|
|
end
|
|
|
|
memoize :page
|
|
end
|
|
end
|
|
end
|