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
92 lines
2.3 KiB
Ruby
92 lines
2.3 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
# @see Source::URL::Foundation
|
|
module Sources
|
|
module Strategies
|
|
class Foundation < Base
|
|
def match?
|
|
Source::URL::Foundation === parsed_url
|
|
end
|
|
|
|
def image_urls
|
|
if parsed_url.full_image_url.present?
|
|
[parsed_url.full_image_url]
|
|
elsif image_url = page&.at(".fullscreen img, .fullscreen video")&.attr(:src)
|
|
[Source::URL.parse(image_url).full_image_url].compact
|
|
else
|
|
[]
|
|
end
|
|
end
|
|
|
|
def page_url
|
|
parsed_url.page_url || parsed_referer&.page_url
|
|
end
|
|
|
|
def page
|
|
return nil if page_url.blank?
|
|
|
|
response = http.cache(1.minute).get(page_url)
|
|
return nil unless response.status == 200
|
|
|
|
response.parse
|
|
end
|
|
|
|
def tags
|
|
tags = api_response.dig("props", "pageProps", "artwork", "tags").to_a
|
|
|
|
tags.map do |tag|
|
|
[tag, "https://foundation.app/tags/#{tag}"]
|
|
end
|
|
end
|
|
|
|
def artist_name
|
|
parsed_url.username || parsed_referer&.username || api_response.dig("props", "pageProps", "artwork", "creator", "username")
|
|
end
|
|
|
|
def profile_url
|
|
return nil if artist_name.blank?
|
|
"https://foundation.app/@#{artist_name}"
|
|
end
|
|
|
|
def profile_urls
|
|
[profile_url, creator_public_key_url].compact
|
|
end
|
|
|
|
def creator_public_key_url
|
|
return nil if creator_public_key.nil?
|
|
"https://foundation.app/#{creator_public_key}"
|
|
end
|
|
|
|
def creator_public_key
|
|
api_response.dig("props", "pageProps", "artwork", "creator", "publicKey")
|
|
end
|
|
|
|
def artist_commentary_title
|
|
return nil if page.blank?
|
|
page.at("meta[property='og:title']")["content"].gsub(/ \| Foundation$/, "")
|
|
end
|
|
|
|
def artist_commentary_desc
|
|
header = page&.xpath("//h2[text()='Description']")&.first
|
|
return nil if header.blank?
|
|
header&.parent&.search("div").first&.to_html
|
|
end
|
|
|
|
def dtext_artist_commentary_desc
|
|
DText.from_html(artist_commentary_desc)
|
|
end
|
|
|
|
def api_response
|
|
return {} if page.nil?
|
|
|
|
data = page.at("#__NEXT_DATA__")&.text
|
|
return {} if data.blank?
|
|
|
|
JSON.parse(data).with_indifferent_access
|
|
end
|
|
|
|
memoize :api_response
|
|
end
|
|
end
|
|
end
|