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
63 lines
1.9 KiB
Ruby
63 lines
1.9 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
class Source::URL::Lofter < Source::URL
|
|
RESERVED_SUBDOMAINS = %w[www.lofter.com i.lofter.com]
|
|
|
|
attr_reader :username, :work_id, :unescaped_tag
|
|
|
|
def self.match?(url)
|
|
url.domain.in?(%w[lofter.com 127.net lf127.net])
|
|
end
|
|
|
|
def parse
|
|
case [host, *path_segments]
|
|
|
|
# https://imglf3.lf127.net/img/S1d2QlVsWkJhSW1qcnpIS0ZSa3ZJSzFCWFlnUWgzb01DcUdpT1lreG5yQjJVMkhGS09HNGR3PT0.png?imageView&thumbnail=1680x0&quality=96&stripmeta=0
|
|
# https://imglf3.lf127.net/img/S1d2QlVsWkJhSW1qcnpIS0ZSa3ZJSzFCWFlnUWgzb01DcUdpT1lreG5yQjJVMkhGS09HNGR3PT0.png
|
|
# http://imglf0.nosdn.127.net/img/cHl3bXNZdDRaaHBnNWJuN1Y4OXBqR01CeVBZSVNmU2FWZWtHc1h4ZTZiUGxlRzMwZnFDM1JnPT0.jpg (404)
|
|
in /127\.net$/, "img", _
|
|
nil
|
|
|
|
# https://www.lofter.com/front/blog/home-page/noshiqian
|
|
in "www.lofter.com", "front", "blog", "home-page", username
|
|
@username = username
|
|
|
|
# http://www.lofter.com/app/xiaokonggedmx
|
|
# http://www.lofter.com/blog/semblance
|
|
in "www.lofter.com", ("app" | "blog"), username
|
|
@username = username
|
|
|
|
# https://gengar563.lofter.com/post/1e82da8c_1c98dae1b
|
|
in /^([a-z0-9-]+)\.lofter\.com$/, "post", work_id unless host.in?(RESERVED_SUBDOMAINS)
|
|
@username = $1
|
|
@work_id = work_id
|
|
|
|
# https://gengar563.lofter.com/tag/%E5%BA%9F%E5%BC%83%E7%9B%90%E9%85%B8%E5%A4%84%E7%90%86%E5%8E%82
|
|
in /^([a-z0-9-]+)\.lofter\.com$/, "tag", tag
|
|
@unescaped_tag = CGI.unescape(tag)
|
|
|
|
# http://gengar563.lofter.com
|
|
in /^([a-z0-9-]+)\.lofter\.com$/, *rest unless host.in?(RESERVED_SUBDOMAINS)
|
|
@username = $1
|
|
|
|
else
|
|
end
|
|
end
|
|
|
|
def image_url?
|
|
url.domain.in?(%w[lf127.net 127.net])
|
|
end
|
|
|
|
def full_image_url
|
|
"#{site}#{path}" if image_url?
|
|
end
|
|
|
|
def page_url
|
|
"https://#{username}.lofter.com/post/#{work_id}" if username.present? && work_id.present?
|
|
end
|
|
|
|
def profile_url
|
|
"https://#{username}.lofter.com" if username.present?
|
|
end
|
|
end
|