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
104 lines
2.9 KiB
Ruby
104 lines
2.9 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
# @see Source::URL::Weibo
|
|
module Sources
|
|
module Strategies
|
|
class Weibo < Base
|
|
|
|
def match?
|
|
Source::URL::Weibo === parsed_url
|
|
end
|
|
|
|
def image_urls
|
|
if parsed_url.image_url?
|
|
[parsed_url.full_image_url]
|
|
elsif api_response.present?
|
|
if api_response["pics"].present?
|
|
api_response["pics"].pluck("url").map { |url| Source::URL.parse(url).full_image_url }
|
|
elsif api_response.dig("page_info", "type") == "video"
|
|
variants = api_response["page_info"]["media_info"].to_h.values + api_response["page_info"]["urls"].to_h.values
|
|
largest_video = variants.max_by do |variant|
|
|
if /template=(?<width>\d+)x(?<height>\d+)/ =~ variant.to_s
|
|
width.to_i * height.to_i
|
|
else
|
|
0
|
|
end
|
|
end
|
|
[largest_video]
|
|
end
|
|
else
|
|
[url]
|
|
end
|
|
end
|
|
|
|
def page_url
|
|
return nil unless api_response.present?
|
|
|
|
artist_id = api_response["user"]["id"]
|
|
illust_base62_id = api_response["bid"]
|
|
"https://www.weibo.com/#{artist_id}/#{illust_base62_id}"
|
|
end
|
|
|
|
def tags
|
|
return [] if api_response.blank?
|
|
|
|
matches = api_response["text"]&.scan(/surl-text">#(.*?)#</).to_a.map { |m| m[0] }
|
|
matches.map do |match|
|
|
[match, "https://s.weibo.com/weibo/#{match}"]
|
|
end
|
|
end
|
|
|
|
def profile_urls
|
|
[parsed_url.profile_url, parsed_referer&.profile_url].compact.uniq
|
|
end
|
|
|
|
def profile_url
|
|
"https://www.weibo.com/u/#{artist_id}" if artist_id.present?
|
|
end
|
|
|
|
def artist_name
|
|
api_response&.dig("user", "screen_name")
|
|
end
|
|
|
|
def artist_id
|
|
parsed_url.artist_short_id || parsed_referer&.artist_short_id || api_response&.dig("user", "id")
|
|
end
|
|
|
|
def artist_commentary_desc
|
|
return if api_response.blank?
|
|
|
|
api_response["text"]
|
|
end
|
|
|
|
def dtext_artist_commentary_desc
|
|
DText.from_html(artist_commentary_desc) do |element|
|
|
if element["href"].present?
|
|
href = Addressable::URI.heuristic_parse(element["href"])
|
|
href.site ||= "https://www.weibo.com"
|
|
href.scheme ||= "https"
|
|
element["href"] = href.to_s
|
|
end
|
|
|
|
if element["src"].present?
|
|
src = Addressable::URI.heuristic_parse(element["src"])
|
|
src.scheme ||= "https"
|
|
element["src"] = src.to_s
|
|
end
|
|
end
|
|
end
|
|
|
|
def api_response
|
|
return {} if (mobile_url = parsed_url.mobile_url || parsed_referer&.mobile_url).blank?
|
|
|
|
resp = http.cache(1.minute).get(mobile_url)
|
|
json_string = resp.to_s[/var \$render_data = \[(.*)\]\[0\]/m, 1]
|
|
|
|
return {} if json_string.blank?
|
|
|
|
JSON.parse(json_string)["status"]
|
|
end
|
|
memoize :api_response
|
|
end
|
|
end
|
|
end
|