b4aea72d04
Remove the `preview_urls` method from strategies. The only place this was used was when doing IQDB searches, to download the thumbnail image from the source instead of the full image. This wasn't worth it for a few reasons: * Thumbnails on other sites are sometimes not the size we want, which could affect IQDB results. * Grabbing thumbnails is complex for some sites. You can't always just rewrite the image URL. Sometimes it requires extra API calls, which can be slower than just grabbing the full image. * For videos and animations, thumbnails from other sites don't always match our thumbnails. We do smart thumbnail generation to try to avoid blank thumbnails, which means we don't always pick the first frame, which could affect IQDB results. API changes: * /iqdb_queries?search[file_url] now downloads the URL as is without any modification. Before it tried to change thumbnail and sample size image URLs to the full version. * /iqdb_queries?search[url] now returns an error if the URL is for a HTML page that contains multiple images. Before it would grab only the first image and silently ignore the rest.
108 lines
2.9 KiB
Ruby
108 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 site_name
|
|
parsed_url.site_name
|
|
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_urls + parsed_referer&.profile_urls.to_a).uniq
|
|
end
|
|
|
|
def profile_url
|
|
profile_urls.first
|
|
end
|
|
|
|
def artist_name
|
|
api_response&.dig("user", "screen_name")
|
|
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 normalize_for_source
|
|
parsed_url.normalized_url
|
|
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
|