panchira 0.3.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e0715fad65f1b2f6654761d9d1132217ce644c49b621a94aff1f0a6372dd327b
-  data.tar.gz: 265c9ab995d2c2913465e0dd17e69c008389c1c06e3b8fbeb798e24dcdced89d
+  metadata.gz: b5625692d52a2fa265db20d62c9311f877a27b4a8d099446bae7dda346b9fcb5
+  data.tar.gz: 0be90bf0354d5f87ca15e213722c7c44b4c522ec9ad048a611c8f0d307e8fb84
 SHA512:
-  metadata.gz: 231b3b600e88c20f3479943c93efd3b8d720c7052c45c26301818b88a860ac8387610fdd7006c2c6211ecf482a76b24389e4e409290c8817869a3a19af0b0966
-  data.tar.gz: a69dfa20c85d5ef15c12d825dd791450835c7ac9edf511a2b3b5592621706ba0c80d94cf258fd513dc8568e5972270fd5e7271a3c7219c0a3ad8724e4a9a0b23
+  metadata.gz: 98c86bab322717af51f335a5c252dd465c3ec06fdb4bd54e3d3c166153e9571d3b6a94625ab708c286cf18ef8846114cc74cc6ec27f66e376bddbd4fbfcb8aae
+  data.tar.gz: 1efabc99a91e770e47a06ddb527cf72ac361f165a0e5f5a4fcfc4ab17eae99436a55bdb70f721da0826117e6febd10062736b47c02442ae8870a6604070bf2e2

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    panchira (0.3.0)
+    panchira (1.0.0)
       fastimage (~> 2.1.7)
       nokogiri (~> 1.10.9)
 

data/README.md

@@ -6,7 +6,7 @@
 
 Due to some legal or ethical issues, most hentai and NSFW platforms don't clarify their content on meta tags. As a result, most hentai platforms are rendered poorly on the card previews on social media.
 
-To solve this issue, Panchira is made to parse correct and uncensored metadata from such web platforms (at this time we cover **DLSite, Komiflo, Melonbooks, Nijie and Pixiv**).
+To solve this issue, Panchira is made to parse correct and uncensored metadata from such web platforms (at this time we cover **DLSite, Komiflo, Melonbooks, Nijie, Pixiv, Shousetsuka ni narou and Twitter**).
 
 If you need card previews of hentai on your web application, but can't get them with simply parsing metatags, then it is time for Panchira.
 
@@ -39,10 +39,12 @@ Or install it yourself as:
 ```
 > Panchira.fetch("https://www.pixiv.net/artworks/61711172")
 
-=> {:canonical_url=>"https://pixiv.net/member_illust.php?mode=medium&illust_id=61711172", :title=>"#輿水幸子 すずしい顔で締め切りを破る幸子 - むらためのイラスト - pixiv", :description=>"(UTF16の)Pietで実行すると「すずしい」と出力する幸子(5色+白Pietカラーゴルフ)。解説記事は http://chy72.hatenablog.com/entry/2016/12/24/1", :image=>{:url=>"https://pixiv.cat/61711172.jpg", :width=>810, :height=>500}}
+=> #<Panchira::PanchiraResult:0x00007fb95d2c53f8 @canonical_url="https://pixiv.net/member_illust.php?mode=medium&illust_id=61711172", @title="#輿水幸子 すずしい顔で締め切りを破る幸子 - むらためのイラスト - pixiv", @description="(UTF16の)Pietで実行すると「すずしい」と出力する幸子(5色+白Pietカラーゴルフ)。解説記事は http://chy72.hatenablog.com/entry/2016/12/24/1", @image=#<Panchira::PanchiraImage:0x00007fb95f126ea0 @url="https://pixiv.cat/61711172.jpg", @width=810, @height=500>, @tags=["輿水幸子", "Piet", "プログラミング"]>
 ```
 
-Panchira is in beta at this time and doesn't have stable API documentation yet.
+In most situation you would call `Panchira#fetch`. It is a singular method that takes a URI and returns an instance of `PanchiraResult`, which is a simple class that stores the website's information, such as title, description and so on.
+
+Panchira has a special treatment for each website. `Resolver` classes are where those treatments take place, and you can use your own `Resolver` classes by registering it to Panchira. See `Panchira::Extensions` documentation in source code for further details.
 
 ## Development
 

data/lib/panchira/panchira_result.rb

@@ -8,6 +8,6 @@ module Panchira
 
   # Result class for Panchira.fetch.
   class PanchiraResult
-    attr_accessor :canonical_url, :title, :description, :image
+    attr_accessor :canonical_url, :title, :description, :image, :tags
   end
 end

data/lib/panchira/resolvers/dlsite_resolver.rb

@@ -9,6 +9,10 @@ module Panchira
     def parse_image_url
       @page.css('//meta[property="og:image"]/@content').first.to_s.sub(/sam/, 'main')
     end
+
+    def parse_tags
+      @page.css('.main_genre').children.children.map(&:text)
+    end
   end
 
   ::Panchira::Extensions.register(Panchira::DlsiteResolver)

data/lib/panchira/resolvers/komiflo_resolver.rb

@@ -37,6 +37,10 @@ module Panchira
       id = @url.slice(%r{komiflo\.com(?:/#!)?/comics/(\d+)}, 1)
       'https://komiflo.com/comics/' + id
     end
+
+    def parse_tags
+      @json['content']['attributes']['tags']['children'].map{|content| content['data']['name']}
+    end
   end
 
   ::Panchira::Extensions.register(Panchira::KomifloResolver)

data/lib/panchira/resolvers/melonbooks_resolver.rb

@@ -25,6 +25,10 @@ module Panchira
     def parse_image_url
       @page.css('//meta[property="og:image"]/@content').first.to_s.sub(/&c=1/, '')
     end
+
+    def parse_tags
+      @page.css('#related_tags .clearfix').children.children.map(&:text)
+    end
   end
 
   ::Panchira::Extensions.register(Panchira::MelonbooksResolver)

data/lib/panchira/resolvers/narou_resolver.rb

@@ -3,18 +3,42 @@
 require 'net/https'
 
 module Panchira
-  class NarouResolver < Resolver
-    URL_REGEXP = %r{novel18\.syosetu\.com/}.freeze
+  module Narou
+    class Novel18Resolver < Resolver
+      URL_REGEXP = %r{novel18\.syosetu\.com/}.freeze
+      ID_REGEXP = %{novel18\.syosetu\.com/(?<id>[^/]+)}.freeze
 
-    def fetch_page(uri)
-      u = URI.parse(uri)
-      http = Net::HTTP.new(u.host, u.port)
-      http.use_ssl = u.port == 443
-      res = http.get u.request_uri, { 'cookie' => 'over18=yes;' }
+      def fetch_page(uri)
+        u = URI.parse(uri)
+        http = Net::HTTP.new(u.host, u.port)
+        http.use_ssl = u.port == 443
+        res = http.get u.request_uri, { 'cookie' => 'over18=yes;' }
 
-      Nokogiri::HTML.parse(res.body, uri)
+        Nokogiri::HTML.parse(res.body, uri)
+      end
+
+      def parse_tags
+        id = @url.match(ID_REGEXP)[:id]
+        return [] unless id
+
+        desc = fetch_page("https://novel18.syosetu.com/novelview/infotop/ncode/#{id}/")
+        desc.xpath('//*[@id="noveltable1"]/tr[3]')&.text&.split("\n\n\n")&.dig(1)&.split(' ') # つらい。
+      end
+    end
+    class NcodeResolver < Resolver
+      URL_REGEXP = %r{ncode\.syosetu\.com}.freeze
+      ID_REGEXP = %{ncode\.syosetu\.com/(?<id>[^/]+)}.freeze
+
+      def parse_tags
+        id = @url.match(ID_REGEXP)[:id]
+        return [] unless id
+
+        desc = fetch_page("https://ncode.syosetu.com/novelview/infotop/ncode/#{id}/")
+        desc.xpath('//*[@id="noveltable1"]/tr[3]')&.text&.split("\n\n\n")&.dig(1)&.delete("\u00A0")&.split(' ')&.grep_v('') # めっちゃつらい。
+      end
     end
   end
 
-  ::Panchira::Extensions.register(Panchira::NarouResolver)
+  ::Panchira::Extensions.register(Panchira::Narou::NcodeResolver)
+  ::Panchira::Extensions.register(Panchira::Narou::Novel18Resolver)
 end

data/lib/panchira/resolvers/nijie_resolver.rb

@@ -24,6 +24,10 @@ module Panchira
         @page.css('//meta[property="og:image"]/@content').first.to_s
       end
     end
+
+    def parse_tags
+      @page.css('#view-tag span.tag_name').map(&:text)
+    end
   end
 
   ::Panchira::Extensions.register(Panchira::NijieResolver)

data/lib/panchira/resolvers/pixiv_resolver.rb

@@ -7,6 +7,9 @@ module Panchira
     def initialize(url)
       super(url)
       @illust_id = url.slice(URL_REGEXP, 2)
+
+      raw_json = URI.parse("https://www.pixiv.net/ajax/illust/#{@illust_id}").read('User-Agent' => USER_AGENT)
+      @json = JSON.parse(raw_json)
     end
 
     private
@@ -27,6 +30,10 @@ module Panchira
     rescue StandardError
       @page.css('//meta[property="og:image"]/@content').first.to_s
     end
+
+    def parse_tags
+      @json['body']['tags']['tags'].map{|content| content['tag']}
+    end
   end
 
   ::Panchira::Extensions.register(Panchira::PixivResolver)

data/lib/panchira/resolvers/resolver.rb

@@ -30,6 +30,7 @@ module Panchira
       result.title = parse_title
       result.description = parse_description
       result.image = parse_image
+      result.tags = parse_tags
 
       result
     end
@@ -97,5 +98,9 @@ module Panchira
     def parse_image_url
       @page.css('//meta[property="og:image"]/@content').first.to_s
     end
+
+    def parse_tags
+      []
+    end
   end
 end

data/lib/panchira/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Panchira
-  VERSION = '0.3.0'
+  VERSION = '1.0.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: panchira
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 1.0.0
 platform: ruby
 authors:
 - kyp
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-06-04 00:00:00.000000000 Z
+date: 2020-06-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler