jekyll-artisync 0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 44f8922f2d59106ea016385d2c1fca07eb4b9a45b46ef8bf9010ba4e671fe6b9
+  data.tar.gz: f3317e83d29eaf5a093be418b2e20af1908ece9dc266def4b55984c8f392f6e8
+SHA512:
+  metadata.gz: 9d65e4847297fbb8c891e2e203edc49ec881e428df7d01e127a7d0a787265906d484f2363f63be5b14a0d031a328093c0bfd534ba8d231b9a1d4eb125580a744
+  data.tar.gz: 1de6cccb4926d3f5d67a94936c2691578c19c5f072b879cb385f9a24da7ee0d222bbfa1784a334e8a1c0929532dcca4254a119035313aea93207cc5b0b891cd3

data/lib/jekyll-artisync.rb

@@ -0,0 +1,62 @@
+require 'net/http'
+require 'nokogiri'
+
+require "jekyll"
+
+# user agent is necessary otherwise certain sites such as Zhihu throws 400
+USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.86 Safari/537.36'
+
+SITE_TO_ARTICLE_XPATH = {
+	'zhihu' => '//div[contains(@class, "Post-RichText") and contains(@class, "ztext")]',
+}
+
+class ArticleSyncEmbed < Liquid::Tag
+
+	def initialize(tagName, content, tokens)
+		super
+		@content = content
+	end
+
+	def _fetch_html(url)
+		uri = URI(url)
+		res = Net::HTTP.start(uri.hostname, uri.port, :use_ssl => true) do |http|
+			# :use_ssl => true for the uri is https
+			http.request(Net::HTTP::Get.new(uri, {'User-Agent' => USER_AGENT}))
+		end
+
+		res.body
+	end
+
+	def _get_xpath(xpath_type)
+
+	end
+
+	def _fetch_article(article_xpath)
+		article_html = _fetch_html()
+
+		xpath = @content.xpath
+		article_doc = Nokogiri::HTML(article_html)
+
+		article_node = article_doc.xpath(article_xpath)
+		content = []
+		article_node.children.each do |node|
+			content.append node.to_html
+		end
+
+	end
+
+	def render(context)
+		url, site = @content.strip.split
+		page_html = self._fetch_html(url)
+		article = Nokogiri::HTML(page_html).xpath(SITE_TO_ARTICLE_XPATH[site])
+		content = []
+    article.children.each do |node|
+      content.append node.to_html
+    end
+
+    content.join("\n")
+	end
+
+	Liquid::Template.register_tag "artisync", self
+
+end

metadata

@@ -0,0 +1,44 @@
+--- !ruby/object:Gem::Specification
+name: jekyll-artisync
+version: !ruby/object:Gem::Version
+  version: '0.1'
+platform: ruby
+authors:
+- Junhan
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-05-21 00:00:00.000000000 Z
+dependencies: []
+description: Take an article from a given site and display on current Jekyll page.
+email:
+- junhanoct@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/jekyll-artisync.rb
+homepage: https://github.com/junhan-z/jekyll-artisync
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Jekyll Plugin to sync articles from other sites.
+test_files: []