website_information 0.4.4 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 403ffaccdf62f41a76c04f5b886a6c2e0aa7adfa
-  data.tar.gz: 69ea0d7fd349fe324ac79aec4cb2b09da03f2801
+  metadata.gz: e1f3b31146d3da07c6be7952cbe78e6121da9e86
+  data.tar.gz: b165e9c3c14503ca4efc03ead798179324b306d0
 SHA512:
-  metadata.gz: 6d5d33d8af94287fb4ca2555b7fead74c4629f8c828c5ec2c488f61208c9d5aaebe73a3c40faa3ad4abe55ed393ea23410900bc7fa9ff03ca44321135fd36f2a
-  data.tar.gz: f78e6b8ebe916607caf6dbb44b0bc9d5db3301114e278c20409ed75a9127f6309cc142a152d720137655f1646f1c52b1145eb6b4a4686a1ec8034c7c2e1fb96d
+  metadata.gz: bdee9b5cd2efe9da8b0e011e6a13024ab0ccf1fb68fb08d7e55d3eb39e98dc956209f2d20586e9952c505d97de85320d00c8d68ec1b24113feba8d1c76002919
+  data.tar.gz: 32811dc8836e78dd65b175f14adf7338d0d81e8256ea970d923405f2d90b46104f86f035e6729f70fa59bee7151bafaa85995934267c5fd4c5cc4cfca2e8ce24

data/README.md

@@ -34,9 +34,26 @@ Please install web driver if you want to use site capture.
 scraped_params = WebsiteInformation::Website.new('scraping_url(ex. https://www.google.com)').scraped_params
 
 # ex) get website title
-scraped_params.title
+scraped_params.title # => Google
+
 ```
 
+### Output
+The list of allowed get `params` values.
+
+ * ```.title```  — ```<title>``` tag value
+ * ```.meta.description```  — ```<meta name="description"　>``` tag content
+ * ```.meta.keyword```  — ```<meta name="keyword"　>``` tag content
+ * ```.og.site_name```  — ```<meta property="og:site_name"　>``` tag content
+ * ```.og.description```  — ```<meta property="og:description"　>``` tag content
+ * ```.og.url```  — ```<meta property="og:url"　>``` tag content
+ * ```.og.type```  — ```<meta property="og:type"　>``` tag content
+ * ```.og.image```  — ```<meta property="og:image"　>``` tag content
+ * ```.feed```  — ```<link rel="alternate"　>``` tag href application/atom+xml or application/rss+xml type
+ * ```.sns.facebook```  — Facebook page plugin (https://developers.facebook.com/docs/plugins/page-plugin/) from data-href
+ * ```.sns.twitter```  — Twitter embedded timelines (https://dev.twitter.com/web/embedded-timelines/list) from href
+
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/miraoto/website_information. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.

data/lib/website_information/params.rb

@@ -1,6 +1,7 @@
 require "website_information/params/site"
 require "website_information/params/meta"
 require "website_information/params/og"
+require "website_information/params/sns"
 
 module WebsiteInformation
   module Params

data/lib/website_information/params/site.rb

@@ -1,3 +1,5 @@
+require 'watir'
+
 module WebsiteInformation
   module Params
     class Site
@@ -7,6 +9,7 @@ module WebsiteInformation
         @url = url
         @meta = WebsiteInformation::Params::Meta.new
         @og = WebsiteInformation::Params::Og.new
+        @sns = WebsiteInformation::Params::Sns.new
       end
 
       def meta
@@ -17,6 +20,10 @@ module WebsiteInformation
         @og
       end
 
+      def sns
+        @sns
+      end
+
       def capture
         if @capture.nil?
           browser = Watir::Browser.new

data/lib/website_information/params/sns.rb

@@ -0,0 +1,7 @@
+module WebsiteInformation
+  module Params
+    class Sns
+      attr_accessor :facebook, :twitter
+    end
+  end
+end

data/lib/website_information/version.rb

@@ -1,3 +1,3 @@
 module WebsiteInformation
-  VERSION = "0.4.4"
+  VERSION = "0.5.0"
 end

data/lib/website_information/website.rb

@@ -1,5 +1,4 @@
 require 'nokogiri'
-require 'watir'
 
 module WebsiteInformation
   class Website
@@ -26,11 +25,19 @@ module WebsiteInformation
       @params.og.type = doc.css('//meta[property="og:type"]/@content').to_s
       @params.og.image = doc.css('//meta[property="og:image"]/@content').to_s
       feed(doc)
+      sns(doc)
     end
 
     def feed(doc)
       @params.feed = doc.css('//link[@rel="alternate"][@type="application/atom+xml"]/@href')[0].to_s
       @params.feed = doc.css('//link[@rel="alternate"][@type="application/rss+xml"]/@href')[0].to_s if @params.feed.empty?
     end
+
+    def sns(doc)
+      # scrape facebook url from page plugin (https://developers.facebook.com/docs/plugins/page-plugin/)
+      @params.sns.facebook = doc.css('//div[class$="fb-page"]/@data-href')[0].to_s
+      # scrape twitter url from embedded timelines (https://dev.twitter.com/web/embedded-timelines/list)
+      @params.sns.twitter = doc.css('//a[class$="twitter-timeline"]/@href')[0].to_s
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: website_information
 version: !ruby/object:Gem::Version
-  version: 0.4.4
+  version: 0.5.0
 platform: ruby
 authors:
 - miraoto
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-10-02 00:00:00.000000000 Z
+date: 2017-10-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -117,6 +117,7 @@ files:
 - lib/website_information/params/meta.rb
 - lib/website_information/params/og.rb
 - lib/website_information/params/site.rb
+- lib/website_information/params/sns.rb
 - lib/website_information/version.rb
 - lib/website_information/website.rb
 - website_information.gemspec