opengraph_parser 0.2.0 → 0.2.4

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: df0c81f7b80017bff4c885d2c414eef59fabf51270ed39deb4c865ad26be55ac
+  data.tar.gz: '02908954486292679e02fe035aedce81fe1575d49ad8d09419bdcdaf43dceb3e'
+SHA512:
+  metadata.gz: aeff1818cd446174ccd6737c11faa59296184186480f373a43967cab9a36a89412cca711a81d1ed6572b20bea2b5b5909b6bcd2614e2047128a2684827135e10
+  data.tar.gz: 196240064499563538c518f454ac15d8498003bae0a732f13e09e109ac0e5037bb3ce5431c47858ea1e797a0622d04ba51c52df3f9f8eab84bd69a7f1074a61f

data/README.md

@@ -0,0 +1,74 @@
+# OpengraphParser
+
+OpengraphParser is a simple Ruby library for parsing Open Graph protocol information from a website. Learn more about the protocol at:
+http://ogp.me
+
+## Installation
+
+```bash
+  gem install opengraph_parser
+```
+
+or add to Gemfile
+
+```bash
+  gem "opengraph_parser"
+```
+
+## Usage
+
+### Parsing an URL
+
+```ruby
+og = OpenGraph.new("http://ogp.me")
+og.title # => "Open Graph protocol"
+og.type # => "website"
+og.url # => "http://ogp.me/"
+og.description # => "The Open Graph protocol enables any web page to become a rich object in a social graph."
+og.images # => ["http://ogp.me/logo.png"]
+```
+
+You can also get other Open Graph metadata as:
+
+```ruby
+og.metadata # => {"og:image:type"=>"image/png", "og:image:width"=>"300", "og:image:height"=>"300"}
+```
+
+### Parsing a HTML document
+
+```ruby
+og = OpenGraph.new(html_string)
+```
+
+### Custom header fields
+In some cases you may need to change fields in HTTP request header for an URL
+```ruby
+og = OpenGraph.new("http://opg.me", { :headers => {'User-Agent' => 'Custom User Agent'} })
+```
+
+### Fallback
+If you try to parse Open Graph information for a website that doesn’t have any Open Graph metadata, the library will try to find other information in the website as the following rules:
+
+* `<title>` for title
+* `<meta name="description">` for description
+* `<link rel="image_src">` or all `<img>` tags for images
+
+You can disable this fallback lookup by passing false to init method:
+
+```ruby
+og = OpenGraph.new("http://ogp.me", false)
+```
+
+## Contributing to opengraph_parser
+
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
+* Fork the project.
+* Start a feature/bugfix branch.
+* Commit and push until you are happy with your contribution.
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+## Copyright
+
+Copyright (c) 2013 Huy Ha. See LICENSE.txt for further details.

data/lib/open_graph.rb

@@ -1,31 +1,43 @@
 require 'nokogiri'
 require 'redirect_follower'
 require "addressable/uri"
+require 'uri'
 
 class OpenGraph
-  attr_accessor :src, :url, :type, :title, :description, :images, :metadata, :response, :original_images
+  attr_accessor :src, :url, :type, :title, :description, :images, :metadata, :response, :original_images, :html_content
 
-  def initialize(src, fallback = true)
+  def initialize(src, fallback = true, options = {})
+    if fallback.is_a? Hash
+      options = fallback
+      fallback = true
+    end
     @src = src
+    @body = nil
     @images = []
     @metadata = {}
-    parse_opengraph
+    parse_opengraph(options)
     load_fallback if fallback
     check_images_path
   end
 
   private
-  def parse_opengraph
+  def parse_opengraph(options = {})
     begin
-      @response = RedirectFollower.new(@src).resolve
+      if @src.include? '</html>'
+        @body = @src
+        @html_content = true
+      else
+        @body = RedirectFollower.new(@src, options).resolve.body
+        @html_content = false
+      end
     rescue
       @title = @url = @src
       return
     end
 
-    if @response && @response.body
+    if @body
       attrs_list = %w(title url type description)
-      doc = Nokogiri.parse(@response.body)
+      doc = Nokogiri.parse(@body)
       doc.css('meta').each do |m|
         if m.attribute('property') && m.attribute('property').to_s.match(/^og:(.+)$/i)
           m_content = m.attribute('content').to_s.strip
@@ -43,8 +55,8 @@ class OpenGraph
   end
 
   def load_fallback
-    if @response && @response.body
-      doc = Nokogiri.parse(@response.body)
+    if @body
+      doc = Nokogiri.parse(@body)
 
       if @title.to_s.empty? && doc.xpath("//head//title").size > 0
         @title = doc.xpath("//head//title").first.text.to_s.strip
@@ -56,6 +68,10 @@ class OpenGraph
         @description = description_meta.attribute("content").to_s.strip
       end
 
+      if @description.to_s.empty?
+        @description = fetch_first_text(doc)
+      end
+
       fetch_images(doc, "//head//link[@rel='image_src']", "href") if @images.empty?
       fetch_images(doc, "//img", "src") if @images.empty?
     end
@@ -63,7 +79,11 @@ class OpenGraph
 
   def check_images_path
     @original_images = @images.dup
-    uri = Addressable::URI.parse(@src)
+
+    uri = Addressable::URI.parse(@url || @src)
+
+    return unless uri
+
     imgs = @images.dup
     @images = []
     imgs.each do |img|
@@ -86,6 +106,13 @@ class OpenGraph
     end
   end
 
+  def fetch_first_text(doc)
+    doc.xpath('//p').each do |p|
+      s = p.text.to_s.strip
+      return s if s.length > 20
+    end
+  end
+
   def add_metadata(metadata_container, path, content)
     path_elements = path.split(':')
     if path_elements.size > 1
@@ -107,4 +134,4 @@ class OpenGraph
       metadata_container
     end
   end
-end
+end

data/lib/redirect_follower.rb

@@ -1,27 +1,30 @@
 require 'net/https'
 
 class RedirectFollower
+  REDIRECT_DEFAULT_LIMIT = 5
   class TooManyRedirects < StandardError; end
 
-  attr_accessor :url, :body, :redirect_limit, :response
+  attr_accessor :url, :body, :redirect_limit, :response, :headers
 
-  def initialize(url, limit = 5)
-    @url, @redirect_limit = url, limit
+  def initialize(url, options = {})
+    @url = url
+    @redirect_limit = options[:redirect_limit] || REDIRECT_DEFAULT_LIMIT
+    @headers = options[:headers] || {}
   end
 
   def resolve
     raise TooManyRedirects if redirect_limit < 0
 
-    uri = URI.parse(URI.escape(url))
+    uri = Addressable::URI.parse(url)
+
+    http = Net::HTTP.new(uri.host, uri.port)
     if uri.scheme == 'https'
-      https = Net::HTTP.new(uri.host, 443)
-      https.use_ssl = true
-      https.verify_mode = OpenSSL::SSL::VERIFY_PEER
-      self.response = https.request_get(uri.request_uri)
-    else
-      self.response = Net::HTTP.get_response(uri)
+      http.use_ssl = true
+      http.verify_mode = OpenSSL::SSL::VERIFY_PEER
     end
 
+    self.response = http.request_get(uri.request_uri, @headers)
+
     if response.kind_of?(Net::HTTPRedirection)
       self.url = redirect_url
       self.redirect_limit -= 1
@@ -39,4 +42,4 @@ class RedirectFollower
       response['location']
     end
   end
-end
+end

metadata

@@ -1,83 +1,100 @@
 --- !ruby/object:Gem::Specification
 name: opengraph_parser
 version: !ruby/object:Gem::Version
-  version: 0.2.0
-  prerelease: 
+  version: 0.2.4
 platform: ruby
 authors:
 - Huy Ha
 - Duc Trinh
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-01-16 00:00:00.000000000 Z
+date: 2021-12-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &70256296829180 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70256296829180
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: addressable
-  requirement: &70256296828540 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70256296828540
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70256296827720 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70256296827720
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &70256296826860 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70256296826860
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &70256296825620 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70256296825620
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &70256296818460 !ruby/object:Gem::Requirement
-    none: false
+  requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70256296818460
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: A simple Ruby library for parsing Open Graph Protocol information from
   a website. It also includes a fallback solution when the website has no Open Graph
   information.
@@ -86,39 +103,34 @@ executables: []
 extensions: []
 extra_rdoc_files:
 - LICENSE.txt
-- README.rdoc
+- README.md
 files:
+- LICENSE.txt
+- README.md
 - lib/open_graph.rb
 - lib/opengraph_parser.rb
 - lib/redirect_follower.rb
-- LICENSE.txt
-- README.rdoc
 homepage: http://github.com/huyha85/opengraph_parser
 licenses:
 - MIT
-post_install_message: 
+metadata: {}
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: -777082750492777387
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 1.8.10
-signing_key: 
+rubygems_version: 3.0.3
+signing_key:
 specification_version: 3
 summary: A simple Ruby library for parsing Open Graph Protocol information from a
   website.

data/README.rdoc

@@ -1,45 +0,0 @@
-= OpengraphParser
-
-OpengraphParser is a simple Ruby library for parsing Open Graph protocol information from a web site. Learn more about the protocol at:
-http://ogp.me
-
-== Installation
-  gem install opengraph_parser
-
-or add to Gemfile
-
-  gem "opengraph_parser"
-
-== Usage
-  og = OpenGraph.new("http://ogp.me")
-  og.title # => "Open Graph protocol"
-  og.type # => "website"
-  og.url # => "http://ogp.me/"
-  og.description # => "The Open Graph protocol enables any web page to become a rich object in a social graph."
-  og.images # => ["http://ogp.me/logo.png"]
-
-You can also get other Open Graph metadata as:
-  og.metadata # => {"og:image:type"=>"image/png", "og:image:width"=>"300", "og:image:height"=>"300"}
-
-If you try to parse Open Graph information for a website that doesn’t have any Open Graph metadata, the library will try to find other information in the website as the following rules:
-  <title> for title
-  <meta name="description"> for description
-  <link rel="image_src"> or all <img> tags for images
-
-You can disable this fallback lookup by passing false to init method:
-  og = OpenGraph.new("http://ogp.me", false)
-
-== Contributing to opengraph_parser
-
-* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
-* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
-* Fork the project.
-* Start a feature/bugfix branch.
-* Commit and push until you are happy with your contribution.
-* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
-* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
-
-== Copyright
-
-Copyright (c) 2012 Huy Ha. See LICENSE.txt for
-further details.