jaimeiniesta-metainspector 1.0.2

data/README

@@ -0,0 +1,8 @@
+--------------
+MetaInspector
+--------------
+DESCRIPTION: Ruby gem for web scraping purposes. It scrapes a given URL, and returns you a hash with data from it like for example the title, meta description, meta keywords, an array with all the links, all the images in it, etc.
+AUTHOR: Jaime Iniesta (jaimeiniesta@gmail.com, http://www.jaimeiniesta.com)
+LICENSE: GPLv3
+
+(more to come soon...)

data/lib/metainspector.rb

@@ -0,0 +1,45 @@
+class MetaInspector
+  require 'open-uri'
+  require 'rubygems'
+  require 'hpricot'
+
+  Hpricot.buffer_size = 300000
+
+  def self.scrape(url)
+    doc = Hpricot(open(url))
+    
+    # Searching title...
+    if doc.at('title')
+      title = doc.at('title').inner_html
+    else
+      title = ""
+    end
+    
+    # Searching meta description...
+    if doc.at("meta[@name='description']")
+      description = doc.at("meta[@name='description']")['content']
+    else
+      description = ""
+    end
+    
+    # Searching meta keywords...
+    if doc.at("meta[@name='keywords']")
+      keywords = doc.at("meta[@name='keywords']")['content']
+    else
+      keywords = ""
+    end
+        
+    # Searching links...
+    links = []
+    doc.search("//a").each do |link|
+      links << link.attributes["href"] if (!link.attributes["href"].nil?)
+    end
+  
+    # Returning all data...
+    {'ok' => true, 'title' => title, 'description' => description, 'keywords' => keywords, 'links' => links}  
+
+    rescue SocketError
+      puts 'MetaInspector exception: The url provided does not exist or is temporarily unavailable (socket error)'
+      {'ok' => false, 'title' => nil, 'description' => nil, 'keywords' => nil, 'links' => nil}  
+  end
+end

data/metainspector.gemspec

@@ -0,0 +1,16 @@
+Gem::Specification.new do |s|
+  s.name = "metainspector"
+  s.version = "1.0.2"
+  s.date = "2008-06-27"
+  s.summary = "Ruby gem for web scraping"
+  s.email = "jaimeiniesta@gmail.com"
+  s.homepage = "http://code.jaimeiniesta.com/metainspector"
+  s.description = "MetaInspector is a ruby gem for web scraping purposes, that returns a hash with metadata from a given URL"
+  s.has_rdoc = false
+  s.authors = ["Jaime Iniesta"]
+  s.files = ["README", "metainspector.gemspec", "lib/metainspector.rb", "test/test_metainspector.rb"]
+  s.test_files = []
+  s.rdoc_options = []
+  s.extra_rdoc_files = []
+  s.add_dependency("hpricot", ["> 0.6"])
+end

data/test/test_metainspector.rb

@@ -0,0 +1 @@
+

metadata

@@ -0,0 +1,64 @@
+--- !ruby/object:Gem::Specification 
+name: jaimeiniesta-metainspector
+version: !ruby/object:Gem::Version 
+  version: 1.0.2
+platform: ruby
+authors: 
+- Jaime Iniesta
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-06-27 00:00:00 -07:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">"
+      - !ruby/object:Gem::Version 
+        version: "0.6"
+    version: 
+description: MetaInspector is a ruby gem for web scraping purposes, that returns a hash with metadata from a given URL
+email: jaimeiniesta@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- README
+- metainspector.gemspec
+- lib/metainspector.rb
+- test/test_metainspector.rb
+has_rdoc: false
+homepage: http://code.jaimeiniesta.com/metainspector
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 2
+summary: Ruby gem for web scraping
+test_files: []
+