webxtractor 0.0.3

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2648fcab56f4879a51dbaeb6300a572a71b43ac2
+  data.tar.gz: ec3d4bb9409bf610379e632912f91640dc0305ce
+SHA512:
+  metadata.gz: d6f48d46163786d466d87aeec573d932494557dd34ee01d7419a115fdc8ab9176a5a8f60e112c2ce624e3b513414374051fa984ed816a7cadbe4b964fec4fdbb
+  data.tar.gz: fdba6ee9ee7a7d7b64b16ea0e9e803a83b0883640e5bd964c4b183dd21098f5c9576a9d55d61809dbbeb11d3dd0049ce387b77b110bec40840ea39f844ee8c87

data/lib/webxtractor.rb

@@ -0,0 +1,33 @@
+require 'ostruct'
+require 'nokogiri'
+
+class Webxtractor
+  def self.get(url=nil)
+    return unless url
+    uri = URI.parse(url)
+    parse(uri.read)
+  end
+
+  def self.parse(body)
+    page = Nokogiri::HTML(body)
+    result = OpenStruct.new
+    result.title = get_tag('title', page)
+    result.h1 = get_tag('h1', page)
+    result
+  end
+
+  def self.get_tag(selector, page)
+    element = page.css(selector)
+    if element.size > 1
+      element.map {|x| normalize(x.text) }
+    else
+      normalize(element.text)
+    end
+  end
+
+  def self.normalize(content='')
+    return if content.nil?
+    content.gsub(/(\r\n|\n|\r)/," ")
+    content.gsub(/\s+/, " ").strip
+  end
+end

metadata

@@ -0,0 +1,84 @@
+--- !ruby/object:Gem::Specification
+name: webxtractor
+version: !ruby/object:Gem::Version
+  version: 0.0.3
+platform: ruby
+authors:
+- schmierkov
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-01-24 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.6.7.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.6.7.2
+- !ruby/object:Gem::Dependency
+  name: pry-byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.3.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.3'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.3.0
+description: A simple content extractor
+email: github@schmierkov.de
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/webxtractor.rb
+homepage: https://github.com/schmierkov/webxtractor
+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: []
+rubyforge_project: 
+rubygems_version: 2.4.8
+signing_key: 
+specification_version: 4
+summary: Extracts meta informations from a HTML Page
+test_files: []