webpager 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1ac6e8597fd5e840e97fa9a51bffa71fd00d1296
+  data.tar.gz: 9280892f178aa0a1f332f09fbb351cf11b8bde71
+SHA512:
+  metadata.gz: 1bdf1fd3866c7446dc240e047df5a0c04f224c818b3a78518615dceed167d7d87da04db1fa40b9d92286db5e52f95871d081880e9a1203588b30edbb64fd2d62
+  data.tar.gz: ace5d5056c86f679c8aba5eefbfa076996ff8bb8a6c0eea1b008f3f71efb1db26ede1f836a5950d38ea4cbe7b8bdcc0357e6390e66935ba9f0e38c1ab446a01a

data/webpager.rb

@@ -0,0 +1,61 @@
+require 'nokogiri'
+require 'open-uri'
+
+# page = Webpager.new('http://seanbehan.com')
+# page.html
+# page.text
+# page.excerpt
+class Webpager
+  def initialize(url)
+    @url = url
+  end
+
+  def html
+    @html ||= open(@url.strip).read
+  end
+
+  def doc
+    @doc ||= Nokogiri::HTML(html)
+  end
+
+  def text
+    all_tags     = /<\/?[^>]+>/i
+    ref_tags     = /<(a|img)(.*)>/i
+    script_tags  = /<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/i
+    style_tags   = /<style\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/style>/i
+    iframe_tags  = /<iframe\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/iframe>/i
+    comment_tags = /<!--\b[^<]*(?:(?!<\/script>)<[^<]*)*-->/i
+
+    regexp = Regexp.union(all_tags, script_tags, style_tags, iframe_tags, comment_tags)
+
+    body
+    .gsub(ref_tags) { |tag| ((links = URI.extract(tag)).any? ? links.join(' ') : '') }
+    .gsub(regexp, '')
+    .split("\n")
+    .map(&:strip)
+    .reject(&:blank?)
+    .join("\n")
+  end
+
+  def body
+    doc.xpath('//body').inner_html
+  end
+
+  def excerptable?(text='')
+    text.split('.').size >= 2 && text.size > 100
+  end
+
+  def title
+    html.match(/<title>(.*)<\/title>/) { $1 }
+  end
+
+  def favicon
+    # doc.xpath('//link/').select { |link| link.value =~ /favi/ }
+  end
+
+  def excerpt
+    (doc.xpath('//p').map do |x|
+      excerptable?(x.content) ? x.content : nil
+    end.compact.first||"").strip
+  end
+end

metadata

@@ -0,0 +1,59 @@
+--- !ruby/object:Gem::Specification
+name: webpager
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Sean Behan
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-04-19 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'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+description: Write a gem description
+email:
+- inbox@seanbehan.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- webpager.rb
+homepage: 
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- .
+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: 2.2.1
+signing_key: 
+specification_version: 4
+summary: Write a gem summary
+test_files: []