RubyGems - html_massage - Versions diffs - 0.0.2 - Mend

html_massage 0.0.2

Files changed (8) hide show

data/.gitignore ADDED Viewed

@@ -0,0 +1,4 @@
+.bundle
+.idea
+Gemfile.lock
+pkg/*

data/Gemfile ADDED Viewed

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+# Specify your gem's dependencies in html_massage.gemspec
+gemspec

data/README.md ADDED Viewed

@@ -0,0 +1,18 @@
+# html_massage
+Give your HTML a massage, in just the ways it loves:
+ * Remove headers and footers and navigation, and strip to only the "content" part of the HTML
+ * Sanitize tags, removing javascript and styling
+ * Convert your HTML to nicely-formatted plain text
+## Usage
+    require 'rubygems'
+    require 'html_massage'
+    html = "<html><body><div id='header'>My Site</div><div>This is some great content!</div></body></html>"
+    html_massage = HtmlMassage.new( html, :ignored_selectors => [ '#header' ] )
+     # => #<HtmlMassager::HtmlMassage ... >
+    html_massage.to_html
+     # => "<div>This is some great content!</div>"
+    html_massage.to_text
+     # => "This is some great content!\n"

data/Rakefile ADDED Viewed

	@@ -0,0 +1 @@
1	+ require 'bundler/gem_tasks'

data/html_massage.gemspec ADDED Viewed

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "html_massage/version"
+Gem::Specification.new do |s|
+  s.name        = "html_massage"
+  s.version     = HtmlMassager::VERSION
+  s.authors     = ["Harlan Knight Wood"]
+  s.email       = ["code@hkw7.org"]
+  s.homepage    = "https://github.com/onesunone/html_massage"
+  s.summary     = %{Massages HTML how you want to.}
+  s.description = %{Massages HTML how you want to: sanitize tags, remove headers and footers, convert to plain text.}
+  s.rubyforge_project = "html_massage"
+  s.add_dependency('nokogiri', ">= 1.4.4")
+  s.add_dependency('sanitize', ">= 2.0.0")
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+end

data/lib/html_massage/version.rb ADDED Viewed

@@ -0,0 +1,3 @@
+module HtmlMassager
+  VERSION = "0.0.2"
+end

data/lib/html_massage.rb ADDED Viewed

@@ -0,0 +1,176 @@
+require "cgi"
+require "nokogiri"
+require "sanitize"
+require "html_massage/version"
+module HtmlMassager
+  class HtmlMassage
+    def initialize( html, options )
+      @source_url        = options[ :source_url ]
+      @ignored_selectors = options[ :ignored_selectors ]
+      @clean_html = massage_html( html )
+    end
+    def massage_html( html )
+      html = content_only( html )
+      html = sanitize_html( html )
+      html = absolutify_links( html ) if @source_url
+      html
+    end
+    def content_only( content )
+      doc = Nokogiri::HTML( content )
+      body = doc / 'html' / 'body'
+      @ignored_selectors.to_a.each do |ignored_selector|
+        ( body / ignored_selector ).remove
+      end
+      content = body / '#content'
+      content = body if content.empty?
+      content = content.inner_html
+      content
+    end
+    def sanitize_html(html)
+      html = html.dup
+      %w[ script noscript style ].each do |tag|
+        html.gsub!( %r{<#{tag}[^>]*>.*?</#{tag}>}mi, '' )
+      end
+      Sanitize.clean(
+          html,
+          {
+              :elements => [
+                  'a', 'abbr', 'acronym', 'address', 'area', 'b', 'big',
+                  'blockquote', 'br', 'button', 'caption', 'center', 'cite',
+                  'code', 'col', 'colgroup', 'dd', 'del', 'dfn', 'dir',
+                  'div', 'dl', 'dt', 'em', 'fieldset', 'form', 'h1',
+                  'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i',
+                  'img',
+                  'input', 'ins', 'kbd', 'label', 'legend', 'li', 'map', 'menu',
+                  'ol', 'optgroup', 'option', 'p', 'pre', 'q', 's', 'samp',
+                  'select', 'small', 'span', 'strike', 'strong', 'sub',
+                  'sup', 'table', 'tbody', 'td', 'textarea', 'tfoot', 'th',
+                  'thead', 'tr', 'tt', 'u', 'ul', 'var',
+              ],
+              :attributes => {
+                  'a' => ['href'],
+                  'img' => ['src'],
+                  :all => ['abbr', 'accept', 'accept-charset',
+                           'accesskey', 'action', 'align', 'alt', 'axis',
+                           'border', 'cellpadding', 'cellspacing', 'char',
+                           'charoff', 'class', 'charset', 'checked', 'cite',
+                           'clear', 'cols', 'colspan', 'color',
+                           'compact', 'coords', 'datetime', 'dir',
+                           'disabled', 'enctype', 'for', 'frame',
+                           'headers', 'height', 'hreflang',
+                           'hspace', 'id', 'ismap', 'label', 'lang',
+                           'longdesc', 'maxlength', 'media', 'method',
+                           'multiple', 'name', 'nohref', 'noshade',
+                           'nowrap', 'prompt', 'readonly', 'rel', 'rev',
+                           'rows', 'rowspan', 'rules', 'scope',
+                           'selected', 'shape', 'size', 'span',
+                           'start', 'summary', 'tabindex', 'target',
+                           'title', 'type', 'usemap', 'valign', 'value',
+                           'vspace', 'width']
+              },
+              :protocols => {
+                  'a' => {'href' => ['http', 'https', 'mailto', :relative]},
+                  'img' => {'src' => ['http', 'https', :relative]}
+              },
+              # consider including for deprecated/historical/or spam-suspect pages:
+              # Gollum has a nice way to add this to your config optionally, see:
+              # https://github.com/github/gollum/blob/master/lib/gollum/sanitization.rb
+              #
+              #        :add_attributes => {
+              #            'a' => {'rel' => 'nofollow'}
+              #        }
+          }
+      )
+    end
+    def absolutify_links( html )
+      match = @source_url.match( %r{(^[a-z]+://[^/]+)(/.+/)}i )
+      return html unless match
+      base_url = match[ 1 ]
+      resource_dir_url = match[ 0 ]   # whole regexp match
+      dom = Nokogiri::HTML.fragment( html )
+      links = dom / 'a'
+      links.each do |link|
+        href = link[ 'href' ]
+        if href
+          link[ 'href' ] =
+            case href
+              when %r{^/}
+                File.join( base_url, href )
+              when %r{^\.\.}
+                File.join( resource_dir_url, href )
+              else
+                href
+            end
+        end
+      end
+      html = dom.to_s
+      html
+    end
+    def to_html
+      @clean_html
+    end
+    def to_text
+      text = CGI.unescapeHTML( @clean_html )
+      # normalize newlines
+      text.gsub!(/\r\n/, "\n")
+      text.gsub!(/\r/, "\n")
+      # nbsp => ' '
+      text.gsub!(/&nbsp;/, ' ')
+      # TODO: figure out how to do these in ruby 1.9.2:
+      # They now throw 'incompatible encoding -- ascii regexp for utf8 string'
+      #    text.gsub!( /\302\240/, ' ' )  # UTF8 for nbsp
+      #    text.gsub!( /\240/, ' ' )      # ascii for nbsp
+      text.gsub!(/\s+/, ' ')   # all whitespace, including newlines, becomes a single space
+      # replace some tags with newlines
+      text.gsub!(%r{<br(\s[^>]*)?/?>}i, "\n")
+      text.gsub!(%r{<p(\s[^>]*)?/?>}i, "\n\n")
+      text.gsub!(%r{</(h\d|p|div|ol|ul)[^>]*>}i, "\n\n")
+      # replace some tags with meaningful text markup
+      text.gsub!(/<hr[^>]*>/i, "\n\n-------------------------\n\n")
+      text.gsub!(/<li[^>]*>/i, "\n* ")
+      # remove some tags and their inner html
+      text.gsub!(%r{<noscript\b.*?</noscript>}i, '')
+      # strip out all remaining tags
+      text.gsub!(/<[^>]+>/, '')
+      # normalize whitespace
+      text.gsub!(/ +/, ' ')
+      text = strip_lines(text)
+      text.gsub!( /\n{3,}/, "\n\n" )
+      text.strip!
+      "#{text}\n"
+    end
+    def strip_lines( text )
+      lines = text.split( "\n" )
+      lines.map!{ |line| line.strip }
+      text = lines.join( "\n" )
+      text.strip
+    end
+  end
+end
+include HtmlMassager

metadata ADDED Viewed

@@ -0,0 +1,82 @@
+--- !ruby/object:Gem::Specification
+name: html_massage
+version: !ruby/object:Gem::Version
+  prerelease:
+  version: 0.0.2
+platform: ruby
+authors:
+- Harlan Knight Wood
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2011-06-18 00:00:00 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.4.4
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency
+  name: sanitize
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  type: :runtime
+  version_requirements: *id002
+description: "Massages HTML how you want to: sanitize tags, remove headers and footers, convert to plain text."
+email:
+- code@hkw7.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- README.md
+- Rakefile
+- html_massage.gemspec
+- lib/html_massage.rb
+- lib/html_massage/version.rb
+homepage: https://github.com/onesunone/html_massage
+licenses: []
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: "0"
+requirements: []
+rubyforge_project: html_massage
+rubygems_version: 1.8.5
+signing_key:
+specification_version: 3
+summary: Massages HTML how you want to.
+test_files: []