yasf 0.0.3

data/.gitignore

@@ -0,0 +1,19 @@
+*.gem
+*.rbc
+*.swp
+.bundle
+.config
+coverage
+InstalledFiles
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+
+# YARD artifacts
+.yardoc
+_yardoc
+doc/

data/.rvmrc

@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+
+# This is an RVM Project .rvmrc file, used to automatically load the ruby
+# development environment upon cd'ing into the directory
+
+# First we specify our desired <ruby>[@<gemset>], the @gemset name is optional,
+# Only full ruby name is supported here, for short names use:
+#     echo "rvm use 1.9.3" > .rvmrc
+environment_id="ruby-1.9.3@yasf"
+
+# Uncomment the following lines if you want to verify rvm version per project
+# rvmrc_rvm_version="1.15.9 ()" # 1.10.1 seams as a safe start
+# eval "$(echo ${rvm_version}.${rvmrc_rvm_version} | awk -F. '{print "[[ "$1*65536+$2*256+$3" -ge "$4*65536+$5*256+$6" ]]"}' )" || {
+#   echo "This .rvmrc file requires at least RVM ${rvmrc_rvm_version}, aborting loading."
+#   return 1
+# }
+
+# First we attempt to load the desired environment directly from the environment
+# file. This is very fast and efficient compared to running through the entire
+# CLI and selector. If you want feedback on which environment was used then
+# insert the word 'use' after --create as this triggers verbose mode.
+if [[ -d "${rvm_path:-$HOME/.rvm}/environments"
+  && -s "${rvm_path:-$HOME/.rvm}/environments/$environment_id" ]]
+then
+  \. "${rvm_path:-$HOME/.rvm}/environments/$environment_id"
+  [[ -s "${rvm_path:-$HOME/.rvm}/hooks/after_use" ]] &&
+    \. "${rvm_path:-$HOME/.rvm}/hooks/after_use" || true
+  if [[ $- == *i* ]] # check for interactive shells
+  then echo "Using: $(tput setaf 2)$GEM_HOME$(tput sgr0)" # show the user the ruby and gemset they are using in green
+  else echo "Using: $GEM_HOME" # don't use colors in non-interactive shells
+  fi
+else
+  # If the environment file has not yet been created, use the RVM CLI to select.
+  rvm --create use  "$environment_id" || {
+    echo "Failed to create RVM environment '${environment_id}'."
+    return 1
+  }
+fi
+
+# If you use bundler, this might be useful to you:
+# if [[ -s Gemfile ]] && {
+#   ! builtin command -v bundle >/dev/null ||
+#   builtin command -v bundle | GREP_OPTIONS= \grep $rvm_path/bin/bundle >/dev/null
+# }
+# then
+#   printf "%b" "The rubygem 'bundler' is not installed. Installing it now.\n"
+#   gem install bundler
+# fi
+# if [[ -s Gemfile ]] && builtin command -v bundle >/dev/null
+# then
+#   bundle install | GREP_OPTIONS= \grep -vE '^Using|Your bundle is complete'
+# fi

data/Gemfile

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

data/Gemfile.lock

@@ -0,0 +1,30 @@
+PATH
+  remote: .
+  specs:
+    yasf (0.0.1)
+      nokogiri (= 1.5.5)
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+    diff-lcs (1.1.3)
+    fakeweb (1.3.0)
+    nokogiri (1.5.5)
+    rake (0.9.2.2)
+    rspec (2.11.0)
+      rspec-core (~> 2.11.0)
+      rspec-expectations (~> 2.11.0)
+      rspec-mocks (~> 2.11.0)
+    rspec-core (2.11.1)
+    rspec-expectations (2.11.3)
+      diff-lcs (~> 1.1.3)
+    rspec-mocks (2.11.3)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  fakeweb
+  rake
+  rspec
+  yasf!

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Algonauti
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,45 @@
+yasf
+====
+
+Yet Another Scraper Framework
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'yasf'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install yasf
+
+## Usage  
+    row_scraper = Yasf.define do
+        scrape "h1.title", :title => :text
+        scrape "a.brand",  :brand => :text, :brand_link => :href
+
+        result :title, :brand, :brand_link
+    end
+
+    scraper = Yasf.define do
+        scrape "table.companies tr.company", :'rows[]' => row_scraper
+        result :rows
+    end
+
+###And using the scraper:
+    url = "http://local.domain"
+    results = scraper.extract_from(url)
+    result = results.first
+    puts result.title
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,7 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new
+
+task :default => :spec
+task :test => :spec

data/lib/yasf/scraper.rb

@@ -0,0 +1,144 @@
+require "nokogiri"
+
+module Yasf
+  class Scraper
+
+    class << self
+
+      def extract_from(source, options = nil)
+        self.new(source, options).extract
+      end
+
+      # Defines a processing rule.
+      def scrape(*args)
+        name = args.shift if args.first.is_a?(Symbol)
+        if args.last.is_a?(Hash)
+          extractor = extractor(args.pop)
+        end
+        raise ArgumentError, "Missing extractor: the last argument tells us what to extract" unless extractor
+        raise ArgumentError, "Missing selector: the first argument tells us what to select" if args.empty?
+        define_method :__extractor, extractor
+        method = instance_method(:__extractor)
+        remove_method :__extractor
+        rules << [args.pop, method, name]
+      end
+
+      # Returns an array of scraper rules
+      def rules()
+        @rules ||= []
+      end
+
+      def result(*symbols)
+        raise ArgumentError, "one symbol to return the value of this accessor" if symbols.empty?
+        symbols = symbols.map {|s| s.to_sym}
+        if symbols.size == 1
+          define_method :result do
+            return self.send(symbols[0])
+          end
+        else
+          struct = Struct.new(*symbols)
+          define_method :result do
+            return struct.new(*symbols.collect {|s| self.send(s) })
+          end
+        end
+      end
+
+      # Creates an extractor that will extract values from the selected
+      # element and place them in instance variables of the scraper.
+      def extractor(map)
+        extracts = []
+        map.each_pair do |target, source|
+          source = extract_value_from(source)
+          target = extract_value_to(target)
+          define_method :__extractor do |element|
+            value = source.call(element)
+            target.call(self, value) unless value.nil?
+          end
+          extracts << instance_method(:__extractor)
+          remove_method :__extractor
+        end
+        lambda do |element|
+          extracts.each do |extract|
+            extract.bind(self).call(element)
+          end
+          true
+        end
+      end
+
+      private
+
+      # Returns a Proc that will extract a value from an element.
+      def extract_value_from(source)
+        case source
+        when Class
+          unless source.ancestors.include?(Yasf::Scraper)
+            raise ArgumentError, "Class must extends Yasf::Scraper"
+          end
+          return lambda { |element| source.new(element).extract }
+        when Symbol
+          return lambda do |element|
+            if element.respond_to?(source)
+              element.send(source)
+            elsif element.respond_to?("[]", source)
+              element.send("[]", source)
+            else
+              raise ArgumentError, "Method not found"
+            end
+          end
+        end
+      end
+
+      # Returns a Proc that will set the extract value in the object.
+      def extract_value_to(target)
+        method_name = target.to_s.tr_s("[]", "")
+
+        attr_accessor method_name
+
+        if target.to_s.end_with? "[]"
+          reader = "#{method_name}".to_sym
+          writer = "#{method_name}=".to_sym
+          return lambda do |object, value|
+            array = object.send(reader)
+            object.send(writer, array = []) unless array
+            array << value
+          end
+        else
+          reader = "#{method_name}=".to_sym
+          return lambda { |object, value| object.send(reader, value) }
+        end
+
+      end
+
+    end # end self
+
+    # The argument +source+ is a String (url format), or Nokogiri::XML::Element
+    def initialize(source, options = nil)
+      @options = options || {}
+      case source
+      when String
+        @document = Nokogiri::HTML(open(source))
+      when Nokogiri::XML::Element
+        @document = source
+      else
+        raise ArgumentError, "source not recognized"
+      end
+    end
+
+    # Returns the document being processed.
+    def document
+      @document
+    end
+
+    # Scrapes the document and returns the result.
+    def extract
+      rules = self.class.rules.clone
+      rules.delete_if do |selector, extractor, rule_name|
+        document.search(selector).each do |element|
+          extractor.bind(self).call(element)
+        end
+      end
+      return result
+    end
+
+  end
+end

data/lib/yasf/version.rb

@@ -0,0 +1,3 @@
+module Yasf
+  VERSION = "0.0.3"
+end

data/lib/yasf.rb

@@ -0,0 +1,15 @@
+require "open-uri"
+
+require "yasf/version"
+require "yasf/scraper"
+
+module Yasf
+  class << self
+    def define(&block)
+      kls = Class.new(Scraper)
+      kls.module_eval &block if block_given?
+      return kls
+    end
+  end
+
+end

data/spec/fixtures/advanced_example_response

@@ -0,0 +1,41 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+  <head>
+    <title>FakePage</title>
+  </head>
+  <body>
+    <table>
+      <tr class="tr_with_title">
+        <td>
+          <h1 class="title_under_table">Title 1</h1>
+          <a href="http://linkto.title.one" class="title_under_table">Link Title 1</a>
+        </td>
+      </tr>
+      <tr class="tr_with_title">
+        <td>
+          <h1 class="title_under_table">Title 2</h1>
+          <a href="http://linkto.title.one" class="title_under_table">Link Title 2</a>
+        </td>
+      </tr>
+      <tr class="tr_with_title">
+        <td>
+          <h1 class="title_under_table">Title 3</h1>
+          <a href="http://linkto.title.one" class="title_under_table">Link Title 3</a>
+        </td>
+      </tr>
+      <tr class="tr_with_title">
+        <td>
+          <h1 class="title_under_table">Title 4</h1>
+          <a href="http://linkto.title.one" class="title_under_table">Link Title 4</a>
+        </td>
+      </tr>
+      <tr class="tr_with_title">
+        <td>
+          <h1 class="title_under_table">Title 5</h1>
+          <a href="http://linkto.title.one" class="title_under_table">Link Title 5</a>
+        </td>
+      </tr>
+    </table>
+  </body>
+</html>
+

data/spec/fixtures/basic_example_response

@@ -0,0 +1,10 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+  <head>
+    <title>Basic Example</title>
+  </head>
+  <body>
+    <h1 class="title">Title 1</h1>
+  </body>
+</html>
+

data/spec/fixtures/medium_example_response

@@ -0,0 +1,13 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<html>
+  <head>
+    <title>FakePage</title>
+  </head>
+  <body>
+    <h1 class="title">Title 1</h1>
+    <h1 class="title">Title 2</h1>
+    <h1 class="title">Title 3</h1>
+    <h1 class="title">Title 4</h1>
+  </body>
+</html>
+