google-browse 0.1.2

data/.gitignore

@@ -0,0 +1,2 @@
+Gemfile.lock
+pkg/

data/Gemfile

@@ -0,0 +1,5 @@
+source :rubygems
+
+gem 'slop'
+gem 'launchy'
+gem 'mechanize'

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Bil Bas (Spooner)
+
+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 +1,132 @@
+Google-Browse
+=============
+
+This is a very simple text browser which aids in searching and navigating on Google.com. Shows results as a simple list, any of which may be opened in a full
+browser.
+
+Not really intended for real use, since it is only really a toy.
+
+WARNING: Used excessively, this tool may get Google locking you out thinking that you are an evil scraper bot! Be careful!
+
+Installation
+------------
+
+Add this line to your application's Gemfile:
+
+    gem 'google-browse'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install google-browse
+
+Usage
+-----
+
+    The gem provides a single command which starts the text search browser:
+
+    $ google-browse
+
+    $ google-browse "spooner github"
+
+Example output
+--------------
+
+    $ ruby bin/google-browse fish
+
+    Google Browse v0.1.1
+
+
+    Page 1, showing results 1 to 5 for: fish
+    ________________________________________
+
+    1: Fish - Wikipedia, the free encyclopedia
+       A fish is any member of a paraphyletic group of organisms that consist of ...
+       http://en.wikipedia.org/wiki/Fish
+
+    2: Official Fish site
+       Official site for Fish: writer, actor and vocalist. Extensive information ...
+       http://www.fish-thecompany.com/
+
+    3: Clever Bird Goes Fishing - YouTube
+       Sign in with your YouTube Account (YouTube, Google+, Gmail, Orkut, Picasa,...
+       http://www.youtube.co.uk/watch?v=uBuPiC3ArL8
+
+    4: Robot Fish - YouTube
+       For more cool animal videos http://ow.ly/7v79B ...
+       http://www.youtube.com/watch?v=eO9oseiCTdk
+
+    5: Fish! | Fish Kitchen! | Jarvis » Fish Kitchen Group
+       Celebrity restaurateur Tony Allan started the fish! empire when he opened ...
+       http://www.fishkitchen.com/
+
+
+    Enter number of link to browse or [N/h/s/q]: n
+
+    Page 2, showing results 6 to 10 for: fish
+    _________________________________________
+
+     6: Fish | Life and style | The Guardian
+        Latest news and comment on Fish from guardian.co.uk.
+        http://www.guardian.co.uk/lifeandstyle/fish
+
+     7: Pet Fish Supplies for Sale at Pets At Home: Fish Pond Supplies, Fish ...
+        Buy fish products from Pets at Home, the UK's largest pet shop, with fast...
+        http://www.petsathome.com/shop/fish/
+
+     8: Fish recipes | Salmon recipes, fish stew & more | Jamie Oliver recipes
+        Good fresh fish smells of the sea and is packed full of good stuff. Check...
+        http://www.jamieoliver.com/recipes/fish-recipes
+
+     9: Hugh's Fish Fight - Half of all fish caught in the North Sea is thrown ...
+        Half of all fish caught in the North Sea is thrown back overboard dead. B...
+        http://www.fishfight.net/
+
+    10: Grafixation web design and business services - Welcome to our site
+        Grafixation: specialists in web design, graphics, site renovation, promot...
+        http://www.the-company.com/
+
+
+    Enter number of link to browse or [N/p/h/s/q]: s
+
+    Enter search string: frog
+
+    Page 1, showing results 1 to 5 for: frog
+    ________________________________________
+
+    1: Frog - Wikipedia, the free encyclopedia
+       Frogs are a diverse and largely carnivorous group of short-bodied,  taille...
+       http://en.wikipedia.org/wiki/Frog
+
+    2: Frog Learning Platform | The UKs most advanced Learning Platform
+       'Frog is like a Lego® kit that allows users to build most things that can ...
+       http://www.frogtrade.com/
+
+    3: frog
+       We are a global innovation firm. We help create and bring to market meanin...
+       http://www.frogdesign.com/
+
+    4: Frog Song - YouTube
+       ... to add danielinvt's video to your playlist. Sign in. Statistics Report...
+       http://www.youtube.com/watch?v=lfFGXG2-6kg
+
+    5: Frog VLE Nonsuch
+       To log in to the Nonsuch Learning Environment enter your username and pass...
+       http://www.nonsuch.sutton.sch.uk/
+
+
+    Enter number of link to browse or [N/h/s/q]: 4
+
+    ((Opens Frog Song Youtube video in default browser))
+
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Added some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"

data/bin/google-browse

@@ -0,0 +1,42 @@
+#!/usr/bin/env ruby
+
+# Google search CLI browser that can open links into a browser.
+
+require 'bundler/setup'
+require 'slop'
+
+require_relative '../lib/google-browse'
+
+# Manage CLI options.
+results_per_page = GoogleBrowse::Browser::DEFAULT_RESULTS_PER_PAGE
+opts = Slop.parse help: true do
+  banner "Usage: #{File.basename $0} [options] ['QUERY-STRING']"
+
+  on 'n=', 'number=', 
+    "Number of results per page (default: #{results_per_page})",
+    as: Integer, default: results_per_page
+end
+
+exit 0 if opts.help?
+
+def cli_error(opts, message)
+  puts "ERROR: #{message}"
+  puts
+  puts opts
+  exit 0
+end
+
+cli_error opts, 'Must have 1 or more results per page!' unless opts[:number] >= 1
+
+# BUG: No idea why the -n option STAYS in argv ;(
+query = ARGV.empty? ? nil : ARGV.join(" ")
+
+puts
+puts "Google Browse v#{GoogleBrowse::VERSION}"
+
+GoogleBrowse.search query: query, results_per_page: opts[:number]
+
+
+
+
+

data/google-browse.gemspec

@@ -0,0 +1,18 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/google_browse/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Bil Bas (Spooner)"]
+  gem.email         = ["bil.bagpuss@gmail.com"]
+  gem.description   = %q{This is a very simple text browser which aids in searching and navigating on Google.com. Shows results as a simple list, any of which may be opened in a full
+browser. Not really intended for real use, since it is only really a toy.}
+  gem.summary       = %q{Simple text-browser for Google.com}
+  gem.homepage      = ""
+
+  gem.files         = `git ls-files`.split($\)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.name          = "google-browse"
+  gem.require_paths = ["lib"]
+  gem.version       = GoogleBrowse::VERSION
+end

data/lib/google-browse.rb

@@ -0,0 +1,11 @@
+# Google search CLI browser that can open links into a browser.
+require 'bundler/setup'
+require 'mechanize'
+require 'launchy'
+
+require 'uri'
+require 'ostruct'
+
+require_relative "google_browse/scraper"
+require_relative "google_browse/browser"
+require_relative "google_browse/version"

data/lib/google_browse/browser.rb

@@ -0,0 +1,208 @@
+# Google search CLI browser that can open links into a browser.
+module GoogleBrowse
+  class << self
+    def search(*args); Browser.new *args; end
+  end
+
+  class Browser
+    DEFAULT_RESULTS_PER_PAGE = 5
+    MIN_RESULTS_PER_PAGE = 1
+    MAX_RESULTS_PER_PAGE = 20 # Avoid being rude to Google.
+    NUM_COLUMNS = 79
+
+    class << self
+      def search(*args); new *args; end
+    end
+
+    # @option :results_per_page [Integer] (5) Number of results to show per page.
+    # @option :query [String] Initial search string.
+    def initialize(options = {})
+      options = {
+        results_per_page: DEFAULT_RESULTS_PER_PAGE,
+      }.merge! options
+
+      @results_per_page = [
+          [MIN_RESULTS_PER_PAGE, options[:results_per_page]].max,
+          MAX_RESULTS_PER_PAGE
+      ].min
+
+      @quit = false
+
+      if options[:query]
+        @scraper = Scraper.new options[:query]
+      else
+        @scraper = nil
+        input_new_search
+      end
+
+      @page_number = 0
+
+      puts
+      list_links
+      navigate until quit?
+    end
+
+    protected
+    def quit?; @quit end
+    # Index, in @links, of the first link to show.
+    def first_link_index; @page_number * @results_per_page end
+    def link_range; first_link_index..last_link_index end 
+
+    protected
+    # Index, in @links, of the last link to show.
+    def last_link_index
+      if @scraper.more_pages?
+        first_link_index + @results_per_page - 1
+      else
+        @scraper.num_links - 1
+      end
+    end
+
+    protected
+    # Are we showing the last page?
+    def last_page?
+      !@scraper.more_pages? && last_link_index == (@scraper.num_links - 1)
+    end  
+
+    protected
+    def underline(title)
+      puts title
+      puts '_' * title.length  
+    end
+
+    protected
+    def list_links
+      limit_page_number
+
+      # Ensure we have enough links downloaded to display them.
+      first, last = first_link_index + 1, last_link_index + 1
+
+      # Force scraper to read as high as it can, then limit the page number.
+      @scraper[last_link_index] 
+      @page_number = [@page_number, @scraper.num_links.div(@results_per_page)].min
+
+      if @scraper.num_links > 0
+        num_columns = last.to_s.length
+
+        puts
+        underline "Page #{@page_number + 1}, showing results #{first} to #{last} for: #{@scraper.query}"
+        
+        @scraper[link_range].each.with_index(first) do |link, i|
+          indent = ' ' * (num_columns + 2)
+          puts
+          max_width = NUM_COLUMNS - indent.size
+          puts "#{i.to_s.rjust num_columns}: #{limit_text link.title, max_width}"
+          puts "#{indent}#{limit_text link.body, max_width}"
+          puts "#{indent}#{link.url}"
+        end
+      else
+        # No joy. Let's try a new search...
+        puts "No results for #{@scraper.query}!"
+        input_new_search
+        list_links
+      end
+    end
+
+    protected
+    def limit_text(text, length)
+      if text.size < length
+        text
+      else
+        text[0, length - 3] + '...'
+      end
+    end
+
+    protected
+    def limit_page_number
+      unless @scraper.more_pages?
+        @page_number = @scraper.num_links.div @results_per_page
+      end
+    end
+
+    protected
+    def navigate
+      # Ask the user for instructions.
+      puts
+
+      next_ = last_page? ? '' : 'N/'
+      previous = @page_number.zero? ? '' : 'p/'
+      print "Enter number of link to browse or [#{next_}#{previous}h/s/q]: "
+      input = $stdin.gets.strip
+
+      case input.upcase
+      when 'N', '' # Next page.
+        unless last_page?
+          @page_number += 1 
+          list_links
+        end
+
+      when 'P' # Previous page.
+        if @page_number > 0
+          @page_number -= 1
+          list_links
+        end
+
+      when 'H', '?'
+        puts <<-END_OF_TEXT
+
+  Browser help
+  ------------
+
+  N(next) - Next page (default action).
+  P(revious) - Previous page.
+  H(elp) - This help message.
+  S(earch) - Enter a new query string.
+  Q(uit) - Quit the browser.
+
+  Enter a link number to open it in your default browser for viewing.
+  END_OF_TEXT
+
+      when 'S' # Search
+        input_new_search
+
+        list_links
+
+      when 'Q' # Quit.
+        @quit = true
+
+      else # Follow link to page.
+        link_index = input.to_i - 1
+        if link_index.between? first_link_index, last_link_index
+          link = @scraper[link_index]
+          puts
+          puts "Navigating to #{link_index}: #{link.title} (#{link.url})"
+          puts
+          Launchy.open link.url
+          puts
+        else
+          puts "Bad input: #{input}"
+        end
+      end 
+
+      puts   
+    end
+
+    protected
+    def input_new_search
+      input = ''
+      while input.empty?
+        puts
+        print "Enter search string: "
+        input = $stdin.gets.strip
+      end
+
+      if @scraper
+        @scraper.query = input
+      else
+        @scraper = Scraper.new input
+      end
+
+      @page_number = 0
+    end
+  end
+end
+
+
+
+
+

data/lib/google_browse/scraper.rb

@@ -0,0 +1,129 @@
+# Google search CLI browser that can open links into a browser.
+module GoogleBrowse
+  class Scraper
+    BASE_PAGE = 'http://google.com'
+    RESULTS_PER_REQUEST = 100 # TODO: Use this! &num=100?
+
+    attr_reader :query
+    def num_links; @links.size; end
+    def more_pages?; @more_pages end
+
+    # @option :query [String] Initial search string.
+    def initialize(query)      
+      @links = [] # All the links retrieved are cached here.
+      @agent = Mechanize.new do |agent|
+        agent.max_history = 1 # We cache the important data ourselves.
+        agent.user_agent = 'Safari' # And why not?
+        agent.user_agent_alias = 'Mac Safari' # And why not?
+        agent.keep_alive = false
+      end
+
+      self.query = query
+    end
+
+    # Set the search query string.
+    def query=(text)
+      retrieve_initial_page text
+    end
+
+    # @param index [Integer, Range]
+    def [](index)
+      case index
+      when Integer
+        retrieve_next_page while more_pages? and index > @links.size 
+        @links[index]
+
+      when Range
+        retrieve_next_page while more_pages? and index.max > @links.size
+        @links[index]
+
+      else
+        raise TypeError, "Expected Integer or Range"
+      end
+    end
+
+    protected
+    def retrieve_initial_page(query)
+      @query = query
+      @links.clear
+
+      # Go to Google home page and create an initial query.
+      get BASE_PAGE
+      query_form = @agent.page.form_with name: /f/
+      
+      # Make the search.
+      query_form.q = @query
+
+      query_form.submit query_form.button_with(name: 'btnK')
+
+      @page_number = 0
+      @more_pages = true
+
+      parse_links
+    end
+
+    protected
+    def get(page)
+      @agent.get page    
+    end
+
+    protected
+    def next_page_link
+      link = @agent.page.search('table#nav td a').last
+      if link 
+        link[:href]
+      else
+        :no_more_pages
+      end
+    end
+
+    protected
+    def retrieve_next_page
+      link = next_page_link
+      
+      if link == :no_more_pages
+        @more_pages = false
+      else
+        get link
+        parse_links
+      end
+    end
+
+    protected
+    # Parse all the links found on the current page.
+    def parse_links
+      results = @agent.page.search 'li.g'
+      results.each do |result|
+        # May be youtube or google images/video links, so ignore these.
+        link = result.search('h3.r a').first
+        next unless link
+
+        body = result.search('span.st').first || OpenStruct.new(text: '')
+
+        # Extract the proper URL from the link, disregarding any that aren't full uris
+        # (e.g. google image/video links)
+        uri = URI.extract(link[:href]).first
+
+        if uri
+          url = uri[/[^\&]*/] # Trim off the trailing crap.
+          @links << OpenStruct.new(title: link.text, url: url, body: body.text)
+        end
+      end
+    end
+
+    protected
+    # Index, in @links, of the last link to show.
+    def last_link_index
+      if more_pages?
+        first_link_index + @results_per_page - 1
+      else
+        @links.size - 1
+      end
+    end
+  end
+end
+
+
+
+
+

data/lib/google_browse/version.rb

@@ -0,0 +1,3 @@
+module GoogleBrowse
+  VERSION = "0.1.2"
+end

data/lib/google_browse/version.rb~

@@ -0,0 +1,3 @@
+module GoogleBrowse
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,62 @@
+--- !ruby/object:Gem::Specification
+name: google-browse
+version: !ruby/object:Gem::Version
+  version: 0.1.2
+  prerelease: 
+platform: ruby
+authors:
+- Bil Bas (Spooner)
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-01-12 00:00:00.000000000 Z
+dependencies: []
+description: ! 'This is a very simple text browser which aids in searching and navigating
+  on Google.com. Shows results as a simple list, any of which may be opened in a full
+
+  browser. Not really intended for real use, since it is only really a toy.'
+email:
+- bil.bagpuss@gmail.com
+executables:
+- google-browse
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- bin/google-browse
+- google-browse.gemspec
+- lib/google-browse.rb
+- lib/google_browse/browser.rb
+- lib/google_browse/scraper.rb
+- lib/google_browse/version.rb
+- lib/google_browse/version.rb~
+homepage: ''
+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: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Simple text-browser for Google.com
+test_files: []
+has_rdoc: