google_scraper_gem 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: e2d5d369bdc61676e20de327fa71d15034c813e4
+  data.tar.gz: fa0ea376e7f622027da3a0a5ce574f90d2060ed2
+SHA512:
+  metadata.gz: a34db3cff8fba2a3686bc85a04c25853f314d0c9ad7efa36a7d6c0d00f45aae9b597e66b72fcdbb4497c0f9e5e283e8ab3554b61cdc9f29c95773441166f8e4a
+  data.tar.gz: e5c9596f98e4e3f17303877ce486c0024525e1ad09eec6c5adcf7974dfec35457faefa0da0820a48b3439e580c66343ada3d1ca12d3d4ca13f119c60da61cd34

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,5 @@
+source 'https://rubygems.org'
+ruby '2.0.0'
+
+# Specify your gem's dependencies in google_scraper_gem.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Han Chang
+
+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 +1,29 @@
+# GoogleScraperGem
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'google_scraper_gem'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install google_scraper_gem
+
+## Usage
+
+TODO: Write usage instructions here
+
+## 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 +1,6 @@
+require "bundler/gem_tasks"
+require 'rake/testtask'
+
+Rake::TestTask.new do |t|
+  t.pattern = "spec/**/*_spec.rb"
+end

data/google_scraper_gem.gemspec

@@ -0,0 +1,25 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'google_scraper_gem/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "google_scraper_gem"
+  spec.version       = GoogleScraperGem::VERSION
+  spec.authors       = ["Han Chang"]
+  spec.email         = ["szu.han.chang@gmail.com"]
+  spec.description   = %q{Scrapes Google Search results}
+  spec.summary       = %q{Scrapes Google Search results}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_runtime_dependency "mechanize"
+  spec.add_runtime_dependency "nokogiri"
+end

data/lib/google_scraper_gem/version.rb

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

data/lib/google_scraper_gem.rb

@@ -0,0 +1,98 @@
+require 'uri'
+require 'mechanize'
+require 'nokogiri'
+
+class GoogleScraper
+  BASE_URL = "http://www.google"
+  SEARCH = "/search?q="
+  CSS_SELECTOR = "li[@class='g'] > div.rc > h3.r > a"
+  RANK_LIMIT = 100 # Stop looking for the target URL after 100 results
+
+  def initialize()
+    # proxy = {:host => "204.12.216.84", :port => 20602, :username => 'pp-henryjay', :password => 'rein&true'}
+    @mech = Mechanize.new { |agent|
+      # User Agent list - http://github.com/tenderlove/mechanize/blob/master/lib/mechanize.rb
+      agent.user_agent_alias = 'Mac Safari' 
+    }
+
+    # @mech.set_proxy proxy[:host], proxy[:port], proxy[:username], proxy[:password]
+  end
+
+  # @return Rank of URL for keyword in google.locale
+  def checkRank(keyword, url, locale: '.com')
+    results = []
+
+    rank_count = 0
+    page_num = 1
+
+    uri = BASE_URL + locale + SEARCH + URI.encode(keyword)
+
+    page = @mech.get(uri)
+    while rank_count < RANK_LIMIT
+      # This parse definition requires the Mac Safari user agent.
+      page.parser.css(CSS_SELECTOR).each do |cite|
+        rank_count += 1
+
+        result = cite.attr('href')
+        puts result
+
+        result.gsub!(%r{^http://}, '')
+        result.gsub!(%r{^https://}, '')
+
+        return rank_count if result.start_with?(url) or result.start_with?("www." + url)
+      end
+
+      # Get next search result page.
+      page_num += 1
+
+      # Add random sleep to prevent blocking of IP.
+      # TODO: Replace this with proxy swap.
+      rand(8)
+
+      # TODO: Click "next" instead?
+      page = page.link_with(:text => page_num.to_s).click
+    end
+
+    return -1
+  end
+
+  # @return Array of domains in the order specified by Google. 
+  def getTopResults(keyword, extension: '.com', top: 10)
+    results = []
+
+    rank_count = 0
+    page_num = 1
+
+    uri = BASE_URL + extension + SEARCH + URI.encode(keyword)
+
+    page = @mech.get(uri)
+    while rank_count < top
+      # This parse definition requires the Mac Safari user agent.
+      page.parser.css(CSS_SELECTOR).each do |cite|
+        rank_count += 1
+
+        result = cite.attr('href')
+        puts result
+        results << result if result.start_with? 'http'
+      end
+
+      return results if rank_count >= top
+
+      # Confirm that there are ten results in this cycle.
+      unless rank_count % 10 == 0
+        puts "WARNING: There were #{rank_count.to_s} results instead of 10 near page #{page_num} for '#{keyword}'."
+      end
+
+      # Get next search result page.
+      page_num += 1
+
+      # Add random sleep to prevent blocking of IP.
+      # TODO: Replace this with proxy swap.
+      rand(8)
+
+      page = page.link_with(:text => page_num.to_s).click
+    end
+
+    results
+  end
+end

data/spec/google_scraper_gem_spec.rb

@@ -0,0 +1,18 @@
+require 'minitest/spec'
+require 'minitest/autorun'
+require_relative '../lib/google_scraper_gem'
+
+@@gs = GoogleScraper.new
+@@results = @@gs.getTopResults('medical assistant')
+
+describe GoogleScraper do
+  it "retrieves the top 10 results by default" do
+    @@results.count.must_equal 10
+  end
+
+  it "should not return results that are invalid URLs" do
+    @@results.each do |result|
+      result.wont_include "›"
+    end
+  end
+end

metadata

@@ -0,0 +1,110 @@
+--- !ruby/object:Gem::Specification
+name: google_scraper_gem
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Han Chang
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-08-05 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Scrapes Google Search results
+email:
+- szu.han.chang@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- google_scraper_gem.gemspec
+- lib/google_scraper_gem.rb
+- lib/google_scraper_gem/version.rb
+- spec/google_scraper_gem_spec.rb
+homepage: ''
+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: 2.0.3
+signing_key: 
+specification_version: 4
+summary: Scrapes Google Search results
+test_files:
+- spec/google_scraper_gem_spec.rb