scraypa 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 428e660dbb1d40ffb042053e7dbc0198b21aff72
+  data.tar.gz: fe07d8c05e7f458a41a234221ddab2c1c79f357c
+SHA512:
+  metadata.gz: 1757aa2cb798597a6588c57975dfa516048286f2c43eebcbd79affb2fba56519fb034b15f44c8b01a0fc80938db5465f578e2cb85b1428ed6f7282a4afc35d77
+  data.tar.gz: 983a91b91f510bdf93142f6614262af81398a33ddcb41fd02e25b408ee944a2e06afaa41e760939bba7b37ab306638d392edb7015b342c27847851d2e9a36a25

data/.gitignore

@@ -0,0 +1,13 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+/.idea/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.3.1
+before_install: gem install bundler -v 1.14.6

data/Gemfile

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

data/Guardfile

@@ -0,0 +1,90 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+## Uncomment and set this to only include directories you want to watch
+#directories %w(lib lib/scraypa/ lib/scraypa/eye/ spec) \
+#  .select{|d| Dir.exists?(d) ? d : UI.warning("Directory #{d} does not exist")}
+
+## Note: if you are using the `directories` clause above and you are not
+## watching the project directory ('.'), then you will want to move
+## the Guardfile to a watched dir and symlink it back, e.g.
+#
+#  $ mkdir config
+#  $ mv Guardfile config/
+#  $ ln -s config/Guardfile .
+#
+# and, you'll have to watch "config/Guardfile" instead of "Guardfile"
+
+# Note: The cmd option is now required due to the increasing number of ways
+#       rspec may be run, below are examples of the most common uses.
+#  * bundler: 'bundle exec rspec'
+#  * bundler binstubs: 'bin/rspec'
+#  * spring: 'bin/rspec' (This will use spring if running and you have
+#                          installed the spring binstubs per the docs)
+#  * zeus: 'zeus rspec' (requires the server to be started separately)
+#  * 'just' rspec: 'rspec'
+=begin
+guard :rspec, cmd: "bundle exec rspec" do
+  require "guard/rspec/dsl"
+  dsl = Guard::RSpec::Dsl.new(self)
+
+  # Feel free to open issues for suggestions and improvements
+
+  # RSpec files
+  rspec = dsl.rspec
+  watch(rspec.spec_helper) { rspec.spec_dir }
+  watch(rspec.spec_support) { rspec.spec_dir }
+  watch(rspec.spec_files)
+
+  # Ruby files
+  ruby = dsl.ruby
+  dsl.watch_spec_files_for(ruby.lib_files)
+
+  # Rails files
+  rails = dsl.rails(view_extensions: %w(erb haml slim))
+  dsl.watch_spec_files_for(rails.app_files)
+  dsl.watch_spec_files_for(rails.views)
+
+  watch(rails.controllers) do |m|
+    [
+      rspec.spec.call("routing/#{m[1]}_routing"),
+      rspec.spec.call("controllers/#{m[1]}_controller"),
+      rspec.spec.call("acceptance/#{m[1]}")
+    ]
+  end
+
+  # Rails config changes
+  watch(rails.spec_helper)     { rspec.spec_dir }
+  watch(rails.routes)          { "#{rspec.spec_dir}/routing" }
+  watch(rails.app_controller)  { "#{rspec.spec_dir}/controllers" }
+
+  # Capybara features specs
+  watch(rails.view_dirs)     { |m| rspec.spec.call("features/#{m[1]}") }
+  watch(rails.layouts)       { |m| rspec.spec.call("features/#{m[1]}") }
+
+  # Turnip features and steps
+  watch(%r{^spec/acceptance/(.+)\.feature$})
+  watch(%r{^spec/acceptance/steps/(.+)_steps\.rb$}) do |m|
+    Dir[File.join("**/#{m[1]}.feature")][0] || "spec/acceptance"
+  end
+end
+=end
+
+guard :rspec, cmd: 'bundle exec rspec' do
+  require "guard/rspec/dsl"
+  dsl = Guard::RSpec::Dsl.new(self)
+
+  # RSpec files
+  rspec = dsl.rspec
+  watch(rspec.spec_helper) { rspec.spec_dir }
+  watch(rspec.spec_support) { rspec.spec_dir }
+  watch(rspec.spec_files)
+
+  # Ruby files
+  ruby = dsl.ruby
+  dsl.watch_spec_files_for(ruby.lib_files)
+
+  #watch(%r{^spec/.+_spec\.rb$})
+  #watch(%r{^lib/(.+)\.rb$})     { |m| "spec/#{m[1]}_spec.rb" }
+  #watch('spec/spec_helper.rb')  { "spec" }
+end

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2017 joshweir
+
+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 +1,142 @@
+# Scraypa
+
+A Ruby gem to scrape web content with configuration options including: 
+ 
+1. [Javscript support](#javascript-support)
+2. [The Onion Router (Tor)](#tor)
+3. [Disguise](#disguise) (TODO)
+
+Scraypa is essentially a wrapper for the light-weight 
+[Rest Client](https://github.com/rest-client/rest-client) (if you dont require javascript support)
+ or [Capybara](https://github.com/teamcapybara/capybara) (for Javascript support). 
+
+## Why? 
+
+A web scraper that can be configured to support javascript and/or Tor. If javascript is not required, 
+ it will use the lighter Rest Client. Scraypa is an attempt to remove the complexities associated to web agent setup. 
+
+## Installation
+
+### Install Tor (optional)
+
+If you want to use Tor, install tor:
+
+`sudo apt-get install tor`
+
+### Install Headless Chrome (optional)
+
+If you want to use `:headless_chrome` with capybara, install 
+headless chrome by following instructions here: 
+
+http://blog.faraday.io/headless-chromium/
+
+For ubuntu I did this: 
+
+1. Install chromium: 
+
+        git clone https://github.com/scheib/chromium-latest-linux.git
+        cd chromium-latest-linux
+        ./update-and-run.sh
+        
+2. Install chromedriver by [following the build instructions](https://chromium.googlesource.com/chromium/src/+/master/docs/linux_build_instructions.md).
+
+### Install Scraypa
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'scraypa'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install scraypa
+
+## Usage
+
+    response = Scraypa.visit(method: :get,
+                             url: "http://example.com")
+    
+    #the response contains the RestClient response object
+    response.code
+    #-> 200
+    response.to_str
+    #-> http://example.com content
+    
+By default Scraypa uses the rest-client gem which does
+not support Javascript. The `#visit` method wraps the  
+[`RestClient#execute` method](https://github.com/rest-client/rest-client#passing-advanced-options)
+so you can pass in whatever `RestClient#execute` will accept, 
+for example:
+
+    Scraypa.visit(method: :get, 
+                  url: 'http://example.com/resource',
+                  timeout: 10, 
+                  headers: {params: {foo: 'bar'}})
+                  
+    ➔ GET http://example.com/resource?foo=bar
+
+### Javascript Support
+
+Capybara is used for Javascript support:
+
+    #configure Scraypa to #use_capybara
+    #and choose your capybara driver, here is poltergeist:
+    Scraypa.configure do |config|
+      config.use_capybara = true
+      config.driver = :poltergeist
+      config.driver_options = {
+          :phantomjs => Phantomjs.path,
+          :js_errors => false,
+          :phantomjs_options => ["--web-security=true"]
+      }
+      
+      #or you could instead use headless_chrome:
+      #config.driver = :headless_chromium
+      #config.driver_options = {
+      #  browser: :chrome,
+      #  desired_capabilities: Selenium::WebDriver::Remote::Capabilities.chrome(
+      #    "chromeOptions" => {
+      #      "binary" => "/home/resrev/chromium/src/out/Default/chrome",
+      #      "args" => %w{headless no-sandbox disable-gpu}
+      #    }
+      #  )
+      #}
+    end
+    
+    #when using capybara, just the url parameter is required:
+    response = Scraypa.visit(url: "http://example.com")
+    
+    #the response contains the capybara page object
+    response.status_code
+    #-> 200
+    response.text
+    #-> http://example.com content 
+    
+    #execute some javascript:
+    response.execute_script(
+      "document.getElementsByTagName('body')[0].innerHTML = 'changed content';")
+    response.text
+    #-> "changed content"
+
+### Tor
+
+TODO
+
+### Disguise
+
+TODO
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/joshweir/scraypa.
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "scraypa"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/scraypa.rb

@@ -0,0 +1,189 @@
+require "scraypa/version"
+require "scraypa/configuration"
+require "scraypa/visit/visit_interface"
+require "scraypa/visit/visit_rest_client"
+require "scraypa/visit/visit_capabara_poltergeist"
+require "scraypa/visit/visit_capabara_headless_chromium"
+require "scraypa/visit/visit_factory"
+require "scraypa/user_agent/user_agent_abstract"
+require "scraypa/user_agent/user_agent_common_aliases_lists"
+require "scraypa/user_agent/user_agent_iterator"
+require "scraypa/user_agent/user_agent_random"
+require "scraypa/user_agent/user_agent_factory"
+require "scraypa/throttle"
+require "scraypa/driver_resetter"
+require 'tormanager'
+
+module Scraypa
+  class TorNotSupportedByAgent < StandardError; end
+  class UnrecognisedUserAgentsMethod < StandardError; end
+  class CapybaraDriverUnsupported < StandardError; end
+  class HeadlessChromiumMissingConfig < StandardError; end
+
+  class << self
+    attr_accessor :agent, :tor_process, :tor_ip_control, :tor_proxy,
+                  :throttle, :user_agent_retriever, :driver_resetter
+
+    def configuration
+      @configuration ||= Configuration.new
+    end
+
+    def configuration=(config)
+      @configuration = config
+    end
+
+    def reset
+      @configuration = Configuration.new
+      reset_throttle
+      setup_scraypa
+      @configuration
+    end
+
+    def configure
+      yield(configuration).tap{
+        validate_configuration
+        setup_scraypa
+      }
+    end
+
+    def visit params={}
+      setup_scraypa unless @agent
+      visit_with_throttle params
+    end
+
+    def change_tor_ip_address
+      @tor_ip_control.get_new_ip if using_tor?
+    end
+
+    def user_agent
+      @user_agent_retriever ?
+          @user_agent_retriever.current_user_agent : nil
+    end
+
+    private
+
+    def validate_configuration
+      headless_chromium_with_tor_is_invalid
+    end
+
+    def headless_chromium_with_tor_is_invalid
+      raise TorNotSupportedByAgent,
+            "Capybara :headless_chromium does not support Tor" if
+          using_tor? && @configuration.driver == :headless_chromium
+    end
+
+    def setup_scraypa
+      setup_user_agent
+      setup_tor
+      setup_driver_resetter
+      setup_agent
+      setup_throttle
+    end
+
+    def setup_user_agent
+      @user_agent_retriever =
+          @configuration.user_agent ?
+              UserAgentFactory.build(
+                  merge_user_agent_list_limit_for_chrome(
+                      @configuration.user_agent)) : nil
+    end
+
+    def merge_user_agent_list_limit_for_chrome config
+      @configuration.driver == :headless_chromium &&
+          !config[:list_limit] ?
+          config.merge({list_limit: 30}) : config
+    end
+
+    def setup_tor
+      ensure_tor_options_are_configured
+      using_tor? && !tor_running_in_current_process? ?
+          reset_tor :
+          (!using_tor? && tor_running_in_current_process? ?
+              destruct_tor : nil)
+    end
+
+    def ensure_tor_options_are_configured
+      if using_tor?
+        @configuration.tor_options ||= {}
+        @configuration.tor_options[:tor_port] ||= 9050
+        @configuration.tor_options[:control_port] ||= 50500
+      else
+        @configuration.tor_options = nil
+      end
+    end
+
+    def using_tor?
+      @configuration.tor
+    end
+
+    def tor_running_in_current_process?
+      @configuration.tor_options &&
+          @configuration.tor_options[:tor_port] ?
+          TorManager::TorProcess
+              .tor_running_on?(port: @configuration.tor_options[:tor_port],
+                               parent_pid: Process.pid) :
+          TorManager::TorProcess
+              .tor_running_on?(parent_pid: Process.pid)
+    end
+
+    def reset_tor
+      destruct_tor
+      initialize_tor(@configuration.tor_options) if @configuration.tor
+    end
+
+    def initialize_tor params={}
+      @tor_process = TorManager::TorProcess.new params || {}
+      @tor_proxy =
+          TorManager::Proxy.new tor_process: @tor_process
+      @tor_ip_control = TorManager::IpAddressControl.new(
+          tor_process: @tor_process, tor_proxy: @tor_proxy)
+      @tor_process.start
+    end
+
+    def destruct_tor
+      @tor_process.stop if @tor_process
+      TorManager::TorProcess.stop_obsolete_processes
+      @tor_ip_control = nil
+      @tor_proxy = nil
+      @tor_process = nil
+    end
+
+    def setup_driver_resetter
+      @driver_resetter =
+          DriverResetter.new(
+              @configuration.reset_driver_every_n_requests)
+    end
+
+    def setup_agent
+      @agent = Scraypa::VisitFactory
+                   .build(config: @configuration,
+                          tor_proxy: @tor_proxy,
+                          driver_resetter: @driver_resetter,
+                          user_agent_retriever: @user_agent_retriever)
+    end
+
+    def setup_throttle
+      @throttle = Throttle.new seconds: @configuration.throttle_seconds if
+          throttle_config_has_changed?
+    end
+
+    def throttle_config_has_changed?
+      @configuration.throttle_seconds &&
+          (@configuration.throttle_seconds.is_a?(Hash) ||
+              @configuration.throttle_seconds.to_f > 0) &&
+          (!@throttle || @throttle.seconds != @configuration.throttle_seconds)
+    end
+
+    def visit_with_throttle params
+      @throttle.throttle if @throttle
+      response = @agent.execute(params)
+      @throttle.last_request_time = Time.now if @throttle
+      response
+    end
+
+    def reset_throttle
+      @throttle.last_request_time = nil if @throttle
+      @throttle = nil
+    end
+  end
+end