requestmanager 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 4f67cdd4a24c5e45ff2509d3d934a1a9024178b8
+  data.tar.gz: ff5e527045259cb2207062af68042afd968f4c3f
+SHA512:
+  metadata.gz: 3419dea05f953ecb677c97cb4a7c06ba6cd264e79b4b8baa4cfa94bac8c0081550615a9b2039402c32e960900eb48e651723380b19d5309137c83e6d4ff78a92
+  data.tar.gz: cdfec6f8eda2883212ee9fdb0cd4fabe11c37b6e8cb525f86fbc05576e8f84dca905a3ecb3bc689474b308d9c4faa68ebdbe47163c4cf83896364a6988e2bff9

data/lib/requestmanager.rb

@@ -0,0 +1,77 @@
+require 'selenium-webdriver'
+require 'uri'
+require 'pry'
+
+
+class RequestManager
+  def initialize(proxy_list, request_interval)
+    @proxy_list = parse_proxy_list(proxy_list)
+    @request_interval = request_interval
+    @used_proxies = Hash.new
+  end
+
+  # Get the page requested
+  def get_page(url, form_input = nil)
+    chosen_proxy = @proxy_list != nil ? get_random_proxy(url) : nil
+    driver = gen_driver(chosen_proxy)
+    driver.navigate.to url
+    puts "Getting page " + url
+
+    # Handle form input if there is any
+    if form_input
+      element = driver.find_element(name: "q")
+      element.send_keys form_input
+      element.submit
+    end
+    
+    page_html = driver.page_source
+    driver.quit
+    return page_html
+  end
+  
+  # Generate driver for searches
+  def gen_driver(chosen_proxy)
+    # Profile settings
+    profile = Selenium::WebDriver::Firefox::Profile.new
+    profile['intl.accept_languages'] = 'en'
+
+    # Set proxy if proxy list, otherwise sleep
+    if chosen_proxy
+      proxy = Selenium::WebDriver::Proxy.new(http: chosen_proxy, ssl: chosen_proxy)
+      profile.proxy = proxy
+    else
+      sleep(rand(@request_interval[0]..@request_interval[1]))
+    end
+    
+    return Selenium::WebDriver.for :firefox, profile: profile
+  end
+
+  # Choose a random proxy that hasn't been used recently
+  def get_random_proxy(url)
+    max = @proxy_list.length
+    chosen = @proxy_list[Random.rand(max)]
+
+    # Only use proxy if it hasn't been used in last n seconds on same host
+    if is_not_used?(chosen, url)
+      @used_proxies[chosen] = [Time.now, URI.parse(url).host]
+      return chosen[0]+":"+chosen[1]
+    else
+      sleep(0.005)
+      get_random_proxy(url)
+    end
+  end
+
+  # Checks if a proxy has been used on domain in the last 20 seconds
+  def is_not_used?(chosen, url)
+    return (!@used_proxies[chosen] ||
+            @used_proxies[chosen][0] <= Time.now-@request_interval[0] ||
+            @used_proxies[chosen][1] != URI.parse(url).host)
+  end
+
+  # Parse the proxy list
+  def parse_proxy_list(proxy_file)
+    if proxy_file
+      return IO.readlines(proxy_file).map{ |proxy| proxy.strip.split(":")}
+    end
+  end
+end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: requestmanager
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- M. C. McGrath
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-11-01 00:00:00.000000000 Z
+dependencies: []
+description: Manages proxies, wait intervals, etc
+email: shidash@shidash.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/requestmanager.rb
+homepage: https://github.com/TransparencyToolkit/linkedincrawler
+licenses:
+- GPL
+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: 2.4.8
+signing_key: 
+specification_version: 4
+summary: Manages scraper http requests
+test_files: []
+has_rdoc: