chrisle · December 10, 2015 02:58 · Jan 4, 2013 · Dec 25, 2012 · Dec 25, 2012 · Dec 25, 2012
diff --git a/capybara_with_phantom_js.rb b/capybara_with_phantom_js.rb
@@ -13,7 +13,7 @@ def new_session
     Capybara.default_selector = :xpath
 
     # Start up a new thread
-    @session = Capybara::Session.new(driver)
+    @session = Capybara::Session.new(:poltergeist)
 
     # Report using a particular user agent
     @session.driver.headers = { 'User-Agent' =>

diff --git a/google_plus_scraper.rb b/google_plus_scraper.rb
@@ -10,7 +10,7 @@
 #   # => { id: 111044299943603359137, in_circles: 1234, timestamp: 123456789 }
 #
 class GooglePlusScraper
-  include PhantomJs
+  include CapybaraWithPhantomJs
 
   def initialize(profile_id)
     @profile_id = profile_id

diff --git a/google_plus_scraper.rb b/google_plus_scraper.rb
@@ -1,7 +1,7 @@
 # Add the mixin
 require 'capybara_with_phantom_js'
 
-# Google+ Scraper that scrapes
+# Google+ Scraper
 #
 # === Example
 #

diff --git a/irb.rb b/irb.rb
@@ -0,0 +1,2 @@
+g_plus = GooglePlusScraper.new(111044299943603359137).to_h
+# => { id: 111044299943603359137, in_circles: 1234, timestamp: 123456789 }
diff --git a/capybara_with_phantom_js.rb b/capybara_with_phantom_js.rb
@@ -0,0 +1,30 @@
+module CapybaraWithPhantomJs
+  include Capybara
+
+  # Create a new PhantomJS session in Capybara
+  def new_session
+
+    # Register PhantomJS (aka poltergeist) as the driver to use
+    Capybara.register_driver :poltergeist do |app|
+      Capybara::Poltergeist::Driver.new(app)
+    end
+
+    # Use XPath as the default selector for the find method
+    Capybara.default_selector = :xpath
+
+    # Start up a new thread
+    @session = Capybara::Session.new(driver)
+
+    # Report using a particular user agent
+    @session.driver.headers = { 'User-Agent' =>
+      "Mozilla/5.0 (Macintosh; Intel Mac OS X)" }
+
+    # Return the driver's session
+    @session
+  end
+
+  # Returns the current session's page
+  def html
+    session.html
+  end
+end
diff --git a/google_plus_scraper.rb b/google_plus_scraper.rb
@@ -0,0 +1,55 @@
+# Add the mixin
+require 'capybara_with_phantom_js'
+
+# Google+ Scraper that scrapes
+#
+# === Example
+#
+#   g_plus = GooglePlusScraper.new(111044299943603359137)
+#   data = g_plus.to_h
+#   # => { id: 111044299943603359137, in_circles: 1234, timestamp: 123456789 }
+#
+class GooglePlusScraper
+  include PhantomJs
+
+  def initialize(profile_id)
+    @profile_id = profile_id
+  end
+
+  # Return a hash
+  def to_h
+    data = {
+      :id => @profile_id,
+      :in_circles => in_circles,
+      :timestamp => Date.today.to_datetime.to_i
+    }
+  end
+
+  # Return the circle count as an integer
+  def in_circles
+    matches = tp_tx_hp
+    return 0 if matches.nil?
+    str = matches.find { |s| s.include?('have them in circles') }
+    (str.nil?) ? 0 : Integer(str.gsub(/,/, '').match(/\d+/)[0])
+  end
+
+  # Return the text found in H3 tags
+  def tp_tx_hp
+    results = google_plus_page.search('//h3[@class="TP tx hp"]/span')
+    results = results.collect(&:text)
+    return nil if results.empty?
+    results
+  end
+
+  # Get the Google Plus page and locally cache it in an instance variable
+  def google_plus_page
+    unless @google_plus_page
+      new_session
+      visit "https://plus.google.com/u/0/#{@profile_id}/posts"
+      sleep 5 # give phantomjs 5 seconds and let the page fill itself in
+      @google_plus_page = Nokogiri::HTML.parse(html)
+    end
+    @google_plus_page
+  end
+
+end
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		g_plus = GooglePlusScraper.new(111044299943603359137).to_h
		# => { id: 111044299943603359137, in_circles: 1234, timestamp: 123456789 }
No results found