content_scrapper 0.0.8 → 0.0.9

data/VERSION

@@ -1 +1 @@
-0.0.8
+0.0.9

data/content_scrapper.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = %q{content_scrapper}
-  s.version = "0.0.8"
+  s.version = "0.0.9"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Gyorgy Frivolt"]

data/lib/content_scrapper.rb

@@ -51,12 +51,12 @@ class ContentScrapper
     end
   end
 
-  def scrap_content(url, full_page = nil)
+  def scrap_content(url, options = {})
     content_mappings.each do | content_mapping |
       if content_mapping.matches_url?(url)
         return nil if content_mapping.content_xpaths_list.empty?
         begin
-          doc = Nokogiri::HTML(full_page || Kernel.open(url))
+          doc = Nokogiri::HTML(options[:use_page] || Kernel.open(url))
           return content_mapping.scrap_content(doc, content_scrapper = self)
         rescue Exception
           @scrapping_exception_handler_block.call($!) unless @scrapping_exception_handler_block.nil?

data/lib/content_scrapper/feedzirra.rb

@@ -6,13 +6,13 @@ module Feedzirra
   module FeedEntryUtilities
 
     # Scrap the content based on the URL and the existing content and return it
-    def scrap_content(scrapper = ContentScrapper.default, full_page = nil)
-      scrapper.scrap_content(self.url, full_page = full_page) || self.content.to_s
+    def scrap_content(scrapper = ContentScrapper.default, options = {})
+      scrapper.scrap_content(self.url, options) || self.content.to_s
     end
 
     # Scrap the content or use the existing one and change the feed entry
-    def scrap_content!(scrapper = ContentScrapper.default, full_page = nil)
-      self.content = scrap_content(scrapper, full_page = full_page)
+    def scrap_content!(scrapper = ContentScrapper.default, options = {})
+      self.content = scrap_content(scrapper, options)
     end
   end
 end

data/test/test_content_scrapper.rb

@@ -112,7 +112,7 @@ class TestContentScrapper < Test::Unit::TestCase
         pretty_content = File.open("#{File.dirname(__FILE__)}/test_pages/pretty.html").read 
         Kernel.expects(:open).never
         @scrapped_content = @scrapper.scrap_content('http://www.pretty.url/hsdae',
-                                                    full_page = pretty_content)
+                                                    :use_page => pretty_content)
       end
       should "scrap from the provided full page" do
         assert_match(%r{<p><strong>This is a strong text</strong></p>}, @scrapped_content)
@@ -157,8 +157,8 @@ class TestContentScrapper < Test::Unit::TestCase
         should("return the original feed content") do
           @feed_entries.each do |feed_entry|
             assert_match(%r{<p><strong>This is a strong text</strong></p>},
-              feed_entry.scrap_content(@scrapper, full_page = @pretty_content))
-            feed_entry.scrap_content!(@scrapper, full_page = @pretty_content)
+              feed_entry.scrap_content(@scrapper, :use_page => @pretty_content))
+            feed_entry.scrap_content!(@scrapper, :use_page => @pretty_content)
             assert_match(%r{<p><strong>This is a strong text</strong></p>}, feed_entry.content)
           end
         end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: content_scrapper
 version: !ruby/object:Gem::Version 
-  version: 0.0.8
+  version: 0.0.9
 platform: ruby
 authors: 
 - Gyorgy Frivolt