object-scraper 0.0.2 → 0.0.3

data/README.rdoc

@@ -31,6 +31,10 @@ extraction of ruby objects from various web sites.
 
   @objects = Scraper.parse(:twitter)
 
+If you define multiple scrapers, you can collect all their objects with one simple method
+
+   @objects = Scraper.parse_all
+
 == Advanced Example
 
 It is possible to use other existing HTML parsers instead of hpricot.

data/Rakefile

@@ -2,7 +2,7 @@ require 'rubygems'
 require 'rake'
 require 'echoe'
 
-Echoe.new('object-scraper', '0.0.2') do |p|
+Echoe.new('object-scraper', '0.0.3') do |p|
   p.summary         = "Recipe like object extraction from HTML sources"
   p.description     = "Object scraper is a thin wrapper for hpricot to enable recipe-like extraction of ruby objects from various web sites."
   p.url             = "http://github.com/enricogenauck/object-scraper"

data/lib/object-scraper/scraper.rb

@@ -42,6 +42,12 @@ class Scraper
   def self.parse(name)
     scraper_by_name(name).parse
   end
+  
+  def self.parse_all
+    objects = []
+    scrapers.each_value { |s| objects << s.parse }
+    objects.flatten
+  end
 
   def parse
     doc = open(@scraper_source) { |f| Scraper.scrape_source_with.call(f) }

data/object-scraper.gemspec

@@ -2,11 +2,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{object-scraper}
-  s.version = "0.0.2"
+  s.version = "0.0.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
   s.authors = ["Enrico Genauck"]
-  s.date = %q{2009-12-10}
+  s.date = %q{2010-02-03}
   s.description = %q{Object scraper is a thin wrapper for hpricot to enable recipe-like extraction of ruby objects from various web sites.}
   s.email = %q{kontakt@enricogenauck.de}
   s.extra_rdoc_files = ["README.rdoc", "lib/object-scraper.rb", "lib/object-scraper/scraper.rb"]

data/spec/object-scraper/scraper_spec.rb

@@ -43,6 +43,22 @@ describe Scraper do
       @objects.first.date.should == DateTime.parse("Mon Nov 30 04:10:51 +0000 2009")
     end
     
+    it "should get the objects from multiple scrapers" do
+      Scraper.define(:twitter_1, :class => :entry, :source => @uri, :node => @pattern) do |s|
+        s.text { |node| node.at(".entry-content").inner_html }
+        s.date { |node| DateTime.parse(node.at(".timestamp")[:data][/\'.*\'/].delete("'")) }
+      end
+      
+      Scraper.define(:twitter_2, :class => :entry, :source => @uri, :node => @pattern) do |s|
+        s.text { |node| node.at(".entry-content").inner_html }
+        s.date { |node| DateTime.parse(node.at(".timestamp")[:data][/\'.*\'/].delete("'")) }
+      end
+      
+      
+      @objects = Scraper.parse_all
+      @objects.size.should == 40
+    end
+    
     it "should use a different html parser" do
       require 'nokogiri'
       Scraper.scrape_source_with = Proc.new { |source| Nokogiri::HTML(source) }

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: object-scraper
 version: !ruby/object:Gem::Version 
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors: 
 - Enrico Genauck
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-12-10 00:00:00 +01:00
+date: 2010-02-03 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency