gscraper 0.1.2 → 0.1.3

data/History.txt

@@ -1,3 +1,8 @@
+== 0.1.3 / 2007-12-22
+
+ * Added the Page class, which contains many of convenance methods for
+   searching through the results within a Page.
+
 == 0.1.2 / 2007-12-22
 
  * Fixed a bug related to extracting the correct content-rights from search

data/Manifest.txt

@@ -11,6 +11,7 @@ lib/gscraper/extensions/uri.rb
 lib/gscraper/extensions.rb
 lib/gscraper/licenses.rb
 lib/gscraper/search/result.rb
+lib/gscraper/search/page.rb
 lib/gscraper/search/query.rb
 lib/gscraper/search/search.rb
 lib/gscraper/search.rb

data/lib/gscraper/search/page.rb

@@ -0,0 +1,224 @@
+require 'gscraper/search/result'
+
+module GScraper
+  module Search
+    class Page < Array
+
+      #
+      # Creates a new Page object with the given _results_.
+      #
+      def initialize(results=[])
+        super(results)
+      end
+
+      #
+      # Returns a mapped Array of the results within the Page using the
+      # given _block_. If the _block_ is not given, the page will be
+      # returned.
+      #
+      #   page.map # => Page
+      #
+      #   page.map { |result| result.url } # => [...]
+      #
+      def map(&block)
+        return self unless block
+
+        mapped = []
+
+        each { |result| mapped << block.call(result) }
+        return mapped
+      end
+
+      #
+      # Selects the results within the Page which match the given _block_.
+      #
+      #   page.select { |result| result.title =~ /ruby/i }
+      #
+      def select(&block)
+        Page.new(super(&block))
+      end
+
+      #
+      # Selects the results using the specified _block_.
+      #
+      #   page.results_with { |result| result.title =~ /blog/ }
+      #
+      def results_with(&block)
+        select(&block)
+      end
+
+      #
+      # Selects the results with the matching _title_. The _title_ may be
+      # either a String or a Regexp. If _block_ is given, each matching
+      # result will be passed to the _block_.
+      #
+      #   page.results_with_title('hackety org') #=> Page
+      #
+      #   page.results_with_title(/awesome/) do |result|
+      #     puts result.url
+      #   end
+      #
+      def results_with_title(title,&block)
+        if title.kind_of?(Regexp)
+          results = results_with { |result| result.title =~ title }
+        else
+          results = results_with { |result| result.title == title }
+        end
+
+        results.each(&block) if block
+        return results
+      end
+
+      #
+      # Selects the results with the matching _url_. The _url_ may be
+      # either a String or a Regexp. If _block_ is given, each matching
+      # result will be passed to the _block_.
+      #
+      #   page.results_with_url(/\.com/) # => Page
+      #
+      #   page.results_with_url(/^https:\/\//) do |result|
+      #     puts result.title
+      #   end
+      #
+      def results_with_url(url,&block)
+        if url.kind_of?(Regexp)
+          results = results_with { |result| result.url =~ url }
+        else
+          results = results_with { |result| result.url == url }
+        end
+
+        results.each(&block) if block
+        return results
+      end
+
+      #
+      # Selects the results with the matching _summary_. The _summary_ may
+      # be either a String or a Regexp. If _block_ is given, each matching
+      # result will be passed to the _block_.
+      #
+      #   page.results_with_summary(/cheese cake/) # => Page
+      #
+      #   page.results_with_summary(/Scientifically/) do |result|
+      #     puts result.url
+      #   end
+      #
+      def results_with_summary(summary,&block)
+        if summary.kind_of?(Regexp)
+          results = results_with { |result| result.summary =~ summary }
+        else
+          results = results_with { |result| result.summary == summary }
+        end
+
+        results.each(&block) if block
+        return results
+      end
+
+      #
+      # Returns an Array containing the ranks of the results within the
+      # Page. If _block_ is given, each rank will be passed to the _block_.
+      #
+      #   page.ranks # => [...]
+      #
+      #   page.ranks do |rank|
+      #     puts ranks
+      #   end
+      #
+      def ranks(&block)
+        mapped = map { |result| result.rank }
+
+        mapped.each(&block) if block
+        return mapped
+      end
+
+      #
+      # Returns an Array containing the titles of the results within the
+      # Page. If _block_ is given, each title will be passed to the _block_.
+      #
+      #   page.titles # => [...]
+      #
+      #   page.titles do |title|
+      #     puts title
+      #   end
+      #
+      def titles(&block)
+        mapped = map { |result| result.title }
+
+        mapped.each(&block) if block
+        return mapped
+      end
+
+      #
+      # Returns an Array containing the URLs of the results within the
+      # Page. If _block_ is given, each URL will be passed to the _block_.
+      #
+      #   page.urls # => [...]
+      #
+      #   page.urls do |url|
+      #     puts url
+      #   end
+      #
+      def urls(&block)
+        mapped = map { |result| result.url }
+
+        mapped.each(&block) if block
+        return mapped
+      end
+
+      #
+      # Returns an Array containing the summaries of the results within the
+      # Page. If _block_ is given, each summary will be passed to the
+      # _block_.
+      #
+      #   page.summaries # => [...]
+      #
+      #   page.summaries do |summary|
+      #     puts summary
+      #   end
+      #
+      def summaries(&block)
+        mapped = map { |result| result.summaries }
+
+        mapped.each(&block) if block
+        return mapped
+      end
+
+      #
+      # Returns the ranks of the results that match the specified _block_.
+      #
+      #   page.ranks_of { |result result.title =~ /awesome/ }
+      #
+      def ranks_of(&block)
+        results_with(&block).ranks
+      end
+
+      #
+      # Returns the titles of the results that match the specified _block_.
+      #
+      #   page.titles_of { |result result.url.include?('www') }
+      #
+      def titles_of(&block)
+        results_with(&block).titles
+      end
+
+      #
+      # Returns the urls of the results that match the specified _block_.
+      #
+      #   page.urls_of { |result result.summary =~ /awesome pants/ }
+      #
+      def urls_of(&block)
+        results_with(&block).urls
+      end
+
+      #
+      # Returns the summaries of the results that match the specified
+      # _block_.
+      #
+      #   page.summaries_of { |result result.title =~ /what if/ }
+      #
+      def summaries_of(&block)
+        results_with(&block).summaries
+      end
+
+    end
+  end
+end

data/lib/gscraper/search/query.rb

@@ -1,4 +1,5 @@
 require 'gscraper/search/result'
+require 'gscraper/search/page'
 require 'gscraper/extensions/uri'
 require 'gscraper/licenses'
 require 'gscraper/gscraper'
@@ -80,7 +81,7 @@ module GScraper
       # Creates a new Query object from the given search options. If a
       # block is given, it will be passed the newly created query object.
       #
-      #   Query.new(:query => 'ruby', :with_words => 'rspec rails')
+      #   Query.new(:query => 'ruby', :with_words => 'sow rspec')
       #
       #   Query.new(:exact_phrase => 'fluent interfaces') do |q|
       #     q.within_past_week = true
@@ -324,12 +325,13 @@ module GScraper
       end
 
       #
-      # Returns an array of Result objects at the specified _page_index_.
-      # If _opts_ are given, they will be used in accessing the SEARCH_URL.
+      # Returns a Page object containing Result objects at the specified
+      # _page_index_. If _opts_ are given, they will be used in accessing
+      # the SEARCH_URL.
       #
       def page(page_index,opts={})
-        results = []
         doc = Hpricot(GScraper.open(page_url(page_index),opts))
+        new_page = Page.new
 
         doc.search('//div.g').each_with_index do |result,index|
           rank = page_index_offset(page_index) + (index + 1)
@@ -340,10 +342,10 @@ module GScraper
 
           # TODO: scrape Cached and Similar links
 
-          results << Result.new(rank,title,url,summary)
+          new_page << Result.new(rank,title,url,summary)
         end
 
-        return results
+        return new_page
       end
 
       #

data/lib/gscraper/search/search.rb

@@ -5,7 +5,7 @@ module GScraper
     #
     # Returns a new Query object with the given _opts_. See Query.new.
     #
-    #   Search.query(:query => 'ruby', :with_words => 'rspec rails')
+    #   Search.query(:query => 'ruby', :with_words => 'sow rspec')
     #
     #   Search.query(:exact_phrase => 'fluent interfaces') do |q|
     #     q.within_past_week = true

data/lib/gscraper/version.rb

@@ -1,3 +1,3 @@
 module GScraper
-  VERSION = '0.1.2'
+  VERSION = '0.1.3'
 end

metadata

@@ -3,7 +3,7 @@ rubygems_version: 0.9.4
 specification_version: 1
 name: gscraper
 version: !ruby/object:Gem::Version 
-  version: 0.1.2
+  version: 0.1.3
 date: 2007-12-21 00:00:00 -08:00
 summary: A ruby web-scraping interface to various Google Services
 require_paths: 
@@ -42,6 +42,7 @@ files:
 - lib/gscraper/extensions.rb
 - lib/gscraper/licenses.rb
 - lib/gscraper/search/result.rb
+- lib/gscraper/search/page.rb
 - lib/gscraper/search/query.rb
 - lib/gscraper/search/search.rb
 - lib/gscraper/search.rb