removing hpricot, updating history

GUIDE.txt

@@ -115,10 +115,8 @@ tell it what file name you want to upload:
   form.file_uploads.first.file_name = "somefile.jpg"
 
 == Scraping Data
-Mechanize uses hpricot[http://code.whytheluckystiff.net/hpricot/] to parse
+Mechanize uses nokogiri[http://nokogiri.rubyforge.org/] to parse
 html.  What does this mean for you?  You can treat a mechanize page like
-an hpricot object.  After you have used Mechanize to navigate to the page
-that you need to scrape, then scrape it using hpricot methods:
+an nokogiri object.  After you have used Mechanize to navigate to the page
+that you need to scrape, then scrape it using nokogiri methods:
   agent.get('http://someurl.com/').search(".//p[@class='posted']")
-For more information on this powerful scraper, take a look at
-HpricotBasics[http://code.whytheluckystiff.net/hpricot/wiki/HpricotBasics]

History.txt

@@ -1,5 +1,15 @@
 = Mechanize CHANGELOG
 
+=== 0.9.0
+
+* Deprecations
+  * WWW::Mechanize::List is gone!
+  * Mechanize uses Nokogiri as it's HTML parser but you may switch to
+    Hpricot by using WWW::Mechanize.html_parser = Hpricot
+
+* Bug Fixes:
+  * Nil check on page when base tag is used #23021
+
 === 0.8.5
 
 * Deprecations

Rakefile

@@ -9,7 +9,7 @@ HOE = Hoe.new('mechanize', WWW::Mechanize::VERSION) do |p|
   p.developer('Aaron Patterson','aaronp@rubyforge.org')
   p.developer('Mike Dalessio','mike.dalessio@gmail.com')
   p.summary         = "Mechanize provides automated web-browsing"
-  p.extra_deps      = [['hpricot', '>= 0.5.0']]
+  p.extra_deps      = [['nokogiri', '>= 1.0.7']]
 end
 
 desc "Update SSL Certificate"

lib/www/mechanize.rb

@@ -6,7 +6,7 @@
 require 'stringio'
 require 'digest/md5'
 require 'fileutils'
-require 'hpricot'
+require 'nokogiri'
 require 'forwardable'
 
 require 'www/mechanize/util'
@@ -18,7 +18,6 @@
 require 'www/mechanize/cookie'
 require 'www/mechanize/cookie_jar'
 require 'www/mechanize/history'
-require 'www/mechanize/list'
 require 'www/mechanize/form'
 require 'www/mechanize/pluggable_parsers'
 require 'www/mechanize/file_response'
@@ -87,7 +86,7 @@ class Mechanize
 
     alias :follow_redirect? :redirect_ok
 
-    @html_parser = Hpricot
+    @html_parser = Nokogiri::HTML
     class << self; attr_accessor :html_parser, :log end
 
     def initialize

lib/www/mechanize/form.rb

@@ -232,11 +232,11 @@ def #{singular}_with criteria = {}
 
       private
       def parse
-        @fields       = WWW::Mechanize::List.new
-        @buttons      = WWW::Mechanize::List.new
-        @file_uploads = WWW::Mechanize::List.new
-        @radiobuttons = WWW::Mechanize::List.new
-        @checkboxes   = WWW::Mechanize::List.new
+        @fields       = []
+        @buttons      = []
+        @file_uploads = []
+        @radiobuttons = []
+        @checkboxes   = []
 
         # Find all input tags
         form_node.search('input').each do |node|

lib/www/mechanize/form/multi_select_list.rb

@@ -14,7 +14,7 @@ class MultiSelectList < Field
 
         def initialize(name, node)
           value = []
-          @options = WWW::Mechanize::List.new
+          @options = []
 
           # parse
           node.search('option').each do |n|

lib/www/mechanize/page.rb

@@ -86,56 +86,47 @@ def #{type}_with(criteria)
       end
 
       def links
-        @links ||= WWW::Mechanize::List.new(
-          %w{ a area }.map do |tag|
-            search(tag).map do |node|
-              Link.new(node, @mech, self)
-            end
-          end.flatten
-        )
+        @links ||= %w{ a area }.map do |tag|
+          search(tag).map do |node|
+            Link.new(node, @mech, self)
+          end
+        end.flatten
       end
 
       def forms
-        @forms ||= WWW::Mechanize::List.new(
-          search('form').map do |html_form|
-            form = Form.new(html_form, @mech, self)
-            form.action ||= @uri.to_s
-            form
-          end
-        )
+        @forms ||= search('form').map do |html_form|
+          form = Form.new(html_form, @mech, self)
+          form.action ||= @uri.to_s
+          form
+        end
       end
 
       def meta
-        @meta ||= WWW::Mechanize::List.new(
-          search('meta').map do |node|
-            next unless node['http-equiv'] && node['content']
-            (equiv, content) = node['http-equiv'], node['content']
-            if equiv && equiv.downcase == 'refresh'
-              if content && content =~ /^\d+\s*;\s*url\s*=\s*'?([^\s']+)/i
-                node['href'] = $1
-                Meta.new(node, @mech, self)
-              end
+        @meta ||= search('meta').map do |node|
+          next unless node['http-equiv'] && node['content']
+          (equiv, content) = node['http-equiv'], node['content']
+          if equiv && equiv.downcase == 'refresh'
+            if content && content =~ /^\d+\s*;\s*url\s*=\s*'?([^\s']+)/i
+              node['href'] = $1
+              Meta.new(node, @mech, self)
             end
-          end.compact
-        )
+          end
+        end.compact
       end
 
       def bases
-        @bases ||= WWW::Mechanize::List.new(
+        @bases ||=
           search('base').map { |node| Base.new(node, @mech, self) }
-        )
       end
 
       def frames
-        @frames ||= WWW::Mechanize::List.new(
+        @frames ||=
           search('frame').map { |node| Frame.new(node, @mech, self) }
-        )
       end
 
       def iframes
-        @iframes ||= WWW::Mechanize::List.new(
+        @iframes ||= 
           search('iframe').map { |node| Frame.new(node, @mech, self) }
-        )
       end
     end
   end