0
@@ -1,101 +1,60 @@
0
 require 'rubygems'
0
-require 'rake'
0
-require 'rake/testtask'
0
-require 'rake/gempackagetask'
0
-require 'rake/rdoctask'
0
-require 'rake/contrib/sshpublisher'
0
-
0
-def announce(msg='')
0
-  STDERR.puts msg
0
-end
0
-
0
-PKG_BUILD = ENV['PKG_BUILD'] ? '.' + ENV['PKG_BUILD'] : ''
0
-PKG_NAME = 'mechanize'
0
-PKG_VERSION = '0.6.0' + PKG_BUILD
0
-PKG_FILES = FileList["{doc,lib,test}/**/*"].exclude("rdoc").to_a
0
-
0
-spec = Gem::Specification.new do |s|
0
-  s.name      = PKG_NAME
0
-  s.version   = PKG_VERSION
0
-  s.author    = "Aaron Patterson"
0
-  s.email     = "aaronp@rubyforge.org"
0
-  s.homepage  = "#{PKG_NAME}.rubyforge.org"
0
-  s.platform  = Gem::Platform::RUBY
0
-  s.summary   = "Mechanize provides automated web-browsing"
0
-  s.files     = Dir.glob("{bin,test,lib,doc}/**/*").delete_if {|item| item.include?(".svn") }
0
-  s.require_path  = "lib"
0
-  s.has_rdoc      = true
0
-  s.extra_rdoc_files = ["README", "EXAMPLES", "CHANGELOG", "LICENSE", "NOTES",
0
-                        "GUIDE"]
0
-  s.rdoc_options << "--main" << 'README' << "--title" << "'WWW::Mechanize RDoc'"
0
-  s.rubyforge_project = PKG_NAME
0
-  s.add_dependency('hpricot') 
0
-end
0
-
0
-Rake::GemPackageTask.new(spec) do |p|
0
-  p.gem_spec = spec
0
-  p.need_tar = true
0
-  p.need_zip = true
0
-end
0
-
0
-Rake::RDocTask.new do |p|
0
-  p.main = "README"
0
-  p.rdoc_dir = "doc"
0
-  p.rdoc_files.include("README", "CHANGELOG", "LICENSE", "EXAMPLES", "NOTES",
0
-                       "GUIDE", "lib/**/*.rb")
0
-  p.options << "--main" << 'README' << "--title" << "WWW::Mechanize RDoc"
0
-end
0
-
0
-desc "Publish the API documentation"
0
-task :pubrdoc => [ :rdoc ] do
0
-  Rake::SshDirPublisher.new(
0
-    "#{ENV['USER']}@rubyforge.org",
0
-    "/var/www/gforge-projects/#{PKG_NAME}/",
0
-    "doc" ).upload
0
-end
0
-
0
-task :update_version do
0
-  announce "Updating Mechanize Version to #{PKG_VERSION}"
0
-  File.open("lib/mechanize/mech_version.rb", "w") do |f|
0
-    f.puts "module WWW"
0
-    f.puts "  class Mechanize"
0
-    f.puts "    Version = '#{PKG_VERSION}'"
0
-    f.puts "  end"
0
-    f.puts "end"
0
+require 'hoe'
0
+
0
+$LOAD_PATH.unshift File.join(File.dirname(__FILE__), "lib")
0
+require 'mechanize'
0
+
0
+class MechHoe < Hoe
0
+  def define_tasks
0
+    super
0
+
0
+    desc "Tag code"
0
+    task :tag do |p|
0
+      abort "Must supply VERSION=x.y.z" unless ENV['VERSION']
0
+      v = ENV['VERSION'].gsub(/\./, '_')
0
+
0
+      rf = RubyForge.new
0
+      user = rf.userconfig['username']
0
+
0
+      baseurl = "svn+ssh://#{user}@rubyforge.org//var/svn/#{name}"
0
+      sh "svn cp -m 'tagged REL-#{v}' . #{ baseurl }/tags/REL-#{ v }"
0
+    end
0
+
0
+    desc "Branch code"
0
+    Rake::Task.define_task("branch") do |p|
0
+      abort "Must supply VERSION=x.y.z" unless ENV['VERSION']
0
+      v = ENV['VERSION'].split(/\./)[0..1].join('_')
0
+
0
+      rf = RubyForge.new
0
+      user = rf.userconfig['username']
0
+
0
+      baseurl = "svn+ssh://#{user}@rubyforge.org/var/svn/#{name}"
0
+      sh "svn cp -m'branched #{v}' #{baseurl}/trunk #{baseurl}/branches/RB-#{v}"
0
+    end
0
+    
0
+    desc "Update SSL Certificate"
0
+    Rake::Task.define_task('ssl_cert') do |p|
0
+      sh "openssl genrsa -des3 -out server.key 1024"
0
+      sh "openssl req -new -key server.key -out server.csr"
0
+      sh "cp server.key server.key.org"
0
+      sh "openssl rsa -in server.key.org -out server.key"
0
+      sh "openssl x509 -req -days 365 -in server.csr -signkey server.key -out server.crt"
0
+      sh "cp server.key server.pem"
0
+      sh "mv server.key server.csr server.crt server.pem test/data/"
0
+      sh "rm server.key.org"
0
+    end
0
   end
0
-  sh 'svn commit -m"updating version" lib/mechanize/mech_version.rb'
0
 end
0
 
0
-desc "Create a new release"
0
-task :release => [ :clobber, :update_version, :package, :tag ] do
0
-  announce 
0
-  announce "**************************************************************"
0
-  announce "* Release #{PKG_VERSION} Complete."
0
-  announce "* Packages ready to upload."
0
-  announce "**************************************************************"
0
-  announce 
0
+MechHoe.new('mechanize', WWW::Mechanize::VERSION) do |p|
0
+  p.rubyforge_name  = 'mechanize'
0
+  p.author          = 'Aaron Patterson'
0
+  p.email           = 'aaronp@rubyforge.org'
0
+  p.summary         = "Mechanize provides automated web-browsing"
0
+  p.description     = p.paragraphs_of('README.txt', 3).join("\n\n")
0
+  p.url             = p.paragraphs_of('README.txt', 1).first.strip
0
+  p.changes         = p.paragraphs_of('CHANGELOG.txt', 0..2).join("\n\n")
0
+  p.extra_deps      = [['hpricot', '>= 0.5.0']]
0
 end
0
 
0
-desc "Tag code"
0
-Rake::Task.define_task("tag") do |p|
0
-  baseurl = "svn+ssh://#{ENV['USER']}@rubyforge.org//var/svn/#{PKG_NAME}"
0
-  sh "svn cp -m 'tagged #{ PKG_VERSION }' . #{ baseurl }/tags/REL-#{ PKG_VERSION }"
0
-end
0
-
0
-desc "Branch code"
0
-Rake::Task.define_task("branch") do |p|
0
-  baseurl = "svn+ssh://#{ENV['USER']}@rubyforge.org/var/svn/#{PKG_NAME}"
0
-  sh "svn cp -m 'branched #{ PKG_VERSION }' #{baseurl}/trunk #{ baseurl }/branches/RB-#{ PKG_VERSION }"
0
-end
0
 
0
-desc "Update SSL Certificate"
0
-Rake::Task.define_task('ssl_cert') do |p|
0
-  sh "openssl genrsa -des3 -out server.key 1024"
0
-  sh "openssl req -new -key server.key -out server.csr"
0
-  sh "cp server.key server.key.org"
0
-  sh "openssl rsa -in server.key.org -out server.key"
0
-  sh "openssl x509 -req -days 365 -in server.csr -signkey server.key -out server.crt"
0
-  sh "cp server.key server.pem"
0
-  sh "mv server.key server.csr server.crt server.pem test/data/"
0
-  sh "rm server.key.org"
0
-end

0
@@ -11,20 +11,31 @@
0
 unless RUBY_VERSION > "1.8.2"
0
   $LOAD_PATH.unshift File.join(File.dirname(__FILE__), "mechanize", "net-overrides")
0
 end
0
+
0
 require 'net/http'
0
 require 'net/https'
0
 
0
+# Monkey patch for ruby 1.8.4
0
+unless RUBY_VERSION > "1.8.4"
0
+module Net # :nodoc:
0
+  class HTTPResponse # :nodoc:
0
+    CODE_TO_OBJ['500'] = HTTPInternalServerError
0
+  end
0
+end
0
+end
0
+
0
 require 'uri'
0
 require 'webrick/httputils'
0
 require 'zlib'
0
 require 'stringio'
0
-require 'mechanize/hpricot'
0
-require 'mechanize/mech_version'
0
+require 'digest/md5'
0
+require 'mechanize/monkey_patch'
0
 require 'mechanize/cookie'
0
 require 'mechanize/errors'
0
 require 'mechanize/pluggable_parsers'
0
 require 'mechanize/form'
0
 require 'mechanize/form_elements'
0
+require 'mechanize/history'
0
 require 'mechanize/list'
0
 require 'mechanize/page'
0
 require 'mechanize/page_elements'
0
@@ -50,20 +61,27 @@ module WWW
0
 #  search_results = agent.submit(search_form)
0
 #  puts search_results.body
0
 class Mechanize
0
+  ##
0
+  # The version of Mechanize you are using.
0
+ 
0
+  VERSION = '0.6.11'
0
+
0
+  ##
0
+  # User Agent aliases
0
   AGENT_ALIASES = {
0
     'Windows IE 6' => 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)',
0
+    'Windows IE 7' => 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
0
     'Windows Mozilla' => 'Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.4b) Gecko/20030516 Mozilla Firebird/0.6',
0
     'Mac Safari' => 'Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en) AppleWebKit/418 (KHTML, like Gecko) Safari/417.9.3',
0
     'Mac FireFox' => 'Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.8.0.3) Gecko/20060426 Firefox/1.5.0.3',
0
     'Mac Mozilla' => 'Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.4a) Gecko/20030401',
0
     'Linux Mozilla' => 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.4) Gecko/20030624',
0
     'Linux Konqueror' => 'Mozilla/5.0 (compatible; Konqueror/3; Linux)',
0
-    'Mechanize' => "WWW-Mechanize/#{Version} (http://rubyforge.org/projects/mechanize/)"
0
+    'Mechanize' => "WWW-Mechanize/#{VERSION} (http://rubyforge.org/projects/mechanize/)"
0
   }
0
 
0
   attr_accessor :cookie_jar
0
   attr_accessor :log
0
-  attr_accessor :max_history
0
   attr_accessor :open_timeout, :read_timeout
0
   attr_accessor :user_agent
0
   attr_accessor :watch_for_set
0
@@ -71,15 +89,24 @@ class Mechanize
0
   attr_accessor :key
0
   attr_accessor :cert
0
   attr_accessor :pass
0
+  attr_accessor :redirect_ok
0
+  attr_accessor :keep_alive_time
0
+  attr_accessor :keep_alive
0
+  attr_accessor :conditional_requests
0
+  attr_accessor :follow_meta_refresh
0
 
0
   attr_reader :history
0
   attr_reader :pluggable_parser
0
 
0
+  alias :follow_redirect? :redirect_ok
0
+
0
+  @@nonce_count = -1
0
+  CNONCE = Digest::MD5.hexdigest("%x" % (Time.now.to_i + rand(65535)))
0
+
0
   def initialize
0
     # attr_accessors
0
-    @cookie_jar = CookieJar.new
0
+    @cookie_jar     = CookieJar.new
0
     @log            = nil
0
-    @max_history    = nil
0
     @open_timeout   = nil
0
     @read_timeout   = nil
0
     @user_agent     = AGENT_ALIASES['Mechanize']
0
@@ -88,14 +115,17 @@ class Mechanize
0
     @cert           = nil # OpenSSL Certificate
0
     @key            = nil # OpenSSL Private Key
0
     @pass           = nil # OpenSSL Password
0
+    @redirect_ok    = true # Should we follow redirects?
0
     
0
     # attr_readers
0
-    @history        = []
0
+    @history        = WWW::Mechanize::History.new
0
     @pluggable_parser = PluggableParser.new
0
 
0
-    # Basic Auth variables
0
-    @user           = nil # Basic Auth User
0
-    @password       = nil # Basic Auth Password
0
+    # Auth variables
0
+    @user           = nil # Auth User
0
+    @password       = nil # Auth Password
0
+    @digest         = nil # DigestAuth Digest
0
+    @auth_hash      = {}  # Keep track of urls for sending auth
0
 
0
     # Proxy settings
0
     @proxy_addr     = nil
0
@@ -103,9 +133,21 @@ class Mechanize
0
     @proxy_port     = nil
0
     @proxy_user     = nil
0
 
0
+    @conditional_requests = true
0
+
0
+    @follow_meta_refresh  = false
0
+
0
+    # Connection Cache & Keep alive
0
+    @connection_cache = {}
0
+    @keep_alive_time  = 300
0
+    @keep_alive       = true
0
+
0
     yield self if block_given?
0
   end
0
 
0
+  def max_history=(length); @history.max_size = length; end
0
+  def max_history; @history.max_size; end
0
+
0
   # Sets the proxy address, port, user, and password
0
   def set_proxy(addr, port, user = nil, pass = nil)
0
     @proxy_addr, @proxy_port, @proxy_user, @proxy_pass = addr, port, user, pass
0
@@ -124,18 +166,23 @@ class Mechanize
0
 
0
   # Sets the user and password to be used for basic authentication.
0
   def basic_auth(user, password)
0
-    @user = user
0
-    @password = password
0
+    auth(user, password)
0
+  end
0
+
0
+  def auth(user, password)
0
+    @user       = user
0
+    @password   = password
0
   end
0
 
0
   # Fetches the URL passed in and returns a page.
0
-  def get(url)
0
-    cur_page = current_page || Page.new( nil, {'content-type'=>'text/html'})
0
+  def get(url, referer=nil, &block)
0
+    cur_page = referer || current_page ||
0
+                    Page.new( nil, {'content-type'=>'text/html'})
0
 
0
     # fetch the page
0
     abs_uri = to_absolute_uri(url, cur_page)
0
     request = fetch_request(abs_uri)
0
-    page = fetch_page(abs_uri, request, cur_page)
0
+    page = fetch_page(abs_uri, request, cur_page, &block)
0
     add_to_history(page)
0
     page
0
   end
0
@@ -149,10 +196,17 @@ class Mechanize
0
   # Clicks the WWW::Mechanize::Link object passed in and returns the
0
   # page fetched.
0
   def click(link)
0
+    referer =
0
+      begin
0
+        link.page
0
+      rescue
0
+        nil
0
+      end
0
     uri = to_absolute_uri(
0
-      link.attributes['href'] || link.attributes['src'] || link.href
0
+      link.attributes['href'] || link.attributes['src'] || link.href,
0
+      referer || current_page()
0
     )
0
-    get(uri)
0
+    get(uri, referer)
0
   end
0
 
0
   # Equivalent to the browser back button.  Returns the most recent page
0
@@ -169,9 +223,8 @@ class Mechanize
0
   #  agent.post('http://example.com/', [ ["foo", "bar"] ])
0
   def post(url, query={})
0
     node = Hpricot::Elem.new(Hpricot::STag.new('form'))
0
-    node.attributes = {}
0
-    node.attributes['method'] = 'POST'
0
-    node.attributes['enctype'] = 'application/x-www-form-urlencoded'
0
+    node['method'] = 'POST'
0
+    node['enctype'] = 'application/x-www-form-urlencoded'
0
 
0
     form = Form.new(node)
0
     query.each { |k,v|
0
@@ -188,17 +241,12 @@ class Mechanize
0
   #  agent.submit(page.forms.first, page.forms.first.buttons.first)
0
   def submit(form, button=nil)
0
     form.add_button_to_query(button) if button
0
-    uri = to_absolute_uri(form.action)
0
+    uri = to_absolute_uri(form.action, form.page)
0
     case form.method.upcase
0
     when 'POST'
0
       post_form(uri, form) 
0
     when 'GET'
0
-      if uri.query.nil?
0
-        uri.query = WWW::Mechanize.build_query_string(form.build_query)
0
-      else
0
-        uri.query = uri.query + "&" +
0
-          WWW::Mechanize.build_query_string(form.build_query)
0
-      end
0
+      uri.query = WWW::Mechanize.build_query_string(form.build_query)
0
       get(uri)
0
     else
0
       raise "unsupported method: #{form.method.upcase}"
0
@@ -212,9 +260,15 @@ class Mechanize
0
 
0
   # Returns whether or not a url has been visited
0
   def visited?(url)
0
-    url = url.uri if url.respond_to? :uri
0
-    uri = to_absolute_uri(url).to_s
0
-    ! @history.find { |h| h.uri.to_s == uri }.nil?
0
+    ! visited_page(url).nil?
0
+  end
0
+
0
+  # Returns a visited page for the url passed in, otherwise nil
0
+  def visited_page(url)
0
+    if url.respond_to? :href
0
+      url = url.href
0
+    end
0
+    @history.visited_page(to_absolute_uri(url))
0
   end
0
 
0
   # Runs given block, then resets the page history as it was before. self is
0
@@ -230,22 +284,136 @@ class Mechanize
0
 
0
   alias :page :current_page
0
 
0
+  protected
0
+  def set_headers(uri, request, cur_page)
0
+    if @keep_alive
0
+      request.add_field('Connection', 'keep-alive')
0
+      request.add_field('Keep-Alive', keep_alive_time.to_s)
0
+    else
0
+      request.add_field('Connection', 'close')
0
+    end
0
+    request.add_field('Accept-Encoding', 'gzip,identity')
0
+    request.add_field('Accept-Language', 'en-us,en;q0.5')
0
+    request.add_field('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.7')
0
+
0
+    unless @cookie_jar.empty?(uri)
0
+      cookies = @cookie_jar.cookies(uri)
0
+      cookie = cookies.length > 0 ? cookies.join("; ") : nil
0
+      if log
0
+        cookies.each do |c|
0
+          log.debug("using cookie: #{c}")
0
+        end
0
+      end
0
+      request.add_field('Cookie', cookie)
0
+    end
0
+
0
+    # Add Referer header to request
0
+    unless cur_page.uri.nil?
0
+      request.add_field('Referer', cur_page.uri.to_s)
0
+    end
0
+
0
+    # Add User-Agent header to request
0
+    request.add_field('User-Agent', @user_agent) if @user_agent 
0
+
0
+    # Add If-Modified-Since if page is in history
0
+    if @conditional_requests
0
+      if( (page = visited_page(uri)) && page.response['Last-Modified'] )
0
+        request.add_field('If-Modified-Since', page.response['Last-Modified'])
0
+      end
0
+    end
0
+
0
+    if( @auth_hash[uri.host] )
0
+      case @auth_hash[uri.host]
0
+      when :basic
0
+        request.basic_auth(@user, @password)
0
+      when :digest
0
+        @digest_response ||= nil
0
+        @digest_response = self.gen_auth_header(uri,request,@digest) if @digest
0
+        request.add_field('Authorization', @digest_response) if @digest_response
0
+      end
0
+    end
0
+
0
+    request
0
+  end
0
+
0
+  def gen_auth_header(uri, request, auth_header, is_IIS = false)
0
+    @@nonce_count += 1
0
+
0
+    user = @digest_user
0
+    password = @digest_password
0
+
0
+    auth_header =~ /^(\w+) (.*)/
0
+
0
+    params = {}
0
+    $2.gsub(/(\w+)="(.*?)"/) { params[$1] = $2 }
0
+
0
+    a_1 = "#{@user}:#{params['realm']}:#{@password}"
0
+    a_2 = "#{request.method}:#{uri.path}"
0
+    request_digest = ''
0
+    request_digest << Digest::MD5.hexdigest(a_1)
0
+    request_digest << ':' << params['nonce']
0
+    request_digest << ':' << ('%08x' % @@nonce_count)
0
+    request_digest << ':' << CNONCE