mechanize 0.4.5 → 0.4.6

data/CHANGELOG

@@ -1,3 +1,14 @@
+== 0.4.6
+
+* Added support for proxies
+* Added a uri field to WWW::Link
+* Added a error class WWW::Mechanize::ContentTypeError
+* Added image alt text to link text
+* Added an visited? method to WWW::Mechanize
+* Added Array#value= which will set the first value to the argument.  That
+  allows syntax as such:    form.fields.name('q').value = 'xyz'
+  Before it was like this:  form.fields.name('q').first.value = 'xyz'
+
 == 0.4.5
 
 * Added support for multiple values of the same name

data/EXAMPLES

@@ -96,3 +96,12 @@ the original filter.
   page = agent.get('http://google.com/')
   page.links.each { |l| puts l.text }
 
+== Using a proxy
+
+  require 'rubygems'
+  require 'mechanize'
+  
+  agent = WWW::Mechanize.new
+  agent.set_proxy('localhost', '8000')
+  page = agent.get(ARGV[0])
+  puts page.body

data/NOTES

@@ -1,5 +1,34 @@
 = Mechanize Release Notes
 
+== 0.4.6
+
+The 0.4.6 release comes with proxy support which can be enabled by calling
+the set_proxy method on your WWW::Mechanize object.  Once you have set your
+proxy settings, all mechanize requests will go through the proxy.
+
+A new "visited?" method has been added to WWW::Mechanize so that you can see
+if any particular URL is in your history.
+
+Image alt text support has been added to links.  If a link contains an image
+with no text, the alt text of the image will be used.  For example:
+
+  <a href="foo.html><img src="foo.gif" alt="Foo Image"></a>
+
+This link will contain the text "Foo Image", and can be found like this:
+
+  link = page.links.text('Foo Image')
+
+Lists of things have been updated so that you can set a value without
+specifying the position in the array.  It will just assume that you want to
+set the value on the first element.  For example, the following two statements
+are equivalent:
+
+  form.fields.name('q').first.value = 'xyz'  # Old syntax
+  form.fields.name('q').value = 'xyz'        # New syntax
+
+This new syntax comes with a note of caution; make sure you know you want to
+set only the first value.  There could be multiple fields with the name 'q'.
+
 == 0.4.5
 
 This release comes with a new filtering system.  You can now manipulate the

data/lib/mechanize.rb

@@ -20,6 +20,7 @@ require 'webrick'
 require 'date'
 require 'web/htmltools/xmltree'   # narf
 require 'mechanize/module'
+require 'mechanize/list'
 require 'mechanize/parsing'
 require 'mechanize/cookie'
 require 'mechanize/form'
@@ -51,8 +52,8 @@ end
 #  agent = WWW::Mechanize.new { |a| a.log = Logger.new("mech.log") }
 #  agent.user_agent_alias = 'Mac Safari'
 #  page = agent.get("http://www.google.com/")
-#  search_form = page.forms.find { |f| f.name == "f" }
-#  search_form.fields.find { |f| f.name == "q" }.value = "Hello"
+#  search_form = page.forms.name("f").first
+#  search_form.fields.name("q").value = "Hello"
 #  search_results = agent.submit(search_form)
 #  puts search_results.body
 class Mechanize
@@ -60,7 +61,8 @@ class Mechanize
   AGENT_ALIASES = {
     'Windows IE 6' => 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)',
     'Windows Mozilla' => 'Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.4b) Gecko/20030516 Mozilla Firebird/0.6',
-    'Mac Safari' => 'Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en-us) AppleWebKit/85 (KHTML, like Gecko) Safari/85',
+    'Mac Safari' => 'Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en) AppleWebKit/418 (KHTML, like Gecko) Safari/417.9.3',
+    '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',
     'Mac Mozilla' => 'Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.4a) Gecko/20030401',
     'Linux Mozilla' => 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.4) Gecko/20030624',
     'Linux Konqueror' => 'Mozilla/5.0 (compatible; Konqueror/3; Linux)',
@@ -87,13 +89,25 @@ class Mechanize
     @body_filter    = lambda { |body| body }
     @cookie_jar = CookieJar.new
     @log = Logger.new(nil)
+    @proxy_addr     = nil
+    @proxy_port     = nil
+    @proxy_user     = nil
+    @proxy_pass     = nil
     yield self if block_given?
   end
 
+  # Sets the proxy address, port, user, and password
+  def set_proxy(addr, port, user = nil, pass = nil)
+    @proxy_addr, @proxy_port, @proxy_user, @proxy_pass = addr, port, user, pass
+  end
+
+  # Set the user agent for the Mechanize object.
+  # See AGENT_ALIASES
   def user_agent_alias=(al)
     self.user_agent = AGENT_ALIASES[al] || raise("unknown agent alias")
   end
 
+  # Returns a list of cookies stored in the cookie jar.
   def cookies
     cookies = []
     @cookie_jar.jar.each_key do |domain|
@@ -104,6 +118,7 @@ class Mechanize
     cookies
   end
 
+  # Sets the user and password to be used for basic authentication.
   def basic_auth(user, password)
     @user = user
     @password = password
@@ -114,6 +129,7 @@ class Mechanize
     basic_auth(user, password)
   end
 
+  # Fetches the URL passed in.
   def get(url)
     cur_page = current_page() || Page.new
 
@@ -123,6 +139,7 @@ class Mechanize
     page
   end
 
+  # Posts to the given URL wht the query parameters passed in.
   def post(url, query={})
     cur_page = current_page() || Page.new
 
@@ -141,11 +158,14 @@ class Mechanize
     page
   end
 
+  # Clicks the WWW::Link object passed in.
   def click(link)
     uri = to_absolute_uri(link.href)
     get(uri)
   end
 
+  # Equivalent to the browser back button.  Returns the most recent page
+  # visited.
   def back
     @history.pop
   end
@@ -154,25 +174,36 @@ class Mechanize
     form.add_button_to_query(button) if button
     query = form.build_query
 
-    uri = to_absolute_uri(URI::escape(form.action))
+    uri = to_absolute_uri(form.action)
     case form.method.upcase
     when 'POST'
       post_form(uri, form) 
     when 'GET'
       if uri.query.nil?
-        get(uri.to_s + "?" + WWW::Mechanize.build_query_string(query))
+        uri.query = WWW::Mechanize.build_query_string(query)
       else
-        get(uri.to_s + "&" + WWW::Mechanize.build_query_string(query))
+        uri.query = uri.query + "&" + WWW::Mechanize.build_query_string(query)
       end
+      get(uri)
     else
       raise 'unsupported method'
     end
   end
 
+  # Returns the current page loaded by Mechanize
   def current_page
     @history.last
   end
 
+  # Returns whether or not a url has been visited
+  def visited?(url)
+    if url.is_a?(WWW::Link)
+      url = url.uri
+    end
+    uri = to_absolute_uri(url)
+    ! @history.find { |h| h.uri.to_s == uri.to_s }.nil?
+  end
+
   alias page current_page
 
   private
@@ -181,13 +212,13 @@ class Mechanize
     if url.is_a?(URI)
       uri = url
     else
-      uri = URI.parse(url)
+      uri = URI.parse(url.gsub(/\s/, '%20'))
     end
 
     # construct an absolute uri
     if uri.relative?
-      if cur_page
-        uri = cur_page.uri + url
+      if cur_page.uri
+        uri = cur_page.uri + (url.is_a?(URI) ? url : URI::escape(url))
       else
         raise 'no history. please specify an absolute URL'
       end
@@ -222,7 +253,13 @@ class Mechanize
 
     page = Page.new(uri)
 
-    http = Net::HTTP.new(uri.host, uri.port)
+    http = Net::HTTP.new( uri.host,
+                          uri.port,
+                          @proxy_addr,
+                          @proxy_port,
+                          @proxy_user,
+                          @proxy_pass
+                        )
 
     if uri.scheme == 'https'
       http.use_ssl = true
@@ -306,7 +343,7 @@ class Mechanize
           return page
         when "301", "302"
           log.info("follow redirect to: #{ response['Location'] }")
-          return fetch_page(to_absolute_uri(response['Location'], page), :get, page)
+          return fetch_page(to_absolute_uri(URI.parse(response['Location'].gsub(/ /, '%20')), page), :get, page)
         else
           raise ResponseCodeError.new(page.code), "Unhandled response", caller
         end
@@ -333,6 +370,14 @@ class Mechanize
     end
   end
 
+  class ContentTypeError < RuntimeError
+    attr_reader :content_type
+  
+    def initialize(content_type)
+      @content_type = content_type
+    end
+  end
+
 end
 
 end # module WWW

data/lib/mechanize/cookie.rb

@@ -1,6 +1,7 @@
 require 'date'
 
 module WWW
+  # This class is used to represent an HTTP Cookie.
   class Cookie
     attr_reader :name, :value, :path, :domain, :expires, :secure
     def initialize(cookie)
@@ -21,7 +22,7 @@ module WWW
         cookie_text.split(/; ?/).each do |data|
           name, value = data.split('=', 2)
           next unless name
-          cookie[name] = value
+          cookie[name.strip] = value
         end
   
         cookie_values[:path] = cookie.delete(
@@ -116,12 +117,15 @@ module WWW
     end
   end
 
+  # This class is used to manage the Cookies that have been returned from
+  # any particular website.
   class CookieJar
     attr_accessor :jar
     def initialize
       @jar = {}
     end
   
+    # Add a cookie to the Jar.
     def add(cookie)
       unless @jar.has_key?(cookie.domain)
         @jar[cookie.domain] = Hash.new
@@ -130,6 +134,7 @@ module WWW
       @jar[cookie.domain][cookie.name] = cookie
     end
   
+    # Fetch the cookies that should be used for the URI object passed in.
     def cookies(url)
       cookies = []
       @jar.each_key do |domain|

data/lib/mechanize/form.rb

@@ -110,11 +110,11 @@ module WWW
     end
   
     def parse
-      @fields = []
-      @buttons = []
-      @file_uploads = []
-      @radiobuttons = []
-      @checkboxes = []
+      @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
   
       @elements_node.each_recursive {|node|
         case node.name.downcase
@@ -140,6 +140,19 @@ module WWW
         end
       }
     end
+
+    def inspect
+      string = "Form: ['#{@name}' -> #{@action}]\n"
+      string << "[radiobuttons]\n"
+      @radiobuttons.each { |f| string << f.inspect }
+      string << "[checkboxes]\n"
+      @checkboxes.each { |f| string << f.inspect }
+      string << "[fields]\n"
+      @fields.each { |f| string << f.inspect }
+      string << "[buttons]\n"
+      @buttons.each { |f| string << f.inspect }
+      string
+    end
   
     private
     def rand_string(len = 10)

data/lib/mechanize/form_elements.rb

@@ -1,4 +1,10 @@
 module WWW
+  # This class represents a field in a form.  It handles the following input
+  # tags found in a form:
+  # text, password, hidden, int, textarea
+  #
+  # To set the value of a field, just use the value method:
+  # field.value = "foo"
   class Field
     attr_accessor :name, :value
   
@@ -19,8 +25,17 @@ module WWW
       }
       return fields
     end
+
+    def inspect
+      "#{name} = #{@value}\n"
+    end
   end
   
+  # This class represents a file upload field found in a form.  To use this
+  # class, set WWW::FileUpload#file_data= to the data of the file you want
+  # to upload and WWW::FileUpload#mime_type= to the appropriate mime type
+  # of the file.
+  # See the example in EXAMPLES[link://files/EXAMPLES.html]
   class FileUpload
     # value is the file-name, not the file-content
     attr_accessor :name
@@ -33,6 +48,7 @@ module WWW
     end
   end
   
+  # This class represents a Submit button in a form.
   class Button
     attr_accessor :name, :value
   
@@ -55,8 +71,14 @@ module WWW
       }
       return buttons
     end
+
+    def inspect
+      "#{name} = #{@value}\n"
+    end
   end 
   
+  # This class represents an image button in a form.  Use the x and y methods
+  # to set the x and y positions for where the mouse "clicked".
   class ImageButton < Button
     attr_accessor :x, :y
     
@@ -69,29 +91,47 @@ module WWW
     end
   end
   
+  # This class represents a radio button found in a Form.  To activate the
+  # RadioButton in the Form, set the checked method to true.
   class RadioButton
     attr_accessor :name, :value, :checked
   
     def initialize(name, value, checked)
       @name, @value, @checked = name, value, checked
     end
+
+    def inspect
+      "#{name} = #{@value}\n"
+    end
   end
   
+  # This class represents a check box found in a Form.  To activate the
+  # CheckBox in the Form, set the checked method to true.
   class CheckBox
     attr_accessor :name, :value, :checked
   
     def initialize(name, value, checked)
       @name, @value, @checked = name, value, checked
     end
+
+    def inspect
+      "#{name} = #{@value}\n"
+    end
   end
   
+  # This class represents a select list or drop down box in a Form.  Set the
+  # value for the list by calling SelectList#value=.  SelectList contains a
+  # list of Option that were found.  After finding the correct option, set
+  # the select lists value to the option value:
+  #  selectlist.value = selectlist.options.first.value
   class SelectList
-    attr_accessor :name, :value, :options
+    attr_accessor :name, :options
+    attr_reader :value
   
     def initialize(name, node)
       @name = name
       @value = nil
-      @options = []
+      @options = WWW::Mechanize::List.new
   
       # parse
       node.each_recursive {|n|
@@ -103,8 +143,18 @@ module WWW
       }
       @value = @options.first.value if (@value == nil && @options.first)
     end
+
+    def value=(value)
+      @value = value.to_s
+    end
+
+    def inspect
+      "#{name} = #{@value}\n"
+    end
   end
 
+  # This class contains option an option found within SelectList.  A
+  # SelectList can have many Option classes associated with it.
   class Option
     attr_reader :value, :selected, :text
 

data/lib/mechanize/list.rb

@@ -0,0 +1,23 @@
+module WWW
+  class Mechanize
+    class List < Array
+      def with
+        self
+      end
+
+      def value=(arg)
+        first().value=(arg)
+      end
+
+      alias :and :with
+
+      def method_missing(meth_sym, arg)
+        if arg.class == Regexp
+          WWW::Mechanize::List.new(find_all { |e| e.send(meth_sym) =~ arg })
+        else
+          WWW::Mechanize::List.new(find_all { |e| e.send(meth_sym) == arg })
+        end
+      end
+    end
+  end
+end

data/lib/mechanize/mech_version.rb

@@ -1,5 +1,5 @@
 # DO NOT EDIT
 # This file is auto-generated by build scripts
 module WWW
-  MechVersion = '0.4.5'
+  MechVersion = '0.4.6'
 end

data/lib/mechanize/module.rb

@@ -19,19 +19,3 @@ class Module
   end
 end
 
-class Array
-  def with
-    self
-  end
-
-  alias :and :with
-
-  def method_missing(meth_sym, arg)
-    if arg.class == Regexp
-      find_all { |e| e.send(meth_sym) =~ arg }
-    else
-      find_all { |e| e.send(meth_sym) == arg }
-    end
-  end
-end
-

data/lib/mechanize/page.rb

@@ -44,29 +44,38 @@ module WWW
       @body_filter  = lambda { |body| body }
     end
   
+    # Set the body filter for the page.  The body should be a Proc object that
+    # returns what the body should be set to.  For example, replace all
+    # occurrences of 'foo' with 'bar':
+    #  page.body_filter = lambda { |body| body.gsub(/foo/, bar) }
     def body_filter=(filter)
       @body_filter = filter
       parse_html()
     end
 
+    # Get the response header
     def header
       @response.header
     end
   
+    # Get the content type
     def content_type
       @response['Content-Type']
     end
   
+    # Get a list of Form associated with this page.
     def forms(*args)
       parse_html() unless @forms
       find_forms(*args)
     end
   
+    # Get a list of Link associated with this page.
     def links(*args)
       parse_html() unless @links
       find_links(*args)
     end
   
+    # Get the root XML parse tree for this page.
     def root
       parse_html() unless @root
       @root
@@ -80,25 +89,43 @@ module WWW
       find_watches(*args)
     end
   
+    # Get a list of Meta links, usually used for refreshing the page.
     def meta(*args)
       parse_html() unless @meta 
       find_meta(*args)
     end
 
+    # Get a list of Frame from the page
     def frames(*args)
       parse_html() unless @frames
       find_frames(*args)
     end
 
+    # Get a list of IFrame from the page
     def iframes(*args)
       parse_html() unless @iframes
       find_iframes(*args)
     end
   
+    def inspect
+      string = "[meta]\n"
+      meta.each { |l| string << l.inspect }
+      string << "[frames]\n"
+      frames.each { |l| string << l.inspect }
+      string << "[iframes]\n"
+      iframes.each { |l| string << l.inspect }
+      string << "[links]\n"
+      links.each { |l| string << l.inspect }
+      string << "[forms]\n"
+      forms.each { |l| string << l.inspect }
+      string
+    end
+
     private
   
     def parse_html
-      raise "no html" unless content_type() =~ /^text\/html/ 
+      raise Mechanize::ContentTypeError.new(content_type()) unless
+        content_type() =~ /^text\/html/ 
   
       # construct parser and feed with HTML
       parser = HTMLTree::XMLParser.new
@@ -120,11 +147,11 @@ module WWW
   
       @root = parser.document
   
-      @forms    = []
-      @links    = []
-      @meta     = []
-      @frames   = []
-      @iframes  = []
+      @forms    = WWW::Mechanize::List.new
+      @links    = WWW::Mechanize::List.new
+      @meta     = WWW::Mechanize::List.new
+      @frames   = WWW::Mechanize::List.new
+      @iframes  = WWW::Mechanize::List.new
       @watches  = {}
   
       @root.each_recursive {|node|

data/lib/mechanize/page_elements.rb

@@ -3,11 +3,30 @@ module WWW
     attr_reader :node
     attr_reader :href
     attr_reader :text
+    alias :to_s :text
   
     def initialize(node)
       @node = node
       @href = node.attributes['href'] 
       @text = node.all_text
+
+      # If there is no text, try to find an image and use it's alt text
+      if (@text.nil? || @text.length == 0) && @node.has_elements?
+        @text = ''
+        @node.each_element { |e|
+          if e.name == 'img'
+            @text << (e.has_attributes? ? e.attributes['alt'] || '' : '')
+          end
+        }
+      end
+    end
+
+    def uri
+      URI.parse(@href)
+    end
+
+    def inspect
+      "'#{@text}' -> #{@href}\n"
     end
   end
   
@@ -24,5 +43,9 @@ module WWW
       @name = node.attributes['name']
       @src  = node.attributes['src']
     end
+
+    def inspect
+      "'#{@name}' -> #{@src}\n"
+    end
   end
 end

data/test/htdocs/alt_text.html

@@ -0,0 +1,9 @@
+<html>
+  <meta http-equiv="Refresh" content="0; url=http://www.drphil.com/">
+  <body>
+    <a href="alt_text.html"><img alt="alt text" src="hello"></a>
+    <a href="no_alt_text.html"><img src="hello"></a>
+    <a href="no_image.html">no image</a>
+    <a href="no_text.html"></a>
+  </body>
+</html>

data/test/htdocs/bad_form_test.html

@@ -0,0 +1,9 @@
+<html>
+  <head><title>Page Title</title></head>
+  <body>
+    <form name="form" method="duh" action="/form_post">
+      <input name="first" type="text" />
+      <input type="submit" value="Submit" />
+    </form>
+  </body>
+</html>

data/test/htdocs/form_test.html

@@ -170,5 +170,6 @@
       </table><br />
       <input type="submit" value="Submit" />
     </form>
+    <a href="/form_test.html">form test</a>
   </body>
 </html>

data/test/server.rb

@@ -19,6 +19,7 @@ s.mount("/form_post", FormTest)
 s.mount("/form post", FormTest)
 s.mount("/response_code", ResponseCodeTest)
 s.mount("/file_upload", FileUploadTest)
+s.mount("/bad_content_type", BadContentTypeTest)
 
 htpasswd = WEBrick::HTTPAuth::Htpasswd.new(base_dir + '/data/htpasswd')
 auth = WEBrick::HTTPAuth::BasicAuth.new(

data/test/servlets.rb

@@ -2,6 +2,13 @@ require 'webrick'
 require 'logger'
 require 'date'
 
+class BadContentTypeTest < WEBrick::HTTPServlet::AbstractServlet
+  def do_GET(req, res)
+    res['Content-Type'] = "text/xml"
+    res.body = "Hello World"
+  end
+end
+
 class FileUploadTest < WEBrick::HTTPServlet::AbstractServlet
   def do_POST(req, res)
     res.body = req.body
@@ -29,7 +36,7 @@ class FormTest < WEBrick::HTTPServlet::AbstractServlet
     res.body = "<HTML><body>"
     req.query.each_key { |k|
       req.query[k].each_data { |data|
-        res.body << "<a href=\"#\">#{k}:#{data}</a><br />"
+        res.body << "<a href=\"#\">#{URI.unescape(k)}:#{URI.unescape(data)}</a><br />"
       }
     }
     res.body << "</body></HTML>"

data/test/tc_errors.rb

@@ -0,0 +1,62 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+
+require 'test/unit'
+require 'rubygems'
+require 'mechanize'
+require 'test_includes'
+
+class MechErrorsTest < Test::Unit::TestCase
+  include TestMethods
+
+  def test_content_type_error
+    agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
+    page = agent.get("http://localhost:#{@port}/bad_content_type")
+    assert_raise(WWW::Mechanize::ContentTypeError) {
+      page.root
+    }
+    begin
+      page.root
+    rescue WWW::Mechanize::ContentTypeError => ex
+      assert_equal('text/xml', ex.content_type)
+    end
+  end
+
+  def test_bad_form_method
+    agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
+    page = agent.get("http://localhost:#{@port}/bad_form_test.html")
+    assert_raise(RuntimeError) {
+      agent.submit(page.forms.first)
+    }
+  end
+
+  def test_too_many_radio
+    agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
+    page = agent.get("http://localhost:#{@port}/form_test.html")
+    form = page.forms.name('post_form1').first
+    form.radiobuttons.each { |r| r.checked = true }
+    assert_raise(RuntimeError) {
+      agent.submit(form)
+    }
+  end
+
+  def test_unknown_agent
+    agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
+    assert_raise(RuntimeError) {
+      agent.user_agent_alias = "Aaron's Browser"
+    }
+  end
+
+  def test_bad_url
+    agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
+    assert_raise(RuntimeError) {
+      agent.get('/foo.html')
+    }
+  end
+
+  def test_unsupported_scheme
+    agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
+    assert_raise(RuntimeError) {
+      agent.get('ftp://server.com/foo.html')
+    }
+  end
+end

data/test/tc_forms.rb

@@ -129,6 +129,38 @@ class FormsMechTest < Test::Unit::TestCase
     )
   end
 
+  def test_select_box
+    agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
+    page = agent.get("http://localhost:#{@port}/form_test.html")
+    post_form = page.forms.find { |f| f.name == "post_form1" }
+    assert_not_nil(post_form, "Post form is null")
+    assert_not_nil(page.header)
+    assert_not_nil(page.root)
+    assert_equal(0, page.iframes.length)
+    assert_equal("post", post_form.method.downcase)
+    assert_equal("/form_post", post_form.action)
+
+    # Find the select list
+    s = post_form.fields.name(/country/).first
+    assert_not_nil(s, "Couldn't find country select list")
+    assert_equal(2, s.options.length)
+    assert_equal("USA", s.value)
+    assert_equal("USA", s.options.first.value)
+    assert_equal("USA", s.options.first.text)
+    assert_equal("CANADA", s.options[1].value)
+    assert_equal("CANADA", s.options[1].text)
+
+    # Now set all the fields
+    post_form.fields.name(/country/).value = s.options[1]
+    page = agent.submit(post_form, post_form.buttons.first)
+
+    # Check that the submitted fields exist
+    assert_not_nil(
+      page.links.find { |l| l.text == "country:CANADA" },
+      "select box not submitted"
+    )
+  end
+
   def test_get
     agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
     page = agent.get("http://localhost:#{@port}/form_test.html")

data/test/tc_links.rb

@@ -21,4 +21,17 @@ class LinksMechTest < Test::Unit::TestCase
     page = agent.get("http://localhost:#{@port}/find_link.html")
     assert_equal(15, page.links.length)
   end
+
+  def test_alt_text
+    agent = WWW::Mechanize.new { |a| a.log = Logger.new(nil) }
+    page = agent.get("http://localhost:#{@port}/alt_text.html")
+    assert_equal(4, page.links.length)
+    assert_equal(1, page.meta.length)
+
+    assert_equal('', page.meta.first.text)
+    assert_equal('alt text', page.links.href('alt_text.html').first.text)
+    assert_equal('', page.links.href('no_alt_text.html').first.text)
+    assert_equal('no image', page.links.href('no_image.html').first.text)
+    assert_equal('', page.links.href('no_text.html').first.text)
+  end
 end

data/test/tc_mech.rb

@@ -21,6 +21,12 @@ class MechMethodsTest < Test::Unit::TestCase
       agent.history.last.uri.to_s)
     assert_equal("http://localhost:#{@port}/",
       agent.history[-2].uri.to_s)
+
+    assert_equal(true, agent.visited?("http://localhost:#{@port}/"))
+    assert_equal(true, agent.visited?("/form_test.html"))
+    assert_equal(false, agent.visited?("http://google.com/"))
+    assert_equal(true, agent.visited?(page.links.first))
+
   end
 
   def test_max_history

data/test/ts_mech.rb

@@ -19,4 +19,5 @@ require 'tc_authenticate'
 require 'tc_filter'
 require 'tc_cookie_class'
 require 'tc_cookie_jar'
+require 'tc_errors'
 

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.8.11
+rubygems_version: 0.8.11.13
 specification_version: 1
 name: mechanize
 version: !ruby/object:Gem::Version 
-  version: 0.4.5
-date: 2006-05-20 00:00:00 -07:00
+  version: 0.4.6
+date: 2006-06-02 00:00:00 -07:00
 summary: Mechanize provides automated web-browsing
 require_paths: 
-  - lib
+- lib
 email: aaronp@rubyforge.org
 homepage: mechanize.rubyforge.org
 rubyforge_project: mechanize
@@ -18,91 +18,98 @@ bindir: bin
 has_rdoc: true
 required_ruby_version: !ruby/object:Gem::Version::Requirement 
   requirements: 
-    - 
-      - ">"
-      - !ruby/object:Gem::Version 
-        version: 0.0.0
+  - - ">"
+    - !ruby/object:Gem::Version 
+      version: 0.0.0
   version: 
 platform: ruby
 signing_key: 
 cert_chain: 
+post_install_message: 
 authors: 
-  - Aaron Patterson
+- Aaron Patterson
 files: 
-  - test/data
-  - test/htdocs
-  - test/README
-  - test/server.rb
-  - test/servlets.rb
-  - test/tc_authenticate.rb
-  - test/tc_cookie_class.rb
-  - test/tc_cookie_jar.rb
-  - test/tc_cookies.rb
-  - test/tc_filter.rb
-  - test/tc_forms.rb
-  - test/tc_frames.rb
-  - test/tc_links.rb
-  - test/tc_mech.rb
-  - test/tc_parsing.rb
-  - test/tc_response_code.rb
-  - test/tc_upload.rb
-  - test/tc_watches.rb
-  - test/test_includes.rb
-  - test/test_mech.rb
-  - test/ts_mech.rb
-  - test/data/htpasswd
-  - test/htdocs/button.jpg
-  - test/htdocs/file_upload.html
-  - test/htdocs/find_link.html
-  - test/htdocs/form_multival.html
-  - test/htdocs/form_test.html
-  - test/htdocs/frame_test.html
-  - test/htdocs/google.html
-  - test/htdocs/iframe_test.html
-  - test/htdocs/index.html
-  - lib/mechanize
-  - lib/mechanize.rb
-  - lib/mechanize/cookie.rb
-  - lib/mechanize/form.rb
-  - lib/mechanize/form_elements.rb
-  - lib/mechanize/mech_version.rb
-  - lib/mechanize/module.rb
-  - lib/mechanize/net-overrides
-  - lib/mechanize/page.rb
-  - lib/mechanize/page_elements.rb
-  - lib/mechanize/parsing.rb
-  - lib/mechanize/net-overrides/net
-  - lib/mechanize/net-overrides/net/http.rb
-  - lib/mechanize/net-overrides/net/https.rb
-  - lib/mechanize/net-overrides/net/protocol.rb
-  - README
-  - EXAMPLES
-  - CHANGELOG
-  - LICENSE
-  - NOTES
+- test/tc_errors.rb
+- test/server.rb
+- test/tc_response_code.rb
+- test/servlets.rb
+- test/tc_cookies.rb
+- test/htdocs
+- test/tc_forms.rb
+- test/tc_upload.rb
+- test/tc_links.rb
+- test/data
+- test/tc_filter.rb
+- test/tc_cookie_class.rb
+- test/tc_watches.rb
+- test/tc_parsing.rb
+- test/test_includes.rb
+- test/tc_frames.rb
+- test/tc_mech.rb
+- test/test_mech.rb
+- test/ts_mech.rb
+- test/tc_cookie_jar.rb
+- test/README
+- test/tc_authenticate.rb
+- test/htdocs/frame_test.html
+- test/htdocs/button.jpg
+- test/htdocs/form_test.html
+- test/htdocs/form_multival.html
+- test/htdocs/alt_text.html
+- test/htdocs/bad_form_test.html
+- test/htdocs/find_link.html
+- test/htdocs/index.html
+- test/htdocs/google.html
+- test/htdocs/file_upload.html
+- test/htdocs/iframe_test.html
+- test/data/htpasswd
+- lib/mechanize
+- lib/mechanize.rb
+- lib/mechanize/net-overrides
+- lib/mechanize/mech_version.rb
+- lib/mechanize/parsing.rb
+- lib/mechanize/module.rb
+- lib/mechanize/page.rb
+- lib/mechanize/cookie.rb
+- lib/mechanize/form_elements.rb
+- lib/mechanize/list.rb
+- lib/mechanize/form.rb
+- lib/mechanize/page_elements.rb
+- lib/mechanize/net-overrides/net
+- lib/mechanize/net-overrides/net/http.rb
+- lib/mechanize/net-overrides/net/protocol.rb
+- lib/mechanize/net-overrides/net/https.rb
+- README
+- EXAMPLES
+- CHANGELOG
+- LICENSE
+- NOTES
 test_files: []
+
 rdoc_options: 
-  - "--main"
-  - README
-  - "--title"
-  - "'WWW::Mechanize RDoc'"
+- --main
+- README
+- --title
+- "'WWW::Mechanize RDoc'"
 extra_rdoc_files: 
-  - README
-  - EXAMPLES
-  - CHANGELOG
-  - LICENSE
-  - NOTES
+- README
+- EXAMPLES
+- CHANGELOG
+- LICENSE
+- NOTES
 executables: []
+
 extensions: []
+
 requirements: []
+
 dependencies: 
-  - !ruby/object:Gem::Dependency 
-    name: ruby-web
-    version_requirement: 
-    version_requirements: !ruby/object:Gem::Version::Requirement 
-      requirements: 
-        - 
-          - ">="
-          - !ruby/object:Gem::Version 
-            version: 1.1.0
-      version: 
+- !ruby/object:Gem::Dependency 
+  name: ruby-web
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Version::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.1.0
+    version: