RubyGems - mechanize-ntlm - Versions diffs - 0.9.1 - Mend

mechanize-ntlm 0.9.1

Files changed (171) hide show

data/CHANGELOG.rdoc +480 -0
data/EXAMPLES.rdoc +171 -0
data/FAQ.rdoc +11 -0
data/GUIDE.rdoc +122 -0
data/LICENSE.rdoc +340 -0
data/Manifest.txt +169 -0
data/README.rdoc +60 -0
data/Rakefile +44 -0
data/examples/flickr_upload.rb +23 -0
data/examples/mech-dump.rb +7 -0
data/examples/proxy_req.rb +9 -0
data/examples/rubyforge.rb +21 -0
data/examples/spider.rb +11 -0
data/lib/mechanize-ntlm.rb +7 -0
data/lib/www/mechanize.rb +582 -0
data/lib/www/mechanize/chain.rb +34 -0
data/lib/www/mechanize/chain/auth_headers.rb +82 -0
data/lib/www/mechanize/chain/body_decoding_handler.rb +43 -0
data/lib/www/mechanize/chain/connection_resolver.rb +78 -0
data/lib/www/mechanize/chain/custom_headers.rb +23 -0
data/lib/www/mechanize/chain/handler.rb +9 -0
data/lib/www/mechanize/chain/header_resolver.rb +48 -0
data/lib/www/mechanize/chain/parameter_resolver.rb +23 -0
data/lib/www/mechanize/chain/post_connect_hook.rb +0 -0
data/lib/www/mechanize/chain/pre_connect_hook.rb +22 -0
data/lib/www/mechanize/chain/request_resolver.rb +32 -0
data/lib/www/mechanize/chain/response_body_parser.rb +40 -0
data/lib/www/mechanize/chain/response_header_handler.rb +51 -0
data/lib/www/mechanize/chain/response_reader.rb +41 -0
data/lib/www/mechanize/chain/ssl_resolver.rb +36 -0
data/lib/www/mechanize/chain/uri_resolver.rb +73 -0
data/lib/www/mechanize/content_type_error.rb +16 -0
data/lib/www/mechanize/cookie.rb +72 -0
data/lib/www/mechanize/cookie_jar.rb +191 -0
data/lib/www/mechanize/file.rb +73 -0
data/lib/www/mechanize/file_response.rb +62 -0
data/lib/www/mechanize/file_saver.rb +39 -0
data/lib/www/mechanize/form.rb +359 -0
data/lib/www/mechanize/form/button.rb +8 -0
data/lib/www/mechanize/form/check_box.rb +13 -0
data/lib/www/mechanize/form/field.rb +28 -0
data/lib/www/mechanize/form/file_upload.rb +24 -0
data/lib/www/mechanize/form/image_button.rb +23 -0
data/lib/www/mechanize/form/multi_select_list.rb +69 -0
data/lib/www/mechanize/form/option.rb +51 -0
data/lib/www/mechanize/form/radio_button.rb +38 -0
data/lib/www/mechanize/form/select_list.rb +45 -0
data/lib/www/mechanize/headers.rb +12 -0
data/lib/www/mechanize/history.rb +67 -0
data/lib/www/mechanize/inspect.rb +90 -0
data/lib/www/mechanize/monkey_patch.rb +37 -0
data/lib/www/mechanize/page.rb +145 -0
data/lib/www/mechanize/page/base.rb +10 -0
data/lib/www/mechanize/page/frame.rb +22 -0
data/lib/www/mechanize/page/link.rb +50 -0
data/lib/www/mechanize/page/meta.rb +10 -0
data/lib/www/mechanize/pluggable_parsers.rb +103 -0
data/lib/www/mechanize/redirect_limit_reached_error.rb +18 -0
data/lib/www/mechanize/redirect_not_get_or_head_error.rb +20 -0
data/lib/www/mechanize/response_code_error.rb +25 -0
data/lib/www/mechanize/unsupported_scheme_error.rb +10 -0
data/lib/www/mechanize/util.rb +76 -0
data/lib/www/ntlm-http/lib/net/ntlm_http.rb +854 -0
data/mechanize.gemspec +24 -0
data/test/chain/test_argument_validator.rb +14 -0
data/test/chain/test_custom_headers.rb +18 -0
data/test/chain/test_parameter_resolver.rb +35 -0
data/test/chain/test_request_resolver.rb +29 -0
data/test/chain/test_response_reader.rb +24 -0
data/test/data/htpasswd +1 -0
data/test/data/server.crt +16 -0
data/test/data/server.csr +12 -0
data/test/data/server.key +15 -0
data/test/data/server.pem +15 -0
data/test/helper.rb +127 -0
data/test/htdocs/alt_text.html +10 -0
data/test/htdocs/bad_form_test.html +9 -0
data/test/htdocs/button.jpg +0 -0
data/test/htdocs/empty_form.html +6 -0
data/test/htdocs/file_upload.html +26 -0
data/test/htdocs/find_link.html +41 -0
data/test/htdocs/form_multi_select.html +16 -0
data/test/htdocs/form_multival.html +37 -0
data/test/htdocs/form_no_action.html +18 -0
data/test/htdocs/form_no_input_name.html +16 -0
data/test/htdocs/form_select.html +16 -0
data/test/htdocs/form_select_all.html +16 -0
data/test/htdocs/form_select_none.html +17 -0
data/test/htdocs/form_select_noopts.html +10 -0
data/test/htdocs/form_set_fields.html +14 -0
data/test/htdocs/form_test.html +188 -0
data/test/htdocs/frame_test.html +30 -0
data/test/htdocs/google.html +13 -0
data/test/htdocs/iframe_test.html +16 -0
data/test/htdocs/index.html +6 -0
data/test/htdocs/link with space.html +5 -0
data/test/htdocs/meta_cookie.html +11 -0
data/test/htdocs/no_title_test.html +6 -0
data/test/htdocs/relative/tc_relative_links.html +21 -0
data/test/htdocs/tc_bad_links.html +5 -0
data/test/htdocs/tc_base_link.html +8 -0
data/test/htdocs/tc_blank_form.html +11 -0
data/test/htdocs/tc_checkboxes.html +19 -0
data/test/htdocs/tc_encoded_links.html +5 -0
data/test/htdocs/tc_follow_meta.html +8 -0
data/test/htdocs/tc_form_action.html +48 -0
data/test/htdocs/tc_links.html +18 -0
data/test/htdocs/tc_no_attributes.html +16 -0
data/test/htdocs/tc_pretty_print.html +17 -0
data/test/htdocs/tc_radiobuttons.html +17 -0
data/test/htdocs/tc_referer.html +10 -0
data/test/htdocs/tc_relative_links.html +19 -0
data/test/htdocs/tc_textarea.html +23 -0
data/test/htdocs/unusual______.html +5 -0
data/test/servlets.rb +339 -0
data/test/ssl_server.rb +48 -0
data/test/test_authenticate.rb +71 -0
data/test/test_bad_links.rb +25 -0
data/test/test_blank_form.rb +16 -0
data/test/test_checkboxes.rb +61 -0
data/test/test_content_type.rb +13 -0
data/test/test_cookie_class.rb +338 -0
data/test/test_cookie_jar.rb +343 -0
data/test/test_cookies.rb +123 -0
data/test/test_encoded_links.rb +20 -0
data/test/test_errors.rb +49 -0
data/test/test_follow_meta.rb +69 -0
data/test/test_form_action.rb +44 -0
data/test/test_form_as_hash.rb +61 -0
data/test/test_form_button.rb +38 -0
data/test/test_form_no_inputname.rb +15 -0
data/test/test_forms.rb +575 -0
data/test/test_frames.rb +25 -0
data/test/test_get_headers.rb +52 -0
data/test/test_gzipping.rb +22 -0
data/test/test_hash_api.rb +45 -0
data/test/test_history.rb +142 -0
data/test/test_history_added.rb +16 -0
data/test/test_html_unscape_forms.rb +39 -0
data/test/test_if_modified_since.rb +20 -0
data/test/test_keep_alive.rb +31 -0
data/test/test_links.rb +120 -0
data/test/test_mech.rb +259 -0
data/test/test_mechanize_file.rb +47 -0
data/test/test_multi_select.rb +106 -0
data/test/test_no_attributes.rb +13 -0
data/test/test_option.rb +18 -0
data/test/test_page.rb +67 -0
data/test/test_pluggable_parser.rb +145 -0
data/test/test_post_form.rb +34 -0
data/test/test_pretty_print.rb +22 -0
data/test/test_radiobutton.rb +75 -0
data/test/test_redirect_limit_reached.rb +41 -0
data/test/test_redirect_verb_handling.rb +45 -0
data/test/test_referer.rb +39 -0
data/test/test_relative_links.rb +40 -0
data/test/test_request.rb +13 -0
data/test/test_response_code.rb +52 -0
data/test/test_save_file.rb +48 -0
data/test/test_scheme.rb +48 -0
data/test/test_select.rb +106 -0
data/test/test_select_all.rb +15 -0
data/test/test_select_none.rb +15 -0
data/test/test_select_noopts.rb +16 -0
data/test/test_set_fields.rb +44 -0
data/test/test_ssl_server.rb +20 -0
data/test/test_subclass.rb +14 -0
data/test/test_textarea.rb +45 -0
data/test/test_upload.rb +109 -0
data/test/test_verbs.rb +25 -0
metadata +284 -0

data/lib/www/mechanize/monkey_patch.rb ADDED

@@ -0,0 +1,37 @@
+module Net
+  class HTTP
+    alias :old_keep_alive? :keep_alive?
+    def keep_alive?(req, res)
+      return false if /close/i =~ req['connection'].to_s
+      return false if @seems_1_0_server
+      return false if /close/i      =~ res['connection'].to_s
+      return true  if /keep-alive/i =~ res['connection'].to_s
+      return false if /close/i      =~ res['proxy-connection'].to_s
+      return true  if /keep-alive/i =~ res['proxy-connection'].to_s
+      (@curr_http_version == '1.1')
+    end
+  end
+end
+# Monkey patch for ruby 1.8.4
+unless RUBY_VERSION > "1.8.4"
+module Net # :nodoc:
+  class HTTPResponse # :nodoc:
+    CODE_TO_OBJ['500'] = HTTPInternalServerError
+  end
+end
+else
+module WWW
+  class Mechanize
+    class Form
+      alias :inspect  :pretty_inspect
+    end
+    class Page
+      alias :inspect  :pretty_inspect
+      class Link
+        alias :inspect  :pretty_inspect
+      end
+    end
+  end
+end
+end

data/lib/www/mechanize/page.rb ADDED

@@ -0,0 +1,145 @@
+require 'www/mechanize/page/link'
+require 'www/mechanize/page/meta'
+require 'www/mechanize/page/base'
+require 'www/mechanize/page/frame'
+require 'www/mechanize/headers'
+module WWW
+  class Mechanize
+    # = Synopsis
+    # This class encapsulates an HTML page.  If Mechanize finds a content
+    # type of 'text/html', this class will be instantiated and returned.
+    #
+    # == Example
+    #  require 'rubygems'
+    #  require 'mechanize'
+    #
+    #  agent = WWW::Mechanize.new
+    #  agent.get('http://google.com/').class  #=> WWW::Mechanize::Page
+    #
+    class Page < WWW::Mechanize::File
+      extend Forwardable
+      attr_accessor :mech
+      attr_accessor :encoding
+      def initialize(uri=nil, response=nil, body=nil, code=nil, mech=nil)
+        @encoding = nil
+        response.each do |header,v|
+          next unless v =~ /charset/i
+          @encoding = v.split('=').last.strip
+        end
+        @encoding ||= Util.detect_charset(body)
+        body = Util.to_native_charset(body, @encoding) rescue body
+        super(uri, response, body, code)
+        @mech           ||= mech
+        raise Mechanize::ContentTypeError.new(response['content-type']) unless
+           response['content-type'] =~ /^(text\/html)|(application\/xhtml\+xml)/i
+        @parser = @links = @forms = @meta = @bases = @frames = @iframes = nil
+      end
+      def title
+        @title ||= if parser && search('title').inner_text.length > 0
+          search('title').inner_text
+        end
+      end
+      def parser
+        return @parser if @parser
+        if body && response
+          html_body = body.length > 0 ? body : '<html></html>'
+          if WWW::Mechanize.html_parser == Nokogiri::HTML
+            @parser = Mechanize.html_parser.parse(html_body, nil, @encoding)
+          else
+            @parser = Mechanize.html_parser.parse(html_body)
+          end
+        end
+        @parser
+      end
+      alias :root :parser
+      # Get the content type
+      def content_type
+        response['content-type']
+      end
+      # Search through the page like HPricot
+      def_delegator :parser, :search, :search
+      def_delegator :parser, :/, :/
+      def_delegator :parser, :at, :at
+      # Find a form matching +criteria+.
+      # Example:
+      #   page.form_with(:action => '/post/login.php') do |f|
+      #     ...
+      #   end
+      [:form, :link, :base, :frame, :iframe].each do |type|
+        eval(<<-eomethod)
+          def #{type}s_with(criteria)
+            criteria = {:name => criteria} if String === criteria
+            f = #{type}s.find_all do |thing|
+              criteria.all? { |k,v| v === thing.send(k) }
+            end
+            yield f if block_given?
+            f
+          end
+          def #{type}_with(criteria)
+            f = #{type}s_with(criteria).first
+            yield f if block_given?
+            f
+          end
+          alias :#{type} :#{type}_with
+        eomethod
+      end
+      def links
+        @links ||= %w{ a area }.map do |tag|
+          search(tag).map do |node|
+            Link.new(node, @mech, self)
+          end
+        end.flatten
+      end
+      def forms
+        @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 ||= 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
+        end.compact
+      end
+      def bases
+        @bases ||=
+          search('base').map { |node| Base.new(node, @mech, self) }
+      end
+      def frames
+        @frames ||=
+          search('frame').map { |node| Frame.new(node, @mech, self) }
+      end
+      def iframes
+        @iframes ||=
+          search('iframe').map { |node| Frame.new(node, @mech, self) }
+      end
+    end
+  end
+end

data/lib/www/mechanize/page/base.rb ADDED

@@ -0,0 +1,10 @@
+module WWW
+  class Mechanize
+    class Page < WWW::Mechanize::File
+      # This class encapsulates a Base tag.  Mechanize treats base tags just
+      # like 'a' tags.  Base objects will contain links, but most likely will
+      # have no text.
+      class Base < Link; end
+    end
+  end
+end

data/lib/www/mechanize/page/frame.rb ADDED

@@ -0,0 +1,22 @@
+module WWW
+  class Mechanize
+    class Page < WWW::Mechanize::File
+      # This class encapsulates a 'frame' tag.  Frame objects can be treated
+      # just like Link objects.  They contain src, the link they refer to,
+      # name, the name of the frame.  'src' and 'name' are aliased to 'href'
+      # and 'text' respectively so that a Frame object can be treated just
+      # like a Link.
+      class Frame < Link
+        alias :src :href
+        alias :name :text
+        def initialize(node, mech, referer)
+          super(node, mech, referer)
+          @node = node
+          @text = node['name']
+          @href = node['src']
+        end
+      end
+    end
+  end
+end

data/lib/www/mechanize/page/link.rb ADDED

@@ -0,0 +1,50 @@
+module WWW
+  class Mechanize
+    class Page < WWW::Mechanize::File
+      # This class encapsulates links.  It contains the text and the URI for
+      # 'a' tags parsed out of an HTML page.  If the link contains an image,
+      # the alt text will be used for that image.
+      #
+      # For example, the text for the following links with both be 'Hello World':
+      #
+      # <a href="http://rubyforge.org">Hello World</a>
+      # <a href="http://rubyforge.org"><img src="test.jpg" alt="Hello World"></a>
+      class Link
+        attr_reader :node
+        attr_reader :href
+        attr_reader :text
+        attr_reader :attributes
+        attr_reader :page
+        alias :to_s :text
+        alias :referer :page
+        def initialize(node, mech, page)
+          @node = node
+          @href = node['href']
+          @text = node.inner_text
+          @page = page
+          @mech = mech
+          @attributes = node
+          # If there is no text, try to find an image and use it's alt text
+          if (@text.nil? || @text.length == 0) && node.search('img').length > 0
+            @text = ''
+            node.search('img').each do |e|
+              @text << ( e['alt'] || '')
+            end
+          end
+        end
+        def uri
+          @href && URI.parse(@href)
+        end
+        # Click on this link
+        def click
+          @mech.click self
+        end
+      end
+    end
+  end
+end

data/lib/www/mechanize/page/meta.rb ADDED

@@ -0,0 +1,10 @@
+module WWW
+  class Mechanize
+    class Page < WWW::Mechanize::File
+      # This class encapsulates a Meta tag.  Mechanize treats meta tags just
+      # like 'a' tags.  Meta objects will contain links, but most likely will
+      # have no text.
+      class Meta < Link; end
+    end
+  end
+end

data/lib/www/mechanize/pluggable_parsers.rb ADDED

@@ -0,0 +1,103 @@
+require 'www/mechanize/file'
+require 'www/mechanize/file_saver'
+require 'www/mechanize/page'
+module WWW
+  class Mechanize
+    # = Synopsis
+    # This class is used to register and maintain pluggable parsers for
+    # Mechanize to use.
+    #
+    # A Pluggable Parser is a parser that Mechanize uses for any particular
+    # content type.  Mechanize will ask PluggableParser for the class it
+    # should initialize given any content type.  This class allows users to
+    # register their own pluggable parsers, or modify existing pluggable
+    # parsers.
+    #
+    # PluggableParser returns a WWW::Mechanize::File object for content types
+    # that it does not know how to handle.  WWW::Mechanize::File provides
+    # basic functionality for any content type, so it is a good class to
+    # extend when building your own parsers.
+    # == Example
+    # To create your own parser, just create a class that takes four
+    # parameters in the constructor.  Here is an example of registering
+    # a pluggable parser that handles CSV files:
+    #  class CSVParser < WWW::Mechanize::File
+    #    attr_reader :csv
+    #    def initialize(uri=nil, response=nil, body=nil, code=nil)
+    #      super(uri, response, body, code)
+    #      @csv = CSV.parse(body)
+    #    end
+    #  end
+    #  agent = WWW::Mechanize.new
+    #  agent.pluggable_parser.csv = CSVParser
+    #  agent.get('http://example.com/test.csv')  # => CSVParser
+    # Now any page that returns the content type of 'text/csv' will initialize
+    # a CSVParser and return that object to the caller.
+    #
+    # To register a pluggable parser for a content type that pluggable parser
+    # does not know about, just use the hash syntax:
+    #  agent.pluggable_parser['text/something'] = SomeClass
+    #
+    # To set the default parser, just use the 'defaut' method:
+    #  agent.pluggable_parser.default = SomeClass
+    # Now all unknown content types will be instances of SomeClass.
+    class PluggableParser
+      CONTENT_TYPES = {
+        :html => 'text/html',
+        :wap  => 'application/vnd.wap.xhtml+xml',
+        :xhtml => 'application/xhtml+xml',
+        :pdf  => 'application/pdf',
+        :csv  => 'text/csv',
+        :xml  => 'text/xml',
+      }
+      attr_accessor :default
+      def initialize
+        @parsers = { CONTENT_TYPES[:html]   => Page,
+                     CONTENT_TYPES[:xhtml]  => Page,
+                     CONTENT_TYPES[:wap]    => Page,
+        }
+        @default = File
+      end
+      def parser(content_type)
+        content_type.nil? ? default : @parsers[content_type] || default
+      end
+      def register_parser(content_type, klass)
+        @parsers[content_type] = klass
+      end
+      def html=(klass)
+        register_parser(CONTENT_TYPES[:html], klass)
+        register_parser(CONTENT_TYPES[:xhtml], klass)
+      end
+      def xhtml=(klass)
+        register_parser(CONTENT_TYPES[:xhtml], klass)
+      end
+      def pdf=(klass)
+        register_parser(CONTENT_TYPES[:pdf], klass)
+      end
+      def csv=(klass)
+        register_parser(CONTENT_TYPES[:csv], klass)
+      end
+      def xml=(klass)
+        register_parser(CONTENT_TYPES[:xml], klass)
+      end
+      def [](content_type)
+        @parsers[content_type]
+      end
+      def []=(content_type, klass)
+        @parsers[content_type] = klass
+      end
+    end
+  end
+end

data/lib/www/mechanize/redirect_limit_reached_error.rb ADDED

@@ -0,0 +1,18 @@
+module WWW
+  class Mechanize
+    # Thrown when too many redirects are sent
+    class RedirectLimitReachedError < RuntimeError
+      attr_reader :page, :response_code, :redirects
+      def initialize(page, redirects)
+        @page           = page
+        @redirects      = redirects
+        @response_code  = page.code
+      end
+      def to_s
+        "Maximum redirect limit (#{redirects}) reached"
+      end
+      alias :inspect :to_s
+    end
+  end
+end

data/lib/www/mechanize/redirect_not_get_or_head_error.rb ADDED

@@ -0,0 +1,20 @@
+module WWW
+  class Mechanize
+    # Thrown when a POST, PUT, or DELETE request results in a redirect
+    # see RFC 2616 10.3.2, 10.3.3 http://www.ietf.org/rfc/rfc2616.txt
+    class RedirectNotGetOrHeadError < RuntimeError
+      attr_reader :page, :response_code, :verb, :uri
+      def initialize(page, verb)
+        @page           = page
+        @verb           = verb
+        @uri            = page.uri
+        @response_code  = page.code
+      end
+      def to_s
+        "#{@response_code} redirect received after a #{@verb} request"
+      end
+      alias :inspect :to_s
+    end
+  end
+end

data/lib/www/mechanize/response_code_error.rb ADDED

@@ -0,0 +1,25 @@
+module WWW
+  class Mechanize
+    # =Synopsis
+    # This error is thrown when Mechanize encounters a response code it does
+    # not know how to handle.  Currently, this exception will be thrown
+    # if Mechanize encounters response codes other than 200, 301, or 302.
+    # Any other response code is up to the user to handle.
+    class ResponseCodeError < RuntimeError
+      attr_reader :response_code
+      attr_reader :page
+      def initialize(page)
+        @page          = page
+        @response_code = page.code
+      end
+      def to_s
+        "#{response_code} => #{Net::HTTPResponse::CODE_TO_OBJ[response_code]}"
+      end
+      def inspect; to_s; end
+    end
+  end
+end