Class: Arachni::Page
- Includes:
- Utilities
- Defined in:
- lib/arachni/page.rb,
lib/arachni/page/dom.rb,
lib/arachni/page/scope.rb,
lib/arachni/page/dom/transition.rb
Overview
It holds page data like elements, cookies, headers, etc…
Defined Under Namespace
Constant Summary collapse
- ELEMENTS =
[ :links, :forms, :cookies, :headers, :link_templates, :jsons, :xmls ]
- METADATA =
[ :nonce_name, :skip_dom ]
Instance Attribute Summary collapse
- #cache ⇒ Hash readonly
-
#dom ⇒ DOM
DOM snapshot.
-
#element_audit_whitelist ⇒ Set<Integer>
readonly
Audit whitelist based on Element::Capabilities::Auditable#coverage_hash.
-
#metadata ⇒ Hash
readonly
Holds page data that will need to persist between #clear_cache calls and other utility data.
-
#response ⇒ HTTP::Response
readonly
HTTP response.
Class Method Summary collapse
- ._load(data) ⇒ Object
- .from_data(data) ⇒ Object
- .from_response(response) ⇒ Page
- .from_rpc_data(data) ⇒ Page
- .from_url(url, opts = {}, &block) ⇒ Page
Instance Method Summary collapse
- #==(other) ⇒ Object
- #_dump(_) ⇒ Object
-
#audit_element?(element) ⇒ Bool
‘true` if the element should be audited, `false` otherwise.
-
#body ⇒ String
HTTP response body.
- #body=(string) ⇒ Object
-
#clear_cache ⇒ Page
‘self` with caches cleared.
-
#code ⇒ String
URL of the page.
-
#cookie_jar ⇒ Array<Element::Cookie>
Cookies extracted from the supplied cookie-jar.
-
#do_not_audit_elements ⇒ Object
It forces #audit_element? to always returns false.
-
#document ⇒ Nokogiri::HTML
Parsed HTML document.
- #dup ⇒ Object
-
#elements ⇒ Array<Element::Base>
All page elements.
-
#elements_within_scope ⇒ Array<Element::Base>
All page elements that are within the scope of the scan.
- #eql?(other) ⇒ Boolean
-
#has_script? ⇒ Boolean
‘true` if the page contains client-side code, `false` otherwise.
- #hash ⇒ Object
- #import_metadata(other, metas = METADATA) ⇒ Object
-
#initialize(options) ⇒ Page
constructor
Needs either a ‘:parser` or a `:response` or user provided data.
-
#method(*args) ⇒ String
The request method that returned the page.
- #parsed_url ⇒ Arachni::URI
- #parser ⇒ Parser
-
#paths ⇒ Array<String>
Paths contained in this page.
-
#performer ⇒ Object
Object which performed the #request which lead to this page.
- #persistent_hash ⇒ Object
-
#platforms ⇒ Platform
Applicable platforms for the page.
- #prepare_for_report ⇒ Object
-
#query_vars ⇒ Hash
URL query parameters.
- #reload_metadata ⇒ Object
-
#request ⇒ HTTP::Request
HTTP request.
- #scope ⇒ Scope
-
#text? ⇒ Boolean
‘true` if the body of the page is text-base, `false` otherwise.
-
#title ⇒ String
Title of the page.
-
#to_h ⇒ Hash
(also: #to_hash)
Converts the page data to a hash.
- #to_initialization_options ⇒ Object
-
#to_rpc_data ⇒ Hash
Data representing this instance that are suitable the RPC transmission.
- #to_s ⇒ Object (also: #inspect)
- #update_element_audit_whitelist(list) ⇒ Set
- #update_metadata ⇒ Object
-
#url ⇒ String
URL of the page.
Methods included from Utilities
#available_port, #caller_name, #caller_path, #cookie_decode, #cookie_encode, #cookies_from_document, #cookies_from_file, #cookies_from_response, #exception_jail, #exclude_path?, #follow_protocol?, #form_decode, #form_encode, #forms_from_document, #forms_from_response, #full_and_absolute_url?, #generate_token, #get_path, #hms_to_seconds, #html_decode, #html_encode, #include_path?, #links_from_document, #links_from_response, #normalize_url, #page_from_response, #page_from_url, #parse_set_cookie, #path_in_domain?, #path_too_deep?, #port_available?, #rand_port, #random_seed, #redundant_path?, #regexp_array_match, #remove_constants, #request_parse_body, #seconds_to_hms, #skip_page?, #skip_path?, #skip_resource?, #skip_response?, #to_absolute, #uri_decode, #uri_encode, #uri_parse, #uri_parse_query, #uri_parser, #uri_rewrite
Constructor Details
#initialize(options) ⇒ Page
Needs either a ‘:parser` or a `:response` or user provided data.
144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
# File 'lib/arachni/page.rb', line 144 def initialize( ) fail ArgumentError, 'Options cannot be empty.' if .empty? = .dup @cache = {} @do_not_audit_elements = .delete(:do_not_audit_elements) @cache[:parser] = .delete(:parser) @response = @cache[:parser].response if @cache[:parser] # We need to know whether or not the page has been dynamically updated # with elements, in order to optimize #dup and #hash operations. @has_custom_elements = Set.new @metadata ||= {} .each do |k, v| send( "#{k}=", try_dup( v ) ) end @dom = DOM.new( ([:dom] || {}).merge( page: self ) ) fail ArgumentError, 'No URL given!' if !url Platform::Manager.fingerprint( self ) @element_audit_whitelist ||= [] @element_audit_whitelist = Set.new( @element_audit_whitelist ) end |
Instance Attribute Details
#dom ⇒ DOM
Returns DOM snapshot.
111 112 113 |
# File 'lib/arachni/page.rb', line 111 def dom @dom end |
#element_audit_whitelist ⇒ Set<Integer> (readonly)
Returns Audit whitelist based on Element::Capabilities::Auditable#coverage_hash.
133 134 135 |
# File 'lib/arachni/page.rb', line 133 def element_audit_whitelist @element_audit_whitelist end |
#metadata ⇒ Hash (readonly)
Returns Holds page data that will need to persist between #clear_cache calls and other utility data.
125 126 127 |
# File 'lib/arachni/page.rb', line 125 def @metadata end |
#response ⇒ HTTP::Response (readonly)
Returns HTTP response.
115 116 117 |
# File 'lib/arachni/page.rb', line 115 def response @response end |
Class Method Details
._load(data) ⇒ Object
575 576 577 |
# File 'lib/arachni/page.rb', line 575 def self._load( data ) new( Marshal.load( data ) ) end |
.from_data(data) ⇒ Object
82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
# File 'lib/arachni/page.rb', line 82 def self.from_data( data ) data = data.dup data[:response] ||= {} data[:response][:code] ||= 200 data[:response][:url] ||= data.delete( :url ) data[:response][:body] ||= data.delete( :body ) || '' data[:response][:request] ||= {} data[:response][:request][:url] ||= data[:response][:url] ELEMENTS.each { |e| data[e] ||= [] } data[:cookie_jar] ||= [] data[:response][:request] = Arachni::HTTP::Request.new( data[:response][:request] ) data[:response] = Arachni::HTTP::Response.new( data[:response] ) new data end |
.from_response(response) ⇒ Page
59 60 61 |
# File 'lib/arachni/page.rb', line 59 def self.from_response( response ) Parser.new( response ).page end |
.from_rpc_data(data) ⇒ Page
543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 |
# File 'lib/arachni/page.rb', line 543 def self.from_rpc_data( data ) dom = data.delete('dom') normalized_data = {} data.each do |name, value| value = case name when 'response' HTTP::Response.from_rpc_data( value ) when *ELEMENTS.map(&:to_s) value.map do |e| Element.const_get(name[0...-1].capitalize.to_sym).from_rpc_data( e ) end.to_a else value end normalized_data[name.to_sym] = value end instance = new( normalized_data ) instance.instance_variable_set( '@dom', DOM.from_rpc_data( dom.merge( page: instance ) ) ) instance end |
.from_url(url, opts = {}, &block) ⇒ Page
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
# File 'lib/arachni/page.rb', line 37 def self.from_url( url, opts = {}, &block ) responses = [] opts[:precision] ||= 2 opts[:precision].times do HTTP::Client.get( url, opts[:http] || {} ) do |res| responses << res next if responses.size != opts[:precision] block.call( from_response( responses ) ) if block_given? end end if !block_given? HTTP::Client.run from_response( responses ) end end |
Instance Method Details
#==(other) ⇒ Object
449 450 451 |
# File 'lib/arachni/page.rb', line 449 def ==( other ) hash == other.hash end |
#_dump(_) ⇒ Object
571 572 573 |
# File 'lib/arachni/page.rb', line 571 def _dump( _ ) Marshal.dump( ) end |
#audit_element?(element) ⇒ Bool
Returns ‘true` if the element should be audited, `false` otherwise.
226 227 228 229 230 231 232 |
# File 'lib/arachni/page.rb', line 226 def audit_element?( element ) return if @do_not_audit_elements return true if @element_audit_whitelist.empty? @element_audit_whitelist.include?( element.is_a?( Integer ) ? element : element.coverage_hash ) end |
#body ⇒ String
Returns HTTP response body.
266 267 268 269 |
# File 'lib/arachni/page.rb', line 266 def body return '' if !@body && !@response @body ||= response.body end |
#body=(string) ⇒ Object
273 274 275 276 277 278 |
# File 'lib/arachni/page.rb', line 273 def body=( string ) @has_javascript = nil clear_cache @body = string.to_s.dup.freeze end |
#clear_cache ⇒ Page
Will preserve caches for elements which have been externally modified.
Returns ‘self` with caches cleared.
347 348 349 350 351 352 353 354 355 356 357 |
# File 'lib/arachni/page.rb', line 347 def clear_cache ELEMENTS.each do |type| next if @has_custom_elements.include? type # Remove the association to this page before clearing the elements # from cache to make it easier on the GC. (@cache[type] || []).each { |e| e.page = nil } end @cache.delete_if { |k, _| !@has_custom_elements.include? k } self end |
#code ⇒ String
Returns URL of the page.
253 254 255 256 |
# File 'lib/arachni/page.rb', line 253 def code return 0 if !@code && !response @code ||= response.code end |
#cookie_jar ⇒ Array<Element::Cookie>
Returns Cookies extracted from the supplied cookie-jar.
297 298 299 |
# File 'lib/arachni/page.rb', line 297 def @cookie_jar ||= (parser ? parser. : []) end |
#do_not_audit_elements ⇒ Object
It forces #audit_element? to always returns false.
235 236 237 |
# File 'lib/arachni/page.rb', line 235 def do_not_audit_elements @do_not_audit_elements = true end |
#document ⇒ Nokogiri::HTML
Returns Parsed HTML document.
339 340 341 |
# File 'lib/arachni/page.rb', line 339 def document @cache[:document] ||= (parser.nil? ? Nokogiri::HTML( body ) : parser.document) end |
#dup ⇒ Object
457 458 459 |
# File 'lib/arachni/page.rb', line 457 def dup self.class.new end |
#elements ⇒ Array<Element::Base>
Returns All page elements.
317 318 319 |
# File 'lib/arachni/page.rb', line 317 def elements ELEMENTS.map { |type| send( type ) }.flatten end |
#elements_within_scope ⇒ Array<Element::Base>
Returns All page elements that are within the scope of the scan.
323 324 325 326 327 328 |
# File 'lib/arachni/page.rb', line 323 def elements_within_scope ELEMENTS.map do |type| next if !Options.audit.element? type send( type ).select { |e| e.scope.in? } end.flatten.compact end |
#eql?(other) ⇒ Boolean
453 454 455 |
# File 'lib/arachni/page.rb', line 453 def eql?( other ) self == other end |
#has_script? ⇒ Boolean
Returns ‘true` if the page contains client-side code, `false` otherwise.
379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 |
# File 'lib/arachni/page.rb', line 379 def has_script? return @has_javascript if !@has_javascript.nil? if !response.headers.content_type.to_s.start_with?( 'text/html' ) || !text? || !document return @has_javascript = false end # First check, quick and simple. return @has_javascript = true if document.css( 'script' ).any? # Check for event attributes, if there are any then there's JS to be # executed. Browser::Javascript.events.flatten.each do |event| return @has_javascript = true if document.xpath( "//*[@#{event}]" ).any? end # If there's 'javascript:' in 'href' and 'action' attributes then # there's JS to be executed. [:action, :href].each do |candidate| document.xpath( "//*[@#{candidate}]" ).each do |attribute| if attribute.attributes[candidate.to_s].to_s.start_with?( 'javascript:' ) return @has_javascript = true end end end @has_javascript = false end |
#hash ⇒ Object
445 446 447 |
# File 'lib/arachni/page.rb', line 445 def hash digest.hash end |
#import_metadata(other, metas = METADATA) ⇒ Object
477 478 479 480 481 482 483 484 485 486 487 488 489 |
# File 'lib/arachni/page.rb', line 477 def ( other, = METADATA ) [].flatten.each do || other..each do |element_type, data| @metadata[element_type] ||= {} @metadata[element_type][.to_s] ||= {} @metadata[element_type][.to_s].merge!( data[.to_s] ) end end self end |
#method(*args) ⇒ String
Returns The request method that returned the page.
332 333 334 335 |
# File 'lib/arachni/page.rb', line 332 def method( *args ) return super( *args ) if args.any? response.request.method end |
#parsed_url ⇒ Arachni::URI
187 188 189 |
# File 'lib/arachni/page.rb', line 187 def parsed_url Arachni::URI( url ) end |
#parser ⇒ Parser
192 193 194 195 196 197 198 199 200 201 |
# File 'lib/arachni/page.rb', line 192 def parser return if !@response return @cache[:parser] if @cache[:parser] @cache[:parser] = Parser.new( @response ) # The page may have a browser-assigned body, set it as the one to parse. @cache[:parser].body = body @cache[:parser] end |
#paths ⇒ Array<String>
Returns Paths contained in this page.
305 306 307 |
# File 'lib/arachni/page.rb', line 305 def paths @cache[:paths] ||= parser ? parser.paths : [] end |
#performer ⇒ Object
Returns Object which performed the #request which lead to this page.
182 183 184 |
# File 'lib/arachni/page.rb', line 182 def performer request.performer end |
#persistent_hash ⇒ Object
441 442 443 |
# File 'lib/arachni/page.rb', line 441 def persistent_hash digest.persistent_hash end |
#platforms ⇒ Platform
Returns Applicable platforms for the page.
311 312 313 |
# File 'lib/arachni/page.rb', line 311 def platforms Platform::Manager[url] end |
#prepare_for_report ⇒ Object
359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 |
# File 'lib/arachni/page.rb', line 359 def prepare_for_report # We want a hard clear, that's why we don't call #clear_cache. @cache.clear # If we're dealing with binary data remove it before storing. if !text? response.body = nil self.body = nil end @cookie_jar.clear if @cookie_jar @dom.digest = nil @dom.skip_states = nil self end |
#query_vars ⇒ Hash
Returns URL query parameters.
260 261 262 |
# File 'lib/arachni/page.rb', line 260 def query_vars @cache[:query_vars] ||= uri_parse_query( url ) end |
#reload_metadata ⇒ Object
469 470 471 472 473 474 475 |
# File 'lib/arachni/page.rb', line 469 def ELEMENTS.each do |type| next if !@cache[type] @cache[type].each { |e| e } end end |
#request ⇒ HTTP::Request
Returns HTTP request.
241 242 243 |
# File 'lib/arachni/page.rb', line 241 def request response.request end |
#scope ⇒ Scope
176 177 178 |
# File 'lib/arachni/page.rb', line 176 def scope @scope = Scope.new( self ) end |
#text? ⇒ Boolean
Returns ‘true` if the body of the page is text-base, `false` otherwise.
411 412 413 414 |
# File 'lib/arachni/page.rb', line 411 def text? return false if !response response.text? end |
#title ⇒ String
Returns Title of the page.
418 419 420 |
# File 'lib/arachni/page.rb', line 418 def title document.css( 'title' ).first.text rescue nil end |
#to_h ⇒ Hash Also known as: to_hash
Returns Converts the page data to a hash.
424 425 426 427 428 429 430 431 432 433 |
# File 'lib/arachni/page.rb', line 424 def to_h skip = [:@document, :@do_not_audit_elements, :@has_custom_elements, :@scope] instance_variables.inject({}) do |h, iv| next h if skip.include? iv h[iv.to_s.gsub( '@', '').to_sym] = try_dup( instance_variable_get( iv ) ) h end.merge(@cache).tap { |h| h.delete :parser } end |
#to_initialization_options ⇒ Object
491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 |
# File 'lib/arachni/page.rb', line 491 def h = {} [:body, :cookie_jar, :element_audit_whitelist, :metadata].each do |m| h[m] = try_dup( instance_variable_get( "@#{m}".to_sym ) ) h.delete( m ) if !h[m] end ELEMENTS.each do |type| next if !@has_custom_elements.include?( type ) h[type] = @cache[type] if !h[type] || h[type].empty? h.delete( type ) next end h[type] = h[type].map { |e| c = e.dup; c.page = nil; c } end h[:response] = response h[:do_not_audit_elements] = @do_not_audit_elements h[:dom] = dom.to_h.keys.inject({}) do |dh, k| dh[k] = try_dup( dom.send( k ) ) dh end h end |
#to_rpc_data ⇒ Hash
Returns Data representing this instance that are suitable the RPC transmission.
523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 |
# File 'lib/arachni/page.rb', line 523 def to_rpc_data data = .my_stringify_keys(false) data['dom'] = dom.to_rpc_data data['element_audit_whitelist'] = element_audit_whitelist.to_a data['response'] = data['response'].to_rpc_data (ELEMENTS - [:headers]).map(&:to_s).each do |e| next if !data[e] data[e] = send(e).map(&:to_rpc_data) end data.delete 'cookie_jar' data end |
#to_s ⇒ Object Also known as: inspect
436 437 438 |
# File 'lib/arachni/page.rb', line 436 def to_s "#<#{self.class}:#{object_id} @url=#{@url.inspect} @dom=#{@dom}>" end |
#update_element_audit_whitelist(list) ⇒ Set
Returns #element_audit_whitelist.
211 212 213 214 215 216 |
# File 'lib/arachni/page.rb', line 211 def update_element_audit_whitelist( list ) [list].flatten.each do |e| @element_audit_whitelist << (e.is_a?( Integer ) ? e : e.coverage_hash ) end end |
#update_metadata ⇒ Object
461 462 463 464 465 466 467 |
# File 'lib/arachni/page.rb', line 461 def ELEMENTS.each do |type| next if !@cache[type] @cache[type].each { |e| e } end end |
#url ⇒ String
Returns URL of the page.
247 248 249 |
# File 'lib/arachni/page.rb', line 247 def url @url ||= @response.url end |