/usr/lib/ruby/vendor_ruby/mechanize/page.rb is in ruby-mechanize 2.7.2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 | ##
# This class encapsulates an HTML page. If Mechanize finds a content
# type of 'text/html', this class will be instantiated and returned.
#
# Example:
#
# require 'mechanize'
#
# agent = Mechanize.new
# agent.get('http://google.com/').class # => Mechanize::Page
class Mechanize::Page < Mechanize::File
extend Forwardable
extend Mechanize::ElementMatcher
DEFAULT_RESPONSE = {
'content-type' => 'text/html',
}.freeze
attr_accessor :mech
##
# Possible encodings for this page based on HTTP headers and meta elements
attr_reader :encodings
def initialize(uri=nil, response=nil, body=nil, code=nil, mech=nil)
response ||= DEFAULT_RESPONSE
@meta_content_type = nil
@encoding = nil
@encodings = [nil]
raise 'no' if mech and not Mechanize === mech
@mech = mech
reset
@encodings << Mechanize::Util.detect_charset(body) if body
@encodings.concat self.class.response_header_charset(response)
if body
# Force the encoding to be 8BIT so we can perform regular expressions.
# We'll set it to the detected encoding later
body.force_encoding 'ASCII-8BIT' if body.respond_to? :force_encoding
@encodings.concat self.class.meta_charset body
meta_content_type = self.class.meta_content_type body
@meta_content_type = meta_content_type if meta_content_type
end
@encodings << mech.default_encoding if mech and mech.default_encoding
super uri, response, body, code
end
def title
@title ||=
if doc = parser
title = doc.search('title').inner_text
title.empty? ? nil : title
end
end
def response_header_charset
self.class.response_header_charset(response)
end
def meta_charset
self.class.meta_charset(body)
end
def detected_encoding
Mechanize::Util.detect_charset(body)
end
def encoding=(encoding)
reset
@encoding = encoding
if @parser
parser_encoding = @parser.encoding
if parser_encoding && encoding && parser_encoding.casecmp(encoding) != 0
# lazy reinitialize the parser with the new encoding
@parser = nil
end
end
encoding
end
def encoding
parser.respond_to?(:encoding) ? parser.encoding : nil
end
# Return whether parser result has errors related to encoding or not.
# false indicates just parser has no encoding errors, not encoding is vaild.
def encoding_error?(parser=nil)
parser = self.parser unless parser
return false if parser.errors.empty?
parser.errors.any? do |error|
error.message =~ /(indicate\ encoding)|
(Invalid\ char)|
(input\ conversion\ failed)/x
end
end
def parser
return @parser if @parser
return nil unless @body
if @encoding then
@parser = @mech.html_parser.parse html_body, nil, @encoding
elsif mech.force_default_encoding then
@parser = @mech.html_parser.parse html_body, nil, @mech.default_encoding
else
@encodings.reverse_each do |encoding|
@parser = @mech.html_parser.parse html_body, nil, encoding
break unless encoding_error? @parser
end
end
@parser
end
alias :root :parser
def pretty_print(q) # :nodoc:
q.object_group(self) {
q.breakable
q.group(1, '{url', '}') {q.breakable; q.pp uri }
q.breakable
q.group(1, '{meta_refresh', '}') {
meta_refresh.each { |link| q.breakable; q.pp link }
}
q.breakable
q.group(1, '{title', '}') { q.breakable; q.pp title }
q.breakable
q.group(1, '{iframes', '}') {
iframes.each { |link| q.breakable; q.pp link }
}
q.breakable
q.group(1, '{frames', '}') {
frames.each { |link| q.breakable; q.pp link }
}
q.breakable
q.group(1, '{links', '}') {
links.each { |link| q.breakable; q.pp link }
}
q.breakable
q.group(1, '{forms', '}') {
forms.each { |form| q.breakable; q.pp form }
}
}
end
alias inspect pretty_inspect # :nodoc:
def reset
@bases = nil
@forms = nil
@frames = nil
@iframes = nil
@links = nil
@labels = nil
@labels_hash = nil
@meta_refresh = nil
@parser = nil
@title = nil
end
# Return the canonical URI for the page if there is a link tag
# with href="canonical".
def canonical_uri
link = at('link[@rel="canonical"][@href]')
return unless link
href = link['href']
URI href
rescue URI::InvalidURIError
URI Mechanize::Util.uri_escape href
end
# Get the content type
def content_type
@meta_content_type || response['content-type']
end
##
# :method: search
#
# Search for +paths+ in the page using Nokogiri's #search. The +paths+ can
# be XPath or CSS and an optional Hash of namespaces may be appended.
#
# See Nokogiri::XML::Node#search for further details.
def_delegator :parser, :search, :search
alias / search
##
# :method: at
#
# Search through the page for +path+ under +namespace+ using Nokogiri's #at.
# The +path+ may be either a CSS or XPath expression.
#
# See also Nokogiri::XML::Node#at
def_delegator :parser, :at, :at
##
# :method: form_with
#
# :call-seq:
# form_with(criteria)
#
# Find a single form matching +criteria+.
# Example:
# page.form_with(:action => '/post/login.php') do |f|
# ...
# end
##
# :method: forms_with
#
# :call-seq: forms_with(criteria)
#
# Find all forms form matching +criteria+.
# Example:
# page.forms_with(:action => '/post/login.php').each do |f|
# ...
# end
elements_with :form
##
# :method: link_with
#
# :call-seq: link_with(criteria)
#
# Find a single link matching +criteria+.
# Example:
# page.link_with(:href => /foo/).click
##
# :method: links_with
#
# :call-seq:
# links_with(criteria)
#
# Find all links matching +criteria+.
# Example:
# page.links_with(:href => /foo/).each do |link|
# puts link.href
# end
elements_with :link
##
# :method: base_with
#
# :call-seq: base_with(criteria)
#
# Find a single base tag matching +criteria+.
# Example:
# page.base_with(:href => /foo/).click
##
# :method: bases_with
#
# :call-seq: bases_with(criteria)
#
# Find all base tags matching +criteria+.
# Example:
# page.bases_with(:href => /foo/).each do |base|
# puts base.href
# end
elements_with :base
##
# :method: frame_with
#
# :call-seq: frame_with(criteria)
#
# Find a single frame tag matching +criteria+.
# Example:
# page.frame_with(:src => /foo/).click
##
# :method: frames_with
#
# :call-seq: frames_with(criteria)
#
# Find all frame tags matching +criteria+.
# Example:
# page.frames_with(:src => /foo/).each do |frame|
# p frame.src
# end
elements_with :frame
##
# :method: iframe_with
#
# :call-seq: iframe_with(criteria)
#
# Find a single iframe tag matching +criteria+.
# Example:
# page.iframe_with(:src => /foo/).click
##
# :method: iframes_with
#
# :call-seq: iframes_with(criteria)
#
# Find all iframe tags matching +criteria+.
# Example:
# page.iframes_with(:src => /foo/).each do |iframe|
# p iframe.src
# end
elements_with :iframe
##
# :method: image_with
#
# :call-seq: image_with(criteria)
#
# Find a single image matching +criteria+.
# Example:
# page.image_with(:alt => /main/).fetch.save
##
# :method: images_with
#
# :call-seq: images_with(criteria)
#
# Find all images matching +criteria+.
# Example:
# page.images_with(:src => /jpg\Z/).each do |img|
# img.fetch.save
# end
elements_with :image
##
# Return a list of all link and area tags
def links
@links ||= %w{ a area }.map do |tag|
search(tag).map do |node|
Link.new(node, @mech, self)
end
end.flatten
end
##
# Return a list of all form tags
def forms
@forms ||= search('form').map do |html_form|
form = Mechanize::Form.new(html_form, @mech, self)
form.action ||= @uri.to_s
form
end
end
##
# Return a list of all meta refresh elements
def meta_refresh
query = @mech.follow_meta_refresh == :anywhere ? 'meta' : 'head > meta'
@meta_refresh ||= search(query).map do |node|
MetaRefresh.from_node node, self
end.compact
end
##
# Return a list of all base tags
def bases
@bases ||=
search('base').map { |node| Base.new(node, @mech, self) }
end
##
# Return a list of all frame tags
def frames
@frames ||=
search('frame').map { |node| Frame.new(node, @mech, self) }
end
##
# Return a list of all iframe tags
def iframes
@iframes ||=
search('iframe').map { |node| Frame.new(node, @mech, self) }
end
##
# Return a list of all img tags
def images
@images ||=
search('img').map { |node| Image.new(node, self) }
end
def image_urls
@image_urls ||= images.map(&:url).uniq
end
##
# Return a list of all label tags
def labels
@labels ||=
search('label').map { |node| Label.new(node, self) }
end
def labels_hash
unless @labels_hash
hash = {}
labels.each do |label|
hash[label.node['for']] = label if label.for
end
@labels_hash = hash
end
return @labels_hash
end
class << self
def charset content_type
charset = content_type[/;(?:\s*,)?\s*charset\s*=\s*([^()<>@,;:\\\"\/\[\]?={}\s]+)/i, 1]
return nil if charset == 'none'
charset
end
alias charset_from_content_type charset
end
def self.response_header_charset response
charsets = []
response.each do |header, value|
next unless header == 'content-type'
next unless value =~ /charset/i
charsets << charset(value)
end
charsets
end
##
# Retrieves all charsets from +meta+ tags in +body+
def self.meta_charset body
# HACK use .map
body.scan(/<meta .*?>/i).map do |meta|
if meta =~ /charset\s*=\s*(["'])?\s*(.+)\s*\1/i then
$2
elsif meta =~ /http-equiv\s*=\s*(["'])?content-type\1/i then
meta =~ /content\s*=\s*(["'])?(.*?)\1/i
m_charset = charset $2 if $2
m_charset if m_charset
end
end.compact
end
##
# Retrieves the last <tt>content-type</tt> set by a +meta+ tag in +body+
def self.meta_content_type body
body.scan(/<meta .*?>/i).reverse.map do |meta|
if meta =~ /http-equiv\s*=\s*(["'])?content-type\1/i then
meta =~ /content=(["'])?(.*?)\1/i
return $2
end
end
nil
end
private
def html_body
if @body
@body.empty? ? '<html></html>' : @body
else
''
end
end
end
require 'mechanize/headers'
require 'mechanize/page/image'
require 'mechanize/page/label'
require 'mechanize/page/link'
require 'mechanize/page/base'
require 'mechanize/page/frame'
require 'mechanize/page/meta_refresh'
|