Class: Mechanize::HTTP::Agent

Inherits:
Object
  • Object
show all
Defined in:
lib/mechanize/http/agent.rb

Overview

An HTTP (and local disk access) user agent. This class is an implementation detail and is subject to change at any time.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Agent

Creates a new Mechanize HTTP user agent. The user agent is an implementation detail of mechanize and its API may change at any time.



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
 
# File 'lib/mechanize/http/agent.rb', line 119

def initialize
  @conditional_requests     = true
  @context                  = nil
  @content_encoding_hooks   = []
  @cookie_jar               = Mechanize::CookieJar.new
  @follow_meta_refresh      = false
  @follow_meta_refresh_self = false
  @gzip_enabled             = true
  @history                  = Mechanize::History.new
  @keep_alive               = true
  @max_file_buffer          = 100_000 # 5MB for response bodies
  @open_timeout             = nil
  @post_connect_hooks       = []
  @pre_connect_hooks        = []
  @read_timeout             = nil
  @redirect_ok              = true
  @redirection_limit        = 20
  @request_headers          = {}
  @robots                   = false
  @user_agent               = nil
  @webrobots                = nil

  # HTTP Authentication
  @authenticate_parser  = Mechanize::HTTP::WWWAuthenticateParser.new
  @authenticate_methods = Hash.new do |methods, uri|
    methods[uri] = Hash.new do |realms, auth_scheme|
      realms[auth_scheme] = []
    end
  end
  @digest_auth          = Net::HTTP::DigestAuth.new
  @digest_challenges    = {}
  @password             = nil # HTTP auth password
  @user                 = nil # HTTP auth user
  @domain               = nil # NTLM HTTP domain

  # SSL
  @pass = nil

  @scheme_handlers = Hash.new { |h, scheme|
    h[scheme] = lambda { |link, page|
      raise Mechanize::UnsupportedSchemeError, scheme
    }
  }

  @scheme_handlers['http']      = lambda { |link, page| link }
  @scheme_handlers['https']     = @scheme_handlers['http']
  @scheme_handlers['relative']  = @scheme_handlers['http']
  @scheme_handlers['file']      = @scheme_handlers['http']

  @http = Net::HTTP::Persistent.new 'mechanize'
  @http.idle_timeout = 5
  @http.keep_alive   = 300
end

Instance Attribute Details

#authenticate_methods ⇒ Object (readonly)

:section: HTTP Authentication



46
47
48
 
# File 'lib/mechanize/http/agent.rb', line 46

def authenticate_methods
  @authenticate_methods
end

#conditional_requests ⇒ Object

Disables If-Modified-Since conditional requests (enabled by default)



15
16
17
 
# File 'lib/mechanize/http/agent.rb', line 15

def conditional_requests
  @conditional_requests
end

#content_encoding_hooks ⇒ Object (readonly)

A list of hooks to call to handle the content-encoding of a request.



42
43
44
 
# File 'lib/mechanize/http/agent.rb', line 42

def content_encoding_hooks
  @content_encoding_hooks
end

#context ⇒ Object

The context parses responses into pages



107
108
109
 
# File 'lib/mechanize/http/agent.rb', line 107

def context
  @context
end

#cookie_jar ⇒ Object

The cookies for this agent



98
99
100
 
# File 'lib/mechanize/http/agent.rb', line 98

def cookie_jar
  @cookie_jar
end

#digest_challenges ⇒ Object (readonly)

:nodoc:



47
48
49
 
# File 'lib/mechanize/http/agent.rb', line 47

def digest_challenges
  @digest_challenges
end

#domain ⇒ Object

Returns the value of attribute domain.



50
51
52
 
# File 'lib/mechanize/http/agent.rb', line 50

def domain
  @domain
end

#follow_meta_refresh ⇒ Object

Follow HTML meta refresh and HTTP Refresh. If set to :anywhere meta refresh tags outside of the head element will be followed.



56
57
58
 
# File 'lib/mechanize/http/agent.rb', line 56

def follow_meta_refresh
  @follow_meta_refresh
end

#follow_meta_refresh_self ⇒ Object

Follow an HTML meta refresh that has no "url=" in the content attribute.

Defaults to false to prevent infinite refresh loops.



61
62
63
 
# File 'lib/mechanize/http/agent.rb', line 61

def follow_meta_refresh_self
  @follow_meta_refresh_self
end

#gzip_enabled ⇒ Object

Is gzip compression of requests enabled?



18
19
20
 
# File 'lib/mechanize/http/agent.rb', line 18

def gzip_enabled
  @gzip_enabled
end

#history ⇒ Object

history of requests made



29
30
31
 
# File 'lib/mechanize/http/agent.rb', line 29

def history
  @history
end

#http ⇒ Object (readonly)

:nodoc:



109
110
111
 
# File 'lib/mechanize/http/agent.rb', line 109

def http
  @http
end

#keep_alive ⇒ Object

Set to false to disable HTTP/1.1 keep-alive requests



87
88
89
 
# File 'lib/mechanize/http/agent.rb', line 87

def keep_alive
  @keep_alive
end

#max_file_buffer ⇒ Object

Responses larger than this will be written to a Tempfile instead of stored in memory. Setting this to nil disables creation of Tempfiles.



102
103
104
 
# File 'lib/mechanize/http/agent.rb', line 102

def max_file_buffer
  @max_file_buffer
end

#open_timeout ⇒ Object

Length of time to wait until a connection is opened in seconds



90
91
92
 
# File 'lib/mechanize/http/agent.rb', line 90

def open_timeout
  @open_timeout
end

#pass ⇒ Object

OpenSSL key password



82
83
84
 
# File 'lib/mechanize/http/agent.rb', line 82

def pass
  @pass
end

#password ⇒ Object

Returns the value of attribute password.



49
50
51
 
# File 'lib/mechanize/http/agent.rb', line 49

def password
  @password
end

#post_connect_hooks ⇒ Object (readonly)

A list of hooks to call after retrieving a response. Hooks are called with the agent and the response returned.



35
36
37
 
# File 'lib/mechanize/http/agent.rb', line 35

def post_connect_hooks
  @post_connect_hooks
end

#pre_connect_hooks ⇒ Object (readonly)

A list of hooks to call before making a request. Hooks are called with the agent and the request to be performed.



39
40
41
 
# File 'lib/mechanize/http/agent.rb', line 39

def pre_connect_hooks
  @pre_connect_hooks
end

#read_timeout ⇒ Object

Length of time to attempt to read data from the server



93
94
95
 
# File 'lib/mechanize/http/agent.rb', line 93

def read_timeout
  @read_timeout
end

#redirect_ok ⇒ Object

Controls how this agent deals with redirects. The following values are allowed:

:all, true:: All 3xx redirects are followed (default) :permanent:: Only 301 Moved Permanantly redirects are followed

false

No redirects are followed



69
70
71
 
# File 'lib/mechanize/http/agent.rb', line 69

def redirect_ok
  @redirect_ok
end

#redirection_limit ⇒ Object

Maximum number of redirects to follow



72
73
74
 
# File 'lib/mechanize/http/agent.rb', line 72

def redirection_limit
  @redirection_limit
end

#request_headers ⇒ Object

A hash of request headers to be used for every request



21
22
23
 
# File 'lib/mechanize/http/agent.rb', line 21

def request_headers
  @request_headers
end

#robots ⇒ Object

When true, this agent will consult the site's robots.txt for each access.



77
78
79
 
# File 'lib/mechanize/http/agent.rb', line 77

def robots
  @robots
end

#scheme_handlers ⇒ Object

Handlers for various URI schemes



112
113
114
 
# File 'lib/mechanize/http/agent.rb', line 112

def scheme_handlers
  @scheme_handlers
end

#user ⇒ Object

Returns the value of attribute user.



48
49
50
 
# File 'lib/mechanize/http/agent.rb', line 48

def user
  @user
end

#user_agent ⇒ Object

The User-Agent header to send



24
25
26
 
# File 'lib/mechanize/http/agent.rb', line 24

def user_agent
  @user_agent
end

Instance Method Details

#auto_io(name, read_size, input_io) ⇒ Object

Creates a new output IO by reading input_io in read_size chunks. If the output is over the max_file_buffer size a Tempfile with name is created.

If a block is provided, each chunk of input_io is yielded for further processing.



1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
 
# File 'lib/mechanize/http/agent.rb', line 1044

def auto_io name, read_size, input_io
  out_io = StringIO.new

  out_io.set_encoding Encoding::BINARY if out_io.respond_to? :set_encoding

  until input_io.eof? do
    if StringIO === out_io and use_tempfile? out_io.size then
      new_io = Tempfile.new name
      new_io.unlink
      new_io.binmode

      new_io.write out_io.string
      out_io = new_io
    end

    chunk = input_io.read read_size
    chunk = yield chunk if block_given?

    out_io.write chunk
  end

  out_io.rewind

  out_io
end

#back ⇒ Object

Equivalent to the browser back button. Returns the most recent page visited.



300
301
302
 
# File 'lib/mechanize/http/agent.rb', line 300

def back
  @history.pop
end

#ca_file ⇒ Object

Path to an OpenSSL CA certificate file



935
936
937
 
# File 'lib/mechanize/http/agent.rb', line 935

def ca_file
  @http.ca_file
end

#ca_file=(ca_file) ⇒ Object

Sets the path to an OpenSSL CA certificate file



940
941
942
 
# File 'lib/mechanize/http/agent.rb', line 940

def ca_file= ca_file
  @http.ca_file = ca_file
end

#cert_store ⇒ Object

The SSL certificate store used for validating connections



945
946
947
 
# File 'lib/mechanize/http/agent.rb', line 945

def cert_store
  @http.cert_store
end

#cert_store=(cert_store) ⇒ Object

Sets the SSL certificate store used for validating connections



950
951
952
 
# File 'lib/mechanize/http/agent.rb', line 950

def cert_store= cert_store
  @http.cert_store = cert_store
end

#certificate ⇒ Object

The client X509 certificate



955
956
957
 
# File 'lib/mechanize/http/agent.rb', line 955

def certificate
  @http.certificate
end

#certificate=(certificate) ⇒ Object

Sets the client certificate to given X509 certificate. If a path is given the certificate will be loaded and set.



961
962
963
964
965
966
967
968
969
 
# File 'lib/mechanize/http/agent.rb', line 961

def certificate= certificate
  certificate = if OpenSSL::X509::Certificate === certificate then
                  certificate
                else
                  OpenSSL::X509::Certificate.new File.read certificate
                end

  @http.certificate = certificate
end

#connection_for(uri) ⇒ Object

:section: Request



361
362
363
364
365
366
367
368
 
# File 'lib/mechanize/http/agent.rb', line 361

def connection_for uri
  case uri.scheme.downcase
  when 'http', 'https' then
    return @http
  when 'file' then
    return Mechanize::FileConnection.new
  end
end

#content_encoding_gunzip(body_io) ⇒ Object

Decodes a gzip-encoded body_io. If it cannot be decoded, inflate is tried followed by raising an error.



374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
 
# File 'lib/mechanize/http/agent.rb', line 374

def content_encoding_gunzip body_io
  log.debug('gzip response') if log

  zio = Zlib::GzipReader.new body_io
  out_io = auto_io 'mechanize-gunzip', 16384, zio
  zio.finish

  return out_io
rescue Zlib::Error
  log.error('unable to gunzip response, trying raw inflate') if log

  body_io.rewind
  body_io.read 10

  begin
    return inflate body_io, -Zlib::MAX_WBITS
  rescue Zlib::Error => e
    log.error("unable to gunzip response: #{e}") if log
    raise
  end
ensure
  zio.close if zio and not zio.closed?
  body_io.close unless body_io.closed?
end

#content_encoding_inflate(body_io) ⇒ Object

Decodes a deflate-encoded body_io. If it cannot be decoded, raw inflate is tried followed by raising an error.



403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
 
# File 'lib/mechanize/http/agent.rb', line 403

def content_encoding_inflate body_io
  log.debug('deflate body') if log

  return inflate body_io
rescue Zlib::Error
  log.error('unable to inflate response, trying raw deflate') if log

  body_io.rewind

  begin
    return inflate body_io, -Zlib::MAX_WBITS
  rescue Zlib::Error => e
    log.error("unable to inflate response: #{e}") if log
    raise
  end
ensure
  body_io.close
end

#current_page ⇒ Object

Returns the latest page loaded by the agent



307
308
309
 
# File 'lib/mechanize/http/agent.rb', line 307

def current_page
  @history.last
end

#disable_keep_alive(request) ⇒ Object 



422
423
424
 
# File 'lib/mechanize/http/agent.rb', line 422

def disable_keep_alive request
  request['connection'] = 'close' unless @keep_alive
end

#enable_gzip(request) ⇒ Object 



426
427
428
429
430
431
432
 
# File 'lib/mechanize/http/agent.rb', line 426

def enable_gzip request
  request['accept-encoding'] = if @gzip_enabled
                                 'gzip,deflate,identity'
                               else
                                 'identity'
                               end
end

#fetch(uri, method = :get, headers = {}, params = [], referer = current_page, redirects = 0) ⇒ Object

Retrieves uri and parses it into a page or other object according to PluggableParser. If the URI is an HTTP or HTTPS scheme URI the given HTTP method is used to retrieve it, along with the HTTP headers, request params and HTTP referer.

redirects tracks the number of redirects experienced when retrieving the page. If it is over the redirection_limit an error will be raised.



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
 
# File 'lib/mechanize/http/agent.rb', line 181

def fetch uri, method = :get, headers = {}, params = [],
          referer = current_page, redirects = 0
  referer_uri = referer ? referer.uri : nil

  uri = resolve uri, referer

  uri, params = resolve_parameters uri, method, params

  request = http_request uri, method, params

  connection = connection_for uri

  request_auth             request, uri

  disable_keep_alive       request
  enable_gzip              request

  request_language_charset request
  request_cookies          request, uri
  request_host             request, uri
  request_referer          request, uri, referer_uri
  request_user_agent       request
  request_add_headers      request, headers

  pre_connect              request

  # Consult robots.txt
  if robots && uri.is_a?(URI::HTTP)
    robots_allowed?(uri) or raise Mechanize::RobotsDisallowedError.new(uri)
  end

  # Add If-Modified-Since if page is in history
  page = visited_page(uri)

  if (page = visited_page(uri)) and page.response['Last-Modified']
    request['If-Modified-Since'] = page.response['Last-Modified']
  end if(@conditional_requests)

  # Specify timeouts if given
  connection.open_timeout = @open_timeout if @open_timeout
  connection.read_timeout = @read_timeout if @read_timeout

  request_log request

  response_body_io = nil

  # Send the request
  response = connection.request(uri, request) { |res|
    response_log res

    response_body_io = response_read res, request, uri

    res
  }

  hook_content_encoding response, uri, response_body_io

  response_body_io = response_content_encoding response, response_body_io if
    request.response_body_permitted?

  post_connect uri, response, response_body_io

  page = response_parse response, response_body_io, uri

  response_cookies response, uri, page

  meta = response_follow_meta_refresh response, uri, page, redirects
  return meta if meta

  case response
  when Net::HTTPSuccess
    if robots && page.is_a?(Mechanize::Page)
      page.parser.noindex? and raise Mechanize::RobotsDisallowedError.new(uri)
    end

    page
  when Mechanize::FileResponse
    page
  when Net::HTTPNotModified
    log.debug("Got cached page") if log
    visited_page(uri) || page
  when Net::HTTPRedirection
    response_redirect response, method, page, redirects, referer
  when Net::HTTPUnauthorized
    response_authenticate(response, page, uri, request, headers, params,
                          referer)
  else
    raise Mechanize::ResponseCodeError.new(page), "Unhandled response"
  end
end

#get_meta_refresh(response, uri, page) ⇒ Object

:section: Response



629
630
631
632
633
634
635
636
637
638
639
640
641
642
 
# File 'lib/mechanize/http/agent.rb', line 629

def get_meta_refresh response, uri, page
  return nil unless @follow_meta_refresh

  if page.respond_to?(:meta_refresh) and
     (redirect = page.meta_refresh.first) then
    [redirect.delay, redirect.href] unless
      not @follow_meta_refresh_self and redirect.link_self
  elsif refresh = response['refresh']
    delay, href, link_self = Mechanize::Page::MetaRefresh.parse refresh, uri
    raise Mechanize::Error, 'Invalid refresh http header' unless delay
    [delay.to_f, href] unless
      not @follow_meta_refresh_self and link_self
  end
end

#get_robots(uri) ⇒ Object

:section: Robots



882
883
884
885
886
887
 
# File 'lib/mechanize/http/agent.rb', line 882

def get_robots(uri) # :nodoc:
  fetch(uri).body
rescue Mechanize::ResponseCodeError => e
  return '' if e.response_code == '404'
  raise e
end

#hook_content_encoding(response, uri, response_body_io) ⇒ Object

:section: Hooks



326
327
328
329
330
 
# File 'lib/mechanize/http/agent.rb', line 326

def hook_content_encoding response, uri, response_body_io
  @content_encoding_hooks.each do |hook|
    hook.call self, uri, response, response_body_io
  end
end

#http_request(uri, method, params = nil) ⇒ Object 



434
435
436
437
438
439
440
441
442
443
444
445
446
 
# File 'lib/mechanize/http/agent.rb', line 434

def http_request uri, method, params = nil
  case uri.scheme.downcase
  when 'http', 'https' then
    klass = Net::HTTP.const_get(method.to_s.capitalize)

    request ||= klass.new(uri.request_uri)
    request.body = params.first if params

    request
  when 'file' then
    Mechanize::FileRequest.new uri
  end
end

#idle_timeout ⇒ Object

Reset connections that have not been used in this many seconds



1025
1026
1027
 
# File 'lib/mechanize/http/agent.rb', line 1025

def idle_timeout
  @http.idle_timeout
end

#idle_timeout=(timeout) ⇒ Object

Sets the connection idle timeout for persistent connections



1030
1031
1032
 
# File 'lib/mechanize/http/agent.rb', line 1030

def idle_timeout= timeout
  @http.idle_timeout = timeout
end

#inflate(compressed, window_bits = nil) ⇒ Object 



1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
 
# File 'lib/mechanize/http/agent.rb', line 1070

def inflate compressed, window_bits = nil
  inflate = Zlib::Inflate.new window_bits

  out_io = auto_io 'mechanize-inflate', 1024, compressed do |chunk|
    inflate.inflate chunk
  end

  out_io.write inflate.finish

  out_io
ensure
  inflate.close
end

#log ⇒ Object 



1084
1085
1086
 
# File 'lib/mechanize/http/agent.rb', line 1084

def log
  @context.log
end

#max_history ⇒ Object 



311
312
313
 
# File 'lib/mechanize/http/agent.rb', line 311

def max_history
  @history.max_size
end

#max_history=(length) ⇒ Object 



315
316
317
 
# File 'lib/mechanize/http/agent.rb', line 315

def max_history=(length)
  @history.max_size = length
end

#post_connect(uri, response, body_io) ⇒ Object

Invokes hooks added to post_connect_hooks after a response is returned and the response body is handled.

Yields the context, the uri for the request, the response and the response body.



339
340
341
342
343
344
345
346
347
 
# File 'lib/mechanize/http/agent.rb', line 339

def post_connect uri, response, body_io # :yields: agent, uri, response, body
  @post_connect_hooks.each do |hook|
    begin
      hook.call self, uri, response, body_io.read
    ensure
      body_io.rewind
    end
  end
end

#pre_connect(request) ⇒ Object

Invokes hooks added to pre_connect_hooks before a request is made. Yields the agent and the request that will be performed to each hook.



353
354
355
356
357
 
# File 'lib/mechanize/http/agent.rb', line 353

def pre_connect request # :yields: agent, request
  @pre_connect_hooks.each do |hook|
    hook.call self, request
  end
end

#private_key ⇒ Object

An OpenSSL private key or the path to a private key



972
973
974
 
# File 'lib/mechanize/http/agent.rb', line 972

def private_key
  @http.private_key
end

#private_key=(private_key) ⇒ Object

Sets the client's private key



977
978
979
980
981
982
983
984
985
 
# File 'lib/mechanize/http/agent.rb', line 977

def private_key= private_key
  private_key = if OpenSSL::PKey::PKey === private_key then
                  private_key
                else
                  OpenSSL::PKey::RSA.new File.read(private_key), @pass
                end

  @http.private_key = private_key
end

#proxy_uri ⇒ Object

URI for a proxy connection



274
275
276
 
# File 'lib/mechanize/http/agent.rb', line 274

def proxy_uri
  @http.proxy_uri
end

#request_add_headers(request, headers = {}) ⇒ Object 



448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
 
# File 'lib/mechanize/http/agent.rb', line 448

def request_add_headers request, headers = {}
  @request_headers.each do |k,v|
    request[k] = v
  end

  headers.each do |field, value|
    case field
    when :etag              then request["ETag"] = value
    when :if_modified_since then request["If-Modified-Since"] = value
    when Symbol then
      raise ArgumentError, "unknown header symbol #{field}"
    else
      request[field] = value
    end
  end
end

#request_auth(request, uri) ⇒ Object 



465
466
467
468
469
470
471
472
473
474
475
476
 
# File 'lib/mechanize/http/agent.rb', line 465

def request_auth request, uri
  base_uri = uri + '/'
  schemes = @authenticate_methods[base_uri]

  if realm = schemes[:digest].find { |r| r.uri == base_uri } then
    request_auth_digest request, uri, realm, base_uri, false
  elsif realm = schemes[:iis_digest].find { |r| r.uri == base_uri } then
    request_auth_digest request, uri, realm, base_uri, true
  elsif schemes[:basic].find { |r| r.uri == base_uri } then
    request.basic_auth @user, @password
  end
end

#request_auth_digest(request, uri, realm, base_uri, iis) ⇒ Object 



478
479
480
481
482
483
484
485
486
 
# File 'lib/mechanize/http/agent.rb', line 478

def request_auth_digest request, uri, realm, base_uri, iis
  challenge = @digest_challenges[realm]

  uri.user = @user
  uri.password = @password

  auth = @digest_auth.auth_header uri, challenge.to_s, request.method, iis
  request['Authorization'] = auth
end

#request_cookies(request, uri) ⇒ Object 



488
489
490
491
492
493
494
495
496
 
# File 'lib/mechanize/http/agent.rb', line 488

def request_cookies request, uri
  return if @cookie_jar.empty? uri

  cookies = @cookie_jar.cookies uri

  return if cookies.empty?

  request.add_field 'Cookie', cookies.join('; ')
end

#request_host(request, uri) ⇒ Object 



498
499
500
501
502
503
 
# File 'lib/mechanize/http/agent.rb', line 498

def request_host request, uri
  port = [80, 443].include?(uri.port.to_i) ? nil : uri.port
  host = uri.host

  request['Host'] = [host, port].compact.join ':'
end

#request_language_charset(request) ⇒ Object 



505
506
507
508
 
# File 'lib/mechanize/http/agent.rb', line 505

def request_language_charset request
  request['accept-charset']  = 'ISO-8859-1,utf-8;q=0.7,*;q=0.7'
  request['accept-language'] = 'en-us,en;q=0.5'
end

#request_log(request) ⇒ Object

Log specified headers for the request



511
512
513
514
515
516
517
518
519
 
# File 'lib/mechanize/http/agent.rb', line 511

def request_log request
  return unless log

  log.info("#{request.class}: #{request.path}")

  request.each_header do |k, v|
    log.debug("request-header: #{k} => #{v}")
  end
end

#request_referer(request, uri, referer) ⇒ Object

Sets a Referer header. Fragment part is removed as demanded by RFC 2616 14.36, and user information part is removed just like major browsers do.



524
525
526
527
528
529
530
531
532
533
 
# File 'lib/mechanize/http/agent.rb', line 524

def request_referer request, uri, referer
  return unless referer
  return if 'https' == referer.scheme.downcase and
            'https' != uri.scheme.downcase
  if referer.fragment || referer.user || referer.password
    referer = referer.dup
    referer.fragment = referer.user = referer.password = nil
  end
  request['Referer'] = referer
end

#request_user_agent(request) ⇒ Object 



535
536
537
 
# File 'lib/mechanize/http/agent.rb', line 535

def request_user_agent request
  request['User-Agent'] = @user_agent if @user_agent
end

#resolve(uri, referer = current_page) ⇒ Object 



539
540
541
542
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
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
 
# File 'lib/mechanize/http/agent.rb', line 539

def resolve(uri, referer = current_page)
  referer_uri = referer && referer.uri
  if uri.is_a?(URI)
    uri = uri.dup
  elsif uri.nil?
    if referer_uri
      return referer_uri
    end
    raise ArgumentError, "absolute URL needed (not nil)"
  else
    url = uri.to_s.strip
    if url.empty?
      if referer_uri
        return referer_uri.dup.tap { |u| u.fragment = nil }
      end
      raise ArgumentError, "absolute URL needed (not #{uri.inspect})"
    end

    url.gsub!(/[^#{0.chr}-#{126.chr}]/o) { |match|
      if RUBY_VERSION >= "1.9.0"
        Mechanize::Util.uri_escape(match)
      else
        sprintf('%%%X', match.unpack($KCODE == 'UTF8' ? 'U' : 'C')[0])
      end
    }

    escaped_url = Mechanize::Util.html_unescape(
      url.split(/((?:%[0-9A-Fa-f]{2})+|#)/).each_slice(2).map { |x, y|
        "#{WEBrick::HTTPUtils.escape(x)}#{y}"
      }.join('')
    )

    begin
      uri = URI.parse(escaped_url)
    rescue
      uri = URI.parse(WEBrick::HTTPUtils.escape(escaped_url))
    end
  end

  scheme = uri.relative? ? 'relative' : uri.scheme.downcase
  uri = @scheme_handlers[scheme].call(uri, referer)

  if referer_uri
    if uri.path.length == 0 && uri.relative?
      uri.path = referer_uri.path
    end
  end

  uri.path = '/' if uri.path.length == 0

  if uri.relative?
    raise ArgumentError, "absolute URL needed (not #{uri})" unless
      referer_uri

    if referer.respond_to?(:bases) && referer.parser &&
        (lbase = referer.bases.last) && lbase.uri && lbase.uri.absolute?
      base = lbase
    else
      base = nil
    end

    uri = referer_uri + (base ? base.uri : referer_uri) + uri
    # Strip initial "/.." bits from the path
    uri.path.sub!(/^(\/\.\.)+(?=\/)/, '')
  end

  unless ['http', 'https', 'file'].include?(uri.scheme.downcase)
    raise ArgumentError, "unsupported scheme: #{uri.scheme}"
  end

  uri
end

#resolve_parameters(uri, method, parameters) ⇒ Object 



612
613
614
615
616
617
618
619
620
621
622
623
624
625
 
# File 'lib/mechanize/http/agent.rb', line 612

def resolve_parameters uri, method, parameters
  case method
  when :head, :get, :delete, :trace then
    if parameters and parameters.length > 0
      uri.query ||= ''
      uri.query << '&' if uri.query.length > 0
      uri.query << Mechanize::Util.build_query_string(parameters)
    end

    return uri, nil
  end

  return uri, parameters
end

#response_authenticate(response, page, uri, request, headers, params, referer) ⇒ Object

Raises:



644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
 
# File 'lib/mechanize/http/agent.rb', line 644

def response_authenticate(response, page, uri, request, headers, params,
                          referer)
  raise Mechanize::UnauthorizedError, page unless @user || @password

  www_authenticate = response['www-authenticate']

  raise Mechanize::UnauthorizedError, page unless www_authenticate

  challenges = @authenticate_parser.parse www_authenticate

  if challenge = challenges.find { |c| c.scheme =~ /^Digest$/i } then
    realm = challenge.realm uri

    auth_scheme = if response['server'] =~ /Microsoft-IIS/ then
                    :iis_digest
                  else
                    :digest
                  end

    existing_realms = @authenticate_methods[realm.uri][auth_scheme]

    raise Mechanize::UnauthorizedError, page if
      existing_realms.include? realm

    existing_realms << realm
    @digest_challenges[realm] = challenge
  elsif challenge = challenges.find { |c| c.scheme == 'NTLM' } then
    existing_realms = @authenticate_methods[uri + '/'][:ntlm]

    raise Mechanize::UnauthorizedError, page if
      existing_realms.include?(realm) and not challenge.params

    existing_realms << realm

    if challenge.params then
      type_2 = Net::NTLM::Message.decode64 challenge.params

      type_3 = type_2.response({ :user => @user, :password => @password, :domain => @domain },
                               { :ntlmv2 => true }).encode64

      headers['Authorization'] = "NTLM #{type_3}"
    else
      type_1 = Net::NTLM::Message::Type1.new.encode64
      headers['Authorization'] = "NTLM #{type_1}"
    end
  elsif challenge = challenges.find { |c| c.scheme == 'Basic' } then
    realm = challenge.realm uri

    existing_realms = @authenticate_methods[realm.uri][:basic]

    raise Mechanize::UnauthorizedError, page if
      existing_realms.include? realm

    existing_realms << realm
  else
    raise Mechanize::UnauthorizedError, page
  end

  fetch uri, request.method.downcase.to_sym, headers, params, referer
end

#response_content_encoding(response, body_io) ⇒ Object 



705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
 
# File 'lib/mechanize/http/agent.rb', line 705

def response_content_encoding response, body_io
  length = response.content_length ||
    case body_io
    when Tempfile, IO then
      body_io.stat.size
    else
      body_io.length
    end

  return body_io if length.zero?

  out_io = case response['Content-Encoding']
           when nil, 'none', '7bit' then
             body_io
           when 'deflate' then
             content_encoding_inflate body_io
           when 'gzip', 'x-gzip' then
             content_encoding_gunzip body_io
           else
             raise Mechanize::Error,
               "unsupported content-encoding: #{response['Content-Encoding']}"
           end

  out_io.flush
  out_io.rewind

  out_io
rescue Zlib::Error => e
  message = "error handling content-encoding #{response['Content-Encoding']}:"
  message << " #{e.message} (#{e.class})"
  raise Mechanize::Error, message
ensure
  begin
    if Tempfile === body_io and
       (StringIO === out_io or out_io.path != body_io.path) then
      body_io.close! 
    end
  rescue IOError
    # HACK ruby 1.8 raises IOError when closing the stream
  end
end

#response_cookies(response, uri, page) ⇒ Object 



747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
 
# File 'lib/mechanize/http/agent.rb', line 747

def response_cookies response, uri, page
  if Mechanize::Page === page and page.body =~ /Set-Cookie/n
    page.search('//head/meta[@http-equiv="Set-Cookie"]').each do |meta|
      save_cookies(uri, meta['content'])
    end
  end

  header_cookies = response.get_fields 'Set-Cookie'

  return unless header_cookies

  header_cookies.each do |set_cookie|
    save_cookies(uri, set_cookie)
  end
end

#response_follow_meta_refresh(response, uri, page, redirects) ⇒ Object

Raises:



774
775
776
777
778
779
780
781
782
783
784
785
786
 
# File 'lib/mechanize/http/agent.rb', line 774

def response_follow_meta_refresh response, uri, page, redirects
  delay, new_url = get_meta_refresh(response, uri, page)
  return nil unless delay
  new_url = new_url ? resolve(new_url, page) : uri

  raise Mechanize::RedirectLimitReachedError.new(page, redirects) if
    redirects + 1 > @redirection_limit

  sleep delay
  @history.push(page, page.uri)
  fetch new_url, :get, {}, [],
        Mechanize::Page.new, redirects
end

#response_log(response) ⇒ Object 



788
789
790
791
792
793
794
795
796
797
 
# File 'lib/mechanize/http/agent.rb', line 788

def response_log response
  return unless log

  log.info("status: #{response.class} #{response.http_version} " \
           "#{response.code} #{response.message}")

  response.each_header do |k, v|
    log.debug("response-header: #{k} => #{v}")
  end
end

#response_parse(response, body_io, uri) ⇒ Object 



799
800
801
 
# File 'lib/mechanize/http/agent.rb', line 799

def response_parse response, body_io, uri
  @context.parse uri, response, body_io
end

#response_read(response, request, uri) ⇒ Object

Raises:



803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
 
# File 'lib/mechanize/http/agent.rb', line 803

def response_read response, request, uri
  content_length = response.content_length

  if use_tempfile? content_length then
    body_io = Tempfile.new 'mechanize-raw'
    body_io.unlink
    body_io.binmode if defined? body_io.binmode
  else
    body_io = StringIO.new
  end

  body_io.set_encoding Encoding::BINARY if body_io.respond_to? :set_encoding
  total = 0

  begin
    response.read_body { |part|
      total += part.length

      if StringIO === body_io and use_tempfile? total then
        new_io = Tempfile.new 'mechanize-raw'
        new_io.unlink
        new_io.binmode

        new_io.write body_io.string

        body_io = new_io
      end

      body_io.write(part)
      log.debug("Read #{part.length} bytes (#{total} total)") if log
    }
  rescue Net::HTTP::Persistent::Error => e
    body_io.rewind
    raise Mechanize::ResponseReadError.new(e, response, body_io, uri,
                                           @context)
  end

  body_io.flush
  body_io.rewind

  raise Mechanize::ResponseCodeError, response if
    Net::HTTPUnknownResponse === response

  content_length = response.content_length

  unless Net::HTTP::Head === request or Net::HTTPRedirection === response then
    raise EOFError, "Content-Length (#{content_length}) does not match " \
                    "response body length (#{body_io.length})" if
      content_length and content_length != body_io.length
  end

  body_io
end

#response_redirect(response, method, page, redirects, referer = current_page) ⇒ Object

Raises:



857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
 
# File 'lib/mechanize/http/agent.rb', line 857

def response_redirect response, method, page, redirects, referer = current_page
  case @redirect_ok
  when true, :all
    # shortcut
  when false, nil
    return page
  when :permanent
    return page unless Net::HTTPMovedPermanently === response
  end

  log.info("follow redirect to: #{response['Location']}") if log

  raise Mechanize::RedirectLimitReachedError.new(page, redirects) if
    redirects + 1 > @redirection_limit

  redirect_method = method == :head ? :head : :get

  @history.push(page, page.uri)
  new_uri = resolve response['Location'].to_s, page

  fetch new_uri, redirect_method, {}, [], referer, redirects + 1
end

#retry_change_requests ⇒ Object

Retry non-idempotent requests?



279
280
281
 
# File 'lib/mechanize/http/agent.rb', line 279

def retry_change_requests
  @http.retry_change_requests
end

#retry_change_requests=(retri) ⇒ Object

Retry non-idempotent requests



285
286
287
 
# File 'lib/mechanize/http/agent.rb', line 285

def retry_change_requests= retri
  @http.retry_change_requests = retri
end

#robots_allowed?(uri) ⇒ Boolean

Tests if this agent is allowed to access url, consulting the site's robots.txt.

Returns:

  • (Boolean) 


899
900
901
902
903
 
# File 'lib/mechanize/http/agent.rb', line 899

def robots_allowed? uri
  return true if uri.request_uri == '/robots.txt'

  webrobots.allowed? uri
end

#robots_disallowed?(url) ⇒ Boolean

Opposite of robots_allowed?

Returns:

  • (Boolean) 


907
908
909
 
# File 'lib/mechanize/http/agent.rb', line 907

def robots_disallowed? url
  !robots_allowed? url
end

#robots_error(url) ⇒ Object

Returns an error object if there is an error in fetching or parsing robots.txt of the site url.



913
914
915
 
# File 'lib/mechanize/http/agent.rb', line 913

def robots_error(url)
  webrobots.error(url)
end

#robots_error!(url) ⇒ Object

Raises the error if there is an error in fetching or parsing robots.txt of the site url.



919
920
921
 
# File 'lib/mechanize/http/agent.rb', line 919

def robots_error!(url)
  webrobots.error!(url)
end

#robots_reset(url) ⇒ Object

Removes robots.txt cache for the site url.



924
925
926
 
# File 'lib/mechanize/http/agent.rb', line 924

def robots_reset(url)
  webrobots.reset(url)
end

#save_cookies(uri, set_cookie) ⇒ Object 



763
764
765
766
767
768
769
770
771
772
 
# File 'lib/mechanize/http/agent.rb', line 763

def save_cookies(uri, set_cookie)
  log = log()	 # reduce method calls
  Mechanize::Cookie.parse(uri, set_cookie, log) { |c|
    if @cookie_jar.add(uri, c)
      log.debug("saved cookie: #{c}") if log
    else
      log.debug("rejected cookie: #{c}") if log
    end
  }
end

#set_proxy(addr, port, user = nil, pass = nil) ⇒ Object

Sets the proxy address, port, user, and password addr should be a host, with no "http://&quot;, port may be a port number, service name or port number string.



1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
 
# File 'lib/mechanize/http/agent.rb', line 1093

def set_proxy addr, port, user = nil, pass = nil
  unless addr and port then
    @http.proxy = nil

    return
  end

  unless Integer === port then
    begin
      port = Socket.getservbyname port
    rescue SocketError
      begin
        port = Integer port
      rescue ArgumentError
        raise ArgumentError, "invalid value for port: #{port.inspect}"
      end
    end
  end

  proxy_uri = URI "http://#{addr}"
  proxy_uri.port = port
  proxy_uri.user     = user if user
  proxy_uri.password = pass if pass

  @http.proxy = proxy_uri
end

#ssl_version ⇒ Object

SSL version to use



988
989
990
 
# File 'lib/mechanize/http/agent.rb', line 988

def ssl_version
  @http.ssl_version
end

#ssl_version=(ssl_version) ⇒ Object

Sets the SSL version to use



993
994
995
 
# File 'lib/mechanize/http/agent.rb', line 993

def ssl_version= ssl_version
  @http.ssl_version = ssl_version
end

#use_tempfile?(size) ⇒ Boolean

Returns:

  • (Boolean) 


1120
1121
1122
1123
1124
1125
 
# File 'lib/mechanize/http/agent.rb', line 1120

def use_tempfile? size
  return false unless @max_file_buffer
  return false unless size

  size >= @max_file_buffer
end

#verify_callback ⇒ Object

A callback for additional certificate verification. See OpenSSL::SSL::SSLContext#verify_callback

The callback can be used for debugging or to ignore errors by always returning true. Specifying nil uses the default method that was valid when the SSLContext was created



1003
1004
1005
 
# File 'lib/mechanize/http/agent.rb', line 1003

def verify_callback
  @http.verify_callback
end

#verify_callback=(verify_callback) ⇒ Object

Sets the certificate verify callback



1008
1009
1010
 
# File 'lib/mechanize/http/agent.rb', line 1008

def verify_callback= verify_callback
  @http.verify_callback = verify_callback
end

#verify_mode ⇒ Object

How to verify SSL connections. Defaults to VERIFY_PEER



1013
1014
1015
 
# File 'lib/mechanize/http/agent.rb', line 1013

def verify_mode
  @http.verify_mode
end

#verify_mode=(verify_mode) ⇒ Object

Sets the mode for verifying SSL connections



1018
1019
1020
 
# File 'lib/mechanize/http/agent.rb', line 1018

def verify_mode= verify_mode
  @http.verify_mode = verify_mode
end

#visited_page(url) ⇒ Object

Returns a visited page for the url passed in, otherwise nil



320
321
322
 
# File 'lib/mechanize/http/agent.rb', line 320

def visited_page url
  @history.visited_page resolve url
end

#webrobots ⇒ Object 



928
929
930
 
# File 'lib/mechanize/http/agent.rb', line 928

def webrobots
  @webrobots ||= WebRobots.new(@user_agent, :http_get => method(:get_robots))
end