ronin-web 1.0.2 → 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/ruby.yml +3 -2
- data/.gitignore +1 -0
- data/.rubocop.yml +5 -0
- data/.ruby-version +1 -1
- data/ChangeLog.md +46 -1
- data/Gemfile +25 -12
- data/README.md +257 -51
- data/Rakefile +9 -0
- data/data/completions/ronin-web +203 -0
- data/gemspec.yml +18 -5
- data/lib/ronin/web/cli/browser_options.rb +92 -0
- data/lib/ronin/web/cli/browser_shell.rb +448 -0
- data/lib/ronin/web/cli/command.rb +1 -1
- data/lib/ronin/web/cli/commands/browser.rb +373 -0
- data/lib/ronin/web/cli/commands/completion.rb +63 -0
- data/lib/ronin/web/cli/commands/diff.rb +60 -8
- data/lib/ronin/web/cli/commands/html.rb +21 -33
- data/lib/ronin/web/cli/commands/irb.rb +1 -1
- data/lib/ronin/web/cli/commands/new/{webapp.rb → app.rb} +8 -8
- data/lib/ronin/web/cli/commands/new/nokogiri.rb +4 -4
- data/lib/ronin/web/cli/commands/new/server.rb +1 -1
- data/lib/ronin/web/cli/commands/new/spider.rb +1 -1
- data/lib/ronin/web/cli/commands/new.rb +5 -3
- data/lib/ronin/web/cli/commands/reverse_proxy.rb +1 -1
- data/lib/ronin/web/cli/commands/screenshot.rb +186 -0
- data/lib/ronin/web/cli/commands/server.rb +1 -1
- data/lib/ronin/web/cli/commands/session_cookie.rb +265 -0
- data/lib/ronin/web/cli/commands/spider.rb +61 -467
- data/lib/ronin/web/cli/commands/user_agent.rb +177 -0
- data/lib/ronin/web/cli/commands/vulns.rb +463 -0
- data/lib/ronin/web/cli/commands/wordlist.rb +484 -0
- data/lib/ronin/web/cli/commands/xml.rb +149 -0
- data/lib/ronin/web/cli/js_shell.rb +69 -0
- data/lib/ronin/web/cli/ruby_shell.rb +1 -1
- data/lib/ronin/web/cli/spider_options.rb +919 -0
- data/lib/ronin/web/cli.rb +3 -1
- data/lib/ronin/web/html.rb +1 -1
- data/lib/ronin/web/root.rb +1 -1
- data/lib/ronin/web/version.rb +2 -2
- data/lib/ronin/web/xml.rb +1 -1
- data/lib/ronin/web.rb +4 -364
- data/man/ronin-web-browser.1 +92 -0
- data/man/ronin-web-browser.1.md +96 -0
- data/man/ronin-web-completion.1 +76 -0
- data/man/ronin-web-completion.1.md +78 -0
- data/man/ronin-web-diff.1 +14 -21
- data/man/ronin-web-diff.1.md +13 -6
- data/man/ronin-web-html.1 +30 -46
- data/man/ronin-web-html.1.md +27 -17
- data/man/ronin-web-irb.1 +9 -16
- data/man/ronin-web-irb.1.md +6 -2
- data/man/ronin-web-new-app.1.md +39 -0
- data/man/ronin-web-new-nokogiri.1 +9 -20
- data/man/ronin-web-new-nokogiri.1.md +5 -5
- data/man/ronin-web-new-server.1 +11 -23
- data/man/ronin-web-new-server.1.md +5 -5
- data/man/ronin-web-new-spider.1 +44 -88
- data/man/ronin-web-new-spider.1.md +37 -37
- data/man/ronin-web-new.1 +18 -30
- data/man/ronin-web-new.1.md +15 -11
- data/man/ronin-web-reverse-proxy.1 +33 -38
- data/man/ronin-web-reverse-proxy.1.md +20 -14
- data/man/ronin-web-screenshot.1 +56 -0
- data/man/ronin-web-screenshot.1.md +56 -0
- data/man/ronin-web-server.1 +15 -29
- data/man/ronin-web-server.1.md +13 -9
- data/man/ronin-web-session-cookie.1 +38 -0
- data/man/ronin-web-session-cookie.1.md +41 -0
- data/man/ronin-web-spider.1 +121 -130
- data/man/ronin-web-spider.1.md +115 -66
- data/man/ronin-web-user-agent.1 +44 -0
- data/man/ronin-web-user-agent.1.md +46 -0
- data/man/ronin-web-vulns.1 +175 -0
- data/man/ronin-web-vulns.1.md +177 -0
- data/man/ronin-web-wordlist.1 +258 -0
- data/man/ronin-web-wordlist.1.md +263 -0
- data/man/ronin-web-xml.1 +43 -0
- data/man/ronin-web-xml.1.md +46 -0
- data/man/ronin-web.1 +67 -18
- data/man/ronin-web.1.md +55 -4
- data/scripts/setup +58 -0
- metadata +121 -30
- data/lib/ronin/web/mechanize.rb +0 -84
- data/man/ronin-web-new-webapp.1.md +0 -39
- /data/data/new/{webapp → app}/.gitignore +0 -0
- /data/data/new/{webapp → app}/.ruby-version.erb +0 -0
- /data/data/new/{webapp → app}/Dockerfile.erb +0 -0
- /data/data/new/{webapp → app}/Gemfile +0 -0
- /data/data/new/{webapp → app}/app.rb.erb +0 -0
- /data/data/new/{webapp → app}/config.ru +0 -0
- /data/data/new/{webapp → app}/docker-compose.yml.erb +0 -0
@@ -0,0 +1,919 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
#
|
3
|
+
# ronin-web - A collection of useful web helper methods and commands.
|
4
|
+
#
|
5
|
+
# Copyright (c) 2006-2024 Hal Brodigan (postmodern.mod3 at gmail.com)
|
6
|
+
#
|
7
|
+
# ronin-web is free software: you can redistribute it and/or modify
|
8
|
+
# it under the terms of the GNU General Public License as published by
|
9
|
+
# the Free Software Foundation, either version 3 of the License, or
|
10
|
+
# (at your option) any later version.
|
11
|
+
#
|
12
|
+
# ronin-web is distributed in the hope that it will be useful,
|
13
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
14
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
15
|
+
# GNU General Public License for more details.
|
16
|
+
#
|
17
|
+
# You should have received a copy of the GNU General Public License
|
18
|
+
# along with ronin-web. If not, see <https://www.gnu.org/licenses/>.
|
19
|
+
#
|
20
|
+
|
21
|
+
require 'ronin/web/spider'
|
22
|
+
require 'ronin/support/network/http/user_agents'
|
23
|
+
|
24
|
+
module Ronin
|
25
|
+
module Web
|
26
|
+
class CLI
|
27
|
+
#
|
28
|
+
# Adds options for spidering a website.
|
29
|
+
#
|
30
|
+
# @since 2.0.0
|
31
|
+
#
|
32
|
+
module SpiderOptions
|
33
|
+
#
|
34
|
+
# Adds options for configuring a web spider and spidering a website.
|
35
|
+
#
|
36
|
+
# @param [Class<Command>] command
|
37
|
+
# The command class including {SpiderOptions}.
|
38
|
+
#
|
39
|
+
def self.included(command)
|
40
|
+
command.usage '[options] {--host HOST | --domain DOMAIN | --site URL}'
|
41
|
+
|
42
|
+
command.option :host, value: {
|
43
|
+
type: String,
|
44
|
+
usage: 'HOST'
|
45
|
+
},
|
46
|
+
desc: 'Spiders the specific HOST'
|
47
|
+
|
48
|
+
command.option :domain, value: {
|
49
|
+
type: String,
|
50
|
+
usage: 'DOMAIN'
|
51
|
+
},
|
52
|
+
desc: 'Spiders the whole domain'
|
53
|
+
|
54
|
+
command.option :site, value: {
|
55
|
+
type: String,
|
56
|
+
usage: 'URL'
|
57
|
+
},
|
58
|
+
desc: 'Spiders the website, starting at the URL'
|
59
|
+
|
60
|
+
command.option :open_timeout, value: {
|
61
|
+
type: Integer,
|
62
|
+
usage: 'SECS',
|
63
|
+
default: Spidr.open_timeout
|
64
|
+
},
|
65
|
+
desc: 'Sets the connection open timeout' do |timeout|
|
66
|
+
self.open_timeout = timeout
|
67
|
+
end
|
68
|
+
|
69
|
+
command.option :read_timeout, value: {
|
70
|
+
type: Integer,
|
71
|
+
usage: 'SECS',
|
72
|
+
default: Spidr.read_timeout
|
73
|
+
},
|
74
|
+
desc: 'Sets the read timeout' do |timeout|
|
75
|
+
self.read_timeout = timeout
|
76
|
+
end
|
77
|
+
|
78
|
+
command.option :ssl_timeout, value: {
|
79
|
+
type: Integer,
|
80
|
+
usage: 'SECS',
|
81
|
+
default: Spidr.ssl_timeout
|
82
|
+
},
|
83
|
+
desc: 'Sets the SSL connection timeout' do |timeout|
|
84
|
+
self.ssl_timeout = timeout
|
85
|
+
end
|
86
|
+
|
87
|
+
command.option :continue_timeout, value: {
|
88
|
+
type: Integer,
|
89
|
+
usage: 'SECS',
|
90
|
+
default: Spidr.continue_timeout
|
91
|
+
},
|
92
|
+
desc: 'Sets the continue timeout' do |timeout|
|
93
|
+
self.continue_timeout = timeout
|
94
|
+
end
|
95
|
+
|
96
|
+
command.option :keep_alive_timeout, value: {
|
97
|
+
type: Integer,
|
98
|
+
usage: 'SECS',
|
99
|
+
default: Spidr.keep_alive_timeout
|
100
|
+
},
|
101
|
+
desc: 'Sets the connection keep alive timeout' do |timeout|
|
102
|
+
self.keep_alive_timeout = timeout
|
103
|
+
end
|
104
|
+
|
105
|
+
command.option :proxy, short: '-P',
|
106
|
+
value: {
|
107
|
+
type: String,
|
108
|
+
usage: 'PROXY'
|
109
|
+
},
|
110
|
+
desc: 'Sets the proxy to use' do |proxy|
|
111
|
+
self.proxy = proxy
|
112
|
+
end
|
113
|
+
|
114
|
+
command.option :header, short: '-H',
|
115
|
+
value: {
|
116
|
+
type: /\A[^\s:]+:.*\z/,
|
117
|
+
usage: 'NAME: VALUE'
|
118
|
+
},
|
119
|
+
desc: 'Sets a default header' do |header|
|
120
|
+
name, value = header.split(/:\s*/,2)
|
121
|
+
|
122
|
+
self.default_headers[name] = value
|
123
|
+
end
|
124
|
+
|
125
|
+
command.option :host_header, value: {
|
126
|
+
type: /\A[^\s=]+=[^\s=]+\z/,
|
127
|
+
usage: 'NAME=VALUE'
|
128
|
+
},
|
129
|
+
desc: 'Sets a default header' do |name_value|
|
130
|
+
name, value = name_value.split('=',2)
|
131
|
+
|
132
|
+
self.host_headers[name] = value
|
133
|
+
end
|
134
|
+
|
135
|
+
command.option :user_agent_string, short: '-U',
|
136
|
+
value: {
|
137
|
+
type: String,
|
138
|
+
usage: 'STRING'
|
139
|
+
},
|
140
|
+
desc: 'The User-Agent string to use' do |ua|
|
141
|
+
self.user_agent = ua
|
142
|
+
end
|
143
|
+
|
144
|
+
command.option :user_agent, short: '-u',
|
145
|
+
value: {
|
146
|
+
type: Support::Network::HTTP::UserAgents::ALIASES.transform_keys { |key|
|
147
|
+
key.to_s.tr('_','-')
|
148
|
+
}
|
149
|
+
},
|
150
|
+
desc: 'The User-Agent to use' do |name|
|
151
|
+
self.user_agent = name
|
152
|
+
end
|
153
|
+
|
154
|
+
command.option :referer, short: '-R',
|
155
|
+
value: {
|
156
|
+
type: String,
|
157
|
+
usage: 'URL'
|
158
|
+
},
|
159
|
+
desc: 'Sets the Referer URL' do |referer|
|
160
|
+
self.referer = referer
|
161
|
+
end
|
162
|
+
|
163
|
+
command.option :delay, short: '-d',
|
164
|
+
value: {
|
165
|
+
type: Numeric,
|
166
|
+
usage: 'SECS'
|
167
|
+
},
|
168
|
+
desc: 'Sets the delay in seconds between each request' do |delay|
|
169
|
+
self.delay = delay
|
170
|
+
end
|
171
|
+
|
172
|
+
command.option :limit, short: '-l',
|
173
|
+
value: {
|
174
|
+
type: Integer,
|
175
|
+
usage: 'COUNT'
|
176
|
+
},
|
177
|
+
desc: 'Only spiders up to COUNT pages' do |limit|
|
178
|
+
self.limit = limit
|
179
|
+
end
|
180
|
+
|
181
|
+
command.option :max_depth, short: '-d',
|
182
|
+
value: {
|
183
|
+
type: Integer,
|
184
|
+
usage: 'DEPTH'
|
185
|
+
},
|
186
|
+
desc: 'Only spiders up to max depth' do |depth|
|
187
|
+
self.max_depth = depth
|
188
|
+
end
|
189
|
+
|
190
|
+
command.option :enqueue, value: {
|
191
|
+
type: String,
|
192
|
+
usage: 'URL'
|
193
|
+
},
|
194
|
+
desc: 'Adds the URL to the queue' do |url|
|
195
|
+
self.queue << url
|
196
|
+
end
|
197
|
+
|
198
|
+
command.option :visited, value: {
|
199
|
+
type: String,
|
200
|
+
usage: 'URL'
|
201
|
+
},
|
202
|
+
desc: 'Marks the URL as previously visited' do |url|
|
203
|
+
self.history << url
|
204
|
+
end
|
205
|
+
|
206
|
+
command.option :strip_fragments, desc: 'Enables/disables stripping the fragment component of every URL' do
|
207
|
+
self.strip_fragments = true
|
208
|
+
end
|
209
|
+
|
210
|
+
command.option :strip_query, desc: 'Enables/disables stripping the query component of every URL' do
|
211
|
+
self.strip_query = true
|
212
|
+
end
|
213
|
+
|
214
|
+
command.option :visit_scheme, value: {
|
215
|
+
type: String,
|
216
|
+
usage: 'SCHEME'
|
217
|
+
},
|
218
|
+
desc: 'Visit URLs with the URI scheme' do |scheme|
|
219
|
+
self.visit_schemes << scheme
|
220
|
+
end
|
221
|
+
|
222
|
+
command.option :visit_schemes_like, value: {
|
223
|
+
type: Regexp,
|
224
|
+
usage: '/REGEX/'
|
225
|
+
},
|
226
|
+
desc: 'Visit URLs with URI schemes that match the REGEX' do |regex|
|
227
|
+
self.visit_schemes << regex
|
228
|
+
end
|
229
|
+
|
230
|
+
command.option :ignore_scheme, value: {
|
231
|
+
type: String,
|
232
|
+
usage: 'SCHEME'
|
233
|
+
},
|
234
|
+
desc: 'Ignore the URLs with the URI scheme' do |scheme|
|
235
|
+
self.ignore_schemes << scheme
|
236
|
+
end
|
237
|
+
|
238
|
+
command.option :ignore_schemes_like, value: {
|
239
|
+
type: Regexp,
|
240
|
+
usage: '/REGEX/'
|
241
|
+
},
|
242
|
+
desc: 'Ignore the URLs with URI schemes matching the REGEX' do |regex|
|
243
|
+
self.ignore_schemes << regex
|
244
|
+
end
|
245
|
+
|
246
|
+
command.option :visit_host, value: {
|
247
|
+
type: String,
|
248
|
+
usage: 'HOST'
|
249
|
+
},
|
250
|
+
desc: 'Visit URLs with the matching host name' do |host|
|
251
|
+
self.visit_hosts << host
|
252
|
+
end
|
253
|
+
|
254
|
+
command.option :visit_hosts_like, value: {
|
255
|
+
type: Regexp,
|
256
|
+
usage: '/REGEX/'
|
257
|
+
},
|
258
|
+
desc: 'Visit URLs with hostnames that match the REGEX' do |regex|
|
259
|
+
self.visit_hosts << regex
|
260
|
+
end
|
261
|
+
|
262
|
+
command.option :ignore_host, value: {
|
263
|
+
type: String,
|
264
|
+
usage: 'HOST'
|
265
|
+
},
|
266
|
+
desc: 'Ignore the host name' do |host|
|
267
|
+
self.ignore_hosts << host
|
268
|
+
end
|
269
|
+
|
270
|
+
command.option :ignore_hosts_like, value: {
|
271
|
+
type: Regexp,
|
272
|
+
usage: '/REGEX/'
|
273
|
+
},
|
274
|
+
desc: 'Ignore the host names matching the REGEX' do |regex|
|
275
|
+
self.ignore_hosts << regex
|
276
|
+
end
|
277
|
+
|
278
|
+
command.option :visit_port, value: {
|
279
|
+
type: Integer,
|
280
|
+
usage: 'PORT'
|
281
|
+
},
|
282
|
+
desc: 'Visit URLs with the matching port number' do |port|
|
283
|
+
self.visit_ports << port
|
284
|
+
end
|
285
|
+
|
286
|
+
command.option :visit_ports_like, value: {
|
287
|
+
type: Regexp,
|
288
|
+
usage: '/REGEX/'
|
289
|
+
},
|
290
|
+
desc: 'Visit URLs with port numbers that match the REGEX' do |regex|
|
291
|
+
self.visit_ports << regex
|
292
|
+
end
|
293
|
+
|
294
|
+
command.option :ignore_port, value: {
|
295
|
+
type: Integer,
|
296
|
+
usage: 'PORT'
|
297
|
+
},
|
298
|
+
desc: 'Ignore the port number' do |port|
|
299
|
+
self.ignore_ports << port
|
300
|
+
end
|
301
|
+
|
302
|
+
command.option :ignore_ports_like, value: {
|
303
|
+
type: Regexp,
|
304
|
+
usage: '/REGEX/'
|
305
|
+
},
|
306
|
+
desc: 'Ignore the port numbers matching the REGEXP' do |regex|
|
307
|
+
self.ignore_ports << regex
|
308
|
+
end
|
309
|
+
|
310
|
+
command.option :visit_link, value: {
|
311
|
+
type: String,
|
312
|
+
usage: 'URL'
|
313
|
+
},
|
314
|
+
desc: 'Visit the URL' do |link|
|
315
|
+
self.visit_links << link
|
316
|
+
end
|
317
|
+
|
318
|
+
command.option :visit_links_like, value: {
|
319
|
+
type: Regexp,
|
320
|
+
usage: '/REGEX/'
|
321
|
+
},
|
322
|
+
desc: 'Visit URLs that match the REGEX' do |regex|
|
323
|
+
self.visit_links << regex
|
324
|
+
end
|
325
|
+
|
326
|
+
command.option :ignore_link, value: {
|
327
|
+
type: String,
|
328
|
+
usage: 'URL'
|
329
|
+
},
|
330
|
+
desc: 'Ignore the URL' do |link|
|
331
|
+
self.ignore_links << link
|
332
|
+
end
|
333
|
+
|
334
|
+
command.option :ignore_links_like, value: {
|
335
|
+
type: Regexp,
|
336
|
+
usage: '/REGEX/'
|
337
|
+
},
|
338
|
+
desc: 'Ignore URLs matching the REGEX' do |regex|
|
339
|
+
self.ignore_links << regex
|
340
|
+
end
|
341
|
+
|
342
|
+
command.option :visit_ext, value: {
|
343
|
+
type: String,
|
344
|
+
usage: 'FILE_EXT'
|
345
|
+
},
|
346
|
+
desc: 'Visit URLs with the matching file ext' do |ext|
|
347
|
+
self.visit_exts << ext
|
348
|
+
end
|
349
|
+
|
350
|
+
command.option :visit_exts_like, value: {
|
351
|
+
type: Regexp,
|
352
|
+
usage: '/REGEX/'
|
353
|
+
},
|
354
|
+
desc: 'Visit URLs with file exts that match the REGEX' do |regex|
|
355
|
+
self.visit_exts << regex
|
356
|
+
end
|
357
|
+
|
358
|
+
command.option :ignore_ext, value: {
|
359
|
+
type: String,
|
360
|
+
usage: 'FILE_EXT'
|
361
|
+
},
|
362
|
+
desc: 'Ignore the URLs with the file ext' do |ext|
|
363
|
+
self.ignore_exts << ext
|
364
|
+
end
|
365
|
+
|
366
|
+
command.option :ignore_exts_like, value: {
|
367
|
+
type: Regexp,
|
368
|
+
usage: '/REGEX/'
|
369
|
+
},
|
370
|
+
desc: 'Ignore URLs with file exts matching the REGEX' do |regex|
|
371
|
+
self.ignore_exts << regex
|
372
|
+
end
|
373
|
+
|
374
|
+
command.option :robots, short: '-r',
|
375
|
+
desc: 'Specifies whether to honor robots.txt' do
|
376
|
+
self.robots = true
|
377
|
+
end
|
378
|
+
end
|
379
|
+
|
380
|
+
# Keyword arguments to initialize a new `Spidr::Agent`.
|
381
|
+
#
|
382
|
+
# @return [Hash{Symbol => Object}]
|
383
|
+
#
|
384
|
+
# @since 2.0.0
|
385
|
+
attr_reader :agent_kwargs
|
386
|
+
|
387
|
+
#
|
388
|
+
# Initializes the command.
|
389
|
+
#
|
390
|
+
# @param [Hash{Symbol => Object}] kwargs
|
391
|
+
# Additional keyword arguments.
|
392
|
+
#
|
393
|
+
def initialize(**kwargs)
|
394
|
+
super(**kwargs)
|
395
|
+
|
396
|
+
@agent_kwargs = {}
|
397
|
+
end
|
398
|
+
|
399
|
+
#
|
400
|
+
# Creates a new web spider agent.
|
401
|
+
#
|
402
|
+
# @yield [agent]
|
403
|
+
# The given block will be given the newly created and configured
|
404
|
+
# web spider agent.
|
405
|
+
#
|
406
|
+
# @yieldparam [Ronin::Web::Spider::Agent] agent
|
407
|
+
# The newly created web spider agent.
|
408
|
+
#
|
409
|
+
# @return [Ronin::Web::Spider::Agent]
|
410
|
+
# The newly created web spider agent, after the agent has completed
|
411
|
+
# it's spidering.
|
412
|
+
#
|
413
|
+
def new_agent(&block)
|
414
|
+
if options[:host]
|
415
|
+
Web::Spider.host(options[:host],**agent_kwargs,&block)
|
416
|
+
elsif options[:domain]
|
417
|
+
Web::Spider.domain(options[:domain],**agent_kwargs,&block)
|
418
|
+
elsif options[:site]
|
419
|
+
Web::Spider.site(options[:site],**agent_kwargs,&block)
|
420
|
+
else
|
421
|
+
print_error "must specify --host, --domain, or --site"
|
422
|
+
exit(-1)
|
423
|
+
end
|
424
|
+
end
|
425
|
+
|
426
|
+
#
|
427
|
+
# The open connection timeout.
|
428
|
+
#
|
429
|
+
# @return [Integer, nil]
|
430
|
+
#
|
431
|
+
# @since 2.0.0
|
432
|
+
#
|
433
|
+
def open_timeout
|
434
|
+
@agent_kwargs[:open_timeout]
|
435
|
+
end
|
436
|
+
|
437
|
+
#
|
438
|
+
# Sets the open connection timeout.
|
439
|
+
#
|
440
|
+
# @param [Integer] new_timeout
|
441
|
+
#
|
442
|
+
# @return [Integer]
|
443
|
+
#
|
444
|
+
# @since 2.0.0
|
445
|
+
#
|
446
|
+
def open_timeout=(new_timeout)
|
447
|
+
@agent_kwargs[:open_timeout] = new_timeout
|
448
|
+
end
|
449
|
+
|
450
|
+
#
|
451
|
+
# The read timeout.
|
452
|
+
#
|
453
|
+
# @return [Integer, nil]
|
454
|
+
#
|
455
|
+
# @since 2.0.0
|
456
|
+
#
|
457
|
+
def read_timeout
|
458
|
+
@agent_kwargs[:read_timeout]
|
459
|
+
end
|
460
|
+
|
461
|
+
#
|
462
|
+
# Sets the read timeout.
|
463
|
+
#
|
464
|
+
# @param [Integer] new_timeout
|
465
|
+
#
|
466
|
+
# @return [Integer]
|
467
|
+
#
|
468
|
+
# @since 2.0.0
|
469
|
+
#
|
470
|
+
def read_timeout=(new_timeout)
|
471
|
+
@agent_kwargs[:read_timeout] = new_timeout
|
472
|
+
end
|
473
|
+
|
474
|
+
#
|
475
|
+
# The SSL timeout.
|
476
|
+
#
|
477
|
+
# @return [Integer, nil]
|
478
|
+
#
|
479
|
+
# @since 2.0.0
|
480
|
+
#
|
481
|
+
def ssl_timeout
|
482
|
+
@agent_kwargs[:ssl_timeout]
|
483
|
+
end
|
484
|
+
|
485
|
+
#
|
486
|
+
# Sets the SSL timeout.
|
487
|
+
#
|
488
|
+
# @param [Integer] new_timeout
|
489
|
+
#
|
490
|
+
# @return [Integer]
|
491
|
+
#
|
492
|
+
# @since 2.0.0
|
493
|
+
#
|
494
|
+
def ssl_timeout=(new_timeout)
|
495
|
+
@agent_kwargs[:ssl_timeout] = new_timeout
|
496
|
+
end
|
497
|
+
|
498
|
+
#
|
499
|
+
# The continue timeout.
|
500
|
+
#
|
501
|
+
# @return [Integer, nil]
|
502
|
+
#
|
503
|
+
# @since 2.0.0
|
504
|
+
#
|
505
|
+
def continue_timeout
|
506
|
+
@agent_kwargs[:continue_timeout]
|
507
|
+
end
|
508
|
+
|
509
|
+
#
|
510
|
+
# Sets the continue timeout.
|
511
|
+
#
|
512
|
+
# @param [Integer] new_timeout
|
513
|
+
#
|
514
|
+
# @return [Integer]
|
515
|
+
#
|
516
|
+
# @since 2.0.0
|
517
|
+
#
|
518
|
+
def continue_timeout=(new_timeout)
|
519
|
+
@agent_kwargs[:continue_timeout] = new_timeout
|
520
|
+
end
|
521
|
+
|
522
|
+
#
|
523
|
+
# The `Keep-Alive` timeout.
|
524
|
+
#
|
525
|
+
# @return [Integer, nil]
|
526
|
+
#
|
527
|
+
# @since 2.0.0
|
528
|
+
#
|
529
|
+
def keep_alive_timeout
|
530
|
+
@agent_kwargs[:keep_alive_timeout]
|
531
|
+
end
|
532
|
+
|
533
|
+
#
|
534
|
+
# Sets the `Keep-Alive` timeout.
|
535
|
+
#
|
536
|
+
# @param [Integer] new_timeout
|
537
|
+
#
|
538
|
+
# @return [Integer]
|
539
|
+
#
|
540
|
+
# @since 2.0.0
|
541
|
+
#
|
542
|
+
def keep_alive_timeout=(new_timeout)
|
543
|
+
@agent_kwargs[:keep_alive_timeout] = new_timeout
|
544
|
+
end
|
545
|
+
|
546
|
+
#
|
547
|
+
# The proxy to use for spidering.
|
548
|
+
#
|
549
|
+
# @return [String, nil]
|
550
|
+
#
|
551
|
+
# @since 0.2.0
|
552
|
+
#
|
553
|
+
def proxy
|
554
|
+
@agent_kwargs[:proxy]
|
555
|
+
end
|
556
|
+
|
557
|
+
#
|
558
|
+
# Sets the proxy to use for spidering.
|
559
|
+
#
|
560
|
+
# @param [String] new_proxy
|
561
|
+
# The new proxy URI.
|
562
|
+
#
|
563
|
+
# @return [String]
|
564
|
+
#
|
565
|
+
# @since 2.0.0
|
566
|
+
#
|
567
|
+
def proxy=(new_proxy)
|
568
|
+
@agent_kwargs[:proxy] = new_proxy
|
569
|
+
end
|
570
|
+
|
571
|
+
#
|
572
|
+
# The default headers to send with every request.
|
573
|
+
#
|
574
|
+
# @return [Hash{String => String}]
|
575
|
+
#
|
576
|
+
# @since 2.0.0
|
577
|
+
#
|
578
|
+
def default_headers
|
579
|
+
@agent_kwargs[:default_headers] ||= {}
|
580
|
+
end
|
581
|
+
|
582
|
+
#
|
583
|
+
# The default `Host` headers to send with every request.
|
584
|
+
#
|
585
|
+
# @return [Hash{String => String}]
|
586
|
+
#
|
587
|
+
# @since 2.0.0
|
588
|
+
#
|
589
|
+
def host_headers
|
590
|
+
@agent_kwargs[:host_headers] ||= {}
|
591
|
+
end
|
592
|
+
|
593
|
+
#
|
594
|
+
# Sets the new `User-Agent` header to use for spidering.
|
595
|
+
#
|
596
|
+
# @return [String, nil]
|
597
|
+
#
|
598
|
+
# @since 2.0.0
|
599
|
+
#
|
600
|
+
def user_agent
|
601
|
+
@agent_kwargs[:user_agent]
|
602
|
+
end
|
603
|
+
|
604
|
+
#
|
605
|
+
# Sets the new `User-Agent` header to use for spidering.
|
606
|
+
#
|
607
|
+
# @param [String] new_user_agent
|
608
|
+
#
|
609
|
+
# @return [String]
|
610
|
+
#
|
611
|
+
# @since 2.0.0
|
612
|
+
#
|
613
|
+
def user_agent=(new_user_agent)
|
614
|
+
@agent_kwargs[:user_agent] = new_user_agent
|
615
|
+
end
|
616
|
+
|
617
|
+
#
|
618
|
+
# The `Referer` header to use for spidering.
|
619
|
+
#
|
620
|
+
# @return [String, nil]
|
621
|
+
#
|
622
|
+
# @since 2.0.0
|
623
|
+
#
|
624
|
+
def referer
|
625
|
+
@agent_kwargs[:referer]
|
626
|
+
end
|
627
|
+
|
628
|
+
#
|
629
|
+
# Sets the `Referer` header to use for spidering.
|
630
|
+
#
|
631
|
+
# @param [String] new_referer
|
632
|
+
#
|
633
|
+
# @return [String, nil]
|
634
|
+
#
|
635
|
+
# @since 2.0.0
|
636
|
+
#
|
637
|
+
def referer=(new_referer)
|
638
|
+
@agent_kwargs[:referer] = new_referer
|
639
|
+
end
|
640
|
+
|
641
|
+
#
|
642
|
+
# The amount of seconds to pause between each request.
|
643
|
+
#
|
644
|
+
# @return [Integer, Float, nil]
|
645
|
+
#
|
646
|
+
# @since 2.0.0
|
647
|
+
#
|
648
|
+
def delay
|
649
|
+
@agent_kwargs[:delay]
|
650
|
+
end
|
651
|
+
|
652
|
+
#
|
653
|
+
# Sets the amount of seconds to pause between each request.
|
654
|
+
#
|
655
|
+
# @param [Integer, Float] new_delay
|
656
|
+
#
|
657
|
+
# @return [Integer, Float]
|
658
|
+
#
|
659
|
+
# @since 2.0.0
|
660
|
+
#
|
661
|
+
def delay=(new_delay)
|
662
|
+
@agent_kwargs[:delay] = new_delay
|
663
|
+
end
|
664
|
+
|
665
|
+
#
|
666
|
+
# The limit to how many URLs to visit.
|
667
|
+
#
|
668
|
+
# @return [Integer, nil]
|
669
|
+
#
|
670
|
+
# @since 2.0.0
|
671
|
+
#
|
672
|
+
def limit
|
673
|
+
@agent_kwargs[:limit]
|
674
|
+
end
|
675
|
+
|
676
|
+
#
|
677
|
+
# Sets the limit of how many URLs to visit.
|
678
|
+
#
|
679
|
+
# @param [Integer] new_limit
|
680
|
+
#
|
681
|
+
# @return [Integer]
|
682
|
+
#
|
683
|
+
# @since 2.0.0
|
684
|
+
#
|
685
|
+
def limit=(new_limit)
|
686
|
+
@agent_kwargs[:limit] = new_limit
|
687
|
+
end
|
688
|
+
|
689
|
+
#
|
690
|
+
# The maximum depth to spider.
|
691
|
+
#
|
692
|
+
# @return [Integer, nil]
|
693
|
+
#
|
694
|
+
# @since 2.0.0
|
695
|
+
#
|
696
|
+
def max_depth
|
697
|
+
@agent_kwargs[:max_depth]
|
698
|
+
end
|
699
|
+
|
700
|
+
#
|
701
|
+
# Sets the maximum depth to spider.
|
702
|
+
#
|
703
|
+
# @param [Integer] new_max_depth
|
704
|
+
#
|
705
|
+
# @return [Integer]
|
706
|
+
#
|
707
|
+
# @since 2.0.0
|
708
|
+
#
|
709
|
+
def max_depth=(new_max_depth)
|
710
|
+
@agent_kwargs[:max_depth] = new_max_depth
|
711
|
+
end
|
712
|
+
|
713
|
+
#
|
714
|
+
# The pre-existing queue of URLs to start spidering.
|
715
|
+
#
|
716
|
+
# @return [Array<String>]
|
717
|
+
#
|
718
|
+
# @since 2.0.0
|
719
|
+
#
|
720
|
+
def queue
|
721
|
+
@agent_kwargs[:queue] ||= []
|
722
|
+
end
|
723
|
+
|
724
|
+
#
|
725
|
+
# The pre-existing history of URLs that have already been spidered.
|
726
|
+
#
|
727
|
+
# @return [Array<String>]
|
728
|
+
#
|
729
|
+
# @since 2.0.0
|
730
|
+
#
|
731
|
+
def history
|
732
|
+
@agent_kwargs[:history] ||= []
|
733
|
+
end
|
734
|
+
|
735
|
+
#
|
736
|
+
# Whether to strip the `#fragment` components of links.
|
737
|
+
#
|
738
|
+
# @return [Boolean]
|
739
|
+
#
|
740
|
+
# @since 2.0.0
|
741
|
+
#
|
742
|
+
def strip_fragments
|
743
|
+
@agent_kwargs[:strip_fragments]
|
744
|
+
end
|
745
|
+
|
746
|
+
#
|
747
|
+
# Sets whether to strip the `#fragment` components of links.
|
748
|
+
#
|
749
|
+
# @param [Boolean] new_value
|
750
|
+
#
|
751
|
+
# @return [Boolean]
|
752
|
+
#
|
753
|
+
# @since 2.0.0
|
754
|
+
#
|
755
|
+
def strip_fragments=(new_value)
|
756
|
+
@agent_kwargs[:strip_fragments] = new_value
|
757
|
+
end
|
758
|
+
|
759
|
+
#
|
760
|
+
# Whether to strip the `?query` components of links.
|
761
|
+
#
|
762
|
+
# @return [Boolean]
|
763
|
+
#
|
764
|
+
# @since 2.0.0
|
765
|
+
#
|
766
|
+
def strip_query
|
767
|
+
@agent_kwargs[:strip_query]
|
768
|
+
end
|
769
|
+
|
770
|
+
#
|
771
|
+
# Sets whether to strip the `?query` components of links.
|
772
|
+
#
|
773
|
+
# @param [Boolean] new_value
|
774
|
+
#
|
775
|
+
# @return [Boolean]
|
776
|
+
#
|
777
|
+
# @since 2.0.0
|
778
|
+
#
|
779
|
+
def strip_query=(new_value)
|
780
|
+
@agent_kwargs[:strip_query] = new_value
|
781
|
+
end
|
782
|
+
|
783
|
+
#
|
784
|
+
# The list of URI schemes to allow spidering.
|
785
|
+
#
|
786
|
+
# @return [Array<String>]
|
787
|
+
#
|
788
|
+
# @since 2.0.0
|
789
|
+
#
|
790
|
+
def visit_schemes
|
791
|
+
@agent_kwargs[:schemes] ||= []
|
792
|
+
end
|
793
|
+
|
794
|
+
#
|
795
|
+
# The list of URI hosts to allow spidering.
|
796
|
+
#
|
797
|
+
# @return [Array<String>]
|
798
|
+
#
|
799
|
+
# @since 2.0.0
|
800
|
+
#
|
801
|
+
def visit_hosts
|
802
|
+
@agent_kwargs[:hosts] ||= []
|
803
|
+
end
|
804
|
+
|
805
|
+
#
|
806
|
+
# The list of URI ports to allow spidering.
|
807
|
+
#
|
808
|
+
# @return [Array<Integer>]
|
809
|
+
#
|
810
|
+
# @since 2.0.0
|
811
|
+
#
|
812
|
+
def visit_ports
|
813
|
+
@agent_kwargs[:ports] ||= []
|
814
|
+
end
|
815
|
+
|
816
|
+
#
|
817
|
+
# The list of URI links to allow spidering.
|
818
|
+
#
|
819
|
+
# @return [Array<String>]
|
820
|
+
#
|
821
|
+
# @since 2.0.0
|
822
|
+
#
|
823
|
+
def visit_links
|
824
|
+
@agent_kwargs[:links] ||= []
|
825
|
+
end
|
826
|
+
|
827
|
+
#
|
828
|
+
# The list of URI file extensions to allow spidering.
|
829
|
+
#
|
830
|
+
# @return [Array<String>]
|
831
|
+
#
|
832
|
+
# @since 2.0.0
|
833
|
+
#
|
834
|
+
def visit_exts
|
835
|
+
@agent_kwargs[:exts] ||= []
|
836
|
+
end
|
837
|
+
|
838
|
+
#
|
839
|
+
# The list of URI schemes to ignore while spidering.
|
840
|
+
#
|
841
|
+
# @return [Array<String>]
|
842
|
+
#
|
843
|
+
# @since 2.0.0
|
844
|
+
#
|
845
|
+
def ignore_schemes
|
846
|
+
@agent_kwargs[:ignore_schemes] ||= []
|
847
|
+
end
|
848
|
+
|
849
|
+
#
|
850
|
+
# The list of URI hosts to ignore while spidering.
|
851
|
+
#
|
852
|
+
# @return [Array<String>]
|
853
|
+
#
|
854
|
+
# @since 2.0.0
|
855
|
+
#
|
856
|
+
def ignore_hosts
|
857
|
+
@agent_kwargs[:ignore_hosts] ||= []
|
858
|
+
end
|
859
|
+
|
860
|
+
#
|
861
|
+
# The list of URI ports to ignore while spidering.
|
862
|
+
#
|
863
|
+
# @return [Array<Integer>]
|
864
|
+
#
|
865
|
+
# @since 2.0.0
|
866
|
+
#
|
867
|
+
def ignore_ports
|
868
|
+
@agent_kwargs[:ignore_ports] ||= []
|
869
|
+
end
|
870
|
+
|
871
|
+
#
|
872
|
+
# The list of URI links to ignore while spidering.
|
873
|
+
#
|
874
|
+
# @return [Array<String>]
|
875
|
+
#
|
876
|
+
# @since 2.0.0
|
877
|
+
#
|
878
|
+
def ignore_links
|
879
|
+
@agent_kwargs[:ignore_links] ||= []
|
880
|
+
end
|
881
|
+
|
882
|
+
#
|
883
|
+
# The list of URI file extensions to ignore while spidering.
|
884
|
+
#
|
885
|
+
# @return [Array<String>]
|
886
|
+
#
|
887
|
+
# @since 2.0.0
|
888
|
+
#
|
889
|
+
def ignore_exts
|
890
|
+
@agent_kwargs[:ignore_exts] ||= []
|
891
|
+
end
|
892
|
+
|
893
|
+
#
|
894
|
+
# Whether to honor the `robots.txt` file while spidering.
|
895
|
+
#
|
896
|
+
# @return [Boolean]
|
897
|
+
#
|
898
|
+
# @since 2.0.0
|
899
|
+
#
|
900
|
+
def robots
|
901
|
+
@agent_kwargs[:robots]
|
902
|
+
end
|
903
|
+
|
904
|
+
#
|
905
|
+
# Sets whether to honor the `robots.txt` file while spidering.
|
906
|
+
#
|
907
|
+
# @param [Boolean] new_value
|
908
|
+
#
|
909
|
+
# @return [Boolean]
|
910
|
+
#
|
911
|
+
# @since 2.0.0
|
912
|
+
#
|
913
|
+
def robots=(new_value)
|
914
|
+
@agent_kwargs[:robots] = new_value
|
915
|
+
end
|
916
|
+
end
|
917
|
+
end
|
918
|
+
end
|
919
|
+
end
|