ronin-web-spider 0.1.0.beta2 → 0.1.0
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 +1 -4
- data/.yardopts +1 -1
- data/ChangeLog.md +3 -0
- data/README.md +302 -30
- data/gemspec.yml +3 -3
- data/lib/ronin/web/spider/agent.rb +62 -2
- data/lib/ronin/web/spider/archive.rb +3 -0
- data/lib/ronin/web/spider/exceptions.rb +1 -1
- data/lib/ronin/web/spider/git_archive.rb +1 -1
- data/lib/ronin/web/spider/version.rb +2 -2
- data/lib/ronin/web/spider.rb +289 -1
- data/ronin-web-spider.gemspec +2 -1
- metadata +7 -17
- data/spec/agent_spec.rb +0 -585
- data/spec/archive_spec.rb +0 -91
- data/spec/example_app.rb +0 -27
- data/spec/git_archive_spec.rb +0 -137
- data/spec/spec_helper.rb +0 -4
- data/spec/spider_spec.rb +0 -252
data/spec/agent_spec.rb
DELETED
@@ -1,585 +0,0 @@
|
|
1
|
-
require 'spec_helper'
|
2
|
-
require 'ronin/web/spider/agent'
|
3
|
-
|
4
|
-
require 'webmock/rspec'
|
5
|
-
require 'sinatra/base'
|
6
|
-
|
7
|
-
describe Ronin::Web::Spider::Agent do
|
8
|
-
describe "#initialize" do
|
9
|
-
context "when Ronin::Support::Network::HTTP.proxy is set" do
|
10
|
-
let(:proxy_host) { 'example.com' }
|
11
|
-
let(:proxy_port) { 8080 }
|
12
|
-
let(:proxy_uri) { URI::HTTP.build(host: proxy_host, port: proxy_port) }
|
13
|
-
|
14
|
-
before { Ronin::Support::Network::HTTP.proxy = proxy_uri }
|
15
|
-
|
16
|
-
it "must parse ENV['RONIN_HTTP_USER_AGENT'] and set #proxy" do
|
17
|
-
expect(subject.proxy).to be_kind_of(Spidr::Proxy)
|
18
|
-
expect(subject.proxy.host).to eq(proxy_host)
|
19
|
-
expect(subject.proxy.port).to eq(proxy_port)
|
20
|
-
end
|
21
|
-
|
22
|
-
after { Ronin::Support::Network::HTTP.proxy = nil }
|
23
|
-
end
|
24
|
-
|
25
|
-
context "when Ronin::Support::Network::HTTP.user_agent is set" do
|
26
|
-
let(:user_agent) { 'Foo Bar' }
|
27
|
-
|
28
|
-
before { Ronin::Support::Network::HTTP.user_agent = user_agent }
|
29
|
-
|
30
|
-
it "must default #user_agent to ENV['RONIN_HTTP_USER_AGENT']" do
|
31
|
-
expect(subject.user_agent).to eq(user_agent)
|
32
|
-
end
|
33
|
-
|
34
|
-
after { Ronin::Support::Network::HTTP.user_agent = nil }
|
35
|
-
end
|
36
|
-
|
37
|
-
context "when given the proxy: keyword argument" do
|
38
|
-
let(:proxy_host) { 'example.com' }
|
39
|
-
let(:proxy_port) { 8080 }
|
40
|
-
|
41
|
-
context "and it's an Addressable::URI" do
|
42
|
-
let(:proxy) { Addressable::URI.new(host: proxy_host, port: proxy_port) }
|
43
|
-
|
44
|
-
subject { described_class.new(proxy: proxy) }
|
45
|
-
|
46
|
-
it "must convert it to a Spidr::Proxy object" do
|
47
|
-
expect(subject.proxy).to be_kind_of(Spidr::Proxy)
|
48
|
-
expect(subject.proxy.host).to eq(proxy_host)
|
49
|
-
expect(subject.proxy.port).to eq(proxy_port)
|
50
|
-
end
|
51
|
-
end
|
52
|
-
|
53
|
-
context "and it's an URI::HTTP" do
|
54
|
-
let(:proxy) { URI::HTTP.build(host: proxy_host, port: proxy_port) }
|
55
|
-
|
56
|
-
subject { described_class.new(proxy: proxy) }
|
57
|
-
|
58
|
-
it "must convert it to a Spidr::Proxy object" do
|
59
|
-
expect(subject.proxy).to be_kind_of(Spidr::Proxy)
|
60
|
-
expect(subject.proxy.host).to eq(proxy_host)
|
61
|
-
expect(subject.proxy.port).to eq(proxy_port)
|
62
|
-
end
|
63
|
-
end
|
64
|
-
|
65
|
-
context "and it's a Hash" do
|
66
|
-
let(:proxy) do
|
67
|
-
{host: proxy_host, port: proxy_port}
|
68
|
-
end
|
69
|
-
|
70
|
-
subject { described_class.new(proxy: proxy) }
|
71
|
-
|
72
|
-
it "must convert it to a Spidr::Proxy object" do
|
73
|
-
expect(subject.proxy).to be_kind_of(Spidr::Proxy)
|
74
|
-
expect(subject.proxy.host).to eq(proxy_host)
|
75
|
-
expect(subject.proxy.port).to eq(proxy_port)
|
76
|
-
end
|
77
|
-
end
|
78
|
-
|
79
|
-
context "and it's a String" do
|
80
|
-
let(:proxy) { "http://#{proxy_host}:#{proxy_port}" }
|
81
|
-
|
82
|
-
subject { described_class.new(proxy: proxy) }
|
83
|
-
|
84
|
-
it "must convert it to a Spidr::Proxy object" do
|
85
|
-
expect(subject.proxy).to be_kind_of(Spidr::Proxy)
|
86
|
-
expect(subject.proxy.host).to eq(proxy_host)
|
87
|
-
expect(subject.proxy.port).to eq(proxy_port)
|
88
|
-
end
|
89
|
-
end
|
90
|
-
end
|
91
|
-
|
92
|
-
context "when given the user_agent: keyword argument" do
|
93
|
-
context "and it's a String" do
|
94
|
-
let(:user_agent) { "test user-agent" }
|
95
|
-
|
96
|
-
subject { described_class.new(user_agent: user_agent) }
|
97
|
-
|
98
|
-
it "must set the #user_agent" do
|
99
|
-
expect(subject.user_agent).to eq(user_agent)
|
100
|
-
end
|
101
|
-
end
|
102
|
-
|
103
|
-
context "and it's a Symbol" do
|
104
|
-
let(:user_agent) { :chrome_linux }
|
105
|
-
let(:expected_user_agent) do
|
106
|
-
Ronin::Support::Network::HTTP::UserAgents[user_agent]
|
107
|
-
end
|
108
|
-
|
109
|
-
subject { described_class.new(user_agent: user_agent) }
|
110
|
-
|
111
|
-
it "must map the Symbol to one of Ronin::Support::Network::HTTP::UserAgents" do
|
112
|
-
expect(subject.user_agent).to eq(expected_user_agent)
|
113
|
-
end
|
114
|
-
end
|
115
|
-
end
|
116
|
-
|
117
|
-
it "must default #visited_hosts to nil" do
|
118
|
-
expect(subject.visited_hosts).to be(nil)
|
119
|
-
end
|
120
|
-
end
|
121
|
-
|
122
|
-
describe "#every_host" do
|
123
|
-
module TestAgentEveryHost
|
124
|
-
class Host1 < Sinatra::Base
|
125
|
-
|
126
|
-
set :host, 'host1.example.com'
|
127
|
-
set :port, 80
|
128
|
-
|
129
|
-
get '/' do
|
130
|
-
<<~HTML
|
131
|
-
<html>
|
132
|
-
<body>
|
133
|
-
<a href="/link1">link1</a>
|
134
|
-
<a href="http://host2.example.com/offsite-link">offsite link</a>
|
135
|
-
<a href="/link2">link2</a>
|
136
|
-
</body>
|
137
|
-
</html>
|
138
|
-
HTML
|
139
|
-
end
|
140
|
-
|
141
|
-
get '/link1' do
|
142
|
-
'<html><body>got here</body></html>'
|
143
|
-
end
|
144
|
-
|
145
|
-
get '/link2' do
|
146
|
-
'<html><body>got here</body></html>'
|
147
|
-
end
|
148
|
-
end
|
149
|
-
|
150
|
-
class Host2 < Sinatra::Base
|
151
|
-
|
152
|
-
set :host, 'host2.example.com'
|
153
|
-
set :port, 80
|
154
|
-
|
155
|
-
get '/offsite-link' do
|
156
|
-
'<html><body>should not get here</body></html>'
|
157
|
-
end
|
158
|
-
|
159
|
-
end
|
160
|
-
end
|
161
|
-
|
162
|
-
let(:host1) { 'host1.example.com' }
|
163
|
-
let(:host2) { 'host2.example.com' }
|
164
|
-
|
165
|
-
let(:host1_app) { TestAgentEveryHost::Host1 }
|
166
|
-
let(:host2_app) { TestAgentEveryHost::Host2 }
|
167
|
-
|
168
|
-
before do
|
169
|
-
stub_request(:any, /#{Regexp.escape(host1)}/).to_rack(host1_app)
|
170
|
-
stub_request(:any, /#{Regexp.escape(host2)}/).to_rack(host2_app)
|
171
|
-
end
|
172
|
-
|
173
|
-
it "must yield every newly discovered hostname while spidering" do
|
174
|
-
yielded_hosts = []
|
175
|
-
|
176
|
-
subject.every_host do |host|
|
177
|
-
yielded_hosts << host
|
178
|
-
end
|
179
|
-
|
180
|
-
subject.start_at("http://#{host1}/")
|
181
|
-
|
182
|
-
expect(yielded_hosts).to eq([host1, host2])
|
183
|
-
end
|
184
|
-
|
185
|
-
it "must popualte #visited_hosts" do
|
186
|
-
subject.every_host { |host| }
|
187
|
-
subject.start_at("http://#{host1}/")
|
188
|
-
|
189
|
-
expect(subject.visited_hosts).to be_kind_of(Set)
|
190
|
-
expect(subject.visited_hosts.entries).to eq([host1, host2])
|
191
|
-
end
|
192
|
-
end
|
193
|
-
|
194
|
-
# TODO: need to figure out how to test #every_cert using webmock.
|
195
|
-
describe "#every_cert"
|
196
|
-
|
197
|
-
describe "#every_favicon" do
|
198
|
-
module TestAgentEveryHost
|
199
|
-
class TestApp < Sinatra::Base
|
200
|
-
|
201
|
-
set :host, 'example.com'
|
202
|
-
set :port, 80
|
203
|
-
|
204
|
-
get '/' do
|
205
|
-
<<~HTML
|
206
|
-
<html>
|
207
|
-
<head>
|
208
|
-
<link rel="favicon" href="/favicon1.ico" type="image/x-icon"/>
|
209
|
-
</head>
|
210
|
-
<body>
|
211
|
-
<a href="/link1">link1</a>
|
212
|
-
<a href="http://host2.example.com/offsite-link">offsite link</a>
|
213
|
-
<a href="/link2">link2</a>
|
214
|
-
</body>
|
215
|
-
</html>
|
216
|
-
HTML
|
217
|
-
end
|
218
|
-
|
219
|
-
get '/favicon1.ico' do
|
220
|
-
content_type 'image/x-icon'
|
221
|
-
|
222
|
-
"favicon1"
|
223
|
-
end
|
224
|
-
|
225
|
-
get '/favicon2.ico' do
|
226
|
-
content_type 'image/vnd.microsoft.icon'
|
227
|
-
|
228
|
-
"favicon2"
|
229
|
-
end
|
230
|
-
|
231
|
-
get '/link1' do
|
232
|
-
'<html><body>got here</body></html>'
|
233
|
-
end
|
234
|
-
|
235
|
-
get '/link2' do
|
236
|
-
<<~HTML
|
237
|
-
<html>
|
238
|
-
<head>
|
239
|
-
<link rel="favicon" href="/favicon2.ico" type="image/x-icon"/>
|
240
|
-
</head>
|
241
|
-
<body>got here</body>
|
242
|
-
</html>
|
243
|
-
HTML
|
244
|
-
end
|
245
|
-
end
|
246
|
-
end
|
247
|
-
|
248
|
-
let(:host) { 'example.com' }
|
249
|
-
|
250
|
-
let(:test_app) { TestAgentEveryHost::TestApp }
|
251
|
-
|
252
|
-
before do
|
253
|
-
stub_request(:any, /#{Regexp.escape(host)}/).to_rack(test_app)
|
254
|
-
end
|
255
|
-
|
256
|
-
it "must yield Spidr::Page objects for each encountered .ico file" do
|
257
|
-
yielded_favicons = []
|
258
|
-
|
259
|
-
subject.every_favicon do |favicon|
|
260
|
-
yielded_favicons << favicon
|
261
|
-
end
|
262
|
-
|
263
|
-
subject.start_at("http://#{host}/")
|
264
|
-
|
265
|
-
expect(yielded_favicons).to_not be_empty
|
266
|
-
|
267
|
-
expect(yielded_favicons[0]).to be_kind_of(Spidr::Page)
|
268
|
-
expect(yielded_favicons[0].content_type).to eq('image/x-icon')
|
269
|
-
expect(yielded_favicons[0].url).to eq(URI("http://#{host}/favicon1.ico"))
|
270
|
-
|
271
|
-
expect(yielded_favicons[1]).to be_kind_of(Spidr::Page)
|
272
|
-
expect(yielded_favicons[1].content_type).to eq('image/vnd.microsoft.icon')
|
273
|
-
expect(yielded_favicons[1].url).to eq(URI("http://#{host}/favicon2.ico"))
|
274
|
-
end
|
275
|
-
end
|
276
|
-
|
277
|
-
describe "#every_html_comment" do
|
278
|
-
module TestAgentEveryHTMLComment
|
279
|
-
class TestApp < Sinatra::Base
|
280
|
-
|
281
|
-
set :host, 'example.com'
|
282
|
-
set :port, 80
|
283
|
-
|
284
|
-
get '/' do
|
285
|
-
<<~HTML
|
286
|
-
<html>
|
287
|
-
<head>
|
288
|
-
<!-- comment 1 -->
|
289
|
-
</head>
|
290
|
-
<!-- -->
|
291
|
-
<body>
|
292
|
-
<!-- comment 2 -->
|
293
|
-
</body>
|
294
|
-
</html>
|
295
|
-
HTML
|
296
|
-
end
|
297
|
-
end
|
298
|
-
end
|
299
|
-
|
300
|
-
let(:host) { 'example.com' }
|
301
|
-
|
302
|
-
let(:test_app) { TestAgentEveryHTMLComment::TestApp }
|
303
|
-
|
304
|
-
before do
|
305
|
-
stub_request(:any, /#{Regexp.escape(host)}/).to_rack(test_app)
|
306
|
-
end
|
307
|
-
|
308
|
-
it "must yield every non-empty/non-whitespace HTML comment String" do
|
309
|
-
yielded_comments = []
|
310
|
-
|
311
|
-
subject.every_html_comment do |comment|
|
312
|
-
yielded_comments << comment
|
313
|
-
end
|
314
|
-
|
315
|
-
subject.start_at("http://#{host}/")
|
316
|
-
|
317
|
-
expect(yielded_comments).to match_array(
|
318
|
-
[
|
319
|
-
'comment 1',
|
320
|
-
'comment 2'
|
321
|
-
]
|
322
|
-
)
|
323
|
-
end
|
324
|
-
end
|
325
|
-
|
326
|
-
describe "#every_javascript" do
|
327
|
-
module TestAgentEveryJavaScript
|
328
|
-
class TestApp < Sinatra::Base
|
329
|
-
|
330
|
-
set :host, 'example.com'
|
331
|
-
set :port, 80
|
332
|
-
|
333
|
-
get '/' do
|
334
|
-
<<~HTML
|
335
|
-
<html>
|
336
|
-
<head>
|
337
|
-
<script type="text/javascript" src="/javascript1.js"></script>
|
338
|
-
<script type="text/javascript">javascript2</script>
|
339
|
-
</head>
|
340
|
-
<body>
|
341
|
-
<a href="/link1">link1</a>
|
342
|
-
<a href="http://host2.example.com/offsite-link">offsite link</a>
|
343
|
-
<a href="/link2">link2</a>
|
344
|
-
</body>
|
345
|
-
</html>
|
346
|
-
HTML
|
347
|
-
end
|
348
|
-
|
349
|
-
get '/javascript1.js' do
|
350
|
-
content_type 'text/javascript'
|
351
|
-
"javascript1"
|
352
|
-
end
|
353
|
-
end
|
354
|
-
end
|
355
|
-
|
356
|
-
let(:host) { 'example.com' }
|
357
|
-
|
358
|
-
let(:test_app) { TestAgentEveryJavaScript::TestApp }
|
359
|
-
|
360
|
-
before do
|
361
|
-
stub_request(:any, /#{Regexp.escape(host)}/).to_rack(test_app)
|
362
|
-
end
|
363
|
-
|
364
|
-
it "must yield both the contents of .js files and inline <script> tags" do
|
365
|
-
yielded_javascripts = []
|
366
|
-
|
367
|
-
subject.every_javascript do |js|
|
368
|
-
yielded_javascripts << js
|
369
|
-
end
|
370
|
-
|
371
|
-
subject.start_at("http://#{host}/")
|
372
|
-
|
373
|
-
expect(yielded_javascripts).to match_array(%w[javascript1 javascript2])
|
374
|
-
end
|
375
|
-
end
|
376
|
-
|
377
|
-
describe "#every_javascript_string" do
|
378
|
-
module TestAgentEveryJavaScriptString
|
379
|
-
class TestApp < Sinatra::Base
|
380
|
-
|
381
|
-
set :host, 'example.com'
|
382
|
-
set :port, 80
|
383
|
-
|
384
|
-
get '/' do
|
385
|
-
<<~HTML
|
386
|
-
<html>
|
387
|
-
<head>
|
388
|
-
<script type="text/javascript" src="/javascript1.js"></script>
|
389
|
-
<script type="text/javascript">
|
390
|
-
var str3 = "string #3";
|
391
|
-
var str4 = 'string #4';
|
392
|
-
</script>
|
393
|
-
</head>
|
394
|
-
<body>
|
395
|
-
<a href="/link1">link1</a>
|
396
|
-
<a href="http://host2.example.com/offsite-link">offsite link</a>
|
397
|
-
<a href="/link2">link2</a>
|
398
|
-
</body>
|
399
|
-
</html>
|
400
|
-
HTML
|
401
|
-
end
|
402
|
-
|
403
|
-
get '/javascript1.js' do
|
404
|
-
content_type 'text/javascript'
|
405
|
-
<<~JS
|
406
|
-
var str1 = "string #1";
|
407
|
-
var str2 = 'string #2';
|
408
|
-
JS
|
409
|
-
end
|
410
|
-
end
|
411
|
-
end
|
412
|
-
|
413
|
-
let(:host) { 'example.com' }
|
414
|
-
|
415
|
-
let(:test_app) { TestAgentEveryJavaScriptString::TestApp }
|
416
|
-
|
417
|
-
before do
|
418
|
-
stub_request(:any, /#{Regexp.escape(host)}/).to_rack(test_app)
|
419
|
-
end
|
420
|
-
|
421
|
-
it "must yield every JavaScript string from any <script> tag" do
|
422
|
-
yielded_javascript_strings = []
|
423
|
-
|
424
|
-
subject.every_javascript_string do |string|
|
425
|
-
yielded_javascript_strings << string
|
426
|
-
end
|
427
|
-
|
428
|
-
subject.start_at("http://#{host}/")
|
429
|
-
|
430
|
-
expect(yielded_javascript_strings).to match_array(
|
431
|
-
[
|
432
|
-
'string #1',
|
433
|
-
'string #2',
|
434
|
-
'string #3',
|
435
|
-
'string #4'
|
436
|
-
]
|
437
|
-
)
|
438
|
-
end
|
439
|
-
end
|
440
|
-
|
441
|
-
describe "#every_javascript_comment" do
|
442
|
-
module TestAgentEveryJavaScriptComment
|
443
|
-
class TestApp < Sinatra::Base
|
444
|
-
|
445
|
-
set :host, 'example.com'
|
446
|
-
set :port, 80
|
447
|
-
|
448
|
-
get '/' do
|
449
|
-
<<~HTML
|
450
|
-
<html>
|
451
|
-
<head>
|
452
|
-
<script type="text/javascript" src="/javascript1.js"></script>
|
453
|
-
<script type="text/javascript">
|
454
|
-
// comment 3
|
455
|
-
var str3 = "string #3";
|
456
|
-
/*
|
457
|
-
comment 4
|
458
|
-
*/
|
459
|
-
var str4 = 'string #4';
|
460
|
-
</script>
|
461
|
-
</head>
|
462
|
-
<body>
|
463
|
-
<a href="/link1">link1</a>
|
464
|
-
<a href="http://host2.example.com/offsite-link">offsite link</a>
|
465
|
-
<a href="/link2">link2</a>
|
466
|
-
</body>
|
467
|
-
</html>
|
468
|
-
HTML
|
469
|
-
end
|
470
|
-
|
471
|
-
get '/javascript1.js' do
|
472
|
-
content_type 'text/javascript'
|
473
|
-
<<~JS
|
474
|
-
// comment 1
|
475
|
-
var str1 = "string #1";
|
476
|
-
/* comment 2 */
|
477
|
-
var str2 = 'string #2';
|
478
|
-
JS
|
479
|
-
end
|
480
|
-
end
|
481
|
-
end
|
482
|
-
|
483
|
-
let(:host) { 'example.com' }
|
484
|
-
|
485
|
-
let(:test_app) { TestAgentEveryJavaScriptComment::TestApp }
|
486
|
-
|
487
|
-
before do
|
488
|
-
stub_request(:any, /#{Regexp.escape(host)}/).to_rack(test_app)
|
489
|
-
end
|
490
|
-
|
491
|
-
it "must yield every JavaScript comment from any <script> tag" do
|
492
|
-
yielded_javascript_comments = []
|
493
|
-
|
494
|
-
subject.every_javascript_comment do |comment|
|
495
|
-
yielded_javascript_comments << comment
|
496
|
-
end
|
497
|
-
|
498
|
-
subject.start_at("http://#{host}/")
|
499
|
-
|
500
|
-
expect(yielded_javascript_comments).to match_array(
|
501
|
-
[
|
502
|
-
"// comment 1\n",
|
503
|
-
"/* comment 2 */",
|
504
|
-
"// comment 3\n",
|
505
|
-
"/*\n comment 4\n */"
|
506
|
-
]
|
507
|
-
)
|
508
|
-
end
|
509
|
-
end
|
510
|
-
|
511
|
-
describe "#every_comment" do
|
512
|
-
module TestAgentEveryComment
|
513
|
-
class TestApp < Sinatra::Base
|
514
|
-
|
515
|
-
set :host, 'example.com'
|
516
|
-
set :port, 80
|
517
|
-
|
518
|
-
get '/' do
|
519
|
-
<<~HTML
|
520
|
-
<html>
|
521
|
-
<head>
|
522
|
-
<!-- HTML comment 1 -->
|
523
|
-
<script type="text/javascript" src="/javascript1.js"></script>
|
524
|
-
<script type="text/javascript">
|
525
|
-
// JavaScript comment 3
|
526
|
-
var str3 = "string #3";
|
527
|
-
/*
|
528
|
-
JavaScript comment 4
|
529
|
-
*/
|
530
|
-
var str4 = 'string #4';
|
531
|
-
</script>
|
532
|
-
</head>
|
533
|
-
<!-- -->
|
534
|
-
<body>
|
535
|
-
<!-- HTML comment 2 -->
|
536
|
-
<a href="/link1">link1</a>
|
537
|
-
<a href="http://host2.example.com/offsite-link">offsite link</a>
|
538
|
-
<a href="/link2">link2</a>
|
539
|
-
</body>
|
540
|
-
</html>
|
541
|
-
HTML
|
542
|
-
end
|
543
|
-
|
544
|
-
get '/javascript1.js' do
|
545
|
-
content_type 'text/javascript'
|
546
|
-
<<~JS
|
547
|
-
// JavaScript comment 1
|
548
|
-
var str1 = "string #1";
|
549
|
-
/* JavaScript comment 2 */
|
550
|
-
var str2 = 'string #2';
|
551
|
-
JS
|
552
|
-
end
|
553
|
-
end
|
554
|
-
end
|
555
|
-
|
556
|
-
let(:host) { 'example.com' }
|
557
|
-
|
558
|
-
let(:test_app) { TestAgentEveryComment::TestApp }
|
559
|
-
|
560
|
-
before do
|
561
|
-
stub_request(:any, /#{Regexp.escape(host)}/).to_rack(test_app)
|
562
|
-
end
|
563
|
-
|
564
|
-
it "must yield every HTML and JavaScript comment from any <script> tag" do
|
565
|
-
yielded_comments = []
|
566
|
-
|
567
|
-
subject.every_comment do |comment|
|
568
|
-
yielded_comments << comment
|
569
|
-
end
|
570
|
-
|
571
|
-
subject.start_at("http://#{host}/")
|
572
|
-
|
573
|
-
expect(yielded_comments).to match_array(
|
574
|
-
[
|
575
|
-
"HTML comment 1",
|
576
|
-
"// JavaScript comment 1\n",
|
577
|
-
"/* JavaScript comment 2 */",
|
578
|
-
"// JavaScript comment 3\n",
|
579
|
-
"/*\n JavaScript comment 4\n */",
|
580
|
-
"HTML comment 2"
|
581
|
-
]
|
582
|
-
)
|
583
|
-
end
|
584
|
-
end
|
585
|
-
end
|
data/spec/archive_spec.rb
DELETED
@@ -1,91 +0,0 @@
|
|
1
|
-
require 'spec_helper'
|
2
|
-
require 'ronin/web/spider/archive'
|
3
|
-
|
4
|
-
require 'tmpdir'
|
5
|
-
|
6
|
-
describe Ronin::Web::Spider::Archive do
|
7
|
-
let(:root) { File.join(Dir.mktmpdir('ronin-web-spider')) }
|
8
|
-
|
9
|
-
subject { described_class.new(root) }
|
10
|
-
|
11
|
-
describe "#initialize" do
|
12
|
-
it "must set #root" do
|
13
|
-
expect(subject.root).to eq(root)
|
14
|
-
end
|
15
|
-
end
|
16
|
-
|
17
|
-
describe ".open" do
|
18
|
-
subject { described_class.open(root) }
|
19
|
-
|
20
|
-
it "must return a new #{described_class}" do
|
21
|
-
expect(subject).to be_kind_of(described_class)
|
22
|
-
end
|
23
|
-
|
24
|
-
context "when given a block" do
|
25
|
-
it "must yield the new #{described_class}" do
|
26
|
-
expect { |b|
|
27
|
-
described_class.open(root,&b)
|
28
|
-
}.to yield_with_args(described_class)
|
29
|
-
end
|
30
|
-
end
|
31
|
-
|
32
|
-
context "when the root directory does not exist" do
|
33
|
-
let(:root) { File.join(super(),'does-not-exist-yet') }
|
34
|
-
|
35
|
-
it "must create the given root directory" do
|
36
|
-
described_class.open(root)
|
37
|
-
|
38
|
-
expect(File.directory?(root)).to be(true)
|
39
|
-
end
|
40
|
-
end
|
41
|
-
|
42
|
-
context "when the root directory does exist" do
|
43
|
-
let(:root) { File.join(super(),'does-not-exist-yet') }
|
44
|
-
|
45
|
-
before { FileUtils.mkdir(root) }
|
46
|
-
|
47
|
-
it "must not raise an error" do
|
48
|
-
expect {
|
49
|
-
described_class.open(root)
|
50
|
-
}.to_not raise_error
|
51
|
-
end
|
52
|
-
end
|
53
|
-
end
|
54
|
-
|
55
|
-
describe "#write" do
|
56
|
-
let(:url) { URI('https://example.com/foo/bar.html') }
|
57
|
-
let(:body) { 'test file' }
|
58
|
-
|
59
|
-
before { subject.write(url,body) }
|
60
|
-
|
61
|
-
it "must automatically create parent directory" do
|
62
|
-
expect(File.directory?(File.join(root,'foo'))).to be(true)
|
63
|
-
end
|
64
|
-
|
65
|
-
it "must write the body into the file" do
|
66
|
-
expect(File.read(File.join(root,'foo','bar.html'))).to eq(body)
|
67
|
-
end
|
68
|
-
|
69
|
-
context "when the URL has a query string" do
|
70
|
-
let(:url) { URI('https://example.com/foo/bar.php?q=1') }
|
71
|
-
|
72
|
-
it "must include the query string as part of the file name" do
|
73
|
-
expect(File.read(File.join(root,'foo','bar.php?q=1'))).to eq(body)
|
74
|
-
end
|
75
|
-
end
|
76
|
-
|
77
|
-
context "when the URL path ends with a '/'" do
|
78
|
-
let(:url) { URI('https://example.com/foo/bar/') }
|
79
|
-
|
80
|
-
it "must write the body to an index.html file within the URL's path" do
|
81
|
-
expect(File.read(File.join(root,'foo','bar','index.html'))).to eq(body)
|
82
|
-
end
|
83
|
-
end
|
84
|
-
end
|
85
|
-
|
86
|
-
describe "#to_s" do
|
87
|
-
it "must return the root directory" do
|
88
|
-
expect(subject.to_s).to eq(root)
|
89
|
-
end
|
90
|
-
end
|
91
|
-
end
|
data/spec/example_app.rb
DELETED
@@ -1,27 +0,0 @@
|
|
1
|
-
require 'rspec'
|
2
|
-
require 'sinatra/base'
|
3
|
-
require 'webmock/rspec'
|
4
|
-
|
5
|
-
require 'ronin/web/spider/agent'
|
6
|
-
|
7
|
-
RSpec.shared_context "example App" do
|
8
|
-
let(:host) { 'example.com' }
|
9
|
-
|
10
|
-
subject { Ronin::Web::Spider::Agent.new(host: host) }
|
11
|
-
|
12
|
-
def self.app(&block)
|
13
|
-
let(:app) do
|
14
|
-
klass = Class.new(Sinatra::Base)
|
15
|
-
klass.set :host, host
|
16
|
-
klass.set :port, 80
|
17
|
-
klass.class_eval(&block)
|
18
|
-
return klass
|
19
|
-
end
|
20
|
-
|
21
|
-
before do
|
22
|
-
stub_request(:any, /#{Regexp.escape(host)}/).to_rack(app)
|
23
|
-
|
24
|
-
subject.start_at("http://#{host}/")
|
25
|
-
end
|
26
|
-
end
|
27
|
-
end
|