spidr_epg 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.gitignore +10 -0
- data/.rspec +1 -0
- data/.yardopts +1 -0
- data/ChangeLog.md +291 -0
- data/ChangeLog.md~ +291 -0
- data/Gemfile +16 -0
- data/Gemfile.lock +49 -0
- data/Gemfile~ +16 -0
- data/LICENSE.txt +20 -0
- data/README.md +193 -0
- data/README.md~ +190 -0
- data/Rakefile +29 -0
- data/gemspec.yml +19 -0
- data/lib/spidr/actions/actions.rb +83 -0
- data/lib/spidr/actions/exceptions/action.rb +9 -0
- data/lib/spidr/actions/exceptions/paused.rb +11 -0
- data/lib/spidr/actions/exceptions/skip_link.rb +12 -0
- data/lib/spidr/actions/exceptions/skip_page.rb +12 -0
- data/lib/spidr/actions/exceptions.rb +4 -0
- data/lib/spidr/actions.rb +2 -0
- data/lib/spidr/agent.rb +866 -0
- data/lib/spidr/auth_credential.rb +28 -0
- data/lib/spidr/auth_store.rb +161 -0
- data/lib/spidr/body.rb +98 -0
- data/lib/spidr/cookie_jar.rb +202 -0
- data/lib/spidr/events.rb +537 -0
- data/lib/spidr/extensions/uri.rb +52 -0
- data/lib/spidr/extensions.rb +1 -0
- data/lib/spidr/filters.rb +539 -0
- data/lib/spidr/headers.rb +370 -0
- data/lib/spidr/links.rb +229 -0
- data/lib/spidr/page.rb +108 -0
- data/lib/spidr/rules.rb +79 -0
- data/lib/spidr/sanitizers.rb +56 -0
- data/lib/spidr/session_cache.rb +145 -0
- data/lib/spidr/spidr.rb +107 -0
- data/lib/spidr/version.rb +4 -0
- data/lib/spidr/version.rb~ +4 -0
- data/lib/spidr.rb +3 -0
- data/pkg/spidr-1.0.0.gem +0 -0
- data/spec/actions_spec.rb +59 -0
- data/spec/agent_spec.rb +81 -0
- data/spec/auth_store_spec.rb +85 -0
- data/spec/cookie_jar_spec.rb +144 -0
- data/spec/extensions/uri_spec.rb +43 -0
- data/spec/filters_spec.rb +61 -0
- data/spec/helpers/history.rb +34 -0
- data/spec/helpers/page.rb +8 -0
- data/spec/helpers/wsoc.rb +83 -0
- data/spec/page_examples.rb +21 -0
- data/spec/page_spec.rb +125 -0
- data/spec/rules_spec.rb +45 -0
- data/spec/sanitizers_spec.rb +61 -0
- data/spec/session_cache.rb +58 -0
- data/spec/spec_helper.rb +4 -0
- data/spec/spidr_spec.rb +39 -0
- data/spidr.gemspec +133 -0
- data/spidr.gemspec~ +131 -0
- metadata +158 -0
@@ -0,0 +1,539 @@
|
|
1
|
+
require 'spidrs/rules'
|
2
|
+
|
3
|
+
module Spidr
|
4
|
+
#
|
5
|
+
# The {Filters} module adds methods to {Agent} for controlling which
|
6
|
+
# URLs the agent will visit.
|
7
|
+
#
|
8
|
+
module Filters
|
9
|
+
# List of acceptable URL schemes to follow
|
10
|
+
attr_reader :schemes
|
11
|
+
|
12
|
+
#
|
13
|
+
# Sets the list of acceptable URL schemes to visit.
|
14
|
+
#
|
15
|
+
# @param [Array] new_schemes
|
16
|
+
# The new schemes to visit.
|
17
|
+
#
|
18
|
+
# @example
|
19
|
+
# agent.schemes = ['http']
|
20
|
+
#
|
21
|
+
def schemes=(new_schemes)
|
22
|
+
@schemes = new_schemes.map { |scheme| scheme.to_s }
|
23
|
+
end
|
24
|
+
|
25
|
+
#
|
26
|
+
# Specifies the patterns that match host-names to visit.
|
27
|
+
#
|
28
|
+
# @return [Array<String, Regexp, Proc>]
|
29
|
+
# The host-name patterns to visit.
|
30
|
+
#
|
31
|
+
def visit_hosts
|
32
|
+
@host_rules.accept
|
33
|
+
end
|
34
|
+
|
35
|
+
#
|
36
|
+
# Adds a given pattern to the {#visit_hosts}.
|
37
|
+
#
|
38
|
+
# @param [String, Regexp] pattern
|
39
|
+
# The pattern to match host-names with.
|
40
|
+
#
|
41
|
+
# @yield [host]
|
42
|
+
# If a block is given, it will be used to filter host-names.
|
43
|
+
#
|
44
|
+
# @yieldparam [String] host
|
45
|
+
# A host-name to accept or reject.
|
46
|
+
#
|
47
|
+
def visit_hosts_like(pattern=nil,&block)
|
48
|
+
if pattern
|
49
|
+
visit_hosts << pattern
|
50
|
+
elsif block
|
51
|
+
visit_hosts << block
|
52
|
+
end
|
53
|
+
|
54
|
+
return self
|
55
|
+
end
|
56
|
+
|
57
|
+
#
|
58
|
+
# Specifies the patterns that match host-names to not visit.
|
59
|
+
#
|
60
|
+
# @return [Array<String, Regexp, Proc>]
|
61
|
+
# The host-name patterns to not visit.
|
62
|
+
#
|
63
|
+
def ignore_hosts
|
64
|
+
@host_rules.reject
|
65
|
+
end
|
66
|
+
|
67
|
+
#
|
68
|
+
# Adds a given pattern to the {#ignore_hosts}.
|
69
|
+
#
|
70
|
+
# @param [String, Regexp] pattern
|
71
|
+
# The pattern to match host-names with.
|
72
|
+
#
|
73
|
+
# @yield [host]
|
74
|
+
# If a block is given, it will be used to filter host-names.
|
75
|
+
#
|
76
|
+
# @yieldparam [String] host
|
77
|
+
# A host-name to reject or accept.
|
78
|
+
#
|
79
|
+
def ignore_hosts_like(pattern=nil,&block)
|
80
|
+
if pattern
|
81
|
+
ignore_hosts << pattern
|
82
|
+
elsif block
|
83
|
+
ignore_hosts << block
|
84
|
+
end
|
85
|
+
|
86
|
+
return self
|
87
|
+
end
|
88
|
+
|
89
|
+
#
|
90
|
+
# Specifies the patterns that match the ports to visit.
|
91
|
+
#
|
92
|
+
# @return [Array<Integer, Regexp, Proc>]
|
93
|
+
# The port patterns to visit.
|
94
|
+
#
|
95
|
+
def visit_ports
|
96
|
+
@port_rules.accept
|
97
|
+
end
|
98
|
+
|
99
|
+
#
|
100
|
+
# Adds a given pattern to the {#visit_ports}.
|
101
|
+
#
|
102
|
+
# @param [Integer, Regexp] pattern
|
103
|
+
# The pattern to match ports with.
|
104
|
+
#
|
105
|
+
# @yield [port]
|
106
|
+
# If a block is given, it will be used to filter ports.
|
107
|
+
#
|
108
|
+
# @yieldparam [Integer] port
|
109
|
+
# A port to accept or reject.
|
110
|
+
#
|
111
|
+
def visit_ports_like(pattern=nil,&block)
|
112
|
+
if pattern
|
113
|
+
visit_ports << pattern
|
114
|
+
elsif block
|
115
|
+
visit_ports << block
|
116
|
+
end
|
117
|
+
|
118
|
+
return self
|
119
|
+
end
|
120
|
+
|
121
|
+
#
|
122
|
+
# Specifies the patterns that match ports to not visit.
|
123
|
+
#
|
124
|
+
# @return [Array<Integer, Regexp, Proc>]
|
125
|
+
# The port patterns to not visit.
|
126
|
+
#
|
127
|
+
def ignore_ports
|
128
|
+
@port_rules.reject
|
129
|
+
end
|
130
|
+
|
131
|
+
#
|
132
|
+
# Adds a given pattern to the {#ignore_ports}.
|
133
|
+
#
|
134
|
+
# @param [Integer, Regexp] pattern
|
135
|
+
# The pattern to match ports with.
|
136
|
+
#
|
137
|
+
# @yield [port]
|
138
|
+
# If a block is given, it will be used to filter ports.
|
139
|
+
#
|
140
|
+
# @yieldparam [Integer] port
|
141
|
+
# A port to reject or accept.
|
142
|
+
#
|
143
|
+
def ignore_ports_like(pattern=nil,&block)
|
144
|
+
if pattern
|
145
|
+
ignore_ports << pattern
|
146
|
+
elsif block
|
147
|
+
ignore_ports << block
|
148
|
+
end
|
149
|
+
|
150
|
+
return self
|
151
|
+
end
|
152
|
+
|
153
|
+
#
|
154
|
+
# Specifies the patterns that match the links to visit.
|
155
|
+
#
|
156
|
+
# @return [Array<String, Regexp, Proc>]
|
157
|
+
# The link patterns to visit.
|
158
|
+
#
|
159
|
+
# @since 0.2.4
|
160
|
+
#
|
161
|
+
def visit_links
|
162
|
+
@link_rules.accept
|
163
|
+
end
|
164
|
+
|
165
|
+
#
|
166
|
+
# Adds a given pattern to the {#visit_links}
|
167
|
+
#
|
168
|
+
# @param [String, Regexp] pattern
|
169
|
+
# The pattern to match link with.
|
170
|
+
#
|
171
|
+
# @yield [link]
|
172
|
+
# If a block is given, it will be used to filter links.
|
173
|
+
#
|
174
|
+
# @yieldparam [String] link
|
175
|
+
# A link to accept or reject.
|
176
|
+
#
|
177
|
+
# @since 0.2.4
|
178
|
+
#
|
179
|
+
def visit_links_like(pattern=nil,&block)
|
180
|
+
if pattern
|
181
|
+
visit_links << pattern
|
182
|
+
elsif block
|
183
|
+
visit_links << block
|
184
|
+
end
|
185
|
+
|
186
|
+
return self
|
187
|
+
end
|
188
|
+
|
189
|
+
#
|
190
|
+
# Specifies the patterns that match links to not visit.
|
191
|
+
#
|
192
|
+
# @return [Array<String, Regexp, Proc>]
|
193
|
+
# The link patterns to not visit.
|
194
|
+
#
|
195
|
+
def ignore_links
|
196
|
+
@link_rules.reject
|
197
|
+
end
|
198
|
+
|
199
|
+
#
|
200
|
+
# Adds a given pattern to the {#ignore_links}.
|
201
|
+
#
|
202
|
+
# @param [String, Regexp] pattern
|
203
|
+
# The pattern to match links with.
|
204
|
+
#
|
205
|
+
# @yield [link]
|
206
|
+
# If a block is given, it will be used to filter links.
|
207
|
+
#
|
208
|
+
# @yieldparam [String] link
|
209
|
+
# A link to reject or accept.
|
210
|
+
#
|
211
|
+
def ignore_links_like(pattern=nil,&block)
|
212
|
+
if pattern
|
213
|
+
ignore_links << pattern
|
214
|
+
elsif block
|
215
|
+
ignore_links << block
|
216
|
+
end
|
217
|
+
|
218
|
+
return self
|
219
|
+
end
|
220
|
+
|
221
|
+
#
|
222
|
+
# Specifies the patterns that match the URLs to visit.
|
223
|
+
#
|
224
|
+
# @return [Array<String, Regexp, Proc>]
|
225
|
+
# The link patterns to visit.
|
226
|
+
#
|
227
|
+
# @since 0.2.4
|
228
|
+
#
|
229
|
+
def visit_urls
|
230
|
+
@url_rules.accept
|
231
|
+
end
|
232
|
+
|
233
|
+
#
|
234
|
+
# Adds a given pattern to the {#visit_urls}
|
235
|
+
#
|
236
|
+
# @param [String, Regexp] pattern
|
237
|
+
# The pattern to match URLs with.
|
238
|
+
#
|
239
|
+
# @yield [url]
|
240
|
+
# If a block is given, it will be used to filter URLs.
|
241
|
+
#
|
242
|
+
# @yieldparam [URI::HTTP, URI::HTTPS] url
|
243
|
+
# A URL to accept or reject.
|
244
|
+
#
|
245
|
+
# @since 0.2.4
|
246
|
+
#
|
247
|
+
def visit_urls_like(pattern=nil,&block)
|
248
|
+
if pattern
|
249
|
+
visit_urls << pattern
|
250
|
+
elsif block
|
251
|
+
visit_urls << block
|
252
|
+
end
|
253
|
+
|
254
|
+
return self
|
255
|
+
end
|
256
|
+
|
257
|
+
#
|
258
|
+
# Specifies the patterns that match URLs to not visit.
|
259
|
+
#
|
260
|
+
# @return [Array<String, Regexp, Proc>]
|
261
|
+
# The URL patterns to not visit.
|
262
|
+
#
|
263
|
+
# @since 0.2.4
|
264
|
+
#
|
265
|
+
def ignore_urls
|
266
|
+
@url_rules.reject
|
267
|
+
end
|
268
|
+
|
269
|
+
#
|
270
|
+
# Adds a given pattern to the {#ignore_urls}.
|
271
|
+
#
|
272
|
+
# @param [String, Regexp] pattern
|
273
|
+
# The pattern to match URLs with.
|
274
|
+
#
|
275
|
+
# @yield [url]
|
276
|
+
# If a block is given, it will be used to filter URLs.
|
277
|
+
#
|
278
|
+
# @yieldparam [URI::HTTP, URI::HTTPS] url
|
279
|
+
# A URL to reject or accept.
|
280
|
+
#
|
281
|
+
# @since 0.2.4
|
282
|
+
#
|
283
|
+
def ignore_urls_like(pattern=nil,&block)
|
284
|
+
if pattern
|
285
|
+
ignore_urls << pattern
|
286
|
+
elsif block
|
287
|
+
ignore_urls << block
|
288
|
+
end
|
289
|
+
|
290
|
+
return self
|
291
|
+
end
|
292
|
+
|
293
|
+
#
|
294
|
+
# Specifies the patterns that match the URI path extensions to visit.
|
295
|
+
#
|
296
|
+
# @return [Array<String, Regexp, Proc>]
|
297
|
+
# The URI path extensions patterns to visit.
|
298
|
+
#
|
299
|
+
def visit_exts
|
300
|
+
@ext_rules.accept
|
301
|
+
end
|
302
|
+
|
303
|
+
#
|
304
|
+
# Adds a given pattern to the {#visit_exts}.
|
305
|
+
#
|
306
|
+
# @param [String, Regexp] pattern
|
307
|
+
# The pattern to match URI path extensions with.
|
308
|
+
#
|
309
|
+
# @yield [ext]
|
310
|
+
# If a block is given, it will be used to filter URI path extensions.
|
311
|
+
#
|
312
|
+
# @yieldparam [String] ext
|
313
|
+
# A URI path extension to accept or reject.
|
314
|
+
#
|
315
|
+
def visit_exts_like(pattern=nil,&block)
|
316
|
+
if pattern
|
317
|
+
visit_exts << pattern
|
318
|
+
elsif block
|
319
|
+
visit_exts << block
|
320
|
+
end
|
321
|
+
|
322
|
+
return self
|
323
|
+
end
|
324
|
+
|
325
|
+
#
|
326
|
+
# Specifies the patterns that match URI path extensions to not visit.
|
327
|
+
#
|
328
|
+
# @return [Array<String, Regexp, Proc>]
|
329
|
+
# The URI path extension patterns to not visit.
|
330
|
+
#
|
331
|
+
def ignore_exts
|
332
|
+
@ext_rules.reject
|
333
|
+
end
|
334
|
+
|
335
|
+
#
|
336
|
+
# Adds a given pattern to the {#ignore_exts}.
|
337
|
+
#
|
338
|
+
# @param [String, Regexp] pattern
|
339
|
+
# The pattern to match URI path extensions with.
|
340
|
+
#
|
341
|
+
# @yield [ext]
|
342
|
+
# If a block is given, it will be used to filter URI path extensions.
|
343
|
+
#
|
344
|
+
# @yieldparam [String] ext
|
345
|
+
# A URI path extension to reject or accept.
|
346
|
+
#
|
347
|
+
def ignore_exts_like(pattern=nil,&block)
|
348
|
+
if pattern
|
349
|
+
ignore_exts << pattern
|
350
|
+
elsif block
|
351
|
+
ignore_exts << block
|
352
|
+
end
|
353
|
+
|
354
|
+
return self
|
355
|
+
end
|
356
|
+
|
357
|
+
protected
|
358
|
+
|
359
|
+
#
|
360
|
+
# Initializes filtering rules.
|
361
|
+
#
|
362
|
+
# @param [Hash] options
|
363
|
+
# Additional options.
|
364
|
+
#
|
365
|
+
# @option options [Array] :schemes (['http', 'https'])
|
366
|
+
# The list of acceptable URI schemes to visit.
|
367
|
+
# The `https` scheme will be ignored if `net/https` cannot be loaded.
|
368
|
+
#
|
369
|
+
# @option options [String] :host
|
370
|
+
# The host-name to visit.
|
371
|
+
#
|
372
|
+
# @option options [Array<String, Regexp, Proc>] :hosts
|
373
|
+
# The patterns which match the host-names to visit.
|
374
|
+
#
|
375
|
+
# @option options [Array<String, Regexp, Proc>] :ignore_hosts
|
376
|
+
# The patterns which match the host-names to not visit.
|
377
|
+
#
|
378
|
+
# @option options [Array<Integer, Regexp, Proc>] :ports
|
379
|
+
# The patterns which match the ports to visit.
|
380
|
+
#
|
381
|
+
# @option options [Array<Integer, Regexp, Proc>] :ignore_ports
|
382
|
+
# The patterns which match the ports to not visit.
|
383
|
+
#
|
384
|
+
# @option options [Array<String, Regexp, Proc>] :links
|
385
|
+
# The patterns which match the links to visit.
|
386
|
+
#
|
387
|
+
# @option options [Array<String, Regexp, Proc>] :ignore_links
|
388
|
+
# The patterns which match the links to not visit.
|
389
|
+
#
|
390
|
+
# @option options [Array<String, Regexp, Proc>] :urls
|
391
|
+
# The patterns which match the URLs to visit.
|
392
|
+
#
|
393
|
+
# @option options [Array<String, Regexp, Proc>] :ignore_urls
|
394
|
+
# The patterns which match the URLs to not visit.
|
395
|
+
#
|
396
|
+
# @option options [Array<String, Regexp, Proc>] :exts
|
397
|
+
# The patterns which match the URI path extensions to visit.
|
398
|
+
#
|
399
|
+
# @option options [Array<String, Regexp, Proc>] :ignore_exts
|
400
|
+
# The patterns which match the URI path extensions to not visit.
|
401
|
+
#
|
402
|
+
def initialize_filters(options={})
|
403
|
+
@schemes = []
|
404
|
+
|
405
|
+
if options[:schemes]
|
406
|
+
@schemes += options[:schemes]
|
407
|
+
else
|
408
|
+
@schemes << 'http'
|
409
|
+
|
410
|
+
begin
|
411
|
+
require 'net/https'
|
412
|
+
|
413
|
+
@schemes << 'https'
|
414
|
+
rescue Gem::LoadError => e
|
415
|
+
raise(e)
|
416
|
+
rescue ::LoadError
|
417
|
+
warn "Warning: cannot load 'net/https', https support disabled"
|
418
|
+
end
|
419
|
+
end
|
420
|
+
|
421
|
+
@host_rules = Rules.new(
|
422
|
+
:accept => options[:hosts],
|
423
|
+
:reject => options[:ignore_hosts]
|
424
|
+
)
|
425
|
+
@port_rules = Rules.new(
|
426
|
+
:accept => options[:ports],
|
427
|
+
:reject => options[:ignore_ports]
|
428
|
+
)
|
429
|
+
@link_rules = Rules.new(
|
430
|
+
:accept => options[:links],
|
431
|
+
:reject => options[:ignore_links]
|
432
|
+
)
|
433
|
+
@url_rules = Rules.new(
|
434
|
+
:accept => options[:urls],
|
435
|
+
:reject => options[:ignore_urls]
|
436
|
+
)
|
437
|
+
@ext_rules = Rules.new(
|
438
|
+
:accept => options[:exts],
|
439
|
+
:reject => options[:ignore_exts]
|
440
|
+
)
|
441
|
+
|
442
|
+
if options[:host]
|
443
|
+
visit_hosts_like(options[:host])
|
444
|
+
end
|
445
|
+
|
446
|
+
if options[:queue]
|
447
|
+
self.queue = options[:queue]
|
448
|
+
end
|
449
|
+
|
450
|
+
if options[:history]
|
451
|
+
self.history = options[:history]
|
452
|
+
end
|
453
|
+
end
|
454
|
+
|
455
|
+
#
|
456
|
+
# Determines if a given URI scheme should be visited.
|
457
|
+
#
|
458
|
+
# @param [String] scheme
|
459
|
+
# The URI scheme.
|
460
|
+
#
|
461
|
+
# @return [Boolean]
|
462
|
+
# Specifies whether the given scheme should be visited.
|
463
|
+
#
|
464
|
+
def visit_scheme?(scheme)
|
465
|
+
if scheme
|
466
|
+
return @schemes.include?(scheme)
|
467
|
+
else
|
468
|
+
return true
|
469
|
+
end
|
470
|
+
end
|
471
|
+
|
472
|
+
#
|
473
|
+
# Determines if a given host-name should be visited.
|
474
|
+
#
|
475
|
+
# @param [String] host
|
476
|
+
# The host-name.
|
477
|
+
#
|
478
|
+
# @return [Boolean]
|
479
|
+
# Specifies whether the given host-name should be visited.
|
480
|
+
#
|
481
|
+
def visit_host?(host)
|
482
|
+
@host_rules.accept?(host)
|
483
|
+
end
|
484
|
+
|
485
|
+
#
|
486
|
+
# Determines if a given port should be visited.
|
487
|
+
#
|
488
|
+
# @param [Integer] port
|
489
|
+
# The port number.
|
490
|
+
#
|
491
|
+
# @return [Boolean]
|
492
|
+
# Specifies whether the given port should be visited.
|
493
|
+
#
|
494
|
+
def visit_port?(port)
|
495
|
+
@port_rules.accept?(port)
|
496
|
+
end
|
497
|
+
|
498
|
+
#
|
499
|
+
# Determines if a given link should be visited.
|
500
|
+
#
|
501
|
+
# @param [String] link
|
502
|
+
# The link.
|
503
|
+
#
|
504
|
+
# @return [Boolean]
|
505
|
+
# Specifies whether the given link should be visited.
|
506
|
+
#
|
507
|
+
def visit_link?(link)
|
508
|
+
@link_rules.accept?(link)
|
509
|
+
end
|
510
|
+
|
511
|
+
#
|
512
|
+
# Determines if a given URL should be visited.
|
513
|
+
#
|
514
|
+
# @param [URI::HTTP, URI::HTTPS] url
|
515
|
+
# The URL.
|
516
|
+
#
|
517
|
+
# @return [Boolean]
|
518
|
+
# Specifies whether the given URL should be visited.
|
519
|
+
#
|
520
|
+
# @since 0.2.4
|
521
|
+
#
|
522
|
+
def visit_url?(link)
|
523
|
+
@url_rules.accept?(link)
|
524
|
+
end
|
525
|
+
|
526
|
+
#
|
527
|
+
# Determines if a given URI path extension should be visited.
|
528
|
+
#
|
529
|
+
# @param [String] path
|
530
|
+
# The path that contains the extension.
|
531
|
+
#
|
532
|
+
# @return [Boolean]
|
533
|
+
# Specifies whether the given URI path extension should be visited.
|
534
|
+
#
|
535
|
+
def visit_ext?(path)
|
536
|
+
@ext_rules.accept?(File.extname(path)[1..-1])
|
537
|
+
end
|
538
|
+
end
|
539
|
+
end
|