dubdubdub 0.3.2 → 0.3.3
Sign up to get free protection for your applications and to get access to all the features.
- data/dubdubdub.gemspec +2 -1
- data/lib/dubdubdub.rb +1 -1
- data/lib/dubdubdub/client.rb +6 -1
- data/lib/dubdubdub/exceptions.rb +3 -0
- data/spec/dubdubdub_spec.rb +5 -1
- data/spec/vcr/get/infinite_redirects.yml +412 -0
- metadata +3 -2
data/dubdubdub.gemspec
CHANGED
@@ -5,7 +5,7 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = "dubdubdub"
|
8
|
-
s.version = "0.3.
|
8
|
+
s.version = "0.3.3"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["James Hu"]
|
@@ -47,6 +47,7 @@ Gem::Specification.new do |s|
|
|
47
47
|
"spec/vcr/follow/uri_error.yml",
|
48
48
|
"spec/vcr/get/basic.yml",
|
49
49
|
"spec/vcr/get/doesnt_exist.yml",
|
50
|
+
"spec/vcr/get/infinite_redirects.yml",
|
50
51
|
"spec/vcr/get/params.yml",
|
51
52
|
"spec/vcr/get/proxy.yml"
|
52
53
|
]
|
data/lib/dubdubdub.rb
CHANGED
data/lib/dubdubdub/client.rb
CHANGED
@@ -125,6 +125,8 @@ class DubDubDub::Client
|
|
125
125
|
def handle_mechanize_exceptions(&block)
|
126
126
|
begin
|
127
127
|
yield
|
128
|
+
rescue Mechanize::RedirectLimitReachedError
|
129
|
+
raise DubDubDub::RedirectLimitReachedError
|
128
130
|
rescue Mechanize::ResponseCodeError => e
|
129
131
|
raise DubDubDub::ResponseError.new(e, e.response_code)
|
130
132
|
end
|
@@ -133,8 +135,11 @@ class DubDubDub::Client
|
|
133
135
|
def handle_rest_client_exceptions(&block)
|
134
136
|
begin
|
135
137
|
yield
|
138
|
+
rescue RestClient::MaxRedirectsReached
|
139
|
+
raise DubDubDub::RedirectLimitReachedError
|
136
140
|
rescue RestClient::Exception => e
|
137
|
-
|
141
|
+
code = e.response.code if e.response
|
142
|
+
raise DubDubDub::ResponseError.new(e, code)
|
138
143
|
end
|
139
144
|
|
140
145
|
end
|
data/lib/dubdubdub/exceptions.rb
CHANGED
@@ -3,6 +3,9 @@ class DubDubDub::Error < RuntimeError; end
|
|
3
3
|
# URL not properly formatted
|
4
4
|
class DubDubDub::URLFormatError < DubDubDub::Error; end
|
5
5
|
|
6
|
+
# Redirect limit reached
|
7
|
+
class DubDubDub::RedirectLimitReachedError < DubDubDub::Error; end
|
8
|
+
|
6
9
|
# There was an unhandled response. Contains
|
7
10
|
# a reference to the originating error.
|
8
11
|
class DubDubDub::ResponseError < DubDubDub::Error
|
data/spec/dubdubdub_spec.rb
CHANGED
@@ -175,7 +175,7 @@ describe DubDubDub do
|
|
175
175
|
html.css('.ip').text.strip.should == "173.234.181.64"
|
176
176
|
end
|
177
177
|
|
178
|
-
it "raises an exception if it doesn't exist", vcr: { cassette_name: "get/doesnt_exist", record: :
|
178
|
+
it "raises an exception if it doesn't exist", vcr: { cassette_name: "get/doesnt_exist", record: :once } do
|
179
179
|
lambda { www.get("https://github.com/asdasd/asdasd") }.should raise_error(DubDubDub::ResponseError)
|
180
180
|
|
181
181
|
begin
|
@@ -186,6 +186,10 @@ describe DubDubDub do
|
|
186
186
|
e.message.should_not be_nil
|
187
187
|
end
|
188
188
|
end
|
189
|
+
|
190
|
+
it "raise the proper exception when exceeding maximum redirects", vcr: { cassette_name: "get/infinite_redirects", record: :once } do
|
191
|
+
lambda { www.get("http://wayback.archive.org/web/20050204085854im_/http://www.drpep.com/images/home_19.gif") }.should raise_error(DubDubDub::RedirectLimitReachedError)
|
192
|
+
end
|
189
193
|
end
|
190
194
|
|
191
195
|
describe '#crawl' do
|
@@ -0,0 +1,412 @@
|
|
1
|
+
---
|
2
|
+
http_interactions:
|
3
|
+
- request:
|
4
|
+
method: get
|
5
|
+
uri: http://wayback.archive.org/web/20050204085854im_/http://www.drpep.com/images/home_19.gif
|
6
|
+
body:
|
7
|
+
encoding: US-ASCII
|
8
|
+
string: ''
|
9
|
+
headers:
|
10
|
+
accept:
|
11
|
+
- ! '*/*; q=0.5, application/xml'
|
12
|
+
accept-encoding:
|
13
|
+
- gzip, deflate
|
14
|
+
user-agent:
|
15
|
+
- Ruby
|
16
|
+
response:
|
17
|
+
status:
|
18
|
+
code: 302
|
19
|
+
message: Moved Temporarily
|
20
|
+
headers:
|
21
|
+
server:
|
22
|
+
- Tengine/1.3.0
|
23
|
+
date:
|
24
|
+
- Thu, 24 Jan 2013 03:03:50 GMT
|
25
|
+
content-type:
|
26
|
+
- image/gif
|
27
|
+
connection:
|
28
|
+
- keep-alive
|
29
|
+
set-cookie:
|
30
|
+
- wayback_server=94;Domain=archive.org;Expires=Sat, 23-Feb-13 03:03:50 GMT;
|
31
|
+
location:
|
32
|
+
- /web/20110715052543im_/http://drpep.com/images/home_19.gif
|
33
|
+
content-length:
|
34
|
+
- '0'
|
35
|
+
x-page-cache:
|
36
|
+
- MISS
|
37
|
+
body:
|
38
|
+
encoding: US-ASCII
|
39
|
+
string: ''
|
40
|
+
http_version: '1.1'
|
41
|
+
recorded_at: Thu, 24 Jan 2013 03:03:50 GMT
|
42
|
+
- request:
|
43
|
+
method: get
|
44
|
+
uri: http://wayback.archive.org/web/20110715052543im_/http:/drpep.com/images/home_19.gif
|
45
|
+
body:
|
46
|
+
encoding: US-ASCII
|
47
|
+
string: ''
|
48
|
+
headers:
|
49
|
+
accept:
|
50
|
+
- ! '*/*; q=0.5, application/xml'
|
51
|
+
accept-encoding:
|
52
|
+
- gzip, deflate
|
53
|
+
cookie:
|
54
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
55
|
+
user-agent:
|
56
|
+
- Ruby
|
57
|
+
response:
|
58
|
+
status:
|
59
|
+
code: 302
|
60
|
+
message: Moved Temporarily
|
61
|
+
headers:
|
62
|
+
server:
|
63
|
+
- Tengine/1.3.0
|
64
|
+
date:
|
65
|
+
- Thu, 24 Jan 2013 03:03:51 GMT
|
66
|
+
connection:
|
67
|
+
- keep-alive
|
68
|
+
location:
|
69
|
+
- /web/20110721121019im_/http://drpep.com/images/home_19.gif
|
70
|
+
content-length:
|
71
|
+
- '0'
|
72
|
+
x-page-cache:
|
73
|
+
- MISS
|
74
|
+
body:
|
75
|
+
encoding: US-ASCII
|
76
|
+
string: ''
|
77
|
+
http_version: '1.1'
|
78
|
+
recorded_at: Thu, 24 Jan 2013 03:03:51 GMT
|
79
|
+
- request:
|
80
|
+
method: get
|
81
|
+
uri: http://wayback.archive.org/web/20110721121019im_/http:/drpep.com/images/home_19.gif
|
82
|
+
body:
|
83
|
+
encoding: US-ASCII
|
84
|
+
string: ''
|
85
|
+
headers:
|
86
|
+
accept:
|
87
|
+
- ! '*/*; q=0.5, application/xml'
|
88
|
+
accept-encoding:
|
89
|
+
- gzip, deflate
|
90
|
+
cookie:
|
91
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
92
|
+
user-agent:
|
93
|
+
- Ruby
|
94
|
+
response:
|
95
|
+
status:
|
96
|
+
code: 302
|
97
|
+
message: Moved Temporarily
|
98
|
+
headers:
|
99
|
+
server:
|
100
|
+
- Tengine/1.3.0
|
101
|
+
date:
|
102
|
+
- Thu, 24 Jan 2013 03:03:51 GMT
|
103
|
+
connection:
|
104
|
+
- keep-alive
|
105
|
+
location:
|
106
|
+
- /web/20110715052543im_/http://drpep.com/images/home_19.gif
|
107
|
+
content-length:
|
108
|
+
- '0'
|
109
|
+
x-page-cache:
|
110
|
+
- MISS
|
111
|
+
body:
|
112
|
+
encoding: US-ASCII
|
113
|
+
string: ''
|
114
|
+
http_version: '1.1'
|
115
|
+
recorded_at: Thu, 24 Jan 2013 03:03:51 GMT
|
116
|
+
- request:
|
117
|
+
method: get
|
118
|
+
uri: http://wayback.archive.org/web/20110715052543im_/http:/drpep.com/images/home_19.gif
|
119
|
+
body:
|
120
|
+
encoding: US-ASCII
|
121
|
+
string: ''
|
122
|
+
headers:
|
123
|
+
accept:
|
124
|
+
- ! '*/*; q=0.5, application/xml'
|
125
|
+
accept-encoding:
|
126
|
+
- gzip, deflate
|
127
|
+
cookie:
|
128
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
129
|
+
user-agent:
|
130
|
+
- Ruby
|
131
|
+
response:
|
132
|
+
status:
|
133
|
+
code: 302
|
134
|
+
message: Moved Temporarily
|
135
|
+
headers:
|
136
|
+
server:
|
137
|
+
- Tengine/1.3.0
|
138
|
+
date:
|
139
|
+
- Thu, 24 Jan 2013 03:03:51 GMT
|
140
|
+
connection:
|
141
|
+
- keep-alive
|
142
|
+
location:
|
143
|
+
- /web/20110721121019im_/http://drpep.com/images/home_19.gif
|
144
|
+
content-length:
|
145
|
+
- '0'
|
146
|
+
x-page-cache:
|
147
|
+
- HIT
|
148
|
+
body:
|
149
|
+
encoding: US-ASCII
|
150
|
+
string: ''
|
151
|
+
http_version: '1.1'
|
152
|
+
recorded_at: Thu, 24 Jan 2013 03:03:51 GMT
|
153
|
+
- request:
|
154
|
+
method: get
|
155
|
+
uri: http://wayback.archive.org/web/20110721121019im_/http:/drpep.com/images/home_19.gif
|
156
|
+
body:
|
157
|
+
encoding: US-ASCII
|
158
|
+
string: ''
|
159
|
+
headers:
|
160
|
+
accept:
|
161
|
+
- ! '*/*; q=0.5, application/xml'
|
162
|
+
accept-encoding:
|
163
|
+
- gzip, deflate
|
164
|
+
cookie:
|
165
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
166
|
+
user-agent:
|
167
|
+
- Ruby
|
168
|
+
response:
|
169
|
+
status:
|
170
|
+
code: 302
|
171
|
+
message: Moved Temporarily
|
172
|
+
headers:
|
173
|
+
server:
|
174
|
+
- Tengine/1.3.0
|
175
|
+
date:
|
176
|
+
- Thu, 24 Jan 2013 03:03:51 GMT
|
177
|
+
connection:
|
178
|
+
- keep-alive
|
179
|
+
location:
|
180
|
+
- /web/20110715052543im_/http://drpep.com/images/home_19.gif
|
181
|
+
content-length:
|
182
|
+
- '0'
|
183
|
+
x-page-cache:
|
184
|
+
- HIT
|
185
|
+
body:
|
186
|
+
encoding: US-ASCII
|
187
|
+
string: ''
|
188
|
+
http_version: '1.1'
|
189
|
+
recorded_at: Thu, 24 Jan 2013 03:03:51 GMT
|
190
|
+
- request:
|
191
|
+
method: get
|
192
|
+
uri: http://wayback.archive.org/web/20110715052543im_/http:/drpep.com/images/home_19.gif
|
193
|
+
body:
|
194
|
+
encoding: US-ASCII
|
195
|
+
string: ''
|
196
|
+
headers:
|
197
|
+
accept:
|
198
|
+
- ! '*/*; q=0.5, application/xml'
|
199
|
+
accept-encoding:
|
200
|
+
- gzip, deflate
|
201
|
+
cookie:
|
202
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
203
|
+
user-agent:
|
204
|
+
- Ruby
|
205
|
+
response:
|
206
|
+
status:
|
207
|
+
code: 302
|
208
|
+
message: Moved Temporarily
|
209
|
+
headers:
|
210
|
+
server:
|
211
|
+
- Tengine/1.3.0
|
212
|
+
date:
|
213
|
+
- Thu, 24 Jan 2013 03:03:51 GMT
|
214
|
+
connection:
|
215
|
+
- keep-alive
|
216
|
+
location:
|
217
|
+
- /web/20110721121019im_/http://drpep.com/images/home_19.gif
|
218
|
+
content-length:
|
219
|
+
- '0'
|
220
|
+
x-page-cache:
|
221
|
+
- HIT
|
222
|
+
body:
|
223
|
+
encoding: US-ASCII
|
224
|
+
string: ''
|
225
|
+
http_version: '1.1'
|
226
|
+
recorded_at: Thu, 24 Jan 2013 03:03:51 GMT
|
227
|
+
- request:
|
228
|
+
method: get
|
229
|
+
uri: http://wayback.archive.org/web/20110721121019im_/http:/drpep.com/images/home_19.gif
|
230
|
+
body:
|
231
|
+
encoding: US-ASCII
|
232
|
+
string: ''
|
233
|
+
headers:
|
234
|
+
accept:
|
235
|
+
- ! '*/*; q=0.5, application/xml'
|
236
|
+
accept-encoding:
|
237
|
+
- gzip, deflate
|
238
|
+
cookie:
|
239
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
240
|
+
user-agent:
|
241
|
+
- Ruby
|
242
|
+
response:
|
243
|
+
status:
|
244
|
+
code: 302
|
245
|
+
message: Moved Temporarily
|
246
|
+
headers:
|
247
|
+
server:
|
248
|
+
- Tengine/1.3.0
|
249
|
+
date:
|
250
|
+
- Thu, 24 Jan 2013 03:03:51 GMT
|
251
|
+
connection:
|
252
|
+
- keep-alive
|
253
|
+
location:
|
254
|
+
- /web/20110715052543im_/http://drpep.com/images/home_19.gif
|
255
|
+
content-length:
|
256
|
+
- '0'
|
257
|
+
x-page-cache:
|
258
|
+
- HIT
|
259
|
+
body:
|
260
|
+
encoding: US-ASCII
|
261
|
+
string: ''
|
262
|
+
http_version: '1.1'
|
263
|
+
recorded_at: Thu, 24 Jan 2013 03:03:51 GMT
|
264
|
+
- request:
|
265
|
+
method: get
|
266
|
+
uri: http://wayback.archive.org/web/20110715052543im_/http:/drpep.com/images/home_19.gif
|
267
|
+
body:
|
268
|
+
encoding: US-ASCII
|
269
|
+
string: ''
|
270
|
+
headers:
|
271
|
+
accept:
|
272
|
+
- ! '*/*; q=0.5, application/xml'
|
273
|
+
accept-encoding:
|
274
|
+
- gzip, deflate
|
275
|
+
cookie:
|
276
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
277
|
+
user-agent:
|
278
|
+
- Ruby
|
279
|
+
response:
|
280
|
+
status:
|
281
|
+
code: 302
|
282
|
+
message: Moved Temporarily
|
283
|
+
headers:
|
284
|
+
server:
|
285
|
+
- Tengine/1.3.0
|
286
|
+
date:
|
287
|
+
- Thu, 24 Jan 2013 03:03:52 GMT
|
288
|
+
connection:
|
289
|
+
- keep-alive
|
290
|
+
location:
|
291
|
+
- /web/20110721121019im_/http://drpep.com/images/home_19.gif
|
292
|
+
content-length:
|
293
|
+
- '0'
|
294
|
+
x-page-cache:
|
295
|
+
- HIT
|
296
|
+
body:
|
297
|
+
encoding: US-ASCII
|
298
|
+
string: ''
|
299
|
+
http_version: '1.1'
|
300
|
+
recorded_at: Thu, 24 Jan 2013 03:03:52 GMT
|
301
|
+
- request:
|
302
|
+
method: get
|
303
|
+
uri: http://wayback.archive.org/web/20110721121019im_/http:/drpep.com/images/home_19.gif
|
304
|
+
body:
|
305
|
+
encoding: US-ASCII
|
306
|
+
string: ''
|
307
|
+
headers:
|
308
|
+
accept:
|
309
|
+
- ! '*/*; q=0.5, application/xml'
|
310
|
+
accept-encoding:
|
311
|
+
- gzip, deflate
|
312
|
+
cookie:
|
313
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
314
|
+
user-agent:
|
315
|
+
- Ruby
|
316
|
+
response:
|
317
|
+
status:
|
318
|
+
code: 302
|
319
|
+
message: Moved Temporarily
|
320
|
+
headers:
|
321
|
+
server:
|
322
|
+
- Tengine/1.3.0
|
323
|
+
date:
|
324
|
+
- Thu, 24 Jan 2013 03:03:52 GMT
|
325
|
+
connection:
|
326
|
+
- keep-alive
|
327
|
+
location:
|
328
|
+
- /web/20110715052543im_/http://drpep.com/images/home_19.gif
|
329
|
+
content-length:
|
330
|
+
- '0'
|
331
|
+
x-page-cache:
|
332
|
+
- HIT
|
333
|
+
body:
|
334
|
+
encoding: US-ASCII
|
335
|
+
string: ''
|
336
|
+
http_version: '1.1'
|
337
|
+
recorded_at: Thu, 24 Jan 2013 03:03:52 GMT
|
338
|
+
- request:
|
339
|
+
method: get
|
340
|
+
uri: http://wayback.archive.org/web/20110715052543im_/http:/drpep.com/images/home_19.gif
|
341
|
+
body:
|
342
|
+
encoding: US-ASCII
|
343
|
+
string: ''
|
344
|
+
headers:
|
345
|
+
accept:
|
346
|
+
- ! '*/*; q=0.5, application/xml'
|
347
|
+
accept-encoding:
|
348
|
+
- gzip, deflate
|
349
|
+
cookie:
|
350
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
351
|
+
user-agent:
|
352
|
+
- Ruby
|
353
|
+
response:
|
354
|
+
status:
|
355
|
+
code: 302
|
356
|
+
message: Moved Temporarily
|
357
|
+
headers:
|
358
|
+
server:
|
359
|
+
- Tengine/1.3.0
|
360
|
+
date:
|
361
|
+
- Thu, 24 Jan 2013 03:03:52 GMT
|
362
|
+
connection:
|
363
|
+
- keep-alive
|
364
|
+
location:
|
365
|
+
- /web/20110721121019im_/http://drpep.com/images/home_19.gif
|
366
|
+
content-length:
|
367
|
+
- '0'
|
368
|
+
x-page-cache:
|
369
|
+
- HIT
|
370
|
+
body:
|
371
|
+
encoding: US-ASCII
|
372
|
+
string: ''
|
373
|
+
http_version: '1.1'
|
374
|
+
recorded_at: Thu, 24 Jan 2013 03:03:52 GMT
|
375
|
+
- request:
|
376
|
+
method: get
|
377
|
+
uri: http://wayback.archive.org/web/20110721121019im_/http:/drpep.com/images/home_19.gif
|
378
|
+
body:
|
379
|
+
encoding: US-ASCII
|
380
|
+
string: ''
|
381
|
+
headers:
|
382
|
+
accept:
|
383
|
+
- ! '*/*; q=0.5, application/xml'
|
384
|
+
accept-encoding:
|
385
|
+
- gzip, deflate
|
386
|
+
cookie:
|
387
|
+
- Domain=archive.org; Expires=Sat; wayback_server=94
|
388
|
+
user-agent:
|
389
|
+
- Ruby
|
390
|
+
response:
|
391
|
+
status:
|
392
|
+
code: 302
|
393
|
+
message: Moved Temporarily
|
394
|
+
headers:
|
395
|
+
server:
|
396
|
+
- Tengine/1.3.0
|
397
|
+
date:
|
398
|
+
- Thu, 24 Jan 2013 03:03:52 GMT
|
399
|
+
connection:
|
400
|
+
- keep-alive
|
401
|
+
location:
|
402
|
+
- /web/20110715052543im_/http://drpep.com/images/home_19.gif
|
403
|
+
content-length:
|
404
|
+
- '0'
|
405
|
+
x-page-cache:
|
406
|
+
- HIT
|
407
|
+
body:
|
408
|
+
encoding: US-ASCII
|
409
|
+
string: ''
|
410
|
+
http_version: '1.1'
|
411
|
+
recorded_at: Thu, 24 Jan 2013 03:03:52 GMT
|
412
|
+
recorded_with: VCR 2.3.0
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dubdubdub
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.
|
4
|
+
version: 0.3.3
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -193,6 +193,7 @@ files:
|
|
193
193
|
- spec/vcr/follow/uri_error.yml
|
194
194
|
- spec/vcr/get/basic.yml
|
195
195
|
- spec/vcr/get/doesnt_exist.yml
|
196
|
+
- spec/vcr/get/infinite_redirects.yml
|
196
197
|
- spec/vcr/get/params.yml
|
197
198
|
- spec/vcr/get/proxy.yml
|
198
199
|
homepage: http://github.com/axsuul/dubdubdub
|
@@ -210,7 +211,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
210
211
|
version: '0'
|
211
212
|
segments:
|
212
213
|
- 0
|
213
|
-
hash:
|
214
|
+
hash: 1726643959394672028
|
214
215
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
215
216
|
none: false
|
216
217
|
requirements:
|