anemone 0.7.1 → 0.7.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,3 +1,9 @@
1
+ == 0.7.2 / 2012-05-30
2
+
3
+ * Bug fixes
4
+
5
+ * Fix bug causing anchor links to have '#' converted to '%23'
6
+
1
7
  == 0.7.1 / 2012-01-20
2
8
 
3
9
  * Minor enhancements
data/VERSION CHANGED
@@ -1 +1 @@
1
- 0.7.1
1
+ 0.7.2
@@ -9,7 +9,7 @@ require 'anemone/storage/base'
9
9
 
10
10
  module Anemone
11
11
 
12
- VERSION = '0.7.1';
12
+ VERSION = '0.7.2';
13
13
 
14
14
  #
15
15
  # Convenience method to start a crawl
@@ -62,7 +62,7 @@ module Anemone
62
62
  doc.search("//a[@href]").each do |a|
63
63
  u = a['href']
64
64
  next if u.nil? or u.empty?
65
- abs = to_absolute(URI(URI.escape(u))) rescue next
65
+ abs = to_absolute(u) rescue next
66
66
  @links << abs if in_domain?(abs)
67
67
  end
68
68
  @links.uniq!
@@ -126,6 +126,14 @@ module Anemone
126
126
  end
127
127
  end
128
128
 
129
+ describe "#links" do
130
+ it "should not convert anchors to %23" do
131
+ page = @http.fetch_page(FakePage.new('', :body => '<a href="#top">Top</a>').url)
132
+ page.links.should have(1).link
133
+ page.links.first.to_s.should == SPEC_DOMAIN
134
+ end
135
+ end
136
+
129
137
  it "should detect, store and expose the base url for the page head" do
130
138
  base = "#{SPEC_DOMAIN}path/to/base_url/"
131
139
  page = @http.fetch_page(FakePage.new('body_test', {:base => base}).url)
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: anemone
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.7.1
4
+ version: 0.7.2
5
5
  prerelease:
6
6
  platform: ruby
7
7
  authors:
@@ -9,11 +9,11 @@ authors:
9
9
  autorequire:
10
10
  bindir: bin
11
11
  cert_chain: []
12
- date: 2012-01-20 00:00:00.000000000Z
12
+ date: 2012-05-30 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
15
  name: nokogiri
16
- requirement: &23166540 !ruby/object:Gem::Requirement
16
+ requirement: !ruby/object:Gem::Requirement
17
17
  none: false
18
18
  requirements:
19
19
  - - ! '>='
@@ -21,10 +21,15 @@ dependencies:
21
21
  version: 1.3.0
22
22
  type: :runtime
23
23
  prerelease: false
24
- version_requirements: *23166540
24
+ version_requirements: !ruby/object:Gem::Requirement
25
+ none: false
26
+ requirements:
27
+ - - ! '>='
28
+ - !ruby/object:Gem::Version
29
+ version: 1.3.0
25
30
  - !ruby/object:Gem::Dependency
26
31
  name: robotex
27
- requirement: &23166060 !ruby/object:Gem::Requirement
32
+ requirement: !ruby/object:Gem::Requirement
28
33
  none: false
29
34
  requirements:
30
35
  - - ! '>='
@@ -32,10 +37,15 @@ dependencies:
32
37
  version: 1.0.0
33
38
  type: :runtime
34
39
  prerelease: false
35
- version_requirements: *23166060
40
+ version_requirements: !ruby/object:Gem::Requirement
41
+ none: false
42
+ requirements:
43
+ - - ! '>='
44
+ - !ruby/object:Gem::Version
45
+ version: 1.0.0
36
46
  - !ruby/object:Gem::Dependency
37
47
  name: rake
38
- requirement: &23165600 !ruby/object:Gem::Requirement
48
+ requirement: !ruby/object:Gem::Requirement
39
49
  none: false
40
50
  requirements:
41
51
  - - ! '>='
@@ -43,10 +53,15 @@ dependencies:
43
53
  version: 0.9.2
44
54
  type: :development
45
55
  prerelease: false
46
- version_requirements: *23165600
56
+ version_requirements: !ruby/object:Gem::Requirement
57
+ none: false
58
+ requirements:
59
+ - - ! '>='
60
+ - !ruby/object:Gem::Version
61
+ version: 0.9.2
47
62
  - !ruby/object:Gem::Dependency
48
63
  name: rdoc
49
- requirement: &23165140 !ruby/object:Gem::Requirement
64
+ requirement: !ruby/object:Gem::Requirement
50
65
  none: false
51
66
  requirements:
52
67
  - - ! '>='
@@ -54,10 +69,15 @@ dependencies:
54
69
  version: '3.12'
55
70
  type: :development
56
71
  prerelease: false
57
- version_requirements: *23165140
72
+ version_requirements: !ruby/object:Gem::Requirement
73
+ none: false
74
+ requirements:
75
+ - - ! '>='
76
+ - !ruby/object:Gem::Version
77
+ version: '3.12'
58
78
  - !ruby/object:Gem::Dependency
59
79
  name: rspec
60
- requirement: &23164680 !ruby/object:Gem::Requirement
80
+ requirement: !ruby/object:Gem::Requirement
61
81
  none: false
62
82
  requirements:
63
83
  - - ! '>='
@@ -65,10 +85,15 @@ dependencies:
65
85
  version: 2.8.0
66
86
  type: :development
67
87
  prerelease: false
68
- version_requirements: *23164680
88
+ version_requirements: !ruby/object:Gem::Requirement
89
+ none: false
90
+ requirements:
91
+ - - ! '>='
92
+ - !ruby/object:Gem::Version
93
+ version: 2.8.0
69
94
  - !ruby/object:Gem::Dependency
70
95
  name: fakeweb
71
- requirement: &18439940 !ruby/object:Gem::Requirement
96
+ requirement: !ruby/object:Gem::Requirement
72
97
  none: false
73
98
  requirements:
74
99
  - - ! '>='
@@ -76,10 +101,15 @@ dependencies:
76
101
  version: 1.3.0
77
102
  type: :development
78
103
  prerelease: false
79
- version_requirements: *18439940
104
+ version_requirements: !ruby/object:Gem::Requirement
105
+ none: false
106
+ requirements:
107
+ - - ! '>='
108
+ - !ruby/object:Gem::Version
109
+ version: 1.3.0
80
110
  - !ruby/object:Gem::Dependency
81
111
  name: redis
82
- requirement: &21684560 !ruby/object:Gem::Requirement
112
+ requirement: !ruby/object:Gem::Requirement
83
113
  none: false
84
114
  requirements:
85
115
  - - ! '>='
@@ -87,10 +117,15 @@ dependencies:
87
117
  version: 2.2.0
88
118
  type: :development
89
119
  prerelease: false
90
- version_requirements: *21684560
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ none: false
122
+ requirements:
123
+ - - ! '>='
124
+ - !ruby/object:Gem::Version
125
+ version: 2.2.0
91
126
  - !ruby/object:Gem::Dependency
92
127
  name: mongo
93
- requirement: &21856420 !ruby/object:Gem::Requirement
128
+ requirement: !ruby/object:Gem::Requirement
94
129
  none: false
95
130
  requirements:
96
131
  - - ! '>='
@@ -98,10 +133,15 @@ dependencies:
98
133
  version: 1.3.1
99
134
  type: :development
100
135
  prerelease: false
101
- version_requirements: *21856420
136
+ version_requirements: !ruby/object:Gem::Requirement
137
+ none: false
138
+ requirements:
139
+ - - ! '>='
140
+ - !ruby/object:Gem::Version
141
+ version: 1.3.1
102
142
  - !ruby/object:Gem::Dependency
103
143
  name: bson_ext
104
- requirement: &21924200 !ruby/object:Gem::Requirement
144
+ requirement: !ruby/object:Gem::Requirement
105
145
  none: false
106
146
  requirements:
107
147
  - - ! '>='
@@ -109,10 +149,15 @@ dependencies:
109
149
  version: 1.3.1
110
150
  type: :development
111
151
  prerelease: false
112
- version_requirements: *21924200
152
+ version_requirements: !ruby/object:Gem::Requirement
153
+ none: false
154
+ requirements:
155
+ - - ! '>='
156
+ - !ruby/object:Gem::Version
157
+ version: 1.3.1
113
158
  - !ruby/object:Gem::Dependency
114
159
  name: tokyocabinet
115
- requirement: &22177700 !ruby/object:Gem::Requirement
160
+ requirement: !ruby/object:Gem::Requirement
116
161
  none: false
117
162
  requirements:
118
163
  - - ! '>='
@@ -120,10 +165,15 @@ dependencies:
120
165
  version: '1.29'
121
166
  type: :development
122
167
  prerelease: false
123
- version_requirements: *22177700
168
+ version_requirements: !ruby/object:Gem::Requirement
169
+ none: false
170
+ requirements:
171
+ - - ! '>='
172
+ - !ruby/object:Gem::Version
173
+ version: '1.29'
124
174
  - !ruby/object:Gem::Dependency
125
175
  name: kyotocabinet-ruby
126
- requirement: &22411440 !ruby/object:Gem::Requirement
176
+ requirement: !ruby/object:Gem::Requirement
127
177
  none: false
128
178
  requirements:
129
179
  - - ! '>='
@@ -131,10 +181,15 @@ dependencies:
131
181
  version: 1.27.1
132
182
  type: :development
133
183
  prerelease: false
134
- version_requirements: *22411440
184
+ version_requirements: !ruby/object:Gem::Requirement
185
+ none: false
186
+ requirements:
187
+ - - ! '>='
188
+ - !ruby/object:Gem::Version
189
+ version: 1.27.1
135
190
  - !ruby/object:Gem::Dependency
136
191
  name: sqlite3
137
- requirement: &22845660 !ruby/object:Gem::Requirement
192
+ requirement: !ruby/object:Gem::Requirement
138
193
  none: false
139
194
  requirements:
140
195
  - - ! '>='
@@ -142,7 +197,12 @@ dependencies:
142
197
  version: 1.3.4
143
198
  type: :development
144
199
  prerelease: false
145
- version_requirements: *22845660
200
+ version_requirements: !ruby/object:Gem::Requirement
201
+ none: false
202
+ requirements:
203
+ - - ! '>='
204
+ - !ruby/object:Gem::Version
205
+ version: 1.3.4
146
206
  description:
147
207
  email:
148
208
  executables:
@@ -156,39 +216,40 @@ files:
156
216
  - CHANGELOG.rdoc
157
217
  - README.rdoc
158
218
  - Rakefile
159
- - lib/anemone.rb
160
- - lib/anemone/cookie_store.rb
161
219
  - lib/anemone/page.rb
220
+ - lib/anemone/cli.rb
162
221
  - lib/anemone/storage.rb
222
+ - lib/anemone/tentacle.rb
163
223
  - lib/anemone/page_store.rb
164
- - lib/anemone/storage/tokyo_cabinet.rb
165
224
  - lib/anemone/storage/pstore.rb
166
225
  - lib/anemone/storage/kyoto_cabinet.rb
226
+ - lib/anemone/storage/redis.rb
227
+ - lib/anemone/storage/sqlite3.rb
228
+ - lib/anemone/storage/tokyo_cabinet.rb
229
+ - lib/anemone/storage/base.rb
167
230
  - lib/anemone/storage/mongodb.rb
168
231
  - lib/anemone/storage/exceptions.rb
169
- - lib/anemone/storage/base.rb
170
- - lib/anemone/storage/sqlite3.rb
171
- - lib/anemone/storage/redis.rb
172
- - lib/anemone/exceptions.rb
173
- - lib/anemone/cli.rb
174
- - lib/anemone/tentacle.rb
175
- - lib/anemone/http.rb
176
- - lib/anemone/core.rb
177
- - lib/anemone/cli/serialize.rb
232
+ - lib/anemone/cookie_store.rb
233
+ - lib/anemone/cli/count.rb
178
234
  - lib/anemone/cli/pagedepth.rb
179
- - lib/anemone/cli/cron.rb
180
235
  - lib/anemone/cli/url_list.rb
181
- - lib/anemone/cli/count.rb
182
- - spec/core_spec.rb
183
- - spec/anemone_spec.rb
236
+ - lib/anemone/cli/serialize.rb
237
+ - lib/anemone/cli/cron.rb
238
+ - lib/anemone/http.rb
239
+ - lib/anemone/core.rb
240
+ - lib/anemone/exceptions.rb
241
+ - lib/anemone.rb
242
+ - spec/fakeweb_helper.rb
184
243
  - spec/spec_helper.rb
185
244
  - spec/page_store_spec.rb
186
- - spec/page_spec.rb
187
245
  - spec/cookie_store_spec.rb
188
- - spec/fakeweb_helper.rb
189
- - spec/http_spec.rb
246
+ - spec/core_spec.rb
247
+ - spec/page_spec.rb
190
248
  - spec/storage_spec.rb
191
- - bin/anemone
249
+ - spec/http_spec.rb
250
+ - spec/anemone_spec.rb
251
+ - !binary |-
252
+ YmluL2FuZW1vbmU=
192
253
  homepage: http://anemone.rubyforge.org
193
254
  licenses: []
194
255
  post_install_message:
@@ -213,17 +274,17 @@ required_rubygems_version: !ruby/object:Gem::Requirement
213
274
  version: '0'
214
275
  requirements: []
215
276
  rubyforge_project: anemone
216
- rubygems_version: 1.8.15
277
+ rubygems_version: 1.8.21
217
278
  signing_key:
218
279
  specification_version: 3
219
280
  summary: Anemone web-spider framework
220
281
  test_files:
221
- - spec/core_spec.rb
222
- - spec/anemone_spec.rb
282
+ - spec/fakeweb_helper.rb
223
283
  - spec/spec_helper.rb
224
284
  - spec/page_store_spec.rb
225
- - spec/page_spec.rb
226
285
  - spec/cookie_store_spec.rb
227
- - spec/fakeweb_helper.rb
228
- - spec/http_spec.rb
286
+ - spec/core_spec.rb
287
+ - spec/page_spec.rb
229
288
  - spec/storage_spec.rb
289
+ - spec/http_spec.rb
290
+ - spec/anemone_spec.rb