sengi 0.1.0
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.
- checksums.yaml +7 -0
- data/.gitignore +7 -0
- data/Gemfile +3 -0
- data/Gemfile.lock +71 -0
- data/Makefile +23 -0
- data/Makefile.common +58 -0
- data/README.md +59 -0
- data/Rakefile +25 -0
- data/bin/config +148 -0
- data/bin/crawler +64 -0
- data/bin/list +129 -0
- data/bin/redis_start +11 -0
- data/bin/redis_stats +13 -0
- data/bin/redis_stop +10 -0
- data/bin/resque_crawler_restart +14 -0
- data/bin/resque_crawler_start +21 -0
- data/bin/resque_crawler_stop +20 -0
- data/bin/resque_scheduler_start +15 -0
- data/bin/resque_scheduler_stop +16 -0
- data/bin/resque_server_start +13 -0
- data/bin/resque_server_stop +13 -0
- data/config/redis.conf +120 -0
- data/config/resque_server_config.rb +6 -0
- data/lib/sengi.rb +5 -0
- data/lib/sengi/crawler.rb +589 -0
- data/lib/sengi/crawler_worker.rb +16 -0
- data/lib/sengi/uri.rb +288 -0
- data/lib/sengi/version.rb +17 -0
- data/sengi.gemspec +37 -0
- data/sengi.sublime-project +10 -0
- data/tests/tc_crawler.rb +14 -0
- data/tests/tc_uri.rb +140 -0
- data/tests/ts_all.rb +4 -0
- metadata +202 -0
data/tests/ts_all.rb
ADDED
metadata
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: sengi
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Christian Mayer
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2016-05-07 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: minitest
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - "~>"
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '5.8'
|
|
20
|
+
type: :development
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - "~>"
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '5.8'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: activesupport
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - "~>"
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '4.2'
|
|
34
|
+
type: :runtime
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - "~>"
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '4.2'
|
|
41
|
+
- !ruby/object:Gem::Dependency
|
|
42
|
+
name: redis
|
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
|
44
|
+
requirements:
|
|
45
|
+
- - "~>"
|
|
46
|
+
- !ruby/object:Gem::Version
|
|
47
|
+
version: '3.2'
|
|
48
|
+
type: :runtime
|
|
49
|
+
prerelease: false
|
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
51
|
+
requirements:
|
|
52
|
+
- - "~>"
|
|
53
|
+
- !ruby/object:Gem::Version
|
|
54
|
+
version: '3.2'
|
|
55
|
+
- !ruby/object:Gem::Dependency
|
|
56
|
+
name: hiredis
|
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
|
58
|
+
requirements:
|
|
59
|
+
- - "~>"
|
|
60
|
+
- !ruby/object:Gem::Version
|
|
61
|
+
version: '0.6'
|
|
62
|
+
type: :runtime
|
|
63
|
+
prerelease: false
|
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
65
|
+
requirements:
|
|
66
|
+
- - "~>"
|
|
67
|
+
- !ruby/object:Gem::Version
|
|
68
|
+
version: '0.6'
|
|
69
|
+
- !ruby/object:Gem::Dependency
|
|
70
|
+
name: resque
|
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
|
72
|
+
requirements:
|
|
73
|
+
- - "~>"
|
|
74
|
+
- !ruby/object:Gem::Version
|
|
75
|
+
version: '1.26'
|
|
76
|
+
type: :runtime
|
|
77
|
+
prerelease: false
|
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
79
|
+
requirements:
|
|
80
|
+
- - "~>"
|
|
81
|
+
- !ruby/object:Gem::Version
|
|
82
|
+
version: '1.26'
|
|
83
|
+
- !ruby/object:Gem::Dependency
|
|
84
|
+
name: resque-scheduler
|
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
|
86
|
+
requirements:
|
|
87
|
+
- - "~>"
|
|
88
|
+
- !ruby/object:Gem::Version
|
|
89
|
+
version: '4.1'
|
|
90
|
+
type: :runtime
|
|
91
|
+
prerelease: false
|
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
93
|
+
requirements:
|
|
94
|
+
- - "~>"
|
|
95
|
+
- !ruby/object:Gem::Version
|
|
96
|
+
version: '4.1'
|
|
97
|
+
- !ruby/object:Gem::Dependency
|
|
98
|
+
name: nokogiri
|
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
|
100
|
+
requirements:
|
|
101
|
+
- - "~>"
|
|
102
|
+
- !ruby/object:Gem::Version
|
|
103
|
+
version: '1.6'
|
|
104
|
+
type: :runtime
|
|
105
|
+
prerelease: false
|
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
107
|
+
requirements:
|
|
108
|
+
- - "~>"
|
|
109
|
+
- !ruby/object:Gem::Version
|
|
110
|
+
version: '1.6'
|
|
111
|
+
- !ruby/object:Gem::Dependency
|
|
112
|
+
name: cookiejar
|
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
|
114
|
+
requirements:
|
|
115
|
+
- - "~>"
|
|
116
|
+
- !ruby/object:Gem::Version
|
|
117
|
+
version: '0.3'
|
|
118
|
+
type: :runtime
|
|
119
|
+
prerelease: false
|
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
121
|
+
requirements:
|
|
122
|
+
- - "~>"
|
|
123
|
+
- !ruby/object:Gem::Version
|
|
124
|
+
version: '0.3'
|
|
125
|
+
- !ruby/object:Gem::Dependency
|
|
126
|
+
name: thefox-ext
|
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
|
128
|
+
requirements:
|
|
129
|
+
- - "~>"
|
|
130
|
+
- !ruby/object:Gem::Version
|
|
131
|
+
version: '1.4'
|
|
132
|
+
type: :runtime
|
|
133
|
+
prerelease: false
|
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
135
|
+
requirements:
|
|
136
|
+
- - "~>"
|
|
137
|
+
- !ruby/object:Gem::Version
|
|
138
|
+
version: '1.4'
|
|
139
|
+
description: A web crawler using Ruby and Redis.
|
|
140
|
+
email: christian@fox21.at
|
|
141
|
+
executables: []
|
|
142
|
+
extensions: []
|
|
143
|
+
extra_rdoc_files: []
|
|
144
|
+
files:
|
|
145
|
+
- ".gitignore"
|
|
146
|
+
- Gemfile
|
|
147
|
+
- Gemfile.lock
|
|
148
|
+
- Makefile
|
|
149
|
+
- Makefile.common
|
|
150
|
+
- README.md
|
|
151
|
+
- Rakefile
|
|
152
|
+
- bin/config
|
|
153
|
+
- bin/crawler
|
|
154
|
+
- bin/list
|
|
155
|
+
- bin/redis_start
|
|
156
|
+
- bin/redis_stats
|
|
157
|
+
- bin/redis_stop
|
|
158
|
+
- bin/resque_crawler_restart
|
|
159
|
+
- bin/resque_crawler_start
|
|
160
|
+
- bin/resque_crawler_stop
|
|
161
|
+
- bin/resque_scheduler_start
|
|
162
|
+
- bin/resque_scheduler_stop
|
|
163
|
+
- bin/resque_server_start
|
|
164
|
+
- bin/resque_server_stop
|
|
165
|
+
- config/redis.conf
|
|
166
|
+
- config/resque_server_config.rb
|
|
167
|
+
- lib/sengi.rb
|
|
168
|
+
- lib/sengi/crawler.rb
|
|
169
|
+
- lib/sengi/crawler_worker.rb
|
|
170
|
+
- lib/sengi/uri.rb
|
|
171
|
+
- lib/sengi/version.rb
|
|
172
|
+
- sengi.gemspec
|
|
173
|
+
- sengi.sublime-project
|
|
174
|
+
- tests/tc_crawler.rb
|
|
175
|
+
- tests/tc_uri.rb
|
|
176
|
+
- tests/ts_all.rb
|
|
177
|
+
homepage: https://github.com/TheFox/sengi
|
|
178
|
+
licenses:
|
|
179
|
+
- GPL-3.0
|
|
180
|
+
metadata: {}
|
|
181
|
+
post_install_message:
|
|
182
|
+
rdoc_options: []
|
|
183
|
+
require_paths:
|
|
184
|
+
- lib
|
|
185
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
186
|
+
requirements:
|
|
187
|
+
- - ">="
|
|
188
|
+
- !ruby/object:Gem::Version
|
|
189
|
+
version: 2.1.0
|
|
190
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
191
|
+
requirements:
|
|
192
|
+
- - ">="
|
|
193
|
+
- !ruby/object:Gem::Version
|
|
194
|
+
version: '0'
|
|
195
|
+
requirements: []
|
|
196
|
+
rubyforge_project:
|
|
197
|
+
rubygems_version: 2.4.7
|
|
198
|
+
signing_key:
|
|
199
|
+
specification_version: 4
|
|
200
|
+
summary: Sengi Web Crawler
|
|
201
|
+
test_files: []
|
|
202
|
+
has_rdoc:
|