apollo-crawler 0.1.18 → 0.1.19
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/lib/apollo_crawler.rb +3 -0
- data/lib/apollo_crawler/cache/mongo_cache.rb +2 -0
- data/lib/apollo_crawler/cli/cli.rb +19 -0
- data/lib/apollo_crawler/config.rb +3 -3
- data/lib/apollo_crawler/crawler/base_crawler.rb +2 -0
- data/lib/apollo_crawler/fetcher/base_fetcher.rb +28 -4
- data/lib/apollo_crawler/lib.rb +4 -0
- data/lib/apollo_crawler/program/crawler_program.rb +1 -2
- data/lib/apollo_crawler/version.rb +1 -1
- metadata +45 -80
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
OGFlNjhjOWJhMjI2YjdkMmU5YzgzMDUxZWEyNGI5MWZhMGIzYmRlZg==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
ODc3YTMzOGIzMWU0Zjg2MDc4Njg5NWFlZWE5MDY0OTc5NWY0YmMyNg==
|
7
|
+
!binary "U0hBNTEy":
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
MDQxM2U1YzYyNjRjOGYzN2RhZjY0ZmFjYTA5YWQxNWE3MDE3NTM3Mjg3OWE4
|
10
|
+
YWRkNmUzZWE3OGY5YjFjOTBiZTQ4YzY5ZGI4NmRmNjEyODVjMDQyZWE5MDk0
|
11
|
+
ZThiMGJmZjRjYWUyZWU1YTgwZGI0NDA1OGNmM2MyZDRiNGQzN2Y=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
Y2M4ZWRlZjFiOTE5OWE5NzA1YzY5YzU4NmYxMjdlMjJjZmM4ZTc5ZGZkOWUy
|
14
|
+
MWU1OTMzNTZhOWJkMzVhMzIxMmQ5MWViMWM0ZmQ5YmI5ZDVkMDc5MDUwYmFh
|
15
|
+
Mzg5MzhlZmUwZmQxZjhmZWFhNTUyNzlkNTZlMDNkNTc2NTFjNTE=
|
data/lib/apollo_crawler.rb
CHANGED
@@ -24,6 +24,9 @@
|
|
24
24
|
# Caches
|
25
25
|
require File.join(File.dirname(__FILE__), 'apollo_crawler/cache/caches')
|
26
26
|
|
27
|
+
# CLI - Command Line Interface
|
28
|
+
require File.join(File.dirname(__FILE__), 'apollo_crawler/cli/cli')
|
29
|
+
|
27
30
|
# Crawlers
|
28
31
|
require File.join(File.dirname(__FILE__), 'apollo_crawler/crawler/crawlers')
|
29
32
|
|
@@ -0,0 +1,19 @@
|
|
1
|
+
# Copyright, 2013, by Tomas Korcak. <korczis@gmail.com>
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
@@ -68,15 +68,15 @@ module RbConfig
|
|
68
68
|
# CACHE_CLASS = Apollo::Cache::NullCache
|
69
69
|
|
70
70
|
# Used caching mechanism by default
|
71
|
-
CACHE_CLASS = Apollo::Cache::
|
71
|
+
CACHE_CLASS = Apollo::Cache::MongoCache
|
72
72
|
|
73
73
|
CACHE_CLASS_OPTIONS = {
|
74
|
-
:host => '
|
74
|
+
:host => 'apollo-crawler.no-ip.org',
|
75
75
|
:port => 27017,
|
76
76
|
:pool_size => 5,
|
77
77
|
:pool_timeout => 5,
|
78
78
|
:db => 'apollo-crawler',
|
79
|
-
:collection => '
|
79
|
+
:collection => 'fetched_docs'
|
80
80
|
}
|
81
81
|
|
82
82
|
|
@@ -18,16 +18,40 @@
|
|
18
18
|
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
19
|
# THE SOFTWARE.
|
20
20
|
|
21
|
+
require 'cgi'
|
22
|
+
require "net/http"
|
21
23
|
require "open-uri"
|
22
|
-
require
|
23
|
-
|
24
|
-
require "em-http-request"
|
24
|
+
require 'faraday'
|
25
|
+
require 'ipaddr'
|
25
26
|
|
26
27
|
module Apollo
|
27
28
|
module Fetcher
|
28
29
|
class BaseFetcher
|
30
|
+
def self.get_fake_headers(url)
|
31
|
+
ip = IPAddr.new(rand(2**32), Socket::AF_INET).to_s
|
32
|
+
|
33
|
+
return {
|
34
|
+
"X-Forwarded-For" => ip
|
35
|
+
}
|
36
|
+
end
|
37
|
+
|
29
38
|
def self.fetch(url)
|
30
|
-
|
39
|
+
uri = URI.parse(url.to_s)
|
40
|
+
|
41
|
+
# See https://github.com/lostisland/faraday
|
42
|
+
conn = Faraday.new(:url => url) do |faraday|
|
43
|
+
# faraday.request :url_encoded # form-encode POST params
|
44
|
+
# faraday.response :logger # log requests to STDOUT
|
45
|
+
faraday.adapter Faraday.default_adapter # make requests with Net::HTTP
|
46
|
+
end
|
47
|
+
|
48
|
+
# Make request
|
49
|
+
res = conn.get(uri) do |request|
|
50
|
+
request.headers = BaseFetcher.get_fake_headers(uri)
|
51
|
+
end
|
52
|
+
|
53
|
+
# Return result
|
54
|
+
return res.body
|
31
55
|
end
|
32
56
|
end # class BaseFetcher
|
33
57
|
end # module Fetcher
|
data/lib/apollo_crawler/lib.rb
CHANGED
@@ -21,11 +21,15 @@
|
|
21
21
|
# Caches
|
22
22
|
require File.join(File.dirname(__FILE__), 'cache/caches')
|
23
23
|
|
24
|
+
# CLI - Command Line Interface
|
25
|
+
require File.join(File.dirname(__FILE__), 'cli/cli')
|
26
|
+
|
24
27
|
# Crawlers
|
25
28
|
require File.join(File.dirname(__FILE__), 'crawler/crawlers')
|
26
29
|
|
27
30
|
# Fetchers
|
28
31
|
require File.join(File.dirname(__FILE__), 'fetcher/fetchers')
|
32
|
+
|
29
33
|
# Formatters
|
30
34
|
require File.join(File.dirname(__FILE__), 'formatter/formatters')
|
31
35
|
|
@@ -65,6 +65,7 @@ module Apollo
|
|
65
65
|
@crawlers = {}
|
66
66
|
@formatter = RbConfig::DEFAULT_FORMATTER
|
67
67
|
@formatters = {}
|
68
|
+
@options = {}
|
68
69
|
|
69
70
|
at_exit {
|
70
71
|
at_exit_handler
|
@@ -73,8 +74,6 @@ module Apollo
|
|
73
74
|
|
74
75
|
# Initialize command-line options
|
75
76
|
def init_options()
|
76
|
-
@options = {}
|
77
|
-
|
78
77
|
@options[:doc_limit] = nil
|
79
78
|
@options[:verbose] = false
|
80
79
|
@options[:version] = false
|
metadata
CHANGED
@@ -1,8 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: apollo-crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
5
|
-
prerelease:
|
4
|
+
version: 0.1.19
|
6
5
|
platform: ruby
|
7
6
|
authors:
|
8
7
|
- Tomas Korcak
|
@@ -14,7 +13,6 @@ dependencies:
|
|
14
13
|
- !ruby/object:Gem::Dependency
|
15
14
|
name: awesome_print
|
16
15
|
requirement: !ruby/object:Gem::Requirement
|
17
|
-
none: false
|
18
16
|
requirements:
|
19
17
|
- - ~>
|
20
18
|
- !ruby/object:Gem::Version
|
@@ -22,7 +20,6 @@ dependencies:
|
|
22
20
|
type: :runtime
|
23
21
|
prerelease: false
|
24
22
|
version_requirements: !ruby/object:Gem::Requirement
|
25
|
-
none: false
|
26
23
|
requirements:
|
27
24
|
- - ~>
|
28
25
|
- !ruby/object:Gem::Version
|
@@ -30,7 +27,6 @@ dependencies:
|
|
30
27
|
- !ruby/object:Gem::Dependency
|
31
28
|
name: activesupport
|
32
29
|
requirement: !ruby/object:Gem::Requirement
|
33
|
-
none: false
|
34
30
|
requirements:
|
35
31
|
- - ! '>='
|
36
32
|
- !ruby/object:Gem::Version
|
@@ -38,7 +34,6 @@ dependencies:
|
|
38
34
|
type: :runtime
|
39
35
|
prerelease: false
|
40
36
|
version_requirements: !ruby/object:Gem::Requirement
|
41
|
-
none: false
|
42
37
|
requirements:
|
43
38
|
- - ! '>='
|
44
39
|
- !ruby/object:Gem::Version
|
@@ -46,7 +41,6 @@ dependencies:
|
|
46
41
|
- !ruby/object:Gem::Dependency
|
47
42
|
name: dalli
|
48
43
|
requirement: !ruby/object:Gem::Requirement
|
49
|
-
none: false
|
50
44
|
requirements:
|
51
45
|
- - ! '>='
|
52
46
|
- !ruby/object:Gem::Version
|
@@ -54,7 +48,6 @@ dependencies:
|
|
54
48
|
type: :runtime
|
55
49
|
prerelease: false
|
56
50
|
version_requirements: !ruby/object:Gem::Requirement
|
57
|
-
none: false
|
58
51
|
requirements:
|
59
52
|
- - ! '>='
|
60
53
|
- !ruby/object:Gem::Version
|
@@ -62,7 +55,6 @@ dependencies:
|
|
62
55
|
- !ruby/object:Gem::Dependency
|
63
56
|
name: fastercsv
|
64
57
|
requirement: !ruby/object:Gem::Requirement
|
65
|
-
none: false
|
66
58
|
requirements:
|
67
59
|
- - ~>
|
68
60
|
- !ruby/object:Gem::Version
|
@@ -70,7 +62,6 @@ dependencies:
|
|
70
62
|
type: :runtime
|
71
63
|
prerelease: false
|
72
64
|
version_requirements: !ruby/object:Gem::Requirement
|
73
|
-
none: false
|
74
65
|
requirements:
|
75
66
|
- - ~>
|
76
67
|
- !ruby/object:Gem::Version
|
@@ -78,7 +69,6 @@ dependencies:
|
|
78
69
|
- !ruby/object:Gem::Dependency
|
79
70
|
name: eventmachine
|
80
71
|
requirement: !ruby/object:Gem::Requirement
|
81
|
-
none: false
|
82
72
|
requirements:
|
83
73
|
- - ! '>='
|
84
74
|
- !ruby/object:Gem::Version
|
@@ -86,7 +76,6 @@ dependencies:
|
|
86
76
|
type: :runtime
|
87
77
|
prerelease: false
|
88
78
|
version_requirements: !ruby/object:Gem::Requirement
|
89
|
-
none: false
|
90
79
|
requirements:
|
91
80
|
- - ! '>='
|
92
81
|
- !ruby/object:Gem::Version
|
@@ -94,7 +83,6 @@ dependencies:
|
|
94
83
|
- !ruby/object:Gem::Dependency
|
95
84
|
name: em-http-request
|
96
85
|
requirement: !ruby/object:Gem::Requirement
|
97
|
-
none: false
|
98
86
|
requirements:
|
99
87
|
- - ! '>='
|
100
88
|
- !ruby/object:Gem::Version
|
@@ -102,7 +90,6 @@ dependencies:
|
|
102
90
|
type: :runtime
|
103
91
|
prerelease: false
|
104
92
|
version_requirements: !ruby/object:Gem::Requirement
|
105
|
-
none: false
|
106
93
|
requirements:
|
107
94
|
- - ! '>='
|
108
95
|
- !ruby/object:Gem::Version
|
@@ -110,7 +97,6 @@ dependencies:
|
|
110
97
|
- !ruby/object:Gem::Dependency
|
111
98
|
name: em-synchrony
|
112
99
|
requirement: !ruby/object:Gem::Requirement
|
113
|
-
none: false
|
114
100
|
requirements:
|
115
101
|
- - ! '>='
|
116
102
|
- !ruby/object:Gem::Version
|
@@ -118,15 +104,27 @@ dependencies:
|
|
118
104
|
type: :runtime
|
119
105
|
prerelease: false
|
120
106
|
version_requirements: !ruby/object:Gem::Requirement
|
121
|
-
none: false
|
122
107
|
requirements:
|
123
108
|
- - ! '>='
|
124
109
|
- !ruby/object:Gem::Version
|
125
110
|
version: '0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: faraday
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ~>
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: 0.8.6
|
118
|
+
type: :runtime
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ~>
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: 0.8.6
|
126
125
|
- !ruby/object:Gem::Dependency
|
127
126
|
name: amqp
|
128
127
|
requirement: !ruby/object:Gem::Requirement
|
129
|
-
none: false
|
130
128
|
requirements:
|
131
129
|
- - ~>
|
132
130
|
- !ruby/object:Gem::Version
|
@@ -134,7 +132,6 @@ dependencies:
|
|
134
132
|
type: :runtime
|
135
133
|
prerelease: false
|
136
134
|
version_requirements: !ruby/object:Gem::Requirement
|
137
|
-
none: false
|
138
135
|
requirements:
|
139
136
|
- - ~>
|
140
137
|
- !ruby/object:Gem::Version
|
@@ -142,7 +139,6 @@ dependencies:
|
|
142
139
|
- !ruby/object:Gem::Dependency
|
143
140
|
name: json
|
144
141
|
requirement: !ruby/object:Gem::Requirement
|
145
|
-
none: false
|
146
142
|
requirements:
|
147
143
|
- - ~>
|
148
144
|
- !ruby/object:Gem::Version
|
@@ -150,7 +146,6 @@ dependencies:
|
|
150
146
|
type: :runtime
|
151
147
|
prerelease: false
|
152
148
|
version_requirements: !ruby/object:Gem::Requirement
|
153
|
-
none: false
|
154
149
|
requirements:
|
155
150
|
- - ~>
|
156
151
|
- !ruby/object:Gem::Version
|
@@ -158,7 +153,6 @@ dependencies:
|
|
158
153
|
- !ruby/object:Gem::Dependency
|
159
154
|
name: memcache-client
|
160
155
|
requirement: !ruby/object:Gem::Requirement
|
161
|
-
none: false
|
162
156
|
requirements:
|
163
157
|
- - ! '>='
|
164
158
|
- !ruby/object:Gem::Version
|
@@ -166,7 +160,6 @@ dependencies:
|
|
166
160
|
type: :runtime
|
167
161
|
prerelease: false
|
168
162
|
version_requirements: !ruby/object:Gem::Requirement
|
169
|
-
none: false
|
170
163
|
requirements:
|
171
164
|
- - ! '>='
|
172
165
|
- !ruby/object:Gem::Version
|
@@ -174,7 +167,6 @@ dependencies:
|
|
174
167
|
- !ruby/object:Gem::Dependency
|
175
168
|
name: mongo
|
176
169
|
requirement: !ruby/object:Gem::Requirement
|
177
|
-
none: false
|
178
170
|
requirements:
|
179
171
|
- - ! '>='
|
180
172
|
- !ruby/object:Gem::Version
|
@@ -182,7 +174,6 @@ dependencies:
|
|
182
174
|
type: :runtime
|
183
175
|
prerelease: false
|
184
176
|
version_requirements: !ruby/object:Gem::Requirement
|
185
|
-
none: false
|
186
177
|
requirements:
|
187
178
|
- - ! '>='
|
188
179
|
- !ruby/object:Gem::Version
|
@@ -190,7 +181,6 @@ dependencies:
|
|
190
181
|
- !ruby/object:Gem::Dependency
|
191
182
|
name: mongoid
|
192
183
|
requirement: !ruby/object:Gem::Requirement
|
193
|
-
none: false
|
194
184
|
requirements:
|
195
185
|
- - ! '>='
|
196
186
|
- !ruby/object:Gem::Version
|
@@ -198,7 +188,6 @@ dependencies:
|
|
198
188
|
type: :runtime
|
199
189
|
prerelease: false
|
200
190
|
version_requirements: !ruby/object:Gem::Requirement
|
201
|
-
none: false
|
202
191
|
requirements:
|
203
192
|
- - ! '>='
|
204
193
|
- !ruby/object:Gem::Version
|
@@ -206,7 +195,6 @@ dependencies:
|
|
206
195
|
- !ruby/object:Gem::Dependency
|
207
196
|
name: mime-types
|
208
197
|
requirement: !ruby/object:Gem::Requirement
|
209
|
-
none: false
|
210
198
|
requirements:
|
211
199
|
- - ! '>='
|
212
200
|
- !ruby/object:Gem::Version
|
@@ -214,7 +202,6 @@ dependencies:
|
|
214
202
|
type: :runtime
|
215
203
|
prerelease: false
|
216
204
|
version_requirements: !ruby/object:Gem::Requirement
|
217
|
-
none: false
|
218
205
|
requirements:
|
219
206
|
- - ! '>='
|
220
207
|
- !ruby/object:Gem::Version
|
@@ -222,7 +209,6 @@ dependencies:
|
|
222
209
|
- !ruby/object:Gem::Dependency
|
223
210
|
name: nokogiri
|
224
211
|
requirement: !ruby/object:Gem::Requirement
|
225
|
-
none: false
|
226
212
|
requirements:
|
227
213
|
- - ~>
|
228
214
|
- !ruby/object:Gem::Version
|
@@ -230,7 +216,6 @@ dependencies:
|
|
230
216
|
type: :runtime
|
231
217
|
prerelease: false
|
232
218
|
version_requirements: !ruby/object:Gem::Requirement
|
233
|
-
none: false
|
234
219
|
requirements:
|
235
220
|
- - ~>
|
236
221
|
- !ruby/object:Gem::Version
|
@@ -238,7 +223,6 @@ dependencies:
|
|
238
223
|
- !ruby/object:Gem::Dependency
|
239
224
|
name: openurl
|
240
225
|
requirement: !ruby/object:Gem::Requirement
|
241
|
-
none: false
|
242
226
|
requirements:
|
243
227
|
- - ! '>='
|
244
228
|
- !ruby/object:Gem::Version
|
@@ -246,7 +230,6 @@ dependencies:
|
|
246
230
|
type: :runtime
|
247
231
|
prerelease: false
|
248
232
|
version_requirements: !ruby/object:Gem::Requirement
|
249
|
-
none: false
|
250
233
|
requirements:
|
251
234
|
- - ! '>='
|
252
235
|
- !ruby/object:Gem::Version
|
@@ -254,7 +237,6 @@ dependencies:
|
|
254
237
|
- !ruby/object:Gem::Dependency
|
255
238
|
name: parallel
|
256
239
|
requirement: !ruby/object:Gem::Requirement
|
257
|
-
none: false
|
258
240
|
requirements:
|
259
241
|
- - ! '>='
|
260
242
|
- !ruby/object:Gem::Version
|
@@ -262,7 +244,6 @@ dependencies:
|
|
262
244
|
type: :runtime
|
263
245
|
prerelease: false
|
264
246
|
version_requirements: !ruby/object:Gem::Requirement
|
265
|
-
none: false
|
266
247
|
requirements:
|
267
248
|
- - ! '>='
|
268
249
|
- !ruby/object:Gem::Version
|
@@ -270,7 +251,6 @@ dependencies:
|
|
270
251
|
- !ruby/object:Gem::Dependency
|
271
252
|
name: rack
|
272
253
|
requirement: !ruby/object:Gem::Requirement
|
273
|
-
none: false
|
274
254
|
requirements:
|
275
255
|
- - ! '>='
|
276
256
|
- !ruby/object:Gem::Version
|
@@ -278,7 +258,6 @@ dependencies:
|
|
278
258
|
type: :runtime
|
279
259
|
prerelease: false
|
280
260
|
version_requirements: !ruby/object:Gem::Requirement
|
281
|
-
none: false
|
282
261
|
requirements:
|
283
262
|
- - ! '>='
|
284
263
|
- !ruby/object:Gem::Version
|
@@ -286,7 +265,6 @@ dependencies:
|
|
286
265
|
- !ruby/object:Gem::Dependency
|
287
266
|
name: terminal-table
|
288
267
|
requirement: !ruby/object:Gem::Requirement
|
289
|
-
none: false
|
290
268
|
requirements:
|
291
269
|
- - ~>
|
292
270
|
- !ruby/object:Gem::Version
|
@@ -294,7 +272,6 @@ dependencies:
|
|
294
272
|
type: :runtime
|
295
273
|
prerelease: false
|
296
274
|
version_requirements: !ruby/object:Gem::Requirement
|
297
|
-
none: false
|
298
275
|
requirements:
|
299
276
|
- - ~>
|
300
277
|
- !ruby/object:Gem::Version
|
@@ -302,7 +279,6 @@ dependencies:
|
|
302
279
|
- !ruby/object:Gem::Dependency
|
303
280
|
name: thor
|
304
281
|
requirement: !ruby/object:Gem::Requirement
|
305
|
-
none: false
|
306
282
|
requirements:
|
307
283
|
- - ~>
|
308
284
|
- !ruby/object:Gem::Version
|
@@ -310,7 +286,6 @@ dependencies:
|
|
310
286
|
type: :runtime
|
311
287
|
prerelease: false
|
312
288
|
version_requirements: !ruby/object:Gem::Requirement
|
313
|
-
none: false
|
314
289
|
requirements:
|
315
290
|
- - ~>
|
316
291
|
- !ruby/object:Gem::Version
|
@@ -318,7 +293,6 @@ dependencies:
|
|
318
293
|
- !ruby/object:Gem::Dependency
|
319
294
|
name: writeexcel
|
320
295
|
requirement: !ruby/object:Gem::Requirement
|
321
|
-
none: false
|
322
296
|
requirements:
|
323
297
|
- - ~>
|
324
298
|
- !ruby/object:Gem::Version
|
@@ -326,7 +300,6 @@ dependencies:
|
|
326
300
|
type: :runtime
|
327
301
|
prerelease: false
|
328
302
|
version_requirements: !ruby/object:Gem::Requirement
|
329
|
-
none: false
|
330
303
|
requirements:
|
331
304
|
- - ~>
|
332
305
|
- !ruby/object:Gem::Version
|
@@ -334,7 +307,6 @@ dependencies:
|
|
334
307
|
- !ruby/object:Gem::Dependency
|
335
308
|
name: ffi
|
336
309
|
requirement: !ruby/object:Gem::Requirement
|
337
|
-
none: false
|
338
310
|
requirements:
|
339
311
|
- - ! '>='
|
340
312
|
- !ruby/object:Gem::Version
|
@@ -342,7 +314,6 @@ dependencies:
|
|
342
314
|
type: :runtime
|
343
315
|
prerelease: false
|
344
316
|
version_requirements: !ruby/object:Gem::Requirement
|
345
|
-
none: false
|
346
317
|
requirements:
|
347
318
|
- - ! '>='
|
348
319
|
- !ruby/object:Gem::Version
|
@@ -350,7 +321,6 @@ dependencies:
|
|
350
321
|
- !ruby/object:Gem::Dependency
|
351
322
|
name: guard
|
352
323
|
requirement: !ruby/object:Gem::Requirement
|
353
|
-
none: false
|
354
324
|
requirements:
|
355
325
|
- - ! '>='
|
356
326
|
- !ruby/object:Gem::Version
|
@@ -358,7 +328,6 @@ dependencies:
|
|
358
328
|
type: :development
|
359
329
|
prerelease: false
|
360
330
|
version_requirements: !ruby/object:Gem::Requirement
|
361
|
-
none: false
|
362
331
|
requirements:
|
363
332
|
- - ! '>='
|
364
333
|
- !ruby/object:Gem::Version
|
@@ -366,7 +335,6 @@ dependencies:
|
|
366
335
|
- !ruby/object:Gem::Dependency
|
367
336
|
name: guard-rake
|
368
337
|
requirement: !ruby/object:Gem::Requirement
|
369
|
-
none: false
|
370
338
|
requirements:
|
371
339
|
- - ! '>='
|
372
340
|
- !ruby/object:Gem::Version
|
@@ -374,7 +342,6 @@ dependencies:
|
|
374
342
|
type: :development
|
375
343
|
prerelease: false
|
376
344
|
version_requirements: !ruby/object:Gem::Requirement
|
377
|
-
none: false
|
378
345
|
requirements:
|
379
346
|
- - ! '>='
|
380
347
|
- !ruby/object:Gem::Version
|
@@ -382,7 +349,6 @@ dependencies:
|
|
382
349
|
- !ruby/object:Gem::Dependency
|
383
350
|
name: guard-rspec
|
384
351
|
requirement: !ruby/object:Gem::Requirement
|
385
|
-
none: false
|
386
352
|
requirements:
|
387
353
|
- - ! '>='
|
388
354
|
- !ruby/object:Gem::Version
|
@@ -390,7 +356,6 @@ dependencies:
|
|
390
356
|
type: :development
|
391
357
|
prerelease: false
|
392
358
|
version_requirements: !ruby/object:Gem::Requirement
|
393
|
-
none: false
|
394
359
|
requirements:
|
395
360
|
- - ! '>='
|
396
361
|
- !ruby/object:Gem::Version
|
@@ -402,69 +367,69 @@ executables:
|
|
402
367
|
extensions: []
|
403
368
|
extra_rdoc_files: []
|
404
369
|
files:
|
405
|
-
- ./lib/apollo_crawler/lib.rb
|
406
|
-
- ./lib/apollo_crawler/program/base_program.rb
|
407
|
-
- ./lib/apollo_crawler/program/programs.rb
|
408
|
-
- ./lib/apollo_crawler/program/crawler_program.rb
|
409
370
|
- ./lib/apollo_crawler/fetcher/smart_fetcher.rb
|
371
|
+
- ./lib/apollo_crawler/fetcher/fetchers.rb
|
410
372
|
- ./lib/apollo_crawler/fetcher/simple_fetcher.rb
|
411
373
|
- ./lib/apollo_crawler/fetcher/base_fetcher.rb
|
412
|
-
- ./lib/apollo_crawler/
|
374
|
+
- ./lib/apollo_crawler/lib.rb
|
413
375
|
- ./lib/apollo_crawler/version.rb
|
376
|
+
- ./lib/apollo_crawler/program/crawler_program.rb
|
377
|
+
- ./lib/apollo_crawler/program/base_program.rb
|
378
|
+
- ./lib/apollo_crawler/program/programs.rb
|
379
|
+
- ./lib/apollo_crawler/logger/console_logger.rb
|
380
|
+
- ./lib/apollo_crawler/logger/base_logger.rb
|
381
|
+
- ./lib/apollo_crawler/logger/loggers.rb
|
382
|
+
- ./lib/apollo_crawler/helper/core_helper.rb
|
383
|
+
- ./lib/apollo_crawler/helper/helpers.rb
|
384
|
+
- ./lib/apollo_crawler/cli/cli.rb
|
385
|
+
- ./lib/apollo_crawler/config.rb
|
386
|
+
- ./lib/apollo_crawler/cache/sqlite_cache.rb
|
387
|
+
- ./lib/apollo_crawler/cache/factory.rb
|
388
|
+
- ./lib/apollo_crawler/cache/null_cache.rb
|
389
|
+
- ./lib/apollo_crawler/cache/memory_cache.rb
|
390
|
+
- ./lib/apollo_crawler/cache/base_cache.rb
|
391
|
+
- ./lib/apollo_crawler/cache/mongo_cache.rb
|
392
|
+
- ./lib/apollo_crawler/cache/memcached_cache.rb
|
393
|
+
- ./lib/apollo_crawler/cache/caches.rb
|
394
|
+
- ./lib/apollo_crawler/crawler/xkcd_crawler.rb
|
395
|
+
- ./lib/apollo_crawler/crawler/google_crawler.rb
|
396
|
+
- ./lib/apollo_crawler/crawler/youjizz_crawler.rb
|
414
397
|
- ./lib/apollo_crawler/crawler/slashdot_crawler.rb
|
415
|
-
- ./lib/apollo_crawler/crawler/stackoverflow_crawler.rb
|
416
398
|
- ./lib/apollo_crawler/crawler/hacker_news_crawler.rb
|
417
|
-
- ./lib/apollo_crawler/crawler/youjizz_crawler.rb
|
418
|
-
- ./lib/apollo_crawler/crawler/google_crawler.rb
|
419
399
|
- ./lib/apollo_crawler/crawler/base_crawler.rb
|
420
|
-
- ./lib/apollo_crawler/crawler/xkcd_crawler.rb
|
421
400
|
- ./lib/apollo_crawler/crawler/crawlers.rb
|
422
|
-
- ./lib/apollo_crawler/
|
423
|
-
- ./lib/apollo_crawler/logger/console_logger.rb
|
424
|
-
- ./lib/apollo_crawler/logger/base_logger.rb
|
425
|
-
- ./lib/apollo_crawler/config.rb
|
401
|
+
- ./lib/apollo_crawler/crawler/stackoverflow_crawler.rb
|
426
402
|
- ./lib/apollo_crawler/formatter/table_formatter.rb
|
427
403
|
- ./lib/apollo_crawler/formatter/base_formatter.rb
|
428
404
|
- ./lib/apollo_crawler/formatter/json_formatter.rb
|
429
405
|
- ./lib/apollo_crawler/formatter/plain_formatter.rb
|
430
406
|
- ./lib/apollo_crawler/formatter/formatters.rb
|
431
|
-
- ./lib/apollo_crawler/cache/memcached_cache.rb
|
432
|
-
- ./lib/apollo_crawler/cache/memory_cache.rb
|
433
|
-
- ./lib/apollo_crawler/cache/mongo_cache.rb
|
434
|
-
- ./lib/apollo_crawler/cache/null_cache.rb
|
435
|
-
- ./lib/apollo_crawler/cache/factory.rb
|
436
|
-
- ./lib/apollo_crawler/cache/caches.rb
|
437
|
-
- ./lib/apollo_crawler/cache/sqlite_cache.rb
|
438
|
-
- ./lib/apollo_crawler/cache/base_cache.rb
|
439
|
-
- ./lib/apollo_crawler/store/base_store.rb
|
440
407
|
- ./lib/apollo_crawler/store/stores.rb
|
441
|
-
- ./lib/apollo_crawler/
|
442
|
-
- ./lib/apollo_crawler/helper/helpers.rb
|
408
|
+
- ./lib/apollo_crawler/store/base_store.rb
|
443
409
|
- ./lib/apollo_crawler.rb
|
444
410
|
- bin/apollo-crawler
|
445
411
|
homepage: https://github.com/korczis/apollo-crawler
|
446
412
|
licenses:
|
447
413
|
- MIT
|
414
|
+
metadata: {}
|
448
415
|
post_install_message: Thanks for installing Apollo Crawler!
|
449
416
|
rdoc_options: []
|
450
417
|
require_paths:
|
451
418
|
- lib
|
452
419
|
required_ruby_version: !ruby/object:Gem::Requirement
|
453
|
-
none: false
|
454
420
|
requirements:
|
455
421
|
- - ! '>='
|
456
422
|
- !ruby/object:Gem::Version
|
457
|
-
version:
|
423
|
+
version: 1.9.3
|
458
424
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
459
|
-
none: false
|
460
425
|
requirements:
|
461
426
|
- - ! '>='
|
462
427
|
- !ruby/object:Gem::Version
|
463
|
-
version:
|
428
|
+
version: 1.8.11
|
464
429
|
requirements: []
|
465
430
|
rubyforge_project:
|
466
|
-
rubygems_version:
|
431
|
+
rubygems_version: 2.0.0
|
467
432
|
signing_key:
|
468
|
-
specification_version:
|
433
|
+
specification_version: 4
|
469
434
|
summary: Apollo Platform Crawler
|
470
435
|
test_files: []
|