kudzu 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/README.md +61 -0
- data/Rakefile +6 -0
- data/lib/kudzu.rb +8 -0
- data/lib/kudzu/adapter/base/all.rb +3 -0
- data/lib/kudzu/adapter/base/link.rb +8 -0
- data/lib/kudzu/adapter/base/page.rb +106 -0
- data/lib/kudzu/adapter/memory.rb +4 -0
- data/lib/kudzu/adapter/memory/all.rb +3 -0
- data/lib/kudzu/adapter/memory/frontier.rb +38 -0
- data/lib/kudzu/adapter/memory/model/link.rb +15 -0
- data/lib/kudzu/adapter/memory/model/page.rb +17 -0
- data/lib/kudzu/adapter/memory/repository.rb +27 -0
- data/lib/kudzu/agent/all.rb +3 -0
- data/lib/kudzu/agent/charset_detector.rb +84 -0
- data/lib/kudzu/agent/fetcher.rb +116 -0
- data/lib/kudzu/agent/filter.rb +40 -0
- data/lib/kudzu/agent/mime_type_detector.rb +34 -0
- data/lib/kudzu/agent/robots.rb +190 -0
- data/lib/kudzu/agent/sleeper.rb +44 -0
- data/lib/kudzu/agent/title_parser.rb +16 -0
- data/lib/kudzu/agent/url_extractor.rb +123 -0
- data/lib/kudzu/agent/url_filter.rb +65 -0
- data/lib/kudzu/callback.rb +41 -0
- data/lib/kudzu/common.rb +23 -0
- data/lib/kudzu/config.rb +79 -0
- data/lib/kudzu/config/filter.rb +39 -0
- data/lib/kudzu/crawler.rb +258 -0
- data/lib/kudzu/logger.rb +20 -0
- data/lib/kudzu/revisit/all.rb +3 -0
- data/lib/kudzu/revisit/scheduler.rb +28 -0
- data/lib/kudzu/util/all.rb +3 -0
- data/lib/kudzu/util/connection_pool.rb +56 -0
- data/lib/kudzu/util/content_type_parser.rb +24 -0
- data/lib/kudzu/util/matcher.rb +21 -0
- data/lib/kudzu/util/thread_pool.rb +38 -0
- data/lib/kudzu/version.rb +3 -0
- metadata +234 -0
data/lib/kudzu/logger.rb
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
module Kudzu
|
2
|
+
class Logger
|
3
|
+
def initialize(file, level)
|
4
|
+
if file.is_a?(::Logger)
|
5
|
+
@logger = file
|
6
|
+
elsif file
|
7
|
+
@logger = ::Logger.new(file)
|
8
|
+
@logger.level = level
|
9
|
+
else
|
10
|
+
@logger = nil
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def log(level, message, error: nil)
|
15
|
+
return unless @logger
|
16
|
+
message += " #{error.class} #{error.message} #{error.backtrace.join("\n")}" if error
|
17
|
+
@logger.send(level, message)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
module Kudzu
|
2
|
+
class Revisit
|
3
|
+
class Scheduler
|
4
|
+
def initialize(config)
|
5
|
+
@config = config
|
6
|
+
end
|
7
|
+
|
8
|
+
def schedule(page, modified: true)
|
9
|
+
page.revisit_interval = next_interval(page.revisit_interval, modified)
|
10
|
+
page.revisit_at = page.fetched_at + page.revisit_interval * 86400
|
11
|
+
end
|
12
|
+
|
13
|
+
private
|
14
|
+
|
15
|
+
def next_interval(curr_interval, modified)
|
16
|
+
if curr_interval
|
17
|
+
if modified
|
18
|
+
[curr_interval - 1, @config.revisit_min_interval].max
|
19
|
+
else
|
20
|
+
[curr_interval + 1, @config.revisit_max_interval].min
|
21
|
+
end
|
22
|
+
else
|
23
|
+
@config.revisit_default_interval
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
module Kudzu
|
2
|
+
class Util
|
3
|
+
class ConnectionPool
|
4
|
+
class Connection
|
5
|
+
attr_accessor :name, :http, :last_used
|
6
|
+
|
7
|
+
def initialize(attr = {})
|
8
|
+
attr.each { |k, v| public_send("#{k}=", v) }
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
12
|
+
def initialize(max_size = 10)
|
13
|
+
@max_size = max_size
|
14
|
+
end
|
15
|
+
|
16
|
+
def checkout(name)
|
17
|
+
pool[name] ||= Connection.new(name: name, http: yield)
|
18
|
+
|
19
|
+
conn = pool[name]
|
20
|
+
conn.last_used = Time.now
|
21
|
+
|
22
|
+
if pool.size > @max_size
|
23
|
+
reduce
|
24
|
+
end
|
25
|
+
|
26
|
+
conn.http
|
27
|
+
end
|
28
|
+
|
29
|
+
def close
|
30
|
+
pool.values.each do |conn|
|
31
|
+
finish_http(conn.http)
|
32
|
+
end
|
33
|
+
Thread.current[:kudzu_connection] = nil
|
34
|
+
end
|
35
|
+
|
36
|
+
private
|
37
|
+
|
38
|
+
def pool
|
39
|
+
Thread.current[:kudzu_connection] ||= {}
|
40
|
+
Thread.current[:kudzu_connection]
|
41
|
+
end
|
42
|
+
|
43
|
+
def reduce
|
44
|
+
conns = pool.values.sort_by { |conn| conn.last_used }
|
45
|
+
conns.first(pool.size - @max_size).each do |conn|
|
46
|
+
finish_http(conn.http)
|
47
|
+
pool.delete(conn.name)
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
def finish_http(http)
|
52
|
+
http.finish if http && http.started?
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
56
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
module Kudzu
|
2
|
+
class Util
|
3
|
+
class ContentTypeParser
|
4
|
+
def parse(content_type)
|
5
|
+
mime, *kvs = content_type.to_s.split(';').map { |str| str.strip.downcase }
|
6
|
+
params = kvs.each_with_object({}) do |kv, hash|
|
7
|
+
k, v = kv.to_s.split('=').map { |str| str.strip }
|
8
|
+
hash[k.to_sym] = unquote(v) if k && v
|
9
|
+
end
|
10
|
+
return mime, params
|
11
|
+
end
|
12
|
+
|
13
|
+
private
|
14
|
+
|
15
|
+
def unquote(str)
|
16
|
+
if str =~ /^"(.*?)"$/
|
17
|
+
$1.gsub(/\\(.)/, '\1')
|
18
|
+
else
|
19
|
+
str
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
module Kudzu
|
2
|
+
class Util
|
3
|
+
class Matcher
|
4
|
+
def match?(text, allows: nil, denies: nil)
|
5
|
+
match_to_allows?(text, allows) && !match_to_denies?(text, denies)
|
6
|
+
end
|
7
|
+
|
8
|
+
private
|
9
|
+
|
10
|
+
def match_to_allows?(text, allows)
|
11
|
+
allows = Array(allows)
|
12
|
+
allows.empty? || allows.any? { |allow| Kudzu::Common.match?(text, allow) }
|
13
|
+
end
|
14
|
+
|
15
|
+
def match_to_denies?(text, denies)
|
16
|
+
denies = Array(denies)
|
17
|
+
!denies.empty? && denies.any? { |deny| Kudzu::Common.match?(text, deny) }
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
module Kudzu
|
2
|
+
class Util
|
3
|
+
class ThreadPool
|
4
|
+
def initialize(size)
|
5
|
+
@size = size
|
6
|
+
@queue = Queue.new
|
7
|
+
@threads = []
|
8
|
+
end
|
9
|
+
|
10
|
+
def start(&block)
|
11
|
+
@threads = 1.upto(@size).map { create_thread(&block) }
|
12
|
+
end
|
13
|
+
|
14
|
+
def wait
|
15
|
+
until @queue.num_waiting == @threads.select { |t| t.alive? }.size
|
16
|
+
Thread.pass
|
17
|
+
sleep 1
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
def shutdown
|
22
|
+
@threads.each { |t| t.kill }
|
23
|
+
@threads = []
|
24
|
+
end
|
25
|
+
|
26
|
+
private
|
27
|
+
|
28
|
+
def create_thread(&block)
|
29
|
+
Thread.start do
|
30
|
+
loop do
|
31
|
+
ret = block.call(@queue)
|
32
|
+
break if ret == :end
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
metadata
ADDED
@@ -0,0 +1,234 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: kudzu
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Yoshikazu Kaneta
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-12-20 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: addressable
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: nokogiri
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: charlock_holmes
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: shared-mime-info
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: mime-types
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: http-cookie
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: rails
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: rspec-rails
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ">="
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ">="
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '0'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: simplecov
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ">="
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ">="
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: pry-rails
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - ">="
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0'
|
146
|
+
type: :development
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - ">="
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '0'
|
153
|
+
- !ruby/object:Gem::Dependency
|
154
|
+
name: pry-byebug
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
156
|
+
requirements:
|
157
|
+
- - ">="
|
158
|
+
- !ruby/object:Gem::Version
|
159
|
+
version: '0'
|
160
|
+
type: :development
|
161
|
+
prerelease: false
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
163
|
+
requirements:
|
164
|
+
- - ">="
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
version: '0'
|
167
|
+
description: A simple web crawler for ruby
|
168
|
+
email:
|
169
|
+
- kaneta@sitebridge.co.jp
|
170
|
+
executables: []
|
171
|
+
extensions: []
|
172
|
+
extra_rdoc_files: []
|
173
|
+
files:
|
174
|
+
- README.md
|
175
|
+
- Rakefile
|
176
|
+
- lib/kudzu.rb
|
177
|
+
- lib/kudzu/adapter/base/all.rb
|
178
|
+
- lib/kudzu/adapter/base/link.rb
|
179
|
+
- lib/kudzu/adapter/base/page.rb
|
180
|
+
- lib/kudzu/adapter/memory.rb
|
181
|
+
- lib/kudzu/adapter/memory/all.rb
|
182
|
+
- lib/kudzu/adapter/memory/frontier.rb
|
183
|
+
- lib/kudzu/adapter/memory/model/link.rb
|
184
|
+
- lib/kudzu/adapter/memory/model/page.rb
|
185
|
+
- lib/kudzu/adapter/memory/repository.rb
|
186
|
+
- lib/kudzu/agent/all.rb
|
187
|
+
- lib/kudzu/agent/charset_detector.rb
|
188
|
+
- lib/kudzu/agent/fetcher.rb
|
189
|
+
- lib/kudzu/agent/filter.rb
|
190
|
+
- lib/kudzu/agent/mime_type_detector.rb
|
191
|
+
- lib/kudzu/agent/robots.rb
|
192
|
+
- lib/kudzu/agent/sleeper.rb
|
193
|
+
- lib/kudzu/agent/title_parser.rb
|
194
|
+
- lib/kudzu/agent/url_extractor.rb
|
195
|
+
- lib/kudzu/agent/url_filter.rb
|
196
|
+
- lib/kudzu/callback.rb
|
197
|
+
- lib/kudzu/common.rb
|
198
|
+
- lib/kudzu/config.rb
|
199
|
+
- lib/kudzu/config/filter.rb
|
200
|
+
- lib/kudzu/crawler.rb
|
201
|
+
- lib/kudzu/logger.rb
|
202
|
+
- lib/kudzu/revisit/all.rb
|
203
|
+
- lib/kudzu/revisit/scheduler.rb
|
204
|
+
- lib/kudzu/util/all.rb
|
205
|
+
- lib/kudzu/util/connection_pool.rb
|
206
|
+
- lib/kudzu/util/content_type_parser.rb
|
207
|
+
- lib/kudzu/util/matcher.rb
|
208
|
+
- lib/kudzu/util/thread_pool.rb
|
209
|
+
- lib/kudzu/version.rb
|
210
|
+
homepage: https://github.com/kanety/kudzu
|
211
|
+
licenses:
|
212
|
+
- MIT
|
213
|
+
metadata: {}
|
214
|
+
post_install_message:
|
215
|
+
rdoc_options: []
|
216
|
+
require_paths:
|
217
|
+
- lib
|
218
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
219
|
+
requirements:
|
220
|
+
- - ">="
|
221
|
+
- !ruby/object:Gem::Version
|
222
|
+
version: '0'
|
223
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
224
|
+
requirements:
|
225
|
+
- - ">="
|
226
|
+
- !ruby/object:Gem::Version
|
227
|
+
version: '0'
|
228
|
+
requirements: []
|
229
|
+
rubyforge_project:
|
230
|
+
rubygems_version: 2.5.2.2
|
231
|
+
signing_key:
|
232
|
+
specification_version: 4
|
233
|
+
summary: A simple web crawler for ruby
|
234
|
+
test_files: []
|