proxy_rotater 0.0.1
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 +17 -0
- data/.rspec +2 -0
- data/.travis.yml +3 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +6 -0
- data/bin/proxy_rotater +3 -0
- data/lib/proxy_rotater.rb +159 -0
- data/lib/proxy_rotater/proxy.rb +81 -0
- data/lib/proxy_rotater/public_proxy/getproxy.rb +22 -0
- data/lib/proxy_rotater/version.rb +3 -0
- data/proxy_rotater.gemspec +28 -0
- data/spec/proxy_rotater_spec.rb +11 -0
- data/spec/spec_helper.rb +2 -0
- metadata +146 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: d1fd8349487bfac47f83d0d6b227b76453a6b3de
|
4
|
+
data.tar.gz: dad5a184ac81cba814338ccaf7d2ec702d5424f5
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: e9484518601163b5275c887c3df3eb5afc52e275bbac87dc3d906ebda0762d3a9ab4500fe22cf923ab7b5ff11b3b0eb3644f6ba9ce65f377518fe8588f126fd6
|
7
|
+
data.tar.gz: b4bf49e0a8e22d03d7d74ce2729fd6c53add00e21ae2eb470a9caf6a5966b23718a363ff87d2d3e837c8a18f65b0c9654d6cbda8dc4b18eaa4fb5b82ef37a120
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 shim0mura
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# ProxyRotater
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'proxy_rotater'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install proxy_rotater
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/bin/proxy_rotater
ADDED
@@ -0,0 +1,159 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
require "httparty"
|
3
|
+
require "parallel"
|
4
|
+
|
5
|
+
require "proxy_rotater/version"
|
6
|
+
require "proxy_rotater/proxy"
|
7
|
+
require "proxy_rotater/public_proxy/getproxy"
|
8
|
+
|
9
|
+
class ProxyRotater
|
10
|
+
CONCURRENT_PROCESS = 10
|
11
|
+
PROXY_UPDATE_WAIT = 60 * 15
|
12
|
+
|
13
|
+
def initialize(domain, options = {})
|
14
|
+
@domain = domain
|
15
|
+
@interval_sec = 1
|
16
|
+
@req_limit_per_hour = 500
|
17
|
+
@request_workers = CONCURRENT_PROCESS
|
18
|
+
|
19
|
+
@available = []
|
20
|
+
@over_heated = []
|
21
|
+
@failed = []
|
22
|
+
|
23
|
+
@custom_fail = []
|
24
|
+
|
25
|
+
get_proxies
|
26
|
+
end
|
27
|
+
|
28
|
+
def get(urls, do_retry = true)
|
29
|
+
urls = [urls] unless urls.kind_of?(Array)
|
30
|
+
retry_url = []
|
31
|
+
|
32
|
+
concurrency = urls.size > @request_workers ? @request_workers : urls.size
|
33
|
+
results = urls.each_slice(concurrency).map do |round_url|
|
34
|
+
round_result = Parallel.map_with_index(round_url, in_processes: concurrency) do |url, i|
|
35
|
+
res = @available[i].get_url(url)
|
36
|
+
if res.nil?
|
37
|
+
next
|
38
|
+
end
|
39
|
+
|
40
|
+
if @custom_fail.any?{|error_proc| error_proc.call(res)}
|
41
|
+
@available.timeout = true
|
42
|
+
next
|
43
|
+
end
|
44
|
+
{
|
45
|
+
body: res.body,
|
46
|
+
response: res.response
|
47
|
+
}
|
48
|
+
end
|
49
|
+
check
|
50
|
+
round_result.each_with_index.inject({}) do |hash, value|
|
51
|
+
retry_url << round_url[value[1]] if value[0].nil?
|
52
|
+
key = round_url[value[1]]
|
53
|
+
hash[key] = value[0]
|
54
|
+
hash
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
r = {}.tap do |hash|
|
59
|
+
results.each{|r|hash.merge!(r)}
|
60
|
+
end
|
61
|
+
|
62
|
+
unless retry_url.empty?
|
63
|
+
if do_retry
|
64
|
+
retried = get(retry_url, false)
|
65
|
+
r.merge!(retried)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
r
|
69
|
+
end
|
70
|
+
|
71
|
+
def check
|
72
|
+
disable_timeouted
|
73
|
+
check_req_limit
|
74
|
+
revival
|
75
|
+
get_proxies if @available.size < @request_workers
|
76
|
+
sleep PROXY_UPDATE_WAIT if @available.empty?
|
77
|
+
sort
|
78
|
+
end
|
79
|
+
|
80
|
+
def add_custom_fail(&block)
|
81
|
+
@custom_fail << block
|
82
|
+
end
|
83
|
+
|
84
|
+
private
|
85
|
+
def get_proxies
|
86
|
+
values = get_proxylist_from_html
|
87
|
+
|
88
|
+
proxies = Parallel.map(values, in_processes: values.size) do |value|
|
89
|
+
Proxy.new(value)
|
90
|
+
end
|
91
|
+
proxies = proxies.group_by{|proxy|proxy.timeout}
|
92
|
+
|
93
|
+
@available = proxies[false]
|
94
|
+
@failed = proxies[true]
|
95
|
+
end
|
96
|
+
|
97
|
+
def disable_timeouted
|
98
|
+
proxies = @available.group_by{|proxy|proxy.timeout}
|
99
|
+
@available = proxies[false]
|
100
|
+
@failed.concat(proxies[true]) unless proxies[true].nil?
|
101
|
+
end
|
102
|
+
|
103
|
+
def check_req_limit
|
104
|
+
proxies = @available.group_by do |proxy|
|
105
|
+
if is_per_sec_limit_over?(proxy.get_request_intervals)
|
106
|
+
proxy.return_at = Time.now.to_f + @interval_sec
|
107
|
+
:disabled
|
108
|
+
elsif is_per_hour_limit_over?(proxy.requested_at)
|
109
|
+
proxy.return_at = Time.now.to_f + 60 * 30
|
110
|
+
:disabled
|
111
|
+
else
|
112
|
+
:available
|
113
|
+
end
|
114
|
+
end
|
115
|
+
|
116
|
+
@available = proxies[:available] if proxies[:available]
|
117
|
+
@over_heated.concat(proxies[:disabled]) if proxies[:disabled]
|
118
|
+
end
|
119
|
+
|
120
|
+
def is_per_sec_limit_over?(req_intervals)
|
121
|
+
size = req_intervals.size
|
122
|
+
return false if size == 0
|
123
|
+
req_time_ave = req_intervals
|
124
|
+
.slice(-1 * size, 10)
|
125
|
+
.inject(0){|sum, i|sum += i}/size
|
126
|
+
req_time_ave > @interval_sec
|
127
|
+
end
|
128
|
+
|
129
|
+
def is_per_hour_limit_over?(req_times)
|
130
|
+
now = Time.now.to_f
|
131
|
+
in_hour_index = req_times.find_index do |timestamp|
|
132
|
+
timestamp > now - (60 * 60)
|
133
|
+
end
|
134
|
+
return false if in_hour_index.nil?
|
135
|
+
req_times.slice(in_hour_index..-1).size > @req_limit_per_hour
|
136
|
+
end
|
137
|
+
|
138
|
+
def revival
|
139
|
+
proxies = @over_heated.group_by do |proxy|
|
140
|
+
proxy.return_at < Time.now.to_f
|
141
|
+
end
|
142
|
+
return if proxies.empty?
|
143
|
+
@over_heated = proxies[false]
|
144
|
+
@available.concat(proxies[true]) if proxies[true]
|
145
|
+
end
|
146
|
+
|
147
|
+
def sort
|
148
|
+
@available.sort_by{|proxy| proxy.last_response_time}
|
149
|
+
end
|
150
|
+
|
151
|
+
def get_proxylist_from_html
|
152
|
+
list = GetProxy.get
|
153
|
+
existing_proxies = [].concat([@available, @failed, @over_heated]).flatten!
|
154
|
+
list.delete_if do |line|
|
155
|
+
existing_proxies.any?{|proxy| proxy.ip_address == line[:ip_address]}
|
156
|
+
end
|
157
|
+
end
|
158
|
+
|
159
|
+
end
|
@@ -0,0 +1,81 @@
|
|
1
|
+
class Proxy
|
2
|
+
include HTTParty
|
3
|
+
default_timeout 4
|
4
|
+
|
5
|
+
ROUND_NUM = 2
|
6
|
+
TEST_REQUEST_URL = "http://www.google.co.jp"
|
7
|
+
BENCHMARK_TIMES = 3
|
8
|
+
|
9
|
+
attr_reader :timeout, :requested_at, :last_response_time
|
10
|
+
|
11
|
+
def initialize(options)
|
12
|
+
options.merge!(
|
13
|
+
requested_at: [],
|
14
|
+
response_time: nil,
|
15
|
+
last_response_time: nil,
|
16
|
+
checked_at: nil,
|
17
|
+
timeout: false,
|
18
|
+
return_at: nil
|
19
|
+
)
|
20
|
+
options.keys.each do |key|
|
21
|
+
instance_variable_set("@#{key}", options[key])
|
22
|
+
end
|
23
|
+
|
24
|
+
self.class.http_proxy(@ip_address, @port)
|
25
|
+
benchmark
|
26
|
+
end
|
27
|
+
|
28
|
+
def get_url(url)
|
29
|
+
start = Time.now
|
30
|
+
# TODO: redirect too deepの時にどうにかする
|
31
|
+
begin
|
32
|
+
res = self.class.get(url)
|
33
|
+
rescue Errno::ETIMEDOUT, Errno::ECONNRESET, EOFError, Errno::ECONNREFUSED => e
|
34
|
+
@timeout = true
|
35
|
+
return nil
|
36
|
+
rescue Net::ReadTimeout, Net::OpenTimeout => e
|
37
|
+
@timeout = true
|
38
|
+
return nil
|
39
|
+
end
|
40
|
+
finish = Time.now
|
41
|
+
@requested_at << finish.to_f
|
42
|
+
@last_response_time = (finish.to_f - start.to_f).round(ROUND_NUM)
|
43
|
+
return res
|
44
|
+
end
|
45
|
+
|
46
|
+
def benchmark
|
47
|
+
urls = BENCHMARK_TIMES.times.map{|i| TEST_REQUEST_URL}
|
48
|
+
response_times = Parallel.map(urls, in_threads: BENCHMARK_TIMES) do |url|
|
49
|
+
start = Time.now.to_f
|
50
|
+
res = get_url(TEST_REQUEST_URL)
|
51
|
+
finish = Time.now.to_f
|
52
|
+
res.nil? ? nil : (finish - start).round(ROUND_NUM)
|
53
|
+
end
|
54
|
+
|
55
|
+
# TODO: 微妙なのでリファクタリングする
|
56
|
+
# sliceとかまとめられそう
|
57
|
+
# ifの中はresponse_timeどうにかしたほうがいいのでは?
|
58
|
+
if response_times.include?(nil)
|
59
|
+
reset_size = @requested_at.size
|
60
|
+
@requested_at.slice!(-1 * reset_size, reset_size)
|
61
|
+
return
|
62
|
+
end
|
63
|
+
|
64
|
+
@response_time = (response_times.inject(0){|v,s|v+s}/response_times.size).round(ROUND_NUM)
|
65
|
+
@checked_at = Time.now
|
66
|
+
|
67
|
+
# ベンチマークの結果はused_rateとrequested_atに影響しないようにする
|
68
|
+
@requested_at.slice!(-1 * BENCHMARK_TIMES, BENCHMARK_TIMES)
|
69
|
+
end
|
70
|
+
|
71
|
+
def get_request_intervals
|
72
|
+
diff = []
|
73
|
+
@requested_at.each_with_index do |num, i|
|
74
|
+
next if i == 0
|
75
|
+
diff << @requested_at[i] - @requested_at[i-1]
|
76
|
+
end
|
77
|
+
|
78
|
+
return diff
|
79
|
+
end
|
80
|
+
|
81
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
module GetProxy
|
2
|
+
|
3
|
+
URL = "http://www.getproxy.jp/"
|
4
|
+
|
5
|
+
def self.get
|
6
|
+
page = HTTParty.get(URL)
|
7
|
+
html = Nokogiri::HTML(page.body)
|
8
|
+
|
9
|
+
tr = html.css("#mytable tr")[1..-1]
|
10
|
+
values = tr.map do |line|
|
11
|
+
td = line.css("td")
|
12
|
+
matched_address = td[0].css("strong").first.content
|
13
|
+
.match(/^((?:\d{,3})(?:\.\d{,3}){3})\:(\d{,5})$/)
|
14
|
+
values = {
|
15
|
+
ip_address: matched_address[1],
|
16
|
+
port: matched_address[2],
|
17
|
+
country: td[1].content
|
18
|
+
}
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'proxy_rotater'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "proxy_rotater"
|
8
|
+
spec.version = ProxyRotater::VERSION
|
9
|
+
spec.authors = ["shim0mura"]
|
10
|
+
spec.email = ["tatshimomura@gmail.com"]
|
11
|
+
spec.description = %q{rotate proxy}
|
12
|
+
spec.summary = %q{rotate proxy}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
spec.add_development_dependency "rspec"
|
24
|
+
|
25
|
+
spec.add_runtime_dependency "httparty"
|
26
|
+
spec.add_runtime_dependency "parallel"
|
27
|
+
spec.add_runtime_dependency "nokogiri"
|
28
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,146 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: proxy_rotater
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- shim0mura
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-12-15 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
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: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
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: httparty
|
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: parallel
|
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: nokogiri
|
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
|
+
description: rotate proxy
|
98
|
+
email:
|
99
|
+
- tatshimomura@gmail.com
|
100
|
+
executables:
|
101
|
+
- proxy_rotater
|
102
|
+
extensions: []
|
103
|
+
extra_rdoc_files: []
|
104
|
+
files:
|
105
|
+
- .gitignore
|
106
|
+
- .rspec
|
107
|
+
- .travis.yml
|
108
|
+
- Gemfile
|
109
|
+
- LICENSE.txt
|
110
|
+
- README.md
|
111
|
+
- Rakefile
|
112
|
+
- bin/proxy_rotater
|
113
|
+
- lib/proxy_rotater.rb
|
114
|
+
- lib/proxy_rotater/proxy.rb
|
115
|
+
- lib/proxy_rotater/public_proxy/getproxy.rb
|
116
|
+
- lib/proxy_rotater/version.rb
|
117
|
+
- proxy_rotater.gemspec
|
118
|
+
- spec/proxy_rotater_spec.rb
|
119
|
+
- spec/spec_helper.rb
|
120
|
+
homepage: ''
|
121
|
+
licenses:
|
122
|
+
- MIT
|
123
|
+
metadata: {}
|
124
|
+
post_install_message:
|
125
|
+
rdoc_options: []
|
126
|
+
require_paths:
|
127
|
+
- lib
|
128
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
129
|
+
requirements:
|
130
|
+
- - '>='
|
131
|
+
- !ruby/object:Gem::Version
|
132
|
+
version: '0'
|
133
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
134
|
+
requirements:
|
135
|
+
- - '>='
|
136
|
+
- !ruby/object:Gem::Version
|
137
|
+
version: '0'
|
138
|
+
requirements: []
|
139
|
+
rubyforge_project:
|
140
|
+
rubygems_version: 2.0.3
|
141
|
+
signing_key:
|
142
|
+
specification_version: 4
|
143
|
+
summary: rotate proxy
|
144
|
+
test_files:
|
145
|
+
- spec/proxy_rotater_spec.rb
|
146
|
+
- spec/spec_helper.rb
|