em-http-fetcher 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +89 -0
- data/em-http-fetcher.gemspec +31 -0
- data/lib/em-http-fetcher.rb +1 -0
- data/lib/em/http-fetcher/fetcher.rb +163 -0
- metadata +82 -0
data/README.rdoc
ADDED
@@ -0,0 +1,89 @@
|
|
1
|
+
= em-http-fetcher
|
2
|
+
|
3
|
+
HTTP fetch client based on ruby EventMachne and EM-HTTP-Request
|
4
|
+
that has configureable concurrency regardless of EM's thread pool.
|
5
|
+
|
6
|
+
== Example
|
7
|
+
|
8
|
+
EM.run do
|
9
|
+
trap(:INT) { EM.stop }
|
10
|
+
fetcher = EM::HttpFetcher.new
|
11
|
+
fetcher.callback do |req| # req is HttpRequest instance
|
12
|
+
# Here is global callback block for all request
|
13
|
+
p "Fetch success! #{req.last_effective_url} (#{req.response.size} bytes)"
|
14
|
+
end
|
15
|
+
|
16
|
+
%w(
|
17
|
+
http://www.google.com/
|
18
|
+
http://heroku.com/
|
19
|
+
http://sourceforge.net/
|
20
|
+
http://github.com/
|
21
|
+
).each do |url|
|
22
|
+
fetcher.request url
|
23
|
+
end
|
24
|
+
|
25
|
+
req = fetcher.request 'http://www.ruby-lang.org/'
|
26
|
+
req.callback do
|
27
|
+
# Here is appendix callback block for this request.
|
28
|
+
# Global callback block will also be called.
|
29
|
+
puts "Hello Ruby!"
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
== Install
|
34
|
+
|
35
|
+
After em-http-request *1.0.4* *or* *above* is released, you can install with gem.
|
36
|
+
Currently em-http-fetcher depends (> 1.0.3) to prevent to install intentionally.
|
37
|
+
|
38
|
+
$ gem install em-http-fetcher
|
39
|
+
|
40
|
+
=== Workaround with bundler
|
41
|
+
|
42
|
+
gem install bundler
|
43
|
+
|
44
|
+
And create Gemfile to fetch develop version of em-http-request.
|
45
|
+
|
46
|
+
source "http://rubygems.org"
|
47
|
+
gem 'em-http-request', :git => 'git://github.com/igrigorik/em-http-request.git'
|
48
|
+
|
49
|
+
Then run bundle to install gems.
|
50
|
+
|
51
|
+
$ bundle
|
52
|
+
|
53
|
+
Finally run your script with "bundle exec".
|
54
|
+
|
55
|
+
$ bundle exec YOUR_SCRIPT
|
56
|
+
|
57
|
+
== Usage
|
58
|
+
|
59
|
+
=== Options for HttpFetcher.new
|
60
|
+
|
61
|
+
[:concurrency] Concurrency for all request.
|
62
|
+
[:host_concurrency] Concurrency per host.
|
63
|
+
[:host_request_wait] Wait specified seconds after request on each request thread.
|
64
|
+
[(all other keys)] Pass through for HttpRequest.new
|
65
|
+
|
66
|
+
=== Options for HttpFetcher#request
|
67
|
+
|
68
|
+
[:uri] Target URI (String or URI object)
|
69
|
+
[:method] Request method (get/head/put...) (default=:get)
|
70
|
+
[(all other keys)] Pass through for HttpRequest#(get/head/put...)
|
71
|
+
|
72
|
+
If first argument is not a hash, it will be treated as :uri.
|
73
|
+
|
74
|
+
== Limitations
|
75
|
+
|
76
|
+
* :host_concurrency is checked only for initial URI.
|
77
|
+
When request is redirected, number of parallel requests for
|
78
|
+
one host may be over host_concurrency.
|
79
|
+
* Redirections will not work until issue #230 of em-http-request
|
80
|
+
is resolved; https://github.com/igrigorik/em-http-request/pull/230
|
81
|
+
|
82
|
+
== License
|
83
|
+
|
84
|
+
Same as Ruby 2.0 (2-clause BSDL or Ruby original license)
|
85
|
+
|
86
|
+
== See Also
|
87
|
+
|
88
|
+
EventMachine:: http://rubyeventmachine.com/
|
89
|
+
EM-HTTP-Request:: https://github.com/igrigorik/em-http-request
|
@@ -0,0 +1,31 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "em-http-fetcher"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "em-http-fetcher"
|
7
|
+
s.version = EventMachine::HttpFetcher::VERSION
|
8
|
+
|
9
|
+
s.platform = Gem::Platform::RUBY
|
10
|
+
s.authors = ["Tatsuki Sugiura"]
|
11
|
+
s.email = ["sugi@nemui.org"]
|
12
|
+
s.homepage = "http://github.com/sugi/em-http-fetcher"
|
13
|
+
s.summary = "HTTP fetch client based on ruby EventMachne and EM-HTTP-Request"
|
14
|
+
s.description = "HTTP fetch client based on ruby EventMachne and EM-HTTP-Request that has configureable concurrency regardless of EM's thread pool."
|
15
|
+
|
16
|
+
# s.rubyforge_project = ""
|
17
|
+
|
18
|
+
s.required_ruby_version = '>= 1.9.0'
|
19
|
+
|
20
|
+
s.add_dependency "addressable", ">= 2.2.3"
|
21
|
+
s.add_dependency "em-http-request", "> 1.0.3"
|
22
|
+
|
23
|
+
# s.add_development_dependency "rspec"
|
24
|
+
# s.add_development_dependency "rake"
|
25
|
+
|
26
|
+
s.files = `git ls-files`.split("\n")
|
27
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
28
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
29
|
+
s.require_paths = ["lib"]
|
30
|
+
end
|
31
|
+
|
@@ -0,0 +1 @@
|
|
1
|
+
require 'em/http-fetcher/fetcher.rb'
|
@@ -0,0 +1,163 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
require 'eventmachine'
|
3
|
+
require 'em/pool'
|
4
|
+
require 'em-http-request'
|
5
|
+
require 'addressable/uri'
|
6
|
+
|
7
|
+
module EventMachine
|
8
|
+
class HttpFetcher
|
9
|
+
VERSION = "0.1.0"
|
10
|
+
|
11
|
+
class RequestPool
|
12
|
+
def initialize(total_size, host_resource_size, host_reuse_wait = 0, opts = {})
|
13
|
+
super()
|
14
|
+
@total_size = total_size
|
15
|
+
@host_reuse_wait = host_reuse_wait
|
16
|
+
@host_resource_size = host_resource_size
|
17
|
+
|
18
|
+
@total_queue = EM::Queue.new
|
19
|
+
total_size.times { @total_queue.push true }
|
20
|
+
@host_pools = Hash.new {|h, k|
|
21
|
+
pool = EM::Pool.new
|
22
|
+
def pool.add item
|
23
|
+
super
|
24
|
+
@removed.delete item
|
25
|
+
end
|
26
|
+
host_resource_size.times {
|
27
|
+
pool.add EM::HttpRequest.new(k)
|
28
|
+
}
|
29
|
+
h[k] = { pool: pool, last_used: Time.now }
|
30
|
+
}
|
31
|
+
run
|
32
|
+
end
|
33
|
+
|
34
|
+
def perform(host, &b)
|
35
|
+
@host_pools[host][:pool].perform do |conn|
|
36
|
+
df = nil
|
37
|
+
@total_queue.pop do |tqi|
|
38
|
+
@host_pools[host][:last_used] = Time.now
|
39
|
+
@host_pools[host][:pool].remove conn
|
40
|
+
rq = proc { |req|
|
41
|
+
@total_queue.push tqi
|
42
|
+
lurl = req.last_effective_url
|
43
|
+
unless "#{lurl.scheme}://#{lurl.host}" == host
|
44
|
+
# Connection has been redirected another server.
|
45
|
+
# Re-create connection instance.
|
46
|
+
conn = EM::HttpRequest.new(host)
|
47
|
+
end
|
48
|
+
|
49
|
+
if @host_reuse_wait > 0
|
50
|
+
EM.add_timer(@host_reuse_wait) {
|
51
|
+
@host_pools[host][:pool].add conn
|
52
|
+
}
|
53
|
+
else
|
54
|
+
@host_pools[host][:pool].add conn
|
55
|
+
end
|
56
|
+
}
|
57
|
+
work = EM::Callback(&b)
|
58
|
+
df = work.call(conn)
|
59
|
+
df.callback(&rq)
|
60
|
+
df.errback(&rq)
|
61
|
+
df
|
62
|
+
end
|
63
|
+
df
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
def run
|
68
|
+
# cleanup host pool timer
|
69
|
+
EM.add_periodic_timer(10) do
|
70
|
+
hrsize = @host_resource_size
|
71
|
+
@host_pools.each do |host, info|
|
72
|
+
info[:pool].instance_eval { @resources.size < hrsize } and next
|
73
|
+
info[:last_used].to_i > Time.now.to_i - 5 * 60 and next
|
74
|
+
@host_pools.delete host
|
75
|
+
end
|
76
|
+
end
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
def initialize(opts = {})
|
81
|
+
@concurrency = opts[:concurrency] || 40
|
82
|
+
@host_concurrency = opts[:host_concurrency] || 2
|
83
|
+
@host_request_wait = opts[:host_request_wait] || 0.2
|
84
|
+
@request_pool = nil
|
85
|
+
@default_callbacks = []
|
86
|
+
@default_errbacks = []
|
87
|
+
@req_opts = {}.merge(opts)
|
88
|
+
@req_opts.delete :concurrency
|
89
|
+
@req_opts.delete :host_concurrency
|
90
|
+
@req_opts.delete :host_request_wait
|
91
|
+
end
|
92
|
+
|
93
|
+
def request_pool
|
94
|
+
@request_pool ||= RequestPool.new(@concurrency, @host_concurrency, @host_request_wait, @req_opts)
|
95
|
+
end
|
96
|
+
|
97
|
+
def callback(&block)
|
98
|
+
@default_callbacks << block
|
99
|
+
end
|
100
|
+
|
101
|
+
def errback(&block)
|
102
|
+
@default_errbacks << block
|
103
|
+
end
|
104
|
+
|
105
|
+
def request(*args)
|
106
|
+
if args.first.kind_of? Hash
|
107
|
+
opts = args[0]
|
108
|
+
uri = opts.delete(:uri)
|
109
|
+
else
|
110
|
+
uri = args.first
|
111
|
+
opts = args[1].kind_of?(Hash) ? args[1] : {}
|
112
|
+
end
|
113
|
+
|
114
|
+
uri.kind_of?(Addressable::URI) or
|
115
|
+
uri = Addressable::URI.parse(uri.to_s)
|
116
|
+
opts = {
|
117
|
+
:keepalive => true,
|
118
|
+
:redirects => 20,
|
119
|
+
:path => uri.path || '/',
|
120
|
+
}.merge(opts)
|
121
|
+
method = opts.delete(:method) || :get
|
122
|
+
uri.query and otps[:query] = uri.query
|
123
|
+
|
124
|
+
df = nil
|
125
|
+
request_pool.perform("#{uri.scheme}://#{uri.host}") do |conn|
|
126
|
+
df = req = conn.__send__(method, opts)
|
127
|
+
@default_callbacks.each do |cb|
|
128
|
+
req.callback(&cb)
|
129
|
+
end
|
130
|
+
@default_errbacks.each do |cb|
|
131
|
+
req.errback(&cb)
|
132
|
+
end
|
133
|
+
req
|
134
|
+
end
|
135
|
+
df
|
136
|
+
end
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
|
141
|
+
if __FILE__ == $0
|
142
|
+
trap(:INT) { EM.stop }
|
143
|
+
EM.run do
|
144
|
+
r = EM::HttpFetcher.new
|
145
|
+
r.callback do |req|
|
146
|
+
p [:success, req.last_effective_url, req.response.size]
|
147
|
+
end
|
148
|
+
r.errback do |req|
|
149
|
+
p [:err, req.last_effective_url, req.response.size]
|
150
|
+
end
|
151
|
+
|
152
|
+
ARGF.each { |line|
|
153
|
+
line.chomp!
|
154
|
+
line or next
|
155
|
+
req = r.request(line)
|
156
|
+
if line == 'http://www.yahoo.co.jp/'
|
157
|
+
req.callback do
|
158
|
+
p :yahoo!
|
159
|
+
end
|
160
|
+
end
|
161
|
+
}
|
162
|
+
end
|
163
|
+
end
|
metadata
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: em-http-fetcher
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Tatsuki Sugiura
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-05-11 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: addressable
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 2.2.3
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 2.2.3
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: em-http-request
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>'
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: 1.0.3
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>'
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: 1.0.3
|
46
|
+
description: HTTP fetch client based on ruby EventMachne and EM-HTTP-Request that
|
47
|
+
has configureable concurrency regardless of EM's thread pool.
|
48
|
+
email:
|
49
|
+
- sugi@nemui.org
|
50
|
+
executables: []
|
51
|
+
extensions: []
|
52
|
+
extra_rdoc_files: []
|
53
|
+
files:
|
54
|
+
- README.rdoc
|
55
|
+
- em-http-fetcher.gemspec
|
56
|
+
- lib/em-http-fetcher.rb
|
57
|
+
- lib/em/http-fetcher/fetcher.rb
|
58
|
+
homepage: http://github.com/sugi/em-http-fetcher
|
59
|
+
licenses: []
|
60
|
+
post_install_message:
|
61
|
+
rdoc_options: []
|
62
|
+
require_paths:
|
63
|
+
- lib
|
64
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: 1.9.0
|
70
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
71
|
+
none: false
|
72
|
+
requirements:
|
73
|
+
- - ! '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
requirements: []
|
77
|
+
rubyforge_project:
|
78
|
+
rubygems_version: 1.8.23
|
79
|
+
signing_key:
|
80
|
+
specification_version: 3
|
81
|
+
summary: HTTP fetch client based on ruby EventMachne and EM-HTTP-Request
|
82
|
+
test_files: []
|