collamine 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +15 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +35 -0
- data/Rakefile +2 -0
- data/collamine.gemspec +28 -0
- data/lib/collamine/request.rb +37 -0
- data/lib/collamine/version.rb +3 -0
- data/lib/collamine.rb +60 -0
- data/test.rb +28 -0
- metadata +140 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 6b539a01cbb2e35c410520e1d2ad60e6a82c6635
|
4
|
+
data.tar.gz: 126dc784195a7c51efac6d7047875fa63a9e049e
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 53d249cb2200ff324cd356c98929f439873105089a69e8ea98aad49af7e36eaee1fffc74a42fa286c1fc9b377f44bf4d92e1f3a3849954540dde3e073262af74
|
7
|
+
data.tar.gz: 53fea6d874d66d6d48b3ac4c6453360e4409c30cd6b3eacc01873bc620f389b488c96420f75bb01c3079f94237cee3209fb220ce73a18fe8c8d94763d1bd26b6
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Belson Heng
|
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 +1,35 @@
|
|
1
|
+
# Collamine
|
2
|
+
|
3
|
+
This is a ruby gem for CollaMine client, which communicates with CollaMine servers to download content from their SmartCache if it exists. It also lets you crawl a web site using [SpiderCrawl](https://github.com/belsonheng/spidercrawl) and share the results with the community via CollaMine servers.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'collamine'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install collamine
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
To get started,
|
24
|
+
|
25
|
+
require 'collamine'
|
26
|
+
Collamine.start('http://forums.hardwarezone.com.sg/hwm-magazine-publication-38/',
|
27
|
+
:pattern => Regexp.new('^http:\/\/forums\.hardwarezone\.com\.sg\/hwm-magazine-publication-38\/?(.*\.html)?$'))
|
28
|
+
|
29
|
+
## Contributing
|
30
|
+
|
31
|
+
1. Fork it ( https://github.com/belsonheng/collamine/fork )
|
32
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
33
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
34
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
35
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
data/collamine.gemspec
ADDED
@@ -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 'collamine/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "collamine"
|
8
|
+
spec.version = Collamine::VERSION
|
9
|
+
spec.authors = ["Belson Heng"]
|
10
|
+
spec.email = ["belsonheng@gmail.com"]
|
11
|
+
spec.summary = %q{Collamine lets you crawl a web site and share the results with the community via CollaMine servers.}
|
12
|
+
spec.description = %q{Collamine is a ruby gem for CollaMine client, which communicates with CollaMine servers to download content from their SmartCache if it exists.}
|
13
|
+
spec.homepage = "http://github.com/belsonheng/collamine/"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
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", "~> 1.7"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
|
24
|
+
spec.add_dependency "multipart-post"
|
25
|
+
spec.add_dependency "domainatrix"
|
26
|
+
spec.add_dependency "mongo"
|
27
|
+
spec.add_dependency "bson_ext"
|
28
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
require 'cgi'
|
2
|
+
require 'net/http/post/multipart'
|
3
|
+
require 'domainatrix'
|
4
|
+
|
5
|
+
# Makes the request to CollaMine servers
|
6
|
+
class Request
|
7
|
+
COLLAMINE_DOWNLOAD_URL = 'http://172.31.22.135:9001/download/html/'
|
8
|
+
COLLAMINE_UPLOAD_URL = 'http://172.31.22.135:9001/upload/html/multipart/'
|
9
|
+
#
|
10
|
+
# Try downloading the content from CollaMine servers
|
11
|
+
#
|
12
|
+
def self.try_collamine(url)
|
13
|
+
uri = URI.parse(COLLAMINE_DOWNLOAD_URL+CGI::escape(url.to_s))
|
14
|
+
Net::HTTP.start(uri.host, uri.port) do |http|
|
15
|
+
response = http.get(uri)
|
16
|
+
case response
|
17
|
+
when Net::HTTPSuccess then
|
18
|
+
return nil if response.body == 'not found' rescue nil
|
19
|
+
return response
|
20
|
+
else nil
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
#
|
25
|
+
# Upload the content to Collamine servers
|
26
|
+
#
|
27
|
+
def self.upload_to_collamine(url, content, filename, crawltime)
|
28
|
+
post_request = Net::HTTP::Post::Multipart.new COLLAMINE_UPLOAD_URL,
|
29
|
+
'domain' => Domainatrix.parse(url).domain,
|
30
|
+
'url' => url,
|
31
|
+
'crawltime' => crawltime,
|
32
|
+
'contributor' => 'belson',
|
33
|
+
'document' => UploadIO.new(StringIO.new(content.encode('UTF-8', 'ISO-8859-15')), 'text/html', filename)
|
34
|
+
response = Net::HTTP.start(URI.parse(COLLAMINE_UPLOAD_URL).host, URI.parse(COLLAMINE_UPLOAD_URL).port) { |http| http.request(post_request) }
|
35
|
+
puts response.body
|
36
|
+
end
|
37
|
+
end
|
data/lib/collamine.rb
ADDED
@@ -0,0 +1,60 @@
|
|
1
|
+
require 'collamine/request'
|
2
|
+
require 'spidercrawl'
|
3
|
+
|
4
|
+
require 'curb'
|
5
|
+
require 'domainatrix'
|
6
|
+
require 'mongo'
|
7
|
+
|
8
|
+
class Collamine
|
9
|
+
include Mongo
|
10
|
+
STORE = MongoClient.new("localhost", 27017).db("smartcache").collection("html")
|
11
|
+
|
12
|
+
def self.start(url, options)
|
13
|
+
from_collamine = []
|
14
|
+
pages = Spiderman.shoot(url, options) do |web|
|
15
|
+
collamine = nil
|
16
|
+
web.before_fetch do |url|
|
17
|
+
# Try to fetch from collamine server
|
18
|
+
puts "trying collamine: #{url}"
|
19
|
+
puts "fetched from collamine: #{url}" if (collamine = Request.try_collamine(url))
|
20
|
+
from_collamine << url if collamine
|
21
|
+
collamine
|
22
|
+
end
|
23
|
+
web.on_redirect do |url|
|
24
|
+
# Try to fetch from collamine server
|
25
|
+
puts "trying collamine: #{url}"
|
26
|
+
puts "fetched from collamine: #{url}" if (collamine = Request.try_collamine(url))
|
27
|
+
from_collamine << url if collamine
|
28
|
+
collamine
|
29
|
+
end
|
30
|
+
web.after_fetch do |page|
|
31
|
+
unless page.content == ''
|
32
|
+
# Upload to collamine if it cannot be found in server
|
33
|
+
unless collamine
|
34
|
+
puts "uploading to collamine: #{page.url}"
|
35
|
+
filename = page.url.split('/').last
|
36
|
+
filename += '.html' unless filename.include?('.html')
|
37
|
+
Request.upload_to_collamine(page.url, page.content, filename, page.crawled_time.to_i)
|
38
|
+
end
|
39
|
+
# Check if duplicate
|
40
|
+
unless STORE.find("url" => page.url).to_a.size > 0
|
41
|
+
# Insert into Mongodb
|
42
|
+
puts "Insert to db: #{page.url}"
|
43
|
+
source = (from_collamine.include?(page.url) ? 'collamine' : 'original')
|
44
|
+
doc = {:url => page.url,
|
45
|
+
:domain => Domainatrix.parse(page.url).domain,
|
46
|
+
:source => source,
|
47
|
+
:content => page.content.encode('UTF-8', 'ISO-8859-15'),
|
48
|
+
:crawled_date => page.crawled_time.to_i,
|
49
|
+
:response_time => page.response_time.to_i
|
50
|
+
}
|
51
|
+
STORE.insert(doc)
|
52
|
+
else
|
53
|
+
puts "url exists"
|
54
|
+
end
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
return pages, from_collamine
|
59
|
+
end
|
60
|
+
end
|
data/test.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
require 'collamine'
|
2
|
+
|
3
|
+
#http://forums.hardwarezone.com.sg/hwm-magazine-publication-38/
|
4
|
+
#http://forums.hardwarezone.com.sg/money-mind-210/
|
5
|
+
#http://sgforums.com/forums/4
|
6
|
+
#http://forums.vr-zone.com/photography-lightroom/
|
7
|
+
#http://forums.gumi.sg/forum/news-boards
|
8
|
+
#http://en.forums.wordpress.com/
|
9
|
+
#http://www.spcnet.tv/forums/showthread.php/38762-Dugu-Jiu-Jian-Really-Unbeatable
|
10
|
+
#http://www.hungrygowhere.com/
|
11
|
+
#http://www.groupon.sg/
|
12
|
+
#http://www.amazon.com/
|
13
|
+
#https://www.apple.com/sg/
|
14
|
+
#http://forums.hardwarezone.com.sg/current-affairs-lounge-17/
|
15
|
+
|
16
|
+
pages, from_collamine = Collamine.start('http://forums.hardwarezone.com.sg/money-mind-210/',
|
17
|
+
:parallel => true,
|
18
|
+
:threads => 10,
|
19
|
+
:pattern => Regexp.new('^http:\/\/forums\.hardwarezone\.com\.sg\/money-mind-210\/?(.*\.html)?$'))
|
20
|
+
|
21
|
+
puts "Total pages crawled: #{pages.size}"
|
22
|
+
|
23
|
+
open('/tmp/ruby.log', 'w') do |f|
|
24
|
+
pages.each do |page|
|
25
|
+
f << "#{page.url}\n"
|
26
|
+
end
|
27
|
+
f << "Total pages crawled: #{pages.size}"
|
28
|
+
end
|
metadata
ADDED
@@ -0,0 +1,140 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: collamine
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.2.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Belson Heng
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-07-31 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: '1.7'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.7'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: multipart-post
|
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: domainatrix
|
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: mongo
|
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: bson_ext
|
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: Collamine is a ruby gem for CollaMine client, which communicates with
|
98
|
+
CollaMine servers to download content from their SmartCache if it exists.
|
99
|
+
email:
|
100
|
+
- belsonheng@gmail.com
|
101
|
+
executables: []
|
102
|
+
extensions: []
|
103
|
+
extra_rdoc_files: []
|
104
|
+
files:
|
105
|
+
- ".gitignore"
|
106
|
+
- Gemfile
|
107
|
+
- LICENSE.txt
|
108
|
+
- README.md
|
109
|
+
- Rakefile
|
110
|
+
- collamine.gemspec
|
111
|
+
- lib/collamine.rb
|
112
|
+
- lib/collamine/request.rb
|
113
|
+
- lib/collamine/version.rb
|
114
|
+
- test.rb
|
115
|
+
homepage: http://github.com/belsonheng/collamine/
|
116
|
+
licenses:
|
117
|
+
- MIT
|
118
|
+
metadata: {}
|
119
|
+
post_install_message:
|
120
|
+
rdoc_options: []
|
121
|
+
require_paths:
|
122
|
+
- lib
|
123
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
124
|
+
requirements:
|
125
|
+
- - ">="
|
126
|
+
- !ruby/object:Gem::Version
|
127
|
+
version: '0'
|
128
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
129
|
+
requirements:
|
130
|
+
- - ">="
|
131
|
+
- !ruby/object:Gem::Version
|
132
|
+
version: '0'
|
133
|
+
requirements: []
|
134
|
+
rubyforge_project:
|
135
|
+
rubygems_version: 2.4.5
|
136
|
+
signing_key:
|
137
|
+
specification_version: 4
|
138
|
+
summary: Collamine lets you crawl a web site and share the results with the community
|
139
|
+
via CollaMine servers.
|
140
|
+
test_files: []
|