cached_web 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +1 -0
- data/cached_web.gemspec +20 -0
- data/lib/cached_web/version.rb +3 -0
- data/lib/cached_web.rb +146 -0
- metadata +69 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Ian Connor
|
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
|
+
# CachedWeb
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'cached_web'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install cached_web
|
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
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/cached_web.gemspec
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'cached_web/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "cached_web"
|
8
|
+
gem.version = CachedWeb::VERSION
|
9
|
+
gem.authors = ["Ian Connor"]
|
10
|
+
gem.email = ["iconnor@projectlounge.com"]
|
11
|
+
gem.description = %q{Simple gem to cache web locally}
|
12
|
+
gem.summary = %q{Cached web with sleeps and local storage}
|
13
|
+
gem.homepage = ""
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
gem.add_development_dependency "mechanize"
|
20
|
+
end
|
data/lib/cached_web.rb
ADDED
@@ -0,0 +1,146 @@
|
|
1
|
+
require "cached_web/version"
|
2
|
+
|
3
|
+
class CachedWeb
|
4
|
+
|
5
|
+
@@min_wait_times = {}
|
6
|
+
@@last_request_times = {}
|
7
|
+
|
8
|
+
def escape_key(key)
|
9
|
+
if key.size > 140
|
10
|
+
Digest::MD5.hexdigest(key)
|
11
|
+
else
|
12
|
+
key.gsub(/[^a-z0-9]/i,"_")
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
def self.get(params)
|
17
|
+
CachedWeb.new.get(params)
|
18
|
+
end
|
19
|
+
|
20
|
+
def get(params)
|
21
|
+
url = params[:url].gsub(" ","%20").gsub("%off", "%25off")
|
22
|
+
page, redirect_url, headers = get_cache(:url=>url, :expires_in=>params[:expires_in], :details=>true) rescue [nil, nil, nil]
|
23
|
+
|
24
|
+
if params[:cache_only]
|
25
|
+
return [nil, nil, nil] if page.blank?
|
26
|
+
return [page, redirect_url, headers]
|
27
|
+
end
|
28
|
+
|
29
|
+
if page.blank?
|
30
|
+
uri = URI.parse(url)
|
31
|
+
domain = uri.host.downcase
|
32
|
+
#puts "Not in cache - getting: #{params[:url]}"
|
33
|
+
# Don't hit a site more than once per 5 seconds
|
34
|
+
time_to_wait = (@@min_wait_times[domain] || 5) -
|
35
|
+
(Time.now - (@@last_request_times[domain] || Time.at(0)))
|
36
|
+
if time_to_wait > 0
|
37
|
+
puts "Waiting for #{time_to_wait} on domain #{domain}"
|
38
|
+
sleep time_to_wait
|
39
|
+
end
|
40
|
+
|
41
|
+
@agent = Mechanize.new unless @agent
|
42
|
+
page = @agent.get(url)
|
43
|
+
@@last_request_times[uri.host]
|
44
|
+
content = page.body
|
45
|
+
redirect_url = page.uri.to_s
|
46
|
+
headers = page.header
|
47
|
+
set_cache(:url=>url, :redirect_url=>redirect_url, :headers=>headers, :content=>content)
|
48
|
+
[content, redirect_url, headers]
|
49
|
+
else
|
50
|
+
[page, redirect_url, headers]
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def self.fetch_cache(params, &block)
|
55
|
+
CachedWeb.new.fetch_cache(params, &block)
|
56
|
+
end
|
57
|
+
|
58
|
+
def fetch_cache(params)
|
59
|
+
ret_val = nil
|
60
|
+
begin
|
61
|
+
ret_val = get_cache(params)
|
62
|
+
rescue
|
63
|
+
#puts "didn't find data in cache: #{$!}"
|
64
|
+
end
|
65
|
+
unless ret_val
|
66
|
+
ret_val = yield self
|
67
|
+
set_cache(params.merge(:page=>ret_val))
|
68
|
+
end
|
69
|
+
|
70
|
+
return ret_val
|
71
|
+
end
|
72
|
+
|
73
|
+
def post(url, params)
|
74
|
+
puts "Not in cache - POSTing to: #{url}"
|
75
|
+
@agent = Mechanize.new unless @agent
|
76
|
+
begin
|
77
|
+
page = @agent.post(url, params)
|
78
|
+
uri = URI.parse(url)
|
79
|
+
@@last_request_times[uri.host]
|
80
|
+
content = page.body
|
81
|
+
redirect_url = page.uri.to_s
|
82
|
+
headers = page.header
|
83
|
+
set_cache(:url=>url, :redirect_url=>redirect_url, :headers=>headers, :page=>content)
|
84
|
+
[content, redirect_url, headers]
|
85
|
+
rescue Exception => e
|
86
|
+
puts e
|
87
|
+
puts e.backtrace
|
88
|
+
Toadhopper(AIRBRAKE_KEY).post!(e)
|
89
|
+
["", url, {}]
|
90
|
+
end
|
91
|
+
end
|
92
|
+
|
93
|
+
def set_cache(params)
|
94
|
+
key = escape_key(params[:url].present? ? params[:url] : params[:key])
|
95
|
+
content = params[:content]
|
96
|
+
redirect_url = params[:redirect_url]
|
97
|
+
|
98
|
+
h = {:content => content, :redirect_url=>redirect_url}
|
99
|
+
|
100
|
+
|
101
|
+
path = "/tmp/cachedweb/#{key}"
|
102
|
+
#puts "Saving file to #{path}"
|
103
|
+
begin
|
104
|
+
File.open(path, 'w') do |out|
|
105
|
+
YAML.dump(h, out)
|
106
|
+
end
|
107
|
+
rescue Exception
|
108
|
+
`mkdir -p /tmp/cachedweb`
|
109
|
+
File.open(path, 'w') do |out|
|
110
|
+
YAML.dump(h, out)
|
111
|
+
end
|
112
|
+
end
|
113
|
+
true
|
114
|
+
end
|
115
|
+
|
116
|
+
def get_cache(params)
|
117
|
+
key = escape_key(params[:url].present? ? params[:url] : params[:key])
|
118
|
+
details = params[:details]
|
119
|
+
expires_in = params[:expires_in]
|
120
|
+
|
121
|
+
timestamp = nil
|
122
|
+
|
123
|
+
path = "/tmp/cachedweb/#{key}"
|
124
|
+
timestamp = File.ctime(path)
|
125
|
+
|
126
|
+
if expires_in and timestamp.nil?
|
127
|
+
#puts "There is no timestamp, force a get of this URL so we can add a timestamp"
|
128
|
+
throw "There is no timestamp, force a get of this URL so we can add a timestamp"
|
129
|
+
end
|
130
|
+
|
131
|
+
if expires_in and timestamp and timestamp < (Time.now - expires_in)
|
132
|
+
#puts "Cache is older than desired, saved on #{timestamp}"
|
133
|
+
throw "Cache is older than desired, saved on #{timestamp}"
|
134
|
+
end
|
135
|
+
|
136
|
+
h = YAML::load_file(path)
|
137
|
+
content = h[:content]
|
138
|
+
redirect_url = h[:redirect_url]
|
139
|
+
if details
|
140
|
+
[content, redirect_url, nil]
|
141
|
+
else
|
142
|
+
content
|
143
|
+
end
|
144
|
+
end
|
145
|
+
|
146
|
+
end
|
metadata
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: cached_web
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Ian Connor
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-06-19 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: mechanize
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
description: Simple gem to cache web locally
|
31
|
+
email:
|
32
|
+
- iconnor@projectlounge.com
|
33
|
+
executables: []
|
34
|
+
extensions: []
|
35
|
+
extra_rdoc_files: []
|
36
|
+
files:
|
37
|
+
- .gitignore
|
38
|
+
- Gemfile
|
39
|
+
- LICENSE.txt
|
40
|
+
- README.md
|
41
|
+
- Rakefile
|
42
|
+
- cached_web.gemspec
|
43
|
+
- lib/cached_web.rb
|
44
|
+
- lib/cached_web/version.rb
|
45
|
+
homepage: ''
|
46
|
+
licenses: []
|
47
|
+
post_install_message:
|
48
|
+
rdoc_options: []
|
49
|
+
require_paths:
|
50
|
+
- lib
|
51
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ! '>='
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '0'
|
57
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
58
|
+
none: false
|
59
|
+
requirements:
|
60
|
+
- - ! '>='
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
version: '0'
|
63
|
+
requirements: []
|
64
|
+
rubyforge_project:
|
65
|
+
rubygems_version: 1.8.24
|
66
|
+
signing_key:
|
67
|
+
specification_version: 3
|
68
|
+
summary: Cached web with sleeps and local storage
|
69
|
+
test_files: []
|