wayback 0.1.0
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.
- data/.yardopts +10 -0
- data/CHANGELOG.md +3 -0
- data/CONTRIBUTING.md +52 -0
- data/LICENSE.md +20 -0
- data/README.md +81 -0
- data/Rakefile +11 -0
- data/lib/wayback.rb +32 -0
- data/lib/wayback/api/archive.rb +42 -0
- data/lib/wayback/api/utils.rb +27 -0
- data/lib/wayback/archive.rb +15 -0
- data/lib/wayback/base.rb +127 -0
- data/lib/wayback/client.rb +62 -0
- data/lib/wayback/configurable.rb +48 -0
- data/lib/wayback/default.rb +68 -0
- data/lib/wayback/error.rb +31 -0
- data/lib/wayback/error/already_favorited.rb +10 -0
- data/lib/wayback/error/already_retweeted.rb +10 -0
- data/lib/wayback/error/bad_gateway.rb +11 -0
- data/lib/wayback/error/bad_request.rb +10 -0
- data/lib/wayback/error/client_error.rb +28 -0
- data/lib/wayback/error/configuration_error.rb +8 -0
- data/lib/wayback/error/decode_error.rb +9 -0
- data/lib/wayback/error/forbidden.rb +10 -0
- data/lib/wayback/error/gateway_timeout.rb +11 -0
- data/lib/wayback/error/identity_map_key_error.rb +9 -0
- data/lib/wayback/error/internal_server_error.rb +11 -0
- data/lib/wayback/error/not_acceptable.rb +10 -0
- data/lib/wayback/error/not_found.rb +10 -0
- data/lib/wayback/error/server_error.rb +28 -0
- data/lib/wayback/error/service_unavailable.rb +11 -0
- data/lib/wayback/error/too_many_requests.rb +12 -0
- data/lib/wayback/error/unauthorized.rb +10 -0
- data/lib/wayback/error/unprocessable_entity.rb +10 -0
- data/lib/wayback/factory.rb +21 -0
- data/lib/wayback/identity.rb +50 -0
- data/lib/wayback/identity_map.rb +22 -0
- data/lib/wayback/page.rb +18 -0
- data/lib/wayback/response/parse_memento.rb +61 -0
- data/lib/wayback/response/parse_memento_page.rb +23 -0
- data/lib/wayback/response/raise_error.rb +31 -0
- data/lib/wayback/version.rb +18 -0
- data/spec/fixtures/list.timemap +9 -0
- data/spec/fixtures/page.html +225 -0
- data/spec/helper.rb +65 -0
- data/spec/wayback/api/archive_spec.rb +73 -0
- data/spec/wayback/archive_spec.rb +23 -0
- data/spec/wayback/base_spec.rb +117 -0
- data/spec/wayback/client_spec.rb +114 -0
- data/spec/wayback/error/client_error_spec.rb +23 -0
- data/spec/wayback/error/server_error_spec.rb +20 -0
- data/spec/wayback/error_spec.rb +20 -0
- data/spec/wayback/identifiable_spec.rb +50 -0
- data/spec/wayback/page_spec.rb +36 -0
- data/spec/wayback_spec.rb +47 -0
- data/wayback.gemspec +26 -0
- metadata +175 -0
data/.yardopts
ADDED
data/CHANGELOG.md
ADDED
data/CONTRIBUTING.md
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
## Contributing
|
2
|
+
In the spirit of [free software][free-sw], **everyone** is encouraged to help
|
3
|
+
improve this project.
|
4
|
+
|
5
|
+
[free-sw]: http://www.fsf.org/licensing/essays/free-sw.html
|
6
|
+
|
7
|
+
Here are some ways *you* can contribute:
|
8
|
+
|
9
|
+
* by using alpha, beta, and prerelease versions
|
10
|
+
* by reporting bugs
|
11
|
+
* by suggesting new features
|
12
|
+
* by writing or editing documentation
|
13
|
+
* by writing specifications
|
14
|
+
* by writing code (**no patch is too small**: fix typos, add comments, clean up
|
15
|
+
inconsistent whitespace)
|
16
|
+
* by refactoring code
|
17
|
+
* by fixing [issues][]
|
18
|
+
* by reviewing patches
|
19
|
+
* [financially][pledgie]
|
20
|
+
|
21
|
+
[issues]: https://github.com/xolator/wayback/issues
|
22
|
+
|
23
|
+
## Submitting an Issue
|
24
|
+
We use the [GitHub issue tracker][issues] to track bugs and features. Before
|
25
|
+
submitting a bug report or feature request, check to make sure it hasn't
|
26
|
+
already been submitted. When submitting a bug report, please include a [Gist][]
|
27
|
+
that includes a stack trace and any details that may be necessary to reproduce
|
28
|
+
the bug, including your gem version, Ruby version, and operating system.
|
29
|
+
Ideally, a bug report should include a pull request with failing specs.
|
30
|
+
|
31
|
+
[gist]: https://gist.github.com/
|
32
|
+
|
33
|
+
## Submitting a Pull Request
|
34
|
+
1. [Fork the repository.][fork]
|
35
|
+
2. [Create a topic branch.][branch]
|
36
|
+
3. Add specs for your unimplemented feature or bug fix.
|
37
|
+
4. Run `bundle exec rake spec`. If your specs pass, return to step 3.
|
38
|
+
5. Implement your feature or bug fix.
|
39
|
+
6. Run `bundle exec rake spec`. If your specs fail, return to step 5.
|
40
|
+
7. Run `open coverage/index.html`. If your changes are not completely covered
|
41
|
+
by your tests, return to step 3.
|
42
|
+
8 Run `RUBYOPT=W2 bundle exec rake spec 2>&1 | grep wayback`. If your changes
|
43
|
+
produce any warnings, return to step 5.
|
44
|
+
9. Add documentation for your feature or bug fix.
|
45
|
+
10. Run `bundle exec rake yard`. If your changes are not 100% documented, go
|
46
|
+
back to step 9.
|
47
|
+
11. Commit and push your changes.
|
48
|
+
12. [Submit a pull request.][pr]
|
49
|
+
|
50
|
+
[fork]: http://help.github.com/fork-a-repo/
|
51
|
+
[branch]: http://learn.github.com/p/branching.html
|
52
|
+
[pr]: http://help.github.com/send-pull-requests/
|
data/LICENSE.md
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2013 XOlator.
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,81 @@
|
|
1
|
+
# Wayback Gem
|
2
|
+
|
3
|
+

|
4
|
+

|
5
|
+
|
6
|
+
A Ruby interface to Archive.org's Wayback Machine Memento API.
|
7
|
+
|
8
|
+
## Installation
|
9
|
+
gem install wayback
|
10
|
+
|
11
|
+
## Quick Start Guide
|
12
|
+
So you want to get up and tweeting as fast as possible?
|
13
|
+
|
14
|
+
|
15
|
+
## Documentation
|
16
|
+
COMING SOON! -- [documentation](http://rdoc.info/gems/wayback)
|
17
|
+
|
18
|
+
|
19
|
+
## Configuration
|
20
|
+
|
21
|
+
There is no real configuration necessary for accessing Archive.org's Wayback Machine Memento API, however you can change endpoint and other basic connection options.
|
22
|
+
|
23
|
+
The current defaults for this gem are:
|
24
|
+
|
25
|
+
```ruby
|
26
|
+
Wayback.configure do |c|
|
27
|
+
c.endpoint = 'http://api.wayback.archive.org'
|
28
|
+
c.connection_options = {
|
29
|
+
:headers => {:user_agent => "Wayback Ruby Gem #{Wayback::Version}"},
|
30
|
+
:request => {:open_timeout => 5, :timeout => 10},
|
31
|
+
:ssl => {:verify => false},
|
32
|
+
}
|
33
|
+
c.identiy_map = false
|
34
|
+
c.middleware = Faraday::Builder.new do |builder|
|
35
|
+
# Convert request params to "www-form-urlencoded"
|
36
|
+
builder.use Faraday::Request::UrlEncoded
|
37
|
+
# Follow redirects
|
38
|
+
builder.use FaradayMiddleware::FollowRedirects
|
39
|
+
# Handle 4xx server responses
|
40
|
+
builder.use Wayback::Response::RaiseError, Wayback::Error::ClientError
|
41
|
+
# Handle 5xx server responses
|
42
|
+
builder.use Wayback::Response::RaiseError, Wayback::Error::ServerError
|
43
|
+
# Parse memento page
|
44
|
+
builder.use Wayback::Response::ParseMementoPage
|
45
|
+
# Parse link-format with custom memento parser
|
46
|
+
builder.use Wayback::Response::ParseMemento
|
47
|
+
# Set Faraday's HTTP adapter
|
48
|
+
builder.adapter Faraday.default_adapter
|
49
|
+
end
|
50
|
+
```
|
51
|
+
|
52
|
+
|
53
|
+
## Usage Examples
|
54
|
+
|
55
|
+
**Fetch the timeline of archived pages**
|
56
|
+
|
57
|
+
```ruby
|
58
|
+
Wayback.list('http://www.xolator.com')
|
59
|
+
```
|
60
|
+
|
61
|
+
**Fetch a specific archived page**
|
62
|
+
|
63
|
+
```ruby
|
64
|
+
Wayback.page('http://www.xolator.com', 1363488758)
|
65
|
+
Wayback.page('http://www.xolator.com', :first)
|
66
|
+
Wayback.page('http://www.xolator.com', :last)
|
67
|
+
```
|
68
|
+
|
69
|
+
|
70
|
+
## Additional Notes
|
71
|
+
Based heavily on the [Twitter gem](https://www.github.com/sferik/twitter). (Xie xie!)
|
72
|
+
|
73
|
+
More information on Archive's Wayback Machine memento API can be found [here](http://mementoweb.org/depot/native/ia/).
|
74
|
+
|
75
|
+
|
76
|
+
|
77
|
+
## Copyright
|
78
|
+
Copyright (c) 2013 XOlator.
|
79
|
+
See [LICENSE][] for details.
|
80
|
+
|
81
|
+
[license]: LICENSE.md
|
data/Rakefile
ADDED
data/lib/wayback.rb
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
require 'wayback/archive'
|
2
|
+
require 'wayback/client'
|
3
|
+
require 'wayback/configurable'
|
4
|
+
require 'wayback/default'
|
5
|
+
require 'wayback/page'
|
6
|
+
|
7
|
+
module Wayback
|
8
|
+
class << self
|
9
|
+
include Wayback::Configurable
|
10
|
+
|
11
|
+
# Delegate to a Wayback::Client
|
12
|
+
#
|
13
|
+
# @return [Wayback::Client]
|
14
|
+
def client
|
15
|
+
@client = Wayback::Client.new(options) unless defined?(@client) && @client.hash == options.hash
|
16
|
+
@client
|
17
|
+
end
|
18
|
+
|
19
|
+
def respond_to_missing?(method_name, include_private=false); client.respond_to?(method_name, include_private); end if RUBY_VERSION >= "1.9"
|
20
|
+
def respond_to?(method_name, include_private=false); client.respond_to?(method_name, include_private) || super; end if RUBY_VERSION < "1.9"
|
21
|
+
|
22
|
+
private
|
23
|
+
|
24
|
+
def method_missing(method_name, *args, &block)
|
25
|
+
return super unless client.respond_to?(method_name)
|
26
|
+
client.send(method_name, *args, &block)
|
27
|
+
end
|
28
|
+
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
Wayback.setup
|
@@ -0,0 +1,42 @@
|
|
1
|
+
require 'time'
|
2
|
+
require 'wayback/api/utils'
|
3
|
+
require 'wayback/error/not_found'
|
4
|
+
|
5
|
+
module Wayback
|
6
|
+
module API
|
7
|
+
module Archive
|
8
|
+
include Wayback::API::Utils
|
9
|
+
|
10
|
+
# Return a list of archived pages
|
11
|
+
#
|
12
|
+
# @return [Wayback::Archive]
|
13
|
+
# @param url [String] The page that of which was archived.
|
14
|
+
# @param options [Hash] A customizable set of options.
|
15
|
+
# @example Return the list of available archives for a web page.
|
16
|
+
# Wayback.list('http://gleu.ch')
|
17
|
+
def list(url, options={})
|
18
|
+
object_from_response(Wayback::Archive, :get, "/list/timemap/link/#{url}", options)
|
19
|
+
end
|
20
|
+
|
21
|
+
# Returns the HTML contents of an archive page, fetched by date
|
22
|
+
#
|
23
|
+
# @raise [Wayback::Error::Unauthorized] Error raised when supplied user credentials are not valid.
|
24
|
+
# @return [Wayback::Page]
|
25
|
+
# @param url [String] The page that of which was archived.
|
26
|
+
# @param options [Hash] A customizable set of options.
|
27
|
+
# @example Return the HTML archive for the page.
|
28
|
+
# Wayback.page('http://gleu.ch')
|
29
|
+
# Wayback.page('http://gleu.ch', 'Tue, 17 Jan 2012 07:33:06 GMT')
|
30
|
+
# Wayback.page('http://gleu.ch', '20130113125339')
|
31
|
+
# Wayback.page('http://gleu.ch', :first)
|
32
|
+
# Wayback.page('http://gleu.ch', :last)
|
33
|
+
def page(url, date=0, options={})
|
34
|
+
date = 0 if date == :first
|
35
|
+
date = Time.now if date == :last
|
36
|
+
date = Time.parse(date).to_i unless [Fixnum,Time,Integer].include?(date.class)
|
37
|
+
object_from_response(Wayback::Page, :get, "/memento/#{date.to_i}/#{url}", options)
|
38
|
+
end
|
39
|
+
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module Wayback
|
2
|
+
module API
|
3
|
+
module Utils
|
4
|
+
|
5
|
+
private
|
6
|
+
|
7
|
+
# @param klass [Class]
|
8
|
+
# @param request_method [Symbol]
|
9
|
+
# @param path [String]
|
10
|
+
# @param options [Hash]
|
11
|
+
# @return [Object]
|
12
|
+
def object_from_response(klass, request_method, path, options={})
|
13
|
+
response = send(request_method.to_sym, path, options)
|
14
|
+
klass.from_response(response)
|
15
|
+
end
|
16
|
+
|
17
|
+
# def handle_forbidden_error(klass, error)
|
18
|
+
# if error.message == klass::MESSAGE
|
19
|
+
# raise klass.new
|
20
|
+
# else
|
21
|
+
# raise error
|
22
|
+
# end
|
23
|
+
# end
|
24
|
+
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
data/lib/wayback/base.rb
ADDED
@@ -0,0 +1,127 @@
|
|
1
|
+
require 'wayback/error/identity_map_key_error'
|
2
|
+
|
3
|
+
module Wayback
|
4
|
+
class Base
|
5
|
+
# Define methods that retrieve the value from an initialized instance variable Hash, using the attribute as a key
|
6
|
+
#
|
7
|
+
# @param attrs [Array, Set, Symbol]
|
8
|
+
def self.attr_reader(*attrs)
|
9
|
+
mod = Module.new do
|
10
|
+
attrs.each do |attribute|
|
11
|
+
define_method attribute do
|
12
|
+
@attrs[attribute.to_sym]
|
13
|
+
end
|
14
|
+
define_method "#{attribute}?" do
|
15
|
+
!!@attrs[attribute.to_sym]
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
const_set(:Attributes, mod)
|
20
|
+
include mod
|
21
|
+
end
|
22
|
+
|
23
|
+
# return [Wayback::IdentityMap]
|
24
|
+
def self.identity_map
|
25
|
+
return unless Wayback.identity_map
|
26
|
+
@identity_map = Wayback.identity_map.new unless defined?(@identity_map) && @identity_map.class == Wayback.identity_map
|
27
|
+
@identity_map
|
28
|
+
end
|
29
|
+
|
30
|
+
# Retrieves an object from the identity map.
|
31
|
+
#
|
32
|
+
# @param attrs [Hash]
|
33
|
+
# @return [Wayback::Base]
|
34
|
+
def self.fetch(attrs)
|
35
|
+
return unless identity_map
|
36
|
+
if object = identity_map.fetch(Marshal.dump(attrs))
|
37
|
+
return object
|
38
|
+
end
|
39
|
+
return yield if block_given?
|
40
|
+
raise Wayback::Error::IdentityMapKeyError, "key not found"
|
41
|
+
end
|
42
|
+
|
43
|
+
# Stores an object in the identity map.
|
44
|
+
#
|
45
|
+
# @param object [Object]
|
46
|
+
# @return [Wayback::Base]
|
47
|
+
def self.store(object)
|
48
|
+
return object unless identity_map
|
49
|
+
identity_map.store(Marshal.dump(object.attrs), object)
|
50
|
+
end
|
51
|
+
|
52
|
+
# Returns a new object based on the response hash
|
53
|
+
#
|
54
|
+
# @param response [Hash]
|
55
|
+
# @return [Wayback::Base]
|
56
|
+
def self.from_response(response={})
|
57
|
+
fetch_or_new(response[:body])
|
58
|
+
end
|
59
|
+
|
60
|
+
# Retrieves an object from the identity map, or stores it in the
|
61
|
+
# identity map if it doesn't already exist.
|
62
|
+
#
|
63
|
+
# @param attrs [Hash]
|
64
|
+
# @return [Wayback::Base]
|
65
|
+
def self.fetch_or_new(attrs={})
|
66
|
+
return unless attrs
|
67
|
+
return new(attrs) unless identity_map
|
68
|
+
|
69
|
+
fetch(attrs) do
|
70
|
+
object = new(attrs)
|
71
|
+
store(object)
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
# Initializes a new object
|
76
|
+
#
|
77
|
+
# @param attrs [Hash]
|
78
|
+
# @return [Wayback::Base]
|
79
|
+
def initialize(attrs={})
|
80
|
+
@attrs = attrs
|
81
|
+
end
|
82
|
+
|
83
|
+
# Fetches an attribute of an object using hash notation
|
84
|
+
#
|
85
|
+
# @param method [String, Symbol] Message to send to the object
|
86
|
+
def [](method)
|
87
|
+
send(method.to_sym)
|
88
|
+
rescue NoMethodError
|
89
|
+
nil
|
90
|
+
end
|
91
|
+
|
92
|
+
# Retrieve the attributes of an object
|
93
|
+
#
|
94
|
+
# @return [Hash]
|
95
|
+
def attrs
|
96
|
+
@attrs.inject({}) do |attrs, (key, value)|
|
97
|
+
attrs.merge!(key => respond_to?(key) ? send(key) : value)
|
98
|
+
end
|
99
|
+
end
|
100
|
+
alias to_hash attrs
|
101
|
+
|
102
|
+
# Update the attributes of an object
|
103
|
+
#
|
104
|
+
# @param attrs [Hash]
|
105
|
+
# @return [Wayback::Base]
|
106
|
+
def update(attrs)
|
107
|
+
@attrs.update(attrs)
|
108
|
+
self
|
109
|
+
end
|
110
|
+
|
111
|
+
protected
|
112
|
+
|
113
|
+
# @param attr [Symbol]
|
114
|
+
# @param other [Wayback::Base]
|
115
|
+
# @return [Boolean]
|
116
|
+
def attr_equal(attr, other)
|
117
|
+
self.class == other.class && !other.send(attr).nil? && send(attr) == other.send(attr)
|
118
|
+
end
|
119
|
+
|
120
|
+
# @param other [Wayback::Base]
|
121
|
+
# @return [Boolean]
|
122
|
+
def attrs_equal(other)
|
123
|
+
self.class == other.class && !other.attrs.empty? && attrs == other.attrs
|
124
|
+
end
|
125
|
+
|
126
|
+
end
|
127
|
+
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
require 'faraday'
|
2
|
+
require 'wayback/api/archive'
|
3
|
+
require 'wayback/configurable'
|
4
|
+
require 'wayback/error/client_error'
|
5
|
+
require 'wayback/error/decode_error'
|
6
|
+
require 'uri'
|
7
|
+
|
8
|
+
module Wayback
|
9
|
+
# Wrapper for the Wayback Memento/Timehop API
|
10
|
+
class Client
|
11
|
+
include Wayback::API::Archive
|
12
|
+
include Wayback::Configurable
|
13
|
+
|
14
|
+
# Initializes a new Client object
|
15
|
+
#
|
16
|
+
# @param options [Hash]
|
17
|
+
# @return [Wayback::Client]
|
18
|
+
def initialize(options={})
|
19
|
+
Wayback::Configurable.keys.each do |key|
|
20
|
+
instance_variable_set(:"@#{key}", options[key] || Wayback.instance_variable_get(:"@#{key}"))
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
# Perform an HTTP DELETE request
|
25
|
+
def delete(path, params={})
|
26
|
+
request(:delete, path, params)
|
27
|
+
end
|
28
|
+
|
29
|
+
# Perform an HTTP GET request
|
30
|
+
def get(path, params={})
|
31
|
+
request(:get, path, params)
|
32
|
+
end
|
33
|
+
|
34
|
+
# Perform an HTTP POST request
|
35
|
+
def post(path, params={})
|
36
|
+
signature_params = params.values.any?{|value| value.respond_to?(:to_io)} ? {} : params
|
37
|
+
request(:post, path, params, signature_params)
|
38
|
+
end
|
39
|
+
|
40
|
+
# Perform an HTTP PUT request
|
41
|
+
def put(path, params={})
|
42
|
+
request(:put, path, params)
|
43
|
+
end
|
44
|
+
|
45
|
+
|
46
|
+
private
|
47
|
+
|
48
|
+
def request(method, path, params={}, signature_params=params)
|
49
|
+
connection.send(method.to_sym, path, params).env
|
50
|
+
rescue Faraday::Error::ClientError
|
51
|
+
raise Wayback::Error::ClientError
|
52
|
+
end
|
53
|
+
|
54
|
+
# Returns a Faraday::Connection object
|
55
|
+
#
|
56
|
+
# @return [Faraday::Connection]
|
57
|
+
def connection
|
58
|
+
@connection ||= Faraday.new(@endpoint, @connection_options.merge(:builder => @middleware))
|
59
|
+
end
|
60
|
+
|
61
|
+
end
|
62
|
+
end
|