wayback_archiver 0.0.1 → 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/bin/wayback_archiver +9 -1
- data/lib/wayback_archiver.rb +18 -38
- data/lib/wayback_archiver/archive.rb +19 -0
- data/lib/wayback_archiver/collector.rb +27 -0
- data/lib/wayback_archiver/request.rb +9 -0
- data/lib/wayback_archiver/version.rb +1 -1
- metadata +7 -10
- data/.gitignore +0 -17
- data/Gemfile +0 -4
- data/LICENSE.txt +0 -22
- data/README.md +0 -30
- data/Rakefile +0 -1
- data/wayback_archiver.gemspec +0 -34
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: c846ec4d2baeb3bc0087387f0501d25587424563
|
4
|
+
data.tar.gz: c7d4b89507ba88b2504e2c409ebe81440aaa1eec
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 16f09492eebc97040f466702cd5308260524dcd18bc04e289aad9813e48f8cf43fb3a77ed636e48a1fae4932c52e57c5b3316508518f327ac754cbfe036440d6
|
7
|
+
data.tar.gz: 8f2842913687e9d917d5ae609c12f598919bf97079d8e9a464ea6f9c679c4ff642708c63c3ab4bf37b30336878d2aab6eef3c73665f7961d971e896aa9a39af2
|
data/bin/wayback_archiver
CHANGED
data/lib/wayback_archiver.rb
CHANGED
@@ -1,46 +1,26 @@
|
|
1
|
-
require 'net/http'
|
2
1
|
require 'uri'
|
2
|
+
require 'net/http'
|
3
3
|
require 'rexml/document'
|
4
4
|
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
def self.archive(source, from)
|
9
|
-
from = from || :sitemap
|
10
|
-
urls = Array.new
|
11
|
-
case from.to_sym
|
12
|
-
when :sitemap
|
13
|
-
urls = WaybackArchiver.urls_from_sitemap("#{source}/sitemap.xml")
|
14
|
-
when :url
|
15
|
-
urls << source
|
16
|
-
when :file
|
17
|
-
urls = WaybackArchiver.urls_from_file(source)
|
18
|
-
end
|
19
|
-
|
20
|
-
urls.each_with_index do |url, index|
|
21
|
-
puts "Archiving (#{index + 1}/#{urls.length}): #{url}"
|
22
|
-
request_url = URI("#{WAYBACK_BASE_URL}#{url}")
|
23
|
-
res = Net::HTTP.get_response(request_url)
|
5
|
+
require 'wayback_archiver/collector'
|
6
|
+
require 'wayback_archiver/archive'
|
7
|
+
require 'wayback_archiver/request'
|
24
8
|
|
25
|
-
|
9
|
+
module WaybackArchiver
|
10
|
+
BASE_URL = 'https://web.archive.org/save/'
|
11
|
+
|
12
|
+
def self.archive(source, from = :sitemap)
|
13
|
+
urls = case from
|
14
|
+
when :sitemap, 'sitemap'
|
15
|
+
Collector.urls_from_sitemap("#{source}/sitemap.xml")
|
16
|
+
when :url, 'url'
|
17
|
+
Array(source)
|
18
|
+
when :file, 'file'
|
19
|
+
Collector.urls_from_file(source)
|
20
|
+
else
|
21
|
+
raise ArgumentError, "Unknown type: '#{from}'. Allowed types: sitemal, url, file"
|
26
22
|
end
|
27
|
-
|
28
|
-
|
29
|
-
def self.urls_from_sitemap(url)
|
30
|
-
urls = Array.new
|
31
|
-
xml_data = Net::HTTP.get_response(URI.parse(url)).body
|
32
|
-
document = REXML::Document.new(xml_data)
|
33
|
-
|
34
|
-
document.elements.each('urlset/url/loc') { |element| urls << element.text }
|
35
|
-
urls
|
36
|
-
end
|
37
|
-
|
38
|
-
def self.urls_from_file(path)
|
39
|
-
urls = Array.new
|
40
|
-
text = File.open(path).read
|
41
|
-
text.gsub!(/\r\n?/, "\n") # Normalize line endings
|
42
|
-
text.each_line { |line| urls << line.gsub(/\n/, '') }
|
43
|
-
urls
|
23
|
+
Archive.post(urls)
|
44
24
|
end
|
45
25
|
|
46
26
|
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
module WaybackArchiver
|
2
|
+
class Archive
|
3
|
+
|
4
|
+
def self.post(urls)
|
5
|
+
urls.each_with_index do |url, index|
|
6
|
+
request_url = "#{BASE_URL}#{url}"
|
7
|
+
puts "Archiving (#{index + 1}/#{urls.length}): #{url}"
|
8
|
+
begin
|
9
|
+
res = Request.get_response(request_url)
|
10
|
+
puts "#{res.code} => #{res.message}"
|
11
|
+
rescue Exception => e
|
12
|
+
puts "Error message: #{e.message}"
|
13
|
+
puts "Failed to archive: #{url}"
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module WaybackArchiver
|
2
|
+
class Collector
|
3
|
+
|
4
|
+
class << self
|
5
|
+
|
6
|
+
def urls_from_sitemap(url)
|
7
|
+
urls = Array.new
|
8
|
+
xml_data = Request.get_response(url).body
|
9
|
+
document = REXML::Document.new(xml_data)
|
10
|
+
|
11
|
+
document.elements.each('urlset/url/loc') { |element| urls << element.text }
|
12
|
+
urls
|
13
|
+
end
|
14
|
+
|
15
|
+
def urls_from_file(path)
|
16
|
+
raise ArgumentError, "No such file: #{path}" unless File.exist?(path)
|
17
|
+
urls = Array.new
|
18
|
+
text = File.open(path).read
|
19
|
+
text.gsub!(/\r\n?/, "\n") # Normalize line endings
|
20
|
+
text.each_line { |line| urls << line.gsub(/\n/, '').strip }
|
21
|
+
urls.reject(&:empty?)
|
22
|
+
end
|
23
|
+
|
24
|
+
end
|
25
|
+
|
26
|
+
end
|
27
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wayback_archiver
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jacob Burenstam
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-07-
|
11
|
+
date: 2014-07-30 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -46,15 +46,12 @@ executables:
|
|
46
46
|
extensions: []
|
47
47
|
extra_rdoc_files: []
|
48
48
|
files:
|
49
|
-
- .gitignore
|
50
|
-
- Gemfile
|
51
|
-
- LICENSE.txt
|
52
|
-
- README.md
|
53
|
-
- Rakefile
|
54
49
|
- bin/wayback_archiver
|
55
|
-
- lib/wayback_archiver.rb
|
50
|
+
- lib/wayback_archiver/archive.rb
|
51
|
+
- lib/wayback_archiver/collector.rb
|
52
|
+
- lib/wayback_archiver/request.rb
|
56
53
|
- lib/wayback_archiver/version.rb
|
57
|
-
- wayback_archiver.
|
54
|
+
- lib/wayback_archiver.rb
|
58
55
|
homepage: https://github.com/buren/wayback_archiver
|
59
56
|
licenses:
|
60
57
|
- MIT
|
@@ -77,6 +74,6 @@ requirements: []
|
|
77
74
|
rubyforge_project:
|
78
75
|
rubygems_version: 2.0.0
|
79
76
|
signing_key:
|
80
|
-
specification_version:
|
77
|
+
specification_version: 4
|
81
78
|
summary: Send URLs to Wayback Machine
|
82
79
|
test_files: []
|
data/.gitignore
DELETED
data/Gemfile
DELETED
data/LICENSE.txt
DELETED
@@ -1,22 +0,0 @@
|
|
1
|
-
Copyright (c) 2014 Jacob Burenstam
|
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
DELETED
@@ -1,30 +0,0 @@
|
|
1
|
-
# WaybackArchiver
|
2
|
-
Send URLs to [Wayback Machine](https://archive.org/web/) from [/sitemap.xml](http://www.sitemaps.org), single URL or file with URLs.
|
3
|
-
|
4
|
-
## Installation
|
5
|
-
Install the gem:
|
6
|
-
```bash
|
7
|
-
gem install wayback_archiver
|
8
|
-
```
|
9
|
-
|
10
|
-
## Usage
|
11
|
-
|
12
|
-
```bash
|
13
|
-
wayback_archiver http://example.com # Send each line defined in http://example.com/sitemap.xml
|
14
|
-
wayback_archiver http://example.com/some/path url # Only send http://example.com/some/path to Wayback Machine
|
15
|
-
wayback_archiver /path/to/some/file # With an URL on each line
|
16
|
-
```
|
17
|
-
|
18
|
-
View domain archive: https://web.archive.org/web/*/http://example.com
|
19
|
-
|
20
|
-
|
21
|
-
## Contributing
|
22
|
-
|
23
|
-
1. Fork it
|
24
|
-
2. Create your feature branch (`git checkout -b my-new-feature`)
|
25
|
-
3. Commit your changes (`git commit -am 'Add some feature'`)
|
26
|
-
4. Push to the branch (`git push origin my-new-feature`)
|
27
|
-
5. Create new Pull Request
|
28
|
-
|
29
|
-
---------
|
30
|
-
Don't know what a sitemap is? [http://sitemaps.org](http://www.sitemaps.org)
|
data/Rakefile
DELETED
@@ -1 +0,0 @@
|
|
1
|
-
require 'bundler/gem_tasks'
|
data/wayback_archiver.gemspec
DELETED
@@ -1,34 +0,0 @@
|
|
1
|
-
# coding: utf-8
|
2
|
-
lib = File.expand_path('../lib', __FILE__)
|
3
|
-
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
-
require 'wayback_archiver/version'
|
5
|
-
|
6
|
-
Gem::Specification.new do |spec|
|
7
|
-
spec.name = 'wayback_archiver'
|
8
|
-
spec.version = WaybackArchiver::VERSION
|
9
|
-
|
10
|
-
spec.required_rubygems_version = Gem::Requirement.new('>= 0') if spec.respond_to? :required_rubygems_version=
|
11
|
-
spec.authors = ['Jacob Burenstam']
|
12
|
-
spec.email = ['burenstam@gmail.com']
|
13
|
-
spec.summary = %q{Send URLs to Wayback Machine}
|
14
|
-
spec.description = %q{Send URLs to Wayback Machine. From: sitemap, file or single URL.}
|
15
|
-
spec.homepage = 'https://github.com/buren/wayback_archiver'
|
16
|
-
spec.license = 'MIT'
|
17
|
-
|
18
|
-
spec.files = `git ls-files`.split($/)
|
19
|
-
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
20
|
-
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
21
|
-
spec.require_paths = ['lib']
|
22
|
-
|
23
|
-
if spec.respond_to? :specification_version then
|
24
|
-
spec.specification_version = 3
|
25
|
-
|
26
|
-
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
27
|
-
else
|
28
|
-
end
|
29
|
-
else
|
30
|
-
end
|
31
|
-
|
32
|
-
spec.add_development_dependency 'bundler', '~> 1.3'
|
33
|
-
spec.add_development_dependency 'rake'
|
34
|
-
end
|