staticfy 0.0.1
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/.gitignore +5 -0
- data/Gemfile +4 -0
- data/Rakefile +44 -0
- data/bin/staticfy +27 -0
- data/lib/staticfy.rb +33 -0
- data/lib/staticfy/anemone_hacks.rb +48 -0
- data/lib/staticfy/crawler.rb +44 -0
- data/lib/staticfy/handlers.rb +63 -0
- data/lib/staticfy/handlers/base.rb +50 -0
- data/lib/staticfy/handlers/css.rb +58 -0
- data/lib/staticfy/handlers/html.rb +89 -0
- data/lib/staticfy/handlers/raw.rb +26 -0
- data/lib/staticfy/version.rb +23 -0
- data/staticfy.gemspec +25 -0
- data/test/staticfy/handlers_test.rb +65 -0
- data/test/test_helper.rb +23 -0
- metadata +92 -0
data/Gemfile
ADDED
data/Rakefile
ADDED
@@ -0,0 +1,44 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
require 'bundler'
|
22
|
+
Bundler::GemHelper.install_tasks
|
23
|
+
|
24
|
+
$: << File.expand_path("../lib", __FILE__)
|
25
|
+
|
26
|
+
task :default => [:test]
|
27
|
+
|
28
|
+
desc "Run tests"
|
29
|
+
task :test do
|
30
|
+
$: << File.expand_path("../test", __FILE__)
|
31
|
+
|
32
|
+
Dir["./test/**/*_test.rb"].each do |test|
|
33
|
+
require test
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
desc "Test run"
|
38
|
+
task :runtest do
|
39
|
+
require 'rubygems'
|
40
|
+
require 'anemone'
|
41
|
+
require 'staticfy'
|
42
|
+
|
43
|
+
Staticfy.crawl("http://www.disqueagua.com/", :output => File.expand_path("../output", __FILE__))
|
44
|
+
end
|
data/bin/staticfy
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# Copyright (c) 2011 Wilker Lúcio
|
3
|
+
#
|
4
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
5
|
+
# of this software and associated documentation files (the "Software"), to deal
|
6
|
+
# in the Software without restriction, including without limitation the rights
|
7
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
8
|
+
# copies of the Software, and to permit persons to whom the Software is
|
9
|
+
# furnished to do so, subject to the following conditions:
|
10
|
+
#
|
11
|
+
# The above copyright notice and this permission notice shall be included in
|
12
|
+
# all copies or substantial portions of the Software.
|
13
|
+
#
|
14
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
15
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
16
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
17
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
18
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
19
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
20
|
+
# THE SOFTWARE.
|
21
|
+
|
22
|
+
require 'rubygems'
|
23
|
+
require 'staticfy'
|
24
|
+
|
25
|
+
url = ARGV[0]
|
26
|
+
|
27
|
+
Staticfy.crawl(url, :output => "output")
|
data/lib/staticfy.rb
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
require 'anemone'
|
22
|
+
require 'staticfy/anemone_hacks'
|
23
|
+
|
24
|
+
module Staticfy
|
25
|
+
autoload :Crawler, "staticfy/crawler"
|
26
|
+
autoload :Handlers, "staticfy/handlers"
|
27
|
+
|
28
|
+
def self.crawl(url, options = {}, &block)
|
29
|
+
crawler = Crawler.new(url, options)
|
30
|
+
block.call(crawler) if block
|
31
|
+
crawler.crawl
|
32
|
+
end
|
33
|
+
end
|
@@ -0,0 +1,48 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
class Anemone::Page
|
22
|
+
alias_method :old_initialize, :initialize
|
23
|
+
|
24
|
+
def initialize(url, params = {})
|
25
|
+
old_initialize(url, params)
|
26
|
+
|
27
|
+
@parser = factory_parser
|
28
|
+
end
|
29
|
+
|
30
|
+
def links
|
31
|
+
@links ||= @parser.fetch_links
|
32
|
+
end
|
33
|
+
|
34
|
+
def local_body
|
35
|
+
@parser.local_body
|
36
|
+
end
|
37
|
+
|
38
|
+
def local_uri
|
39
|
+
Staticfy::Handlers.local_uri(url)
|
40
|
+
end
|
41
|
+
|
42
|
+
private
|
43
|
+
|
44
|
+
def factory_parser
|
45
|
+
extension = File.extname(url.path)
|
46
|
+
Staticfy::Handlers.factory(extension).new(self)
|
47
|
+
end
|
48
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
module Staticfy
|
22
|
+
class Crawler
|
23
|
+
attr_accessor :url
|
24
|
+
|
25
|
+
def initialize(url, options = {})
|
26
|
+
@url = url
|
27
|
+
@options = options
|
28
|
+
end
|
29
|
+
|
30
|
+
def crawl
|
31
|
+
Anemone.crawl(url) do |anemone|
|
32
|
+
anemone.on_every_page do |page|
|
33
|
+
local_path = File.join(@options[:output], page.local_uri)
|
34
|
+
|
35
|
+
File.open(local_path, "wb") do |file|
|
36
|
+
file << page.local_body
|
37
|
+
end
|
38
|
+
|
39
|
+
puts "Saved #{local_path}"
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
module Staticfy
|
22
|
+
module Handlers
|
23
|
+
autoload :Base, "staticfy/handlers/base"
|
24
|
+
autoload :HTML, "staticfy/handlers/html"
|
25
|
+
autoload :CSS, "staticfy/handlers/css"
|
26
|
+
autoload :Raw, "staticfy/handlers/raw"
|
27
|
+
|
28
|
+
class << self
|
29
|
+
KNOW_EXTENSIONS = [".htm", ".js", ".css", ".gif", ".jpg", ".jpeg", ".png", ".swf"]
|
30
|
+
|
31
|
+
def factory(ext)
|
32
|
+
ext_table = {
|
33
|
+
".css" => CSS
|
34
|
+
}
|
35
|
+
|
36
|
+
unless klass = ext_table[ext.to_s.downcase]
|
37
|
+
klass = HTML
|
38
|
+
end
|
39
|
+
|
40
|
+
klass
|
41
|
+
end
|
42
|
+
|
43
|
+
def local_uri(uri)
|
44
|
+
invalid_chars = /[*?\\\/=&]/
|
45
|
+
|
46
|
+
current_ext = File.extname(uri.path)
|
47
|
+
ext = KNOW_EXTENSIONS.include?(current_ext) ? current_ext : ".html"
|
48
|
+
|
49
|
+
local = uri.path[1..-1]
|
50
|
+
local = "index" unless local.length > 0
|
51
|
+
|
52
|
+
if uri.query
|
53
|
+
local += "?" + uri.query.to_s
|
54
|
+
local += ext
|
55
|
+
else
|
56
|
+
local += ext unless current_ext == ext
|
57
|
+
end
|
58
|
+
|
59
|
+
local.gsub(invalid_chars, "_")
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
@@ -0,0 +1,50 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
module Staticfy
|
22
|
+
module Handlers
|
23
|
+
class Base
|
24
|
+
def initialize(page)
|
25
|
+
@page = page
|
26
|
+
end
|
27
|
+
|
28
|
+
def local_uri
|
29
|
+
Handlers.local_uri(url)
|
30
|
+
end
|
31
|
+
|
32
|
+
def fetch_links
|
33
|
+
[]
|
34
|
+
end
|
35
|
+
|
36
|
+
def local_body
|
37
|
+
body
|
38
|
+
end
|
39
|
+
|
40
|
+
# redirect calls to page, if it responds to
|
41
|
+
def method_missing(name, *args)
|
42
|
+
if @page.respond_to?(name)
|
43
|
+
@page.send(name, *args)
|
44
|
+
else
|
45
|
+
super
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
@@ -0,0 +1,58 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
module Staticfy
|
22
|
+
module Handlers
|
23
|
+
class CSS < Base
|
24
|
+
URL_PATTERN = /url\s*\(['"]?(.+?)['"]?\)/
|
25
|
+
|
26
|
+
def fetch_links
|
27
|
+
links = []
|
28
|
+
|
29
|
+
body.scan(URL_PATTERN) do |url|
|
30
|
+
url = url[0]
|
31
|
+
next if url.empty?
|
32
|
+
abs = to_absolute(URI(url))
|
33
|
+
|
34
|
+
if in_domain?(abs)
|
35
|
+
links << abs
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
links
|
40
|
+
end
|
41
|
+
|
42
|
+
def local_body
|
43
|
+
body.gsub(URL_PATTERN) do |url|
|
44
|
+
parts = url.match(URL_PATTERN)
|
45
|
+
next if url.empty?
|
46
|
+
abs = to_absolute(URI(parts[1]))
|
47
|
+
|
48
|
+
if in_domain?(abs)
|
49
|
+
local = Staticfy::Handlers.local_uri(abs).to_s
|
50
|
+
"url('#{local}')"
|
51
|
+
else
|
52
|
+
url
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
@@ -0,0 +1,89 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
module Staticfy
|
22
|
+
module Handlers
|
23
|
+
class HTML < Base
|
24
|
+
def fetch_links
|
25
|
+
return [] unless doc
|
26
|
+
|
27
|
+
links = []
|
28
|
+
|
29
|
+
# follow links
|
30
|
+
attribute_iterator(doc, "a", "href") do |abs, tag|
|
31
|
+
links << abs
|
32
|
+
end
|
33
|
+
|
34
|
+
# fetch scripts
|
35
|
+
attribute_iterator(doc, "script", "src") do |abs, tag|
|
36
|
+
links << abs
|
37
|
+
end
|
38
|
+
|
39
|
+
# follow styles
|
40
|
+
attribute_iterator(doc, "link", "href") do |abs, tag|
|
41
|
+
links << abs
|
42
|
+
end
|
43
|
+
|
44
|
+
# images
|
45
|
+
attribute_iterator(doc, "img", "src") do |abs, tag|
|
46
|
+
links << abs
|
47
|
+
end
|
48
|
+
|
49
|
+
attribute_iterator(doc, "input", "src") do |abs, tag|
|
50
|
+
links << abs
|
51
|
+
end
|
52
|
+
|
53
|
+
links.uniq!
|
54
|
+
links
|
55
|
+
end
|
56
|
+
|
57
|
+
def local_body
|
58
|
+
return body unless doc
|
59
|
+
|
60
|
+
html = doc.dup
|
61
|
+
|
62
|
+
update_links(html, "a", "href")
|
63
|
+
update_links(html, "script", "src")
|
64
|
+
update_links(html, "link", "href")
|
65
|
+
update_links(html, "img", "src")
|
66
|
+
update_links(html, "input", "src")
|
67
|
+
|
68
|
+
html.to_s
|
69
|
+
end
|
70
|
+
|
71
|
+
def attribute_iterator(document, tag, attr)
|
72
|
+
document.search("//#{tag}[@#{attr}]").each do |tag|
|
73
|
+
a = tag[attr]
|
74
|
+
next if a.nil? or a.empty?
|
75
|
+
abs = to_absolute(URI(a)) rescue next
|
76
|
+
if in_domain?(abs)
|
77
|
+
yield abs, tag
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
def update_links(document, tag, attr)
|
83
|
+
attribute_iterator(document, tag, attr) do |abs, tag|
|
84
|
+
tag[attr] = Staticfy::Handlers.local_uri(abs)
|
85
|
+
end
|
86
|
+
end
|
87
|
+
end
|
88
|
+
end
|
89
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
module Staticfy
|
22
|
+
module Handlers
|
23
|
+
class Raw < Base
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
module Staticfy
|
22
|
+
VERSION = "0.0.1"
|
23
|
+
end
|
data/staticfy.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "staticfy/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "staticfy"
|
7
|
+
s.version = Staticfy::VERSION
|
8
|
+
s.platform = Gem::Platform::RUBY
|
9
|
+
s.authors = ["Wilker Lúcio"]
|
10
|
+
s.email = ["wilkerlucio@gmail.com"]
|
11
|
+
s.homepage = "https://www.github.com/wilkerlucio/staticfy"
|
12
|
+
s.summary = %q{Turn online sites into html static ones.}
|
13
|
+
s.description = %q{This gem provides a simple tool to make a full online website into a static one. This can be useful for companies that needs to take system off from a client, but want to keep it online in static manner.}
|
14
|
+
|
15
|
+
s.rubyforge_project = "staticfy"
|
16
|
+
|
17
|
+
s.files = `git ls-files`.split("\n")
|
18
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
19
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
20
|
+
s.require_paths = ["lib"]
|
21
|
+
|
22
|
+
s.add_dependency("anemone", "0.6.1") # currently the Staticfy do some hacks on Anemone, so, specifique version may be required
|
23
|
+
|
24
|
+
s.add_development_dependency("mocha")
|
25
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
require "test_helper"
|
22
|
+
|
23
|
+
class StaticfyHandlersTest < Test::Unit::TestCase
|
24
|
+
def test_factory_handler_html
|
25
|
+
assert_equal Staticfy::Handlers::HTML, Staticfy::Handlers.factory(".html")
|
26
|
+
end
|
27
|
+
|
28
|
+
def test_factory_handler_css
|
29
|
+
assert_equal Staticfy::Handlers::CSS, Staticfy::Handlers.factory(".css")
|
30
|
+
end
|
31
|
+
|
32
|
+
def test_factory_handler_other
|
33
|
+
assert_equal Staticfy::Handlers::Raw, Staticfy::Handlers.factory(".other")
|
34
|
+
end
|
35
|
+
|
36
|
+
def test_local_uri_replace_invalid_chars
|
37
|
+
uri = URI.parse("http://example.com/some/place/here.html")
|
38
|
+
|
39
|
+
assert_equal "some_place_here.html", Staticfy::Handlers.local_uri(uri)
|
40
|
+
end
|
41
|
+
|
42
|
+
def test_local_uri_append_querystring_and_extension
|
43
|
+
uri = URI.parse("http://example.com/some/place/here?with=query&and=data")
|
44
|
+
|
45
|
+
assert_equal "some_place_here_with_query_and_data.html", Staticfy::Handlers.local_uri(uri)
|
46
|
+
end
|
47
|
+
|
48
|
+
def test_local_uri_use_index_if_root
|
49
|
+
uri = URI.parse("http://example.com/")
|
50
|
+
|
51
|
+
assert_equal "index.html", Staticfy::Handlers.local_uri(uri)
|
52
|
+
end
|
53
|
+
|
54
|
+
def test_local_uri_add_html_for_unknow_extensions
|
55
|
+
uri = URI.parse("http://example.com/page.php")
|
56
|
+
|
57
|
+
assert_equal "page.php.html", Staticfy::Handlers.local_uri(uri)
|
58
|
+
end
|
59
|
+
|
60
|
+
def test_local_uri_preserve_know_extension_in_with_query_data
|
61
|
+
uri = URI.parse("http://example.com/some/place/here.png?with=query&and=data")
|
62
|
+
|
63
|
+
assert_equal "some_place_here.png_with_query_and_data.png", Staticfy::Handlers.local_uri(uri)
|
64
|
+
end
|
65
|
+
end
|
data/test/test_helper.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# Copyright (c) 2011 Wilker Lúcio
|
2
|
+
#
|
3
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
# of this software and associated documentation files (the "Software"), to deal
|
5
|
+
# in the Software without restriction, including without limitation the rights
|
6
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
# copies of the Software, and to permit persons to whom the Software is
|
8
|
+
# furnished to do so, subject to the following conditions:
|
9
|
+
#
|
10
|
+
# The above copyright notice and this permission notice shall be included in
|
11
|
+
# all copies or substantial portions of the Software.
|
12
|
+
#
|
13
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
# THE SOFTWARE.
|
20
|
+
|
21
|
+
require 'test/unit'
|
22
|
+
require 'mocha'
|
23
|
+
require 'staticfy'
|
metadata
ADDED
@@ -0,0 +1,92 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: staticfy
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease:
|
5
|
+
version: 0.0.1
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- "Wilker L\xC3\xBAcio"
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
|
13
|
+
date: 2011-06-27 00:00:00 Z
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: anemone
|
17
|
+
prerelease: false
|
18
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
19
|
+
none: false
|
20
|
+
requirements:
|
21
|
+
- - "="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.6.1
|
24
|
+
type: :runtime
|
25
|
+
version_requirements: *id001
|
26
|
+
- !ruby/object:Gem::Dependency
|
27
|
+
name: mocha
|
28
|
+
prerelease: false
|
29
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
30
|
+
none: false
|
31
|
+
requirements:
|
32
|
+
- - ">="
|
33
|
+
- !ruby/object:Gem::Version
|
34
|
+
version: "0"
|
35
|
+
type: :development
|
36
|
+
version_requirements: *id002
|
37
|
+
description: This gem provides a simple tool to make a full online website into a static one. This can be useful for companies that needs to take system off from a client, but want to keep it online in static manner.
|
38
|
+
email:
|
39
|
+
- wilkerlucio@gmail.com
|
40
|
+
executables:
|
41
|
+
- staticfy
|
42
|
+
extensions: []
|
43
|
+
|
44
|
+
extra_rdoc_files: []
|
45
|
+
|
46
|
+
files:
|
47
|
+
- .gitignore
|
48
|
+
- Gemfile
|
49
|
+
- Rakefile
|
50
|
+
- bin/staticfy
|
51
|
+
- lib/staticfy.rb
|
52
|
+
- lib/staticfy/anemone_hacks.rb
|
53
|
+
- lib/staticfy/crawler.rb
|
54
|
+
- lib/staticfy/handlers.rb
|
55
|
+
- lib/staticfy/handlers/base.rb
|
56
|
+
- lib/staticfy/handlers/css.rb
|
57
|
+
- lib/staticfy/handlers/html.rb
|
58
|
+
- lib/staticfy/handlers/raw.rb
|
59
|
+
- lib/staticfy/version.rb
|
60
|
+
- staticfy.gemspec
|
61
|
+
- test/staticfy/handlers_test.rb
|
62
|
+
- test/test_helper.rb
|
63
|
+
homepage: https://www.github.com/wilkerlucio/staticfy
|
64
|
+
licenses: []
|
65
|
+
|
66
|
+
post_install_message:
|
67
|
+
rdoc_options: []
|
68
|
+
|
69
|
+
require_paths:
|
70
|
+
- lib
|
71
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
72
|
+
none: false
|
73
|
+
requirements:
|
74
|
+
- - ">="
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: "0"
|
77
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
78
|
+
none: false
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: "0"
|
83
|
+
requirements: []
|
84
|
+
|
85
|
+
rubyforge_project: staticfy
|
86
|
+
rubygems_version: 1.7.2
|
87
|
+
signing_key:
|
88
|
+
specification_version: 3
|
89
|
+
summary: Turn online sites into html static ones.
|
90
|
+
test_files:
|
91
|
+
- test/staticfy/handlers_test.rb
|
92
|
+
- test/test_helper.rb
|