simple_sitemap 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/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +63 -0
- data/Rakefile +2 -0
- data/lib/simple_sitemap.rb +41 -0
- data/lib/simple_sitemap/generators/base.rb +39 -0
- data/lib/simple_sitemap/generators/index.rb +52 -0
- data/lib/simple_sitemap/generators/sitemap.rb +134 -0
- data/lib/simple_sitemap/version.rb +3 -0
- data/lib/simple_sitemap/writers/gzip_writer.rb +18 -0
- data/lib/simple_sitemap/writers/plain_writer.rb +17 -0
- data/simple_sitemap.gemspec +23 -0
- metadata +69 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 ryanlower
|
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 +1,63 @@
|
|
1
|
+
# SimpleSitemap
|
2
|
+
|
3
|
+
A simple sitemap generator
|
4
|
+
|
5
|
+
## Basic Usage
|
6
|
+
|
7
|
+
### Configure
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
SimpleSitemap.configure do |config|
|
11
|
+
config.local_path = 'tmp/'
|
12
|
+
config.default_path = 'http://yoursite.com'
|
13
|
+
config.sitemap_location = 'http://yoursite.com/sitemap'
|
14
|
+
end
|
15
|
+
```
|
16
|
+
|
17
|
+
### Build your sitemap
|
18
|
+
|
19
|
+
```ruby
|
20
|
+
SimpleSitemap.build do
|
21
|
+
add_path 'home'
|
22
|
+
add_path 'about'
|
23
|
+
sitemap 'ryan' do
|
24
|
+
6.times do |i|
|
25
|
+
add_url i, priority: 0.5
|
26
|
+
end
|
27
|
+
end
|
28
|
+
sitemap 'lower' do
|
29
|
+
5.times do |i|
|
30
|
+
add_url i
|
31
|
+
end
|
32
|
+
end
|
33
|
+
sitemap 'ryan' do
|
34
|
+
6.times do |i|
|
35
|
+
add_path i, priority: 1.0
|
36
|
+
end
|
37
|
+
end
|
38
|
+
add_url 'http://signup.yoursite.com'
|
39
|
+
add_path 'login'
|
40
|
+
end
|
41
|
+
```
|
42
|
+
|
43
|
+
## Hooks
|
44
|
+
|
45
|
+
SimpleSitemap gives you a after_write hook for easy access to sitemap files as they are written.
|
46
|
+
|
47
|
+
For example, to upload sitmaps to S3
|
48
|
+
|
49
|
+
```ruby
|
50
|
+
SimpleSitemap.after_write do |filename|
|
51
|
+
s3 = Fog::Storage.new({
|
52
|
+
provider: 'AWS',
|
53
|
+
aws_access_key_id: 'YOUR_AWS_KEY',
|
54
|
+
aws_secret_access_key: 'YOUR_AWS_SECRET'
|
55
|
+
})
|
56
|
+
bucket = s3.directories.first
|
57
|
+
bucket.files.create(
|
58
|
+
:key => File.basename(filename),
|
59
|
+
:body => open(filename),
|
60
|
+
:public => true
|
61
|
+
)
|
62
|
+
end
|
63
|
+
```
|
data/Rakefile
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
|
2
|
+
require 'simple_sitemap/generators/base'
|
3
|
+
require 'simple_sitemap/generators/index'
|
4
|
+
require 'simple_sitemap/generators/sitemap'
|
5
|
+
require 'simple_sitemap/writers/gzip_writer'
|
6
|
+
require 'simple_sitemap/writers/plain_writer'
|
7
|
+
|
8
|
+
require 'simple_sitemap/version'
|
9
|
+
|
10
|
+
|
11
|
+
module SimpleSitemap
|
12
|
+
|
13
|
+
MAX_LINKS_PER_FILE = 50000
|
14
|
+
MAX_FILE_SIZE = 10*1024*1024 # 10 megabytes
|
15
|
+
|
16
|
+
class << self
|
17
|
+
|
18
|
+
attr_accessor :config, :hooks
|
19
|
+
|
20
|
+
def configure(&block)
|
21
|
+
@config = OpenStruct.new
|
22
|
+
@config.gzip = true
|
23
|
+
@config.verbose = false
|
24
|
+
yield @config
|
25
|
+
end
|
26
|
+
|
27
|
+
def build(opts={}, &block)
|
28
|
+
start_time = Time.now
|
29
|
+
generator = Generators::Sitemap.new @config, @hooks
|
30
|
+
generator.instance_eval &block
|
31
|
+
generator.write!
|
32
|
+
puts "Time taken: #{Time.now - start_time}" if @config.verbose
|
33
|
+
end
|
34
|
+
|
35
|
+
def after_write(&block)
|
36
|
+
@hooks ||= {}
|
37
|
+
@hooks[:after_write] = block
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
end
|
@@ -0,0 +1,39 @@
|
|
1
|
+
|
2
|
+
require 'nokogiri'
|
3
|
+
|
4
|
+
module SimpleSitemap
|
5
|
+
|
6
|
+
module Generators
|
7
|
+
|
8
|
+
class Base
|
9
|
+
|
10
|
+
attr_writer :config, :hooks
|
11
|
+
|
12
|
+
def initialize(config, hooks)
|
13
|
+
@config = config
|
14
|
+
@hooks = hooks
|
15
|
+
end
|
16
|
+
|
17
|
+
private
|
18
|
+
|
19
|
+
def write_file(filename, xml)
|
20
|
+
path = File.expand_path filename, @config.local_path
|
21
|
+
if @config.gzip
|
22
|
+
Writers::GzipWriter.new.write path, xml
|
23
|
+
else
|
24
|
+
Writers::PlainWriter.new.write path, xml
|
25
|
+
end
|
26
|
+
call_hooks path if @hooks
|
27
|
+
end
|
28
|
+
|
29
|
+
def call_hooks(path)
|
30
|
+
if @hooks[:after_write]
|
31
|
+
@hooks[:after_write].call path
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
end
|
36
|
+
|
37
|
+
end
|
38
|
+
|
39
|
+
end
|
@@ -0,0 +1,52 @@
|
|
1
|
+
|
2
|
+
require 'nokogiri'
|
3
|
+
|
4
|
+
module SimpleSitemap
|
5
|
+
|
6
|
+
module Generators
|
7
|
+
|
8
|
+
class Index < Base
|
9
|
+
|
10
|
+
attr_accessor :sitemaps
|
11
|
+
|
12
|
+
def initialize(config, hooks)
|
13
|
+
super
|
14
|
+
@sitemaps = []
|
15
|
+
end
|
16
|
+
|
17
|
+
def add_sitemap(name)
|
18
|
+
url = if @config.sitemap_location[-1,1] == '/'
|
19
|
+
"#{@config.sitemap_location}#{name}"
|
20
|
+
else
|
21
|
+
"#{@config.sitemap_location}/#{name}"
|
22
|
+
end
|
23
|
+
@sitemaps << url
|
24
|
+
end
|
25
|
+
|
26
|
+
def write!
|
27
|
+
xml = to_xml
|
28
|
+
index_filename = 'index.xml'
|
29
|
+
if @config.gzip
|
30
|
+
index_filename << '.gz'
|
31
|
+
end
|
32
|
+
write_file index_filename, xml
|
33
|
+
end
|
34
|
+
|
35
|
+
def to_xml
|
36
|
+
builder = Nokogiri::XML::Builder.new(encoding: 'UTF-8') do |xml|
|
37
|
+
xml.sitemapindex(xmlns: 'http://www.sitemaps.org/schemas/sitemap/0.9') do
|
38
|
+
@sitemaps.each do |sitemap_url|
|
39
|
+
xml.sitemap do
|
40
|
+
xml.loc sitemap_url
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
builder.to_xml
|
46
|
+
end
|
47
|
+
|
48
|
+
end
|
49
|
+
|
50
|
+
end
|
51
|
+
|
52
|
+
end
|
@@ -0,0 +1,134 @@
|
|
1
|
+
|
2
|
+
require 'nokogiri'
|
3
|
+
|
4
|
+
module SimpleSitemap
|
5
|
+
|
6
|
+
module Generators
|
7
|
+
|
8
|
+
class Sitemap < Base
|
9
|
+
|
10
|
+
attr_accessor :sitemap_name, :sitemap_data
|
11
|
+
|
12
|
+
def initialize(config, hooks)
|
13
|
+
super
|
14
|
+
@sitemap_data = {}
|
15
|
+
enter_sitemap nil
|
16
|
+
end
|
17
|
+
|
18
|
+
def add_url(url, opts={})
|
19
|
+
link = { url: url }
|
20
|
+
link.merge! opts
|
21
|
+
@sitemap_data[@sitemap_name][:links] << link
|
22
|
+
@sitemap_data[@sitemap_name][:size] += 1
|
23
|
+
## TODO, add correct bytesize (this is an overestimate)
|
24
|
+
@sitemap_data[@sitemap_name][:bytesize] += 200
|
25
|
+
if @sitemap_data[@sitemap_name][:size] >= SimpleSitemap::MAX_LINKS_PER_FILE
|
26
|
+
write @sitemap_name
|
27
|
+
end
|
28
|
+
if @sitemap_data[@sitemap_name][:bytesize] >= SimpleSitemap::MAX_FILE_SIZE
|
29
|
+
write @sitemap_name
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
def add_path(path, opts={})
|
34
|
+
if @config.default_path
|
35
|
+
if @config.default_path[-1,1] != '/' && path[0] != '/'
|
36
|
+
path = "/#{path}"
|
37
|
+
end
|
38
|
+
add_url "#{@config.default_path}#{path}", opts
|
39
|
+
else
|
40
|
+
raise "Can't add a path without configuring default_path"
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
def sitemap(name, &block)
|
45
|
+
enter_sitemap name
|
46
|
+
yield
|
47
|
+
exit_sitemap
|
48
|
+
end
|
49
|
+
|
50
|
+
def write!
|
51
|
+
@sitemap_data.keys.each do |name|
|
52
|
+
if @sitemap_data[name][:links].size > 0
|
53
|
+
write name
|
54
|
+
end
|
55
|
+
end
|
56
|
+
write_index
|
57
|
+
end
|
58
|
+
|
59
|
+
private
|
60
|
+
|
61
|
+
def enter_sitemap(name)
|
62
|
+
unless @sitemap_data.has_key? name
|
63
|
+
@sitemap_data[name] = { index: 1 }
|
64
|
+
reset_sitemap_data name
|
65
|
+
end
|
66
|
+
@sitemap_name = name
|
67
|
+
end
|
68
|
+
|
69
|
+
def exit_sitemap
|
70
|
+
@sitemap_name = nil
|
71
|
+
end
|
72
|
+
|
73
|
+
def write_index
|
74
|
+
index = Generators::Index.new @config, @hooks
|
75
|
+
@sitemap_data.keys.each do |name|
|
76
|
+
(1...sitemap_data[name][:index]).each do |i|
|
77
|
+
index.add_sitemap sitemap_filename(name, i)
|
78
|
+
end
|
79
|
+
end
|
80
|
+
index.write!
|
81
|
+
end
|
82
|
+
|
83
|
+
def write(name)
|
84
|
+
puts "Writing sitemap #{name}#{@sitemap_data[name][:index]}\t [#{@sitemap_data[name][:size]} urls]" if @config.verbose
|
85
|
+
xml = to_xml name
|
86
|
+
write_file sitemap_filename(name), xml
|
87
|
+
reset_sitemap_data name
|
88
|
+
@sitemap_data[name][:index] += 1
|
89
|
+
enter_sitemap name
|
90
|
+
end
|
91
|
+
|
92
|
+
def reset_sitemap_data(name)
|
93
|
+
default_sitemap_data = {
|
94
|
+
links: [],
|
95
|
+
size: 0,
|
96
|
+
bytesize: 110
|
97
|
+
}
|
98
|
+
@sitemap_data[name].merge! default_sitemap_data
|
99
|
+
end
|
100
|
+
|
101
|
+
def sitemap_filename(name, index=nil)
|
102
|
+
index ||= @sitemap_data[name][:index]
|
103
|
+
filename = if name
|
104
|
+
"#{name}_#{index}.xml"
|
105
|
+
else
|
106
|
+
"sitemap_#{index}.xml"
|
107
|
+
end
|
108
|
+
if @config.gzip
|
109
|
+
filename << '.gz'
|
110
|
+
end
|
111
|
+
filename
|
112
|
+
end
|
113
|
+
|
114
|
+
def to_xml(name)
|
115
|
+
builder = Nokogiri::XML::Builder.new(encoding: 'UTF-8') do |xml|
|
116
|
+
xml.urlset(xmlns: 'http://www.sitemaps.org/schemas/sitemap/0.9') do
|
117
|
+
@sitemap_data[name][:links].each do |url|
|
118
|
+
xml.url do
|
119
|
+
xml.loc url[:url]
|
120
|
+
# xml.lastmod url[:lastmod].utc if url[:lastmod]
|
121
|
+
xml.changefreq url[:changefreq] if url[:changefreq]
|
122
|
+
xml.priority url[:priority] if url[:priority]
|
123
|
+
end
|
124
|
+
end
|
125
|
+
end
|
126
|
+
end
|
127
|
+
builder.to_xml
|
128
|
+
end
|
129
|
+
|
130
|
+
end
|
131
|
+
|
132
|
+
end
|
133
|
+
|
134
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path('../lib', __FILE__)
|
3
|
+
require 'simple_sitemap/version'
|
4
|
+
|
5
|
+
Gem::Specification.new do |gem|
|
6
|
+
|
7
|
+
gem.name = 'simple_sitemap'
|
8
|
+
gem.version = SimpleSitemap::VERSION
|
9
|
+
|
10
|
+
gem.add_dependency 'nokogiri', '~> 1.5.0'
|
11
|
+
|
12
|
+
gem.authors = ['ryanlower']
|
13
|
+
gem.email = ['rpjlower@gmail.com']
|
14
|
+
gem.description = 'A simple sitemap generator'
|
15
|
+
gem.summary = 'Simple sitemap generator'
|
16
|
+
gem.homepage = 'https://github.com/academia-edu/simple-sitemap'
|
17
|
+
|
18
|
+
gem.files = `git ls-files`.split($\)
|
19
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
20
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
21
|
+
gem.require_paths = ['lib']
|
22
|
+
|
23
|
+
end
|
metadata
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: simple_sitemap
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- ryanlower
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-03-22 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
16
|
+
requirement: &70222280337640 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 1.5.0
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70222280337640
|
25
|
+
description: A simple sitemap generator
|
26
|
+
email:
|
27
|
+
- rpjlower@gmail.com
|
28
|
+
executables: []
|
29
|
+
extensions: []
|
30
|
+
extra_rdoc_files: []
|
31
|
+
files:
|
32
|
+
- .gitignore
|
33
|
+
- Gemfile
|
34
|
+
- LICENSE
|
35
|
+
- README.md
|
36
|
+
- Rakefile
|
37
|
+
- lib/simple_sitemap.rb
|
38
|
+
- lib/simple_sitemap/generators/base.rb
|
39
|
+
- lib/simple_sitemap/generators/index.rb
|
40
|
+
- lib/simple_sitemap/generators/sitemap.rb
|
41
|
+
- lib/simple_sitemap/version.rb
|
42
|
+
- lib/simple_sitemap/writers/gzip_writer.rb
|
43
|
+
- lib/simple_sitemap/writers/plain_writer.rb
|
44
|
+
- simple_sitemap.gemspec
|
45
|
+
homepage: https://github.com/academia-edu/simple-sitemap
|
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: 1.8.11
|
66
|
+
signing_key:
|
67
|
+
specification_version: 3
|
68
|
+
summary: Simple sitemap generator
|
69
|
+
test_files: []
|