sitemap_reader 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.
- checksums.yaml +7 -0
- data/lib/sitemap_reader.rb +39 -0
- metadata +86 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 30568b1c862fc5439bf0734f084bcc259ac333fa
|
4
|
+
data.tar.gz: d94a700a7066fb98451c1e9b79b97b14fd958c71
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: e95e71e627293bc2d97645e3f9ac0336cad354ddf61d74c9a9f5e5af8075ebace47b4f050a9f86f53f10fff634d0e7efdea90f0d900ab83a0b99a081ff0ae4ea
|
7
|
+
data.tar.gz: d0fa3bfeefd221c1cbbe29be4d473f71042e55edab16fc73d68a4f6326272444922afade133ef9683a442546556fd92d9872c209acfffef68ac4918e3c891959
|
@@ -0,0 +1,39 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
|
3
|
+
# Parse sitemap
|
4
|
+
#
|
5
|
+
# Example:
|
6
|
+
# >> sm = SitemapReader.new('http://example.com/sitemap.xml').get_urls
|
7
|
+
# => [{:loc=>"http://example.com/page1", :lastmod=>"2013-08-18"},{:loc=>"http://example.com/page2", :lastmod=>nil}]
|
8
|
+
#
|
9
|
+
# ... or read from file like this:
|
10
|
+
# >> sm = SitemapReader.new('./sitemap.xml').get_urls
|
11
|
+
# => [{:loc=>"http://example.com/page1", :lastmod=>"2013-08-18"},{:loc=>"http://example.com/page2", :lastmod=>nil}]
|
12
|
+
class SitemapReader
|
13
|
+
|
14
|
+
# Arguments:
|
15
|
+
# file_or_url: (String)
|
16
|
+
def initialize(file_or_url)
|
17
|
+
@doc = Nokogiri::XML(get_sitemap(file_or_url))
|
18
|
+
@urls= get_urls
|
19
|
+
end
|
20
|
+
|
21
|
+
def get_urls
|
22
|
+
@doc.css('url').map do |u|
|
23
|
+
loc = u.css('loc').first.content
|
24
|
+
lastmod = u.css('lastmod').first.content unless u.css('lastmod').first.nil?
|
25
|
+
{loc: loc, lastmod: lastmod}
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
private
|
30
|
+
|
31
|
+
def get_sitemap(file_or_url)
|
32
|
+
if File.exist?(file_or_url)
|
33
|
+
File.open(file_or_url)
|
34
|
+
else
|
35
|
+
require 'open-uri'
|
36
|
+
open(file_or_url)
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
metadata
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: sitemap_reader
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Michal Pawlowski
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-08-19 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nokogiri
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.3'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.3'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
description:
|
56
|
+
email: misza@misza.co.uk
|
57
|
+
executables: []
|
58
|
+
extensions: []
|
59
|
+
extra_rdoc_files: []
|
60
|
+
files:
|
61
|
+
- lib/sitemap_reader.rb
|
62
|
+
homepage: https://github.com/itsudo/sitemap_reader
|
63
|
+
licenses:
|
64
|
+
- MIT
|
65
|
+
metadata: {}
|
66
|
+
post_install_message:
|
67
|
+
rdoc_options: []
|
68
|
+
require_paths:
|
69
|
+
- lib
|
70
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - '>='
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '0'
|
75
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
76
|
+
requirements:
|
77
|
+
- - '>='
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: '0'
|
80
|
+
requirements: []
|
81
|
+
rubyforge_project:
|
82
|
+
rubygems_version: 2.0.3
|
83
|
+
signing_key:
|
84
|
+
specification_version: 4
|
85
|
+
summary: Ruby library for reading sitemaps
|
86
|
+
test_files: []
|