sitemap-parser 0.0.3 → 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.
- checksums.yaml +4 -4
- data/lib/sitemap-parser.rb +22 -2
- metadata +16 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 5cf7f24d9633d44bd80514db606dafa869de8e8a
|
4
|
+
data.tar.gz: 5dc60886285798683a43f21e81f44f7afdbafc19
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 07241173a5e14eb552827d48b75a3caa27c5b40f1e3eaf39db588a7009d1c8f65b7c302072eef7d9e6a9ce6bce0b7ad94ec36130039a42640d159e8ddcea140f
|
7
|
+
data.tar.gz: c3a5d2fa4b2e182eb0b335cb04ba65839d213690fad73f12d3055b85e2ad10da5133aa88fa6baab304576dd0d04fd870de793c1b73c849f08cfaaf691f90b238
|
data/lib/sitemap-parser.rb
CHANGED
@@ -1,5 +1,5 @@
|
|
1
1
|
require 'nokogiri'
|
2
|
-
require '
|
2
|
+
require 'typhoeus'
|
3
3
|
|
4
4
|
class SitemapParser
|
5
5
|
|
@@ -7,15 +7,35 @@ class SitemapParser
|
|
7
7
|
@url = url
|
8
8
|
end
|
9
9
|
|
10
|
+
def raw_sitemap
|
11
|
+
@raw_sitemap ||= begin
|
12
|
+
request = Typhoeus::Request.new(@url, followlocation: true)
|
13
|
+
request.on_complete do |response|
|
14
|
+
if response.success?
|
15
|
+
return response.body
|
16
|
+
else
|
17
|
+
return nil
|
18
|
+
end
|
19
|
+
end
|
20
|
+
request.run
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
10
24
|
def sitemap
|
11
|
-
@sitemap ||= Nokogiri::XML(
|
25
|
+
@sitemap ||= Nokogiri::XML(raw_sitemap)
|
26
|
+
rescue
|
27
|
+
nil
|
12
28
|
end
|
13
29
|
|
14
30
|
def urls
|
15
31
|
sitemap.at("urlset").search("url")
|
32
|
+
rescue
|
33
|
+
nil
|
16
34
|
end
|
17
35
|
|
18
36
|
def to_a
|
19
37
|
urls.map { |url| url.at("loc").content }
|
38
|
+
rescue
|
39
|
+
[]
|
20
40
|
end
|
21
41
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: sitemap-parser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0
|
4
|
+
version: 0.1.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ben Balter
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-03-
|
11
|
+
date: 2014-03-04 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -24,6 +24,20 @@ dependencies:
|
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: 1.5.6
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: typhoeus
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.6.7
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 0.6.7
|
27
41
|
description: Ruby Gem to parse sitemaps.org compliant sitemaps.
|
28
42
|
email: ben.balter@github.com
|
29
43
|
executables: []
|