sitemap_check 0.1.0 → 0.1.1
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 +4 -4
- data/README.md +9 -0
- data/lib/sitemap_check/logger.rb +16 -0
- data/lib/sitemap_check/page.rb +1 -1
- data/lib/sitemap_check/sitemap.rb +7 -6
- data/lib/sitemap_check/version.rb +1 -1
- data/lib/sitemap_check.rb +25 -5
- metadata +3 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 84dc68b7fb5e1fec3814c8f6e82f94d8cf43b619
|
4
|
+
data.tar.gz: 37cefa64e976770366fafe82b89d5d34dc97adce
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: a89b4e56d7df0b4cafef3e5844c64afc5510d7dfeccf6db602bcfecd591d1a95acc15370fa10468de214d5965e0bc47e9d066fdd306a6f1827e931b089360bf2
|
7
|
+
data.tar.gz: 0cc65ef4219b022f7675b53e10a3a242ac3e723d75ea89b0ad38b4c5650011f70c06828286b3fe123d37929141f6a246946808a2fb4f8dcc02861a63a9c09829
|
data/README.md
CHANGED
@@ -9,3 +9,12 @@
|
|
9
9
|
```bash
|
10
10
|
$ CHECK_URL=http://reevoo.com/sitemap_index.xml sitemap_check
|
11
11
|
```
|
12
|
+
|
13
|
+
## Config
|
14
|
+
|
15
|
+
Config can be set with enviroment variables
|
16
|
+
|
17
|
+
variable | default | description
|
18
|
+
-------------|---------|-------------
|
19
|
+
`CHECK_URL` | `nil` | The url of the sitemap or sitemap index to check
|
20
|
+
`CONCURRENCY`| `10` | The number of concurent threads to use when checking the sitemap
|
@@ -0,0 +1,16 @@
|
|
1
|
+
class SitemapCheck
|
2
|
+
class Logger
|
3
|
+
def initialize(stream = $stdout)
|
4
|
+
self.stream = stream
|
5
|
+
self.mutex = Mutex.new
|
6
|
+
end
|
7
|
+
|
8
|
+
def log(message)
|
9
|
+
mutex.synchronize { stream.puts message }
|
10
|
+
end
|
11
|
+
|
12
|
+
protected
|
13
|
+
|
14
|
+
attr_accessor :stream, :mutex
|
15
|
+
end
|
16
|
+
end
|
data/lib/sitemap_check/page.rb
CHANGED
@@ -13,7 +13,7 @@ class SitemapCheck
|
|
13
13
|
|
14
14
|
def exists?
|
15
15
|
@_exists ||= http.head(url, follow_redirect: true).ok?
|
16
|
-
rescue SocketError, HTTPClient::ConnectTimeoutError
|
16
|
+
rescue SocketError, HTTPClient::ConnectTimeoutError, Errno::ETIMEDOUT
|
17
17
|
self.tries += 1
|
18
18
|
if tries < 5
|
19
19
|
sleep holdoff
|
@@ -1,11 +1,13 @@
|
|
1
1
|
require 'httpclient'
|
2
2
|
require 'sitemap_check/page'
|
3
|
+
require 'sitemap_check/logger'
|
3
4
|
require 'nokogiri'
|
4
5
|
require 'colorize'
|
5
6
|
|
6
7
|
class SitemapCheck
|
7
8
|
class Sitemap
|
8
|
-
def initialize(url, http = HTTPClient.new)
|
9
|
+
def initialize(url, http = HTTPClient.new, logger = Logger.new)
|
10
|
+
self.logger = logger
|
9
11
|
self.url = url
|
10
12
|
self.checked = 0
|
11
13
|
self.http = http
|
@@ -32,33 +34,32 @@ class SitemapCheck
|
|
32
34
|
|
33
35
|
protected
|
34
36
|
|
35
|
-
attr_accessor :http, :doc
|
37
|
+
attr_accessor :http, :doc, :logger
|
36
38
|
attr_writer :url, :checked
|
37
39
|
|
38
40
|
private
|
39
41
|
|
40
42
|
def concurency
|
41
|
-
ENV.fetch('
|
43
|
+
ENV.fetch('CONCURRENCY', '10').to_i
|
42
44
|
end
|
43
45
|
|
44
46
|
def find_missing_pages # rubocop:disable Metrics/AbcSize
|
45
47
|
q = Queue.new
|
46
|
-
mutex = Mutex.new
|
47
48
|
pages.each { |page| q.push page }
|
48
49
|
concurency.times.map do
|
49
50
|
Thread.new do
|
50
51
|
begin
|
51
52
|
while (page = q.pop(true))
|
52
53
|
unless page.exists?
|
53
|
-
|
54
|
+
logger.log " missing: #{page.url}".red
|
54
55
|
page
|
55
56
|
end
|
56
|
-
mutex.synchronize { self.checked += 1 }
|
57
57
|
end
|
58
58
|
rescue ThreadError # rubocop:disable Lint/HandleExceptions
|
59
59
|
end
|
60
60
|
end
|
61
61
|
end.each(&:join)
|
62
|
+
self.checked = pages.count
|
62
63
|
pages.reject(&:exists?)
|
63
64
|
end
|
64
65
|
|
data/lib/sitemap_check.rb
CHANGED
@@ -3,12 +3,14 @@ require 'sitemap_check/sitemap'
|
|
3
3
|
|
4
4
|
class SitemapCheck
|
5
5
|
|
6
|
+
|
6
7
|
def self.check
|
7
8
|
$stdout.sync = true
|
8
9
|
new.check
|
9
10
|
end
|
10
11
|
|
11
12
|
def initialize(http = HTTPClient.new)
|
13
|
+
self.start_time = Time.now
|
12
14
|
self.exit_code = 0
|
13
15
|
puts "Expanding Sitemaps from #{ENV['CHECK_URL']}"
|
14
16
|
self.sitemaps = Sitemap.new(ENV['CHECK_URL'], http).sitemaps
|
@@ -17,18 +19,36 @@ class SitemapCheck
|
|
17
19
|
def check
|
18
20
|
check_indexes
|
19
21
|
check_pages
|
22
|
+
stats
|
20
23
|
exit exit_code
|
21
24
|
end
|
22
25
|
|
23
26
|
protected
|
24
27
|
|
25
|
-
attr_accessor :sitemaps, :exit_code
|
28
|
+
attr_accessor :sitemaps, :exit_code, :start_time, :logger
|
26
29
|
|
27
30
|
private
|
28
31
|
|
32
|
+
def stats
|
33
|
+
puts "checked #{sitemaps.count} sitemaps and #{checked_pages} in #{time_taken} seconds"
|
34
|
+
puts "thats #{pages_per_second} pages per second"
|
35
|
+
end
|
36
|
+
|
37
|
+
def pages_per_second
|
38
|
+
checked_pages / time_taken
|
39
|
+
end
|
40
|
+
|
41
|
+
def time_taken
|
42
|
+
Time.now - start_time
|
43
|
+
end
|
44
|
+
|
45
|
+
def checked_pages
|
46
|
+
sitemaps.map(&:checked).reduce(&:+)
|
47
|
+
end
|
48
|
+
|
29
49
|
def check_indexes
|
30
50
|
sitemaps.reject(&:exists?).each do |sitemap|
|
31
|
-
puts "#{sitemap.url} does not exist".red.bold
|
51
|
+
puts " #{sitemap.url} does not exist".red.bold
|
32
52
|
self.exit_code = 1
|
33
53
|
end
|
34
54
|
puts ''
|
@@ -58,14 +78,14 @@ class SitemapCheck
|
|
58
78
|
|
59
79
|
def missing_pages(sitemap)
|
60
80
|
self.exit_code = 1
|
61
|
-
puts "checked #{sitemap.checked} pages and #{sitemap.missing_pages.count} were missing".red.bold
|
81
|
+
puts " checked #{sitemap.checked} pages and #{sitemap.missing_pages.count} were missing".red.bold
|
62
82
|
end
|
63
83
|
|
64
84
|
def a_ok(sitemap)
|
65
|
-
puts "checked #{sitemap.checked} pages and everything was ok".green.bold
|
85
|
+
puts " checked #{sitemap.checked} pages and everything was ok".green.bold
|
66
86
|
end
|
67
87
|
|
68
88
|
def nothing_doing
|
69
|
-
puts 'this sitemap did not contain any pages'.green
|
89
|
+
puts ' this sitemap did not contain any pages'.green
|
70
90
|
end
|
71
91
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: sitemap_check
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ed Robinson
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-04-
|
11
|
+
date: 2015-04-23 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -155,6 +155,7 @@ files:
|
|
155
155
|
- Rakefile
|
156
156
|
- bin/sitemap_check
|
157
157
|
- lib/sitemap_check.rb
|
158
|
+
- lib/sitemap_check/logger.rb
|
158
159
|
- lib/sitemap_check/page.rb
|
159
160
|
- lib/sitemap_check/sitemap.rb
|
160
161
|
- lib/sitemap_check/version.rb
|