wp-sessioniser 0.2.1

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 ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: a465c16ccbeda920f06585cdd4c72d757dd8e487
4
+ data.tar.gz: d5127fad61ff5fbbaa7089dd22473786104de6b6
5
+ SHA512:
6
+ metadata.gz: 383efaf6690603b322a023aa77f4652aa2898f15ad22b5d66d7949a648b2b0eef12562de642c1b38b4e780e99aa899819b5f163ded6d70858a2b28306868e757
7
+ data.tar.gz: 1decebd5af6c90656cb871889743e0f2783f9f5b09e748bfc934cc85e2f252c42fb49395647ea306b1e82a65fbfca1ec4df3c19d33c33512f48168050f8ad8f6
@@ -0,0 +1,40 @@
1
+ #!/usr/bin/ruby
2
+
3
+ #################################################################
4
+ # #
5
+ # Copyright 2016, Ryan McCoskrie under the MIT License #
6
+ # #
7
+ #################################################################
8
+
9
+ require 'apache_log_regex'
10
+ require 'wp-sessioniser'
11
+
12
+
13
+
14
+
15
+ begin
16
+ #Check arguments
17
+ if ARGV.length != 1
18
+ $stderr.puts "Usage: httpscanner logfile"
19
+ exit 1
20
+ end
21
+
22
+ file = File.open(ARGV[0], "r")
23
+
24
+ visitors = WPSessioniser.parse(file)
25
+
26
+ visitors.each do |ip, visitor|
27
+ puts "ip: #{ip}:"
28
+ visitor.hits.each do |page, time|
29
+ puts "\tpage: #{page}, time: #{time}"
30
+ end
31
+ end
32
+ rescue SystemCallError => e
33
+ $stderr.puts "Could not open #{ARGV[0]}"
34
+ $stderr.puts e.to_s
35
+ rescue ApacheLogRegex::ParseError => e
36
+ $stderr.puts "Could not parse #{ARGV[0]}"
37
+ $stder.puts e.to_s
38
+ exit 1
39
+ end
40
+
@@ -0,0 +1,60 @@
1
+ #
2
+ # = WP Sessioniser
3
+ #
4
+ # Convert access logs from wordpress blogs into tidy user sessions
5
+ #
6
+ # Category::
7
+ # Package:: WPSessioniser
8
+ # Author:: Ryan McCoskrie <ryan.mccoskrie@gmail.com>
9
+ # License:: MIT License
10
+
11
+ require 'apache_log_regex'
12
+ require 'wp-sessioniser/Visitor'
13
+
14
+
15
+ #
16
+ # = WPSessioniser
17
+ #
18
+ # == Example Usage
19
+ #
20
+ # file = File.open("/var/log/apache/access.log")
21
+ # visitors = WPSessioniser.parse(file)
22
+ #
23
+
24
+ module WPSessioniser
25
+ #Changing this string breaks parsing. I don't know why.
26
+ FORMAT = '%h %l %u %t \"%r\" %>s %b \"{Referer}i\" \"%{User-Agent}i\"'
27
+ PARSER = ApacheLogRegex.new(FORMAT)
28
+
29
+ def WPSessioniser.parse file
30
+ visitors = Hash.new()
31
+
32
+ file.each do |line|
33
+ h = PARSER.parse! line
34
+ #Ignore non-pages
35
+ next if h["%r"] !~ /GET/
36
+ next if h["%r"] =~ /xmlrpc.php/
37
+ next if h["%r"] =~ /favicon.ico/
38
+ next if h["%r"] =~ /robots.txt/
39
+ next if h["%r"] =~ /\?sccss/
40
+ next if h["%r"] =~ /wp-admin/
41
+ next if h["%r"] =~ /wp-content/
42
+ next if h["%r"] =~ /wp-includes/
43
+ next if h["%r"] =~ /wp-json/
44
+ next if h["%r"] =~ /\/\/images/
45
+ next if h["%r"] =~ /\?plugin=/
46
+
47
+ page = h["%r"].delete('GET ', '').delete(' HTTP/1.1', '')
48
+
49
+ if visitors.has_key? h["%h"]
50
+ visitors[h["%h"]].push_hit page, h["%t"]
51
+ else
52
+ visitors[h["%h"]] = Visitor.new
53
+ visitors[h["%h"]].push_hit page, h["%t"]
54
+ end
55
+ end
56
+
57
+ return visitors
58
+ end
59
+ end
60
+
@@ -0,0 +1,27 @@
1
+ #
2
+ # = Visitor
3
+ #
4
+ # Used to handle Visitor profiles in WPSessioniser
5
+ #
6
+ # Category::
7
+ # Package:: WPSessioniser
8
+ # Author:: Ryan McCoskrie <ryan.mccoskrie@gmail.com>
9
+ # License:: MIT License
10
+ #
11
+
12
+ class Visitor
13
+ attr_reader :hits
14
+
15
+ def initialize
16
+ @hits = Hash.new
17
+ end
18
+
19
+ def push_hit(page, date)
20
+ if @hits.has_key?(page)
21
+ @hits[page].push(date)
22
+ else
23
+ @hits[page] = [date]
24
+ end
25
+ end
26
+ end
27
+
metadata ADDED
@@ -0,0 +1,61 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: wp-sessioniser
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.2.1
5
+ platform: ruby
6
+ authors:
7
+ - Ryan McCoskrie
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2016-03-27 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: apachelogregex
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: '0.1'
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '0.1'
27
+ description: Displays reader sessions from an apache wordpress log
28
+ email: ryan.mccoskrie@gmail.com
29
+ executables:
30
+ - wp-sessioniser
31
+ extensions: []
32
+ extra_rdoc_files: []
33
+ files:
34
+ - bin/wp-sessioniser
35
+ - lib/wp-sessioniser.rb
36
+ - lib/wp-sessioniser/Visitor.rb
37
+ homepage: http://rubygems.org/gems/wp-sessioniser
38
+ licenses:
39
+ - MIT
40
+ metadata: {}
41
+ post_install_message:
42
+ rdoc_options: []
43
+ require_paths:
44
+ - lib
45
+ required_ruby_version: !ruby/object:Gem::Requirement
46
+ requirements:
47
+ - - ">="
48
+ - !ruby/object:Gem::Version
49
+ version: '0'
50
+ required_rubygems_version: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ requirements: []
56
+ rubyforge_project:
57
+ rubygems_version: 2.5.1
58
+ signing_key:
59
+ specification_version: 4
60
+ summary: Wordpress session analyser
61
+ test_files: []