wwwtf 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +33 -0
- data/Rakefile +1 -0
- data/bin/wwwtf +17 -0
- data/lib/wwwtf.rb +24 -0
- data/lib/wwwtf/cache.rb +11 -0
- data/lib/wwwtf/cache/king.rb +95 -0
- data/lib/wwwtf/http.rb +54 -0
- data/lib/wwwtf/http/url.rb +22 -0
- data/lib/wwwtf/utils/string.rb +14 -0
- data/lib/wwwtf/utils/time.rb +16 -0
- data/lib/wwwtf/version.rb +3 -0
- data/wwwtf.gemspec +24 -0
- metadata +94 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 abhishekkr
|
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 +1,33 @@
|
|
1
|
+
# WWWTF
|
2
|
+
|
3
|
+
World Wide Web's Trolls and Flaws
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'wwwtf'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install wwwtf
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
Cache is King like summary
|
22
|
+
$ wwwtf --cache-king $URL
|
23
|
+
|
24
|
+
in Debug mode, let's you know of all dependent URLs
|
25
|
+
$ WWWTF_DEBUG=on bin/wwwtf --cache-king $URL
|
26
|
+
|
27
|
+
## Contributing
|
28
|
+
|
29
|
+
1. Fork it
|
30
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
31
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
32
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
33
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/bin/wwwtf
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
$LOAD_PATH.unshift File.dirname(__FILE__) + '/../lib'
|
3
|
+
|
4
|
+
require 'arg0'
|
5
|
+
require 'wwwtf'
|
6
|
+
|
7
|
+
if %x{which curl}.empty?
|
8
|
+
puts 'Error: curl utility is \'currently\' required but not found in system path, fix it.'
|
9
|
+
puts 'Notice: Will change curl dependency to Ruby HTTP but there are few missing features in internal library, WIP.'
|
10
|
+
exit 1
|
11
|
+
end
|
12
|
+
|
13
|
+
cache_stats_for = Arg0::Console.value_for(['-ck', '--cache-king'])
|
14
|
+
cache_stats_for.each do |url|
|
15
|
+
url = "http://#{url}" unless url.match(/^https*\:\/\//)
|
16
|
+
Wwwtf.cache_king url
|
17
|
+
end
|
data/lib/wwwtf.rb
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
# Wwwtf
|
2
|
+
wwwtf_all = File.join(File.dirname(File.expand_path __FILE__), '*', '*.rb')
|
3
|
+
Dir.glob(wwwtf_all).each {|lib| require lib}
|
4
|
+
wwwtf_all_all = File.join(File.dirname(File.expand_path __FILE__), '*', '*', '*.rb')
|
5
|
+
Dir.glob(wwwtf_all_all).each {|lib| require lib}
|
6
|
+
require 'xml-motor'
|
7
|
+
require 'time'
|
8
|
+
|
9
|
+
module Wwwtf
|
10
|
+
|
11
|
+
def self.cache_king(url)
|
12
|
+
cache_stat = Wwwtf::Cache::King.stat url
|
13
|
+
lm_median_hrs = cache_stat['last_modified_hours_median'].to_i
|
14
|
+
lm_median_days = lm_median_hrs / 24
|
15
|
+
puts "#{url} has:
|
16
|
+
#{cache_stat['total_count']} number of dependent content locations,
|
17
|
+
#{cache_stat['cache_control%']}% of it is Cache-Control decisive,
|
18
|
+
#{cache_stat['expire_in_day%']}% of cached expires within a day,
|
19
|
+
#{cache_stat['last_modified%']}% is aware of Last-Modified,
|
20
|
+
#{lm_median_hrs}hrs. (i.e. #{lm_median_days} days) is L-M median
|
21
|
+
"
|
22
|
+
puts "\tDependent URLs:\n\t#{cache_stat['page_urls'].join("\n\t")}\n" unless ENV['WWWTF_DEBUG'].nil?
|
23
|
+
end
|
24
|
+
end
|
data/lib/wwwtf/cache.rb
ADDED
@@ -0,0 +1,95 @@
|
|
1
|
+
# Wwwtf::Cache::King
|
2
|
+
|
3
|
+
module Wwwtf
|
4
|
+
module Cache
|
5
|
+
module King
|
6
|
+
|
7
|
+
def self.stat(url)
|
8
|
+
begin
|
9
|
+
page_urls = Wwwtf::HTTP.page_dependency(url)
|
10
|
+
all_headers = headers(page_urls)
|
11
|
+
cache_control, last_modified = [], []
|
12
|
+
all_headers.each do |url, headr|
|
13
|
+
max_age = Wwwtf::Cache.cache_control_max_age(headr['Cache-Control'])
|
14
|
+
cache_control.push max_age
|
15
|
+
last_modified.push headr['Last-Modified']
|
16
|
+
end
|
17
|
+
{
|
18
|
+
'page_urls' => page_urls,
|
19
|
+
'total_count' => page_urls.size,
|
20
|
+
'cache_control%' => cache_control_percent(cache_control),
|
21
|
+
'expire_in_day%' => expire_in_day_percent(cache_control),
|
22
|
+
'last_modified%' => last_modified_percent(last_modified),
|
23
|
+
'last_modified_hours_median' => last_modified_median(last_modified)
|
24
|
+
}
|
25
|
+
rescue
|
26
|
+
puts "WWWTF Cache King failed in collecting statistic for #{url}."
|
27
|
+
exit 1
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
def self.headers(page_urls)
|
32
|
+
headers = {}
|
33
|
+
page_urls.each do |src|
|
34
|
+
headers = headers.merge({src => Wwwtf::HTTP.headers(src)})
|
35
|
+
end
|
36
|
+
filter_cache_headers(headers)
|
37
|
+
end
|
38
|
+
|
39
|
+
def self.filter_cache_headers(headers_batch)
|
40
|
+
filtered_headers = {}
|
41
|
+
reqd_headers = ['Cache-Control', 'Last-Modified']
|
42
|
+
headers_batch.each do |url, headers|
|
43
|
+
filtered = {}
|
44
|
+
reqd_headers.each {|hdr|
|
45
|
+
filtered = filtered.merge(
|
46
|
+
{hdr => headers[hdr]}
|
47
|
+
)
|
48
|
+
}
|
49
|
+
filtered_headers = filtered_headers.merge( {url => filtered} )
|
50
|
+
end
|
51
|
+
filtered_headers
|
52
|
+
end
|
53
|
+
|
54
|
+
def self.cache_control_percent(cache_control)
|
55
|
+
(cache_control.compact.size * 100) / cache_control.size
|
56
|
+
end
|
57
|
+
|
58
|
+
def self.expire_in_day_percent(cache_control)
|
59
|
+
max_age_in_days = cache_control.compact.collect{|max_age|
|
60
|
+
max_age.to_i / 86400 # i.e. 60 * 60 * 24
|
61
|
+
}
|
62
|
+
max_age_in_days.delete(0)
|
63
|
+
(max_age_in_days.size * 100 ) / cache_control.size
|
64
|
+
end
|
65
|
+
|
66
|
+
def self.last_modified_percent(last_modified)
|
67
|
+
(last_modified.compact.size * 100) / last_modified.size
|
68
|
+
end
|
69
|
+
|
70
|
+
def self.last_modified_median(last_modified)
|
71
|
+
require 'time'
|
72
|
+
last_modified = last_modified.compact
|
73
|
+
return nil if last_modified.empty?
|
74
|
+
last_mod_sorted = last_modified.each {|mod_time|
|
75
|
+
Time.parse(mod_time)
|
76
|
+
}.sort
|
77
|
+
half_size = last_mod_sorted.size / 2
|
78
|
+
if ( last_mod_sorted.size % 2 ) == 0
|
79
|
+
median_mod_time = Wwwtf::UtilsTime.hours_until_now(
|
80
|
+
last_mod_sorted[half_size]
|
81
|
+
)
|
82
|
+
median_mod_time += Wwwtf::UtilsTime.hours_until_now(
|
83
|
+
last_mod_sorted[half_size - 1]
|
84
|
+
)
|
85
|
+
median_mod_time = median_mod_time / 2
|
86
|
+
else
|
87
|
+
median_mod_time = Wwwtf::UtilsTime.hours_until_now(
|
88
|
+
last_mod_sorted[half_size]
|
89
|
+
)
|
90
|
+
end
|
91
|
+
median_mod_time
|
92
|
+
end
|
93
|
+
end
|
94
|
+
end
|
95
|
+
end
|
data/lib/wwwtf/http.rb
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
# Wwwtf::HTTP
|
2
|
+
|
3
|
+
module Wwwtf
|
4
|
+
module HTTP
|
5
|
+
|
6
|
+
class << self
|
7
|
+
attr_accessor :curl_headers
|
8
|
+
end
|
9
|
+
@curl_headers = 'User Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.4 (KHTML, Linuxke Gecko) Chrome/22.0.1229.52 Safari/537.4'
|
10
|
+
|
11
|
+
def self.headers(url)
|
12
|
+
hdrs = %x{curl -IkLs -H '#{curl_headers}' #{url}}
|
13
|
+
headr = {}
|
14
|
+
return headr if hdrs.match(/HTTP\/1\.[01]\s*[45][0-9][0-9]\s*\w/)
|
15
|
+
hdr = hdrs.split("\r\n")
|
16
|
+
hdr = hdr.collect{|h| {h.split(':')[0].strip => h.split(':')[1..-1].join.strip} }
|
17
|
+
hdr.each{|h| headr = headr.merge h}
|
18
|
+
headr
|
19
|
+
end
|
20
|
+
|
21
|
+
def self.body(url)
|
22
|
+
%x{curl -kLs -H '#{curl_headers}' #{url}}
|
23
|
+
end
|
24
|
+
|
25
|
+
def self.page_dependency(url)
|
26
|
+
page_content = body url
|
27
|
+
xtmp_nodes = XMLMotor.splitter page_content
|
28
|
+
xtmp_tags = XMLMotor.indexify xtmp_nodes
|
29
|
+
tag_src = XMLMotor.xmlattrib 'src', xtmp_nodes, xtmp_tags
|
30
|
+
src_in_page = tag_src.uniq.collect{|src|
|
31
|
+
fix_urls url, src
|
32
|
+
}
|
33
|
+
Wwwtf::HTTP::URL.uniq([url] + src_in_page).compact
|
34
|
+
end
|
35
|
+
|
36
|
+
def self.fix_urls(base_url, src_string)
|
37
|
+
begin
|
38
|
+
src_string = src_string.unescape.strip
|
39
|
+
src_string = src_string[1..-2] if src_string.match(/^\".*\"$/)
|
40
|
+
http = base_url.scan(/^(https*)\:\/\//).flatten.join
|
41
|
+
if src_string.match(/^https*\:\/\//i)
|
42
|
+
src_string
|
43
|
+
elsif src_string.match(/^\/\//)
|
44
|
+
"#{http}:#{src_string}"
|
45
|
+
else
|
46
|
+
File.join base_url, src_string
|
47
|
+
end
|
48
|
+
rescue
|
49
|
+
puts "ERR: #{src_string}"
|
50
|
+
return nil
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# Wwwtf::HTTP::URL
|
2
|
+
|
3
|
+
module Wwwtf
|
4
|
+
module HTTP
|
5
|
+
module URL
|
6
|
+
|
7
|
+
def self.unroot(url)
|
8
|
+
File.join File.dirname(url), File.basename(url)
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.same(url1, url2)
|
12
|
+
url1 = url1.gsub(/^https*\:\/\//, '')
|
13
|
+
url2 = url2.gsub(/^https*\:\/\//, '')
|
14
|
+
File.expand_path(url) === File.expand_path(url2)
|
15
|
+
end
|
16
|
+
|
17
|
+
def self.uniq(urls)
|
18
|
+
urls.collect{|url| unroot(url)}.uniq
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
class String
|
2
|
+
|
3
|
+
def unescape
|
4
|
+
string = self
|
5
|
+
unescaped_string = ''
|
6
|
+
escaped_at = string.index(/\\/)
|
7
|
+
until escaped_at.nil?
|
8
|
+
unescaped_string = "#{unescaped_string}#{string[0...escaped_at]}#{string[escaped_at + 1]}"
|
9
|
+
string = string[(escaped_at + 2)..-1]
|
10
|
+
escaped_at = string.index(/\\/)
|
11
|
+
end
|
12
|
+
"#{unescaped_string}#{string}"
|
13
|
+
end
|
14
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
# Wwwtf::Utils::Time
|
2
|
+
|
3
|
+
module Wwwtf
|
4
|
+
module UtilsTime
|
5
|
+
|
6
|
+
def self.hours_until_now(time)
|
7
|
+
begin
|
8
|
+
(Time.now - Time.parse(time)).to_i / 3600
|
9
|
+
rescue
|
10
|
+
msg = time.nil? ? 'NIL Times' : "Bad Times #{time}"
|
11
|
+
puts "This app has seen #{msg}"
|
12
|
+
exit 1
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
data/wwwtf.gemspec
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'wwwtf/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "wwwtf"
|
8
|
+
gem.version = Wwwtf::VERSION
|
9
|
+
gem.authors = ["abhishekkr"]
|
10
|
+
gem.email = ["abhikumar163@gmail.com"]
|
11
|
+
gem.description = %q{World Wide Web's Trolls and Flaws giving varied Trolls & Flaws analyzing the BAD WWW around.}
|
12
|
+
gem.summary = %q{World Wide Web's Trolls and Flaws}
|
13
|
+
gem.homepage = "https://github.com/abhishekkr/wwwtf"
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
|
20
|
+
gem.executables = %w( wwwtf )
|
21
|
+
|
22
|
+
gem.add_runtime_dependency 'xml-motor', '>= 0.1.6'
|
23
|
+
gem.add_runtime_dependency 'arg0', '>= 0.0.2'
|
24
|
+
end
|
metadata
ADDED
@@ -0,0 +1,94 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: wwwtf
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- abhishekkr
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-02-06 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: xml-motor
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 0.1.6
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 0.1.6
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: arg0
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: 0.0.2
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: 0.0.2
|
46
|
+
description: World Wide Web's Trolls and Flaws giving varied Trolls & Flaws analyzing
|
47
|
+
the BAD WWW around.
|
48
|
+
email:
|
49
|
+
- abhikumar163@gmail.com
|
50
|
+
executables:
|
51
|
+
- wwwtf
|
52
|
+
extensions: []
|
53
|
+
extra_rdoc_files: []
|
54
|
+
files:
|
55
|
+
- .gitignore
|
56
|
+
- Gemfile
|
57
|
+
- LICENSE.txt
|
58
|
+
- README.md
|
59
|
+
- Rakefile
|
60
|
+
- bin/wwwtf
|
61
|
+
- lib/wwwtf.rb
|
62
|
+
- lib/wwwtf/cache.rb
|
63
|
+
- lib/wwwtf/cache/king.rb
|
64
|
+
- lib/wwwtf/http.rb
|
65
|
+
- lib/wwwtf/http/url.rb
|
66
|
+
- lib/wwwtf/utils/string.rb
|
67
|
+
- lib/wwwtf/utils/time.rb
|
68
|
+
- lib/wwwtf/version.rb
|
69
|
+
- wwwtf.gemspec
|
70
|
+
homepage: https://github.com/abhishekkr/wwwtf
|
71
|
+
licenses: []
|
72
|
+
post_install_message:
|
73
|
+
rdoc_options: []
|
74
|
+
require_paths:
|
75
|
+
- lib
|
76
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
77
|
+
none: false
|
78
|
+
requirements:
|
79
|
+
- - ! '>='
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '0'
|
82
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
83
|
+
none: false
|
84
|
+
requirements:
|
85
|
+
- - ! '>='
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: '0'
|
88
|
+
requirements: []
|
89
|
+
rubyforge_project:
|
90
|
+
rubygems_version: 1.8.24
|
91
|
+
signing_key:
|
92
|
+
specification_version: 3
|
93
|
+
summary: World Wide Web's Trolls and Flaws
|
94
|
+
test_files: []
|