PageRankr 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +24 -0
- data/LICENSE.md +20 -0
- data/README.md +54 -0
- data/Rakefile +46 -0
- data/VERSION +1 -0
- data/lib/page_rankr.rb +25 -0
- data/lib/page_rankr/alexa.rb +14 -0
- data/lib/page_rankr/backlinks.rb +37 -0
- data/lib/page_rankr/google.rb +24 -0
- data/lib/page_rankr/google/checksum.rb +74 -0
- data/spec/page_rankr_spec.rb +7 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +9 -0
- metadata +116 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE.md
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 blatyo
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
# PageRankr
|
2
|
+
|
3
|
+
Provides an easy way to retrieve Google Page Rank, Alexa Rank, and backlink counts.
|
4
|
+
|
5
|
+
## Exampes
|
6
|
+
|
7
|
+
### Backlinks
|
8
|
+
Backlinks are the result of doing a search with a query like "link:www.google.com". The number of returned results indicates how many sites point to that url.
|
9
|
+
|
10
|
+
`PageRankr.backlinks('www.google.com', :google, :bing) #=> {:google=>161000, :bing=>208000000}`
|
11
|
+
|
12
|
+
`PageRankr.backlinks('www.google.com', :yahoo) #=> {:yahoo=>256300062}`
|
13
|
+
|
14
|
+
Valid search engines are: `:google, :bing, :yahoo, :altavista, :alltheweb, :alexa`.
|
15
|
+
|
16
|
+
### Ranks
|
17
|
+
`PageRankr.ranks('www.google.com', :alexa, :google) #=> {:alexa=>1, :google=>10}`
|
18
|
+
|
19
|
+
There are two valid rank trackers supported: `:alexa, :google`.
|
20
|
+
Alexa ranks are descending where 1 is the most popular. If a site has an alexa rank of 0 then the site is unranked.
|
21
|
+
Google page ranks are in the range 0-10 where 10 is the most popular. If a site is unindexed then the rank will be -1.
|
22
|
+
|
23
|
+
|
24
|
+
## Note on Patches/Pull Requests
|
25
|
+
|
26
|
+
* Fork the project.
|
27
|
+
* Make your feature addition or bug fix.
|
28
|
+
* Add tests for it. This is important so I don't break it in a
|
29
|
+
future version unintentionally.
|
30
|
+
* Commit, do not mess with rakefile, version, or history.
|
31
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
32
|
+
* Send me a pull request. Bonus points for topic branches.
|
33
|
+
|
34
|
+
## TODO
|
35
|
+
* <del>Get backlink counts for:</del>
|
36
|
+
* <del>Google</del>
|
37
|
+
* <del>Bing</del>
|
38
|
+
* <del>Yahoo!</del>
|
39
|
+
* <del>AltaVista</del>
|
40
|
+
* <del>AllTheWeb</del>
|
41
|
+
* <del>Alexa</del>
|
42
|
+
* <del>Get Google Page Rank</del>
|
43
|
+
* <del>Implement Hashing Algorithm</del>
|
44
|
+
* <del>Get Alexa ranking</del>
|
45
|
+
|
46
|
+
## Shout Out
|
47
|
+
Gotta give credit where credits due!
|
48
|
+
* http://github.com/alexmipego/PageRankSharp
|
49
|
+
* http://snipplr.com/view/18329/google-page-range-lookup/
|
50
|
+
* http://www.sitetoolcenter.com/free-website-scripts/ajax-pr-checker.php
|
51
|
+
|
52
|
+
## Copyright
|
53
|
+
|
54
|
+
Copyright (c) 2010 Allen Madsen. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "PageRankr"
|
8
|
+
gem.summary = %Q{Easy way to retrieve Google Page Rank, Alexa Rank, and backlink counts}
|
9
|
+
gem.description = %Q{Easy way to retrieve Google Page Rank, Alexa Rank, and backlink counts}
|
10
|
+
gem.email = "blatyo@gmail.com"
|
11
|
+
gem.homepage = "http://github.com/blatyo/page_rankr"
|
12
|
+
gem.authors = ["Allen Madsen"]
|
13
|
+
gem.add_dependency "nokogiri", ">= 1.4.1"
|
14
|
+
gem.add_development_dependency "rspec", ">= 1.2.9"
|
15
|
+
gem.add_development_dependency "yard", ">= 0"
|
16
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
17
|
+
end
|
18
|
+
Jeweler::GemcutterTasks.new
|
19
|
+
rescue LoadError
|
20
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
21
|
+
end
|
22
|
+
|
23
|
+
require 'spec/rake/spectask'
|
24
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
25
|
+
spec.libs << 'lib' << 'spec'
|
26
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
27
|
+
end
|
28
|
+
|
29
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
30
|
+
spec.libs << 'lib' << 'spec'
|
31
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
32
|
+
spec.rcov = true
|
33
|
+
end
|
34
|
+
|
35
|
+
task :spec => :check_dependencies
|
36
|
+
|
37
|
+
task :default => :spec
|
38
|
+
|
39
|
+
begin
|
40
|
+
require 'yard'
|
41
|
+
YARD::Rake::YardocTask.new
|
42
|
+
rescue LoadError
|
43
|
+
task :yardoc do
|
44
|
+
abort "YARD is not available. In order to run yardoc, you must: sudo gem install yard"
|
45
|
+
end
|
46
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
1.0.0
|
data/lib/page_rankr.rb
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
path = File.expand_path(File.dirname(__FILE__)) + '/page_rankr/'
|
2
|
+
require path + 'backlinks'
|
3
|
+
require path + 'alexa'
|
4
|
+
require path + 'google'
|
5
|
+
|
6
|
+
module PageRankr
|
7
|
+
class << self
|
8
|
+
def backlinks(site, *search_engines)
|
9
|
+
Backlinks.lookup site, *search_engines
|
10
|
+
end
|
11
|
+
|
12
|
+
def ranks(site, *rank_trackers)
|
13
|
+
ranks = {}
|
14
|
+
rank_trackers.each do |tracker|
|
15
|
+
case tracker
|
16
|
+
when :google
|
17
|
+
ranks[tracker] = Google.lookup(site)
|
18
|
+
when :alexa
|
19
|
+
ranks[tracker] = Alexa.lookup(site)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
ranks
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
require 'cgi'
|
3
|
+
require 'nokogiri'
|
4
|
+
|
5
|
+
module PageRankr
|
6
|
+
class Alexa
|
7
|
+
class << self
|
8
|
+
def lookup(site)
|
9
|
+
url = "http://data.alexa.com/data?cli=10&dat=snbamz&url="
|
10
|
+
Nokogiri::HTML(open(url + CGI.escape(site))).search("//reach/@rank").to_s.to_i
|
11
|
+
end
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
require 'cgi'
|
3
|
+
require 'nokogiri'
|
4
|
+
|
5
|
+
module PageRankr
|
6
|
+
class Backlinks
|
7
|
+
SEARCH_ENGINE_URLS = {
|
8
|
+
:google => "http://www.google.com/search?q=link%3A",
|
9
|
+
:bing => "http://www.bing.com/search?q=link%3A",
|
10
|
+
:yahoo => "http://siteexplorer.search.yahoo.com/search?p=",
|
11
|
+
:altavista => "http://www.altavista.com/web/results?q=link%3A",
|
12
|
+
:alltheweb => "http://www.alltheweb.com/search?q=link%3A",
|
13
|
+
:alexa => "http://data.alexa.com/data?cli=10&dat=snbamz&url="
|
14
|
+
}
|
15
|
+
|
16
|
+
SEARCH_EGNINE_PATHS = {
|
17
|
+
:google => "//p[@id='resultStats']/b[3]/text()",
|
18
|
+
:bing => "//span[@class='sb_count']/text()",
|
19
|
+
:yahoo => "//ol[@id='results-tab']/li[2]/a/text()",
|
20
|
+
:altavista => "//a[@class='lbl']/text()",
|
21
|
+
:alltheweb => "//span[@class='ofSoMany']/text()",
|
22
|
+
:alexa => "//linksin/@num"
|
23
|
+
}
|
24
|
+
|
25
|
+
def self.lookup(site, *search_engines)
|
26
|
+
backlinks = {}
|
27
|
+
search_engines.each do |engine|
|
28
|
+
next unless SEARCH_ENGINE_URLS[engine]
|
29
|
+
doc = Nokogiri::HTML(open(SEARCH_ENGINE_URLS[engine] + CGI.escape(site)))
|
30
|
+
count = doc.at(SEARCH_EGNINE_PATHS[engine]).to_s
|
31
|
+
count = count.gsub('1-10', '').gsub(/[a-zA-Z,\s\(\)]/, '')
|
32
|
+
backlinks[engine] = count.to_i
|
33
|
+
end
|
34
|
+
backlinks
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
path = File.expand_path(File.dirname(__FILE__)) + '/google/'
|
2
|
+
require "open-uri"
|
3
|
+
require path + 'checksum'
|
4
|
+
|
5
|
+
module PageRankr
|
6
|
+
module Google
|
7
|
+
class << self
|
8
|
+
def lookup(site)
|
9
|
+
checksum = Checksum.generate(site)
|
10
|
+
begin
|
11
|
+
open(url(site, checksum)) {|io| io.read.scan(/Rank_\d+:\d+:(\d+)/)[0][0].to_i}
|
12
|
+
rescue
|
13
|
+
-1
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
private
|
18
|
+
|
19
|
+
def url(site, checksum)
|
20
|
+
"http://toolbarqueries.google.com/search?client=navclient-auto&ch=#{checksum}&features=Rank&q=info:#{site}"
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,74 @@
|
|
1
|
+
module PageRankr
|
2
|
+
module Google
|
3
|
+
class Checksum
|
4
|
+
class << self
|
5
|
+
def generate(site)
|
6
|
+
bytes = byte_array('info:' + site)
|
7
|
+
length = bytes.length
|
8
|
+
a = b = 0x9E3779B9
|
9
|
+
c = 0xE6359A60
|
10
|
+
k, len = 0, length
|
11
|
+
while(len >= 12)
|
12
|
+
a = m(a + bytes[k + 0] + (bytes[k + 1] << 8) + (bytes[k + 2] << 16) + (bytes[k + 3] << 24))
|
13
|
+
b = m(b + bytes[k + 4] + (bytes[k + 5] << 8) + (bytes[k + 6] << 16) + (bytes[k + 7] << 24))
|
14
|
+
c = m(c + bytes[k + 8] + (bytes[k + 9] << 8) + (bytes[k + 10] << 16) + (bytes[k + 11] << 24))
|
15
|
+
|
16
|
+
a, b, c = mix(a, b, c)
|
17
|
+
k += 12
|
18
|
+
len -= 12
|
19
|
+
end
|
20
|
+
|
21
|
+
c = c + length
|
22
|
+
|
23
|
+
c = mix(*toss(a, b, c, bytes, len, k))[2]
|
24
|
+
"6" + c.to_s
|
25
|
+
end
|
26
|
+
|
27
|
+
private
|
28
|
+
|
29
|
+
def byte_array(site)
|
30
|
+
bytes = []
|
31
|
+
site.each_byte {|b| bytes << b}
|
32
|
+
bytes
|
33
|
+
end
|
34
|
+
|
35
|
+
# Need to keep numbers in the unsigned int 32 range
|
36
|
+
def m(v)
|
37
|
+
v % 0x100000000
|
38
|
+
end
|
39
|
+
|
40
|
+
def mix(a, b, c)
|
41
|
+
a, b, c = m(a), m(b), m(c)
|
42
|
+
|
43
|
+
a = m(a-b-c) ^ m(c >> 13)
|
44
|
+
b = m(b-c-a) ^ m(a << 8)
|
45
|
+
c = m(c-a-b) ^ m(b >> 13)
|
46
|
+
|
47
|
+
a = m(a-b-c) ^ m(c >> 12)
|
48
|
+
b = m(b-c-a) ^ m(a << 16)
|
49
|
+
c = m(c-a-b) ^ m(b >> 5)
|
50
|
+
|
51
|
+
a = m(a-b-c) ^ m(c >> 3)
|
52
|
+
b = m(b-c-a) ^ m(a << 10)
|
53
|
+
c = m(c-a-b) ^ m(b >> 15)
|
54
|
+
|
55
|
+
[a, b, c]
|
56
|
+
end
|
57
|
+
|
58
|
+
def toss(a, b, c, bytes, len, k)
|
59
|
+
case len
|
60
|
+
when 9..11
|
61
|
+
c = c + (bytes[k+len-1] << ((len % 8) * 8))
|
62
|
+
when 5..8
|
63
|
+
b = b + (bytes[k+len-1] << ((len % 5) * 8))
|
64
|
+
when 1..4
|
65
|
+
a = a + (bytes[k+len-1] << ((len - 1) * 8))
|
66
|
+
else
|
67
|
+
return [a, b, c]
|
68
|
+
end
|
69
|
+
toss(a, b, c, bytes, len-1, k)
|
70
|
+
end
|
71
|
+
end
|
72
|
+
end
|
73
|
+
end
|
74
|
+
end
|
data/spec/spec.opts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,116 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: PageRankr
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 1
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
version: 1.0.0
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- Allen Madsen
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2010-04-18 00:00:00 -04:00
|
18
|
+
default_executable:
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: nokogiri
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - ">="
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
segments:
|
28
|
+
- 1
|
29
|
+
- 4
|
30
|
+
- 1
|
31
|
+
version: 1.4.1
|
32
|
+
type: :runtime
|
33
|
+
version_requirements: *id001
|
34
|
+
- !ruby/object:Gem::Dependency
|
35
|
+
name: rspec
|
36
|
+
prerelease: false
|
37
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - ">="
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
segments:
|
42
|
+
- 1
|
43
|
+
- 2
|
44
|
+
- 9
|
45
|
+
version: 1.2.9
|
46
|
+
type: :development
|
47
|
+
version_requirements: *id002
|
48
|
+
- !ruby/object:Gem::Dependency
|
49
|
+
name: yard
|
50
|
+
prerelease: false
|
51
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
52
|
+
requirements:
|
53
|
+
- - ">="
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
segments:
|
56
|
+
- 0
|
57
|
+
version: "0"
|
58
|
+
type: :development
|
59
|
+
version_requirements: *id003
|
60
|
+
description: Easy way to retrieve Google Page Rank, Alexa Rank, and backlink counts
|
61
|
+
email: blatyo@gmail.com
|
62
|
+
executables: []
|
63
|
+
|
64
|
+
extensions: []
|
65
|
+
|
66
|
+
extra_rdoc_files:
|
67
|
+
- LICENSE.md
|
68
|
+
- README.md
|
69
|
+
files:
|
70
|
+
- .document
|
71
|
+
- .gitignore
|
72
|
+
- LICENSE.md
|
73
|
+
- README.md
|
74
|
+
- Rakefile
|
75
|
+
- VERSION
|
76
|
+
- lib/page_rankr.rb
|
77
|
+
- lib/page_rankr/alexa.rb
|
78
|
+
- lib/page_rankr/backlinks.rb
|
79
|
+
- lib/page_rankr/google.rb
|
80
|
+
- lib/page_rankr/google/checksum.rb
|
81
|
+
- spec/page_rankr_spec.rb
|
82
|
+
- spec/spec.opts
|
83
|
+
- spec/spec_helper.rb
|
84
|
+
has_rdoc: true
|
85
|
+
homepage: http://github.com/blatyo/page_rankr
|
86
|
+
licenses: []
|
87
|
+
|
88
|
+
post_install_message:
|
89
|
+
rdoc_options:
|
90
|
+
- --charset=UTF-8
|
91
|
+
require_paths:
|
92
|
+
- lib
|
93
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
94
|
+
requirements:
|
95
|
+
- - ">="
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
segments:
|
98
|
+
- 0
|
99
|
+
version: "0"
|
100
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
101
|
+
requirements:
|
102
|
+
- - ">="
|
103
|
+
- !ruby/object:Gem::Version
|
104
|
+
segments:
|
105
|
+
- 0
|
106
|
+
version: "0"
|
107
|
+
requirements: []
|
108
|
+
|
109
|
+
rubyforge_project:
|
110
|
+
rubygems_version: 1.3.6
|
111
|
+
signing_key:
|
112
|
+
specification_version: 3
|
113
|
+
summary: Easy way to retrieve Google Page Rank, Alexa Rank, and backlink counts
|
114
|
+
test_files:
|
115
|
+
- spec/page_rankr_spec.rb
|
116
|
+
- spec/spec_helper.rb
|