common-crawl-index 0.0.2.alpha → 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG.md +4 -0
- data/Gemfile +1 -4
- data/README.md +28 -2
- data/common-crawl-index.gemspec +3 -0
- data/lib/common-crawl-index.rb +5 -4
- data/lib/common-crawl-index/version.rb +1 -1
- data/spec/basic_spec.rb +7 -1
- metadata +37 -5
data/CHANGELOG.md
CHANGED
data/Gemfile
CHANGED
data/README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
# CommonCrawlIndex
|
2
2
|
|
3
|
-
|
3
|
+
Use this gem to access [Common Crawl URL Index](http://commoncrawl.org/common-crawl-url-index/) with ruby. You can get more information on format and original python implementation at https://github.com/trivio/common_crawl_index
|
4
4
|
|
5
5
|
## Installation
|
6
6
|
|
@@ -18,7 +18,33 @@ Or install it yourself as:
|
|
18
18
|
|
19
19
|
## Usage
|
20
20
|
|
21
|
-
|
21
|
+
When using with Rails in `config/initializers/common_crawl_index.rb`
|
22
|
+
|
23
|
+
```ruby
|
24
|
+
CommonCrawlIndex::Client.config({
|
25
|
+
:access_key_id => "amazon aws access_key",
|
26
|
+
:secret_access_key => "amazon aws secret_key",
|
27
|
+
:cc_index_path => "s3://aws-publicdatasets/common-crawl/projects/url-index/url-index.1356128792" # optional
|
28
|
+
})
|
29
|
+
```
|
30
|
+
|
31
|
+
And to find URLs matching certain prefix use following syntax
|
32
|
+
|
33
|
+
```ruby
|
34
|
+
client = CommonCrawlIndex::Client.new(AMAZON_ACCESS_KEY_ID, AMAZON_SECRET_ACCESS_KEY)
|
35
|
+
|
36
|
+
# or
|
37
|
+
|
38
|
+
client = CommonCrawlIndex::Client.new() # already configured
|
39
|
+
|
40
|
+
url = "http://www.amazon.com/"
|
41
|
+
|
42
|
+
client.find_by_prefix(url) do |url_data|
|
43
|
+
# get all URLs starting with http://www.amazon.com/
|
44
|
+
end
|
45
|
+
```
|
46
|
+
|
47
|
+
See `spec/basic_spec.rb` for more examples on usage.
|
22
48
|
|
23
49
|
## Contributing
|
24
50
|
|
data/common-crawl-index.gemspec
CHANGED
@@ -18,4 +18,7 @@ Gem::Specification.new do |gem|
|
|
18
18
|
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
19
19
|
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
20
20
|
gem.require_paths = ["lib"]
|
21
|
+
|
22
|
+
gem.add_runtime_dependency('aws-sdk')
|
23
|
+
gem.add_runtime_dependency('addressable')
|
21
24
|
end
|
data/lib/common-crawl-index.rb
CHANGED
@@ -1,7 +1,7 @@
|
|
1
|
-
require
|
1
|
+
require 'common-crawl-index/version'
|
2
2
|
require 'aws-sdk'
|
3
3
|
require 'open3'
|
4
|
-
|
4
|
+
require 'addressable/uri'
|
5
5
|
|
6
6
|
module CommonCrawlIndex
|
7
7
|
class Client
|
@@ -42,7 +42,7 @@ module CommonCrawlIndex
|
|
42
42
|
|
43
43
|
def self.normalize_url(url, append_scheme = true)
|
44
44
|
url_to_find = url
|
45
|
-
norm_url_to_find = URI(url_to_find)
|
45
|
+
norm_url_to_find = Addressable::URI.parse(url_to_find)
|
46
46
|
norm_url_to_find.host = norm_url_to_find.host.split(".").reverse.join(".")
|
47
47
|
norm_url = norm_url_to_find.to_s
|
48
48
|
norm_url = norm_url[norm_url.index("\/\/")+2..-1]
|
@@ -58,7 +58,7 @@ module CommonCrawlIndex
|
|
58
58
|
scheme = normalized_url[colon_index+1..-1] if colon_index
|
59
59
|
end
|
60
60
|
url_with_scheme = scheme + "://" + normalized_url[0..colon_index-1]
|
61
|
-
uri = URI(url_with_scheme)
|
61
|
+
uri = Addressable::URI.parse(url_with_scheme)
|
62
62
|
uri.host = uri.host.split(".").reverse.join(".")
|
63
63
|
uri.to_s
|
64
64
|
end
|
@@ -119,6 +119,7 @@ module CommonCrawlIndex
|
|
119
119
|
end
|
120
120
|
cur_loc = nil_loc + 32 + 1
|
121
121
|
end
|
122
|
+
true
|
122
123
|
end
|
123
124
|
|
124
125
|
def read(target_range)
|
data/spec/basic_spec.rb
CHANGED
@@ -26,7 +26,7 @@ describe CommonCrawlIndex do
|
|
26
26
|
it "should find by prefix" do
|
27
27
|
client = CommonCrawlIndex::Client.new(AMAZON_ACCESS_KEY_ID, AMAZON_SECRET_ACCESS_KEY)
|
28
28
|
|
29
|
-
total_urls_to_test =
|
29
|
+
total_urls_to_test = 2500
|
30
30
|
|
31
31
|
url = "http://www.amazon.com/"
|
32
32
|
normalized_url = CommonCrawlIndex::Client.normalize_url(url, false)
|
@@ -52,6 +52,9 @@ describe CommonCrawlIndex do
|
|
52
52
|
it "should normalize the urls correctly" do
|
53
53
|
normalized_url = CommonCrawlIndex::Client.normalize_url("http://www.google.com/test/path")
|
54
54
|
normalized_url.should == "com.google.www/test/path:http"
|
55
|
+
|
56
|
+
normalized_url = CommonCrawlIndex::Client.normalize_url("http://www.google.com/cse?cx=009462381166450434430:-woy8fnynf8&ie=UTF-8&q=physician+Cardiology+Diagnostics+md+\"Greater+Atlanta+Area\"+-recruiter&sa=Search&siteurl=www.google.com/cse/home%3Fcx%3D009462381166450434430%253A-woy8fnynf8")
|
57
|
+
normalized_url.should == "com.google.www/cse?cx=009462381166450434430:-woy8fnynf8&ie=UTF-8&q=physician+Cardiology+Diagnostics+md+\"Greater+Atlanta+Area\"+-recruiter&sa=Search&siteurl=www.google.com/cse/home%3Fcx%3D009462381166450434430%253A-woy8fnynf8:http"
|
55
58
|
end
|
56
59
|
|
57
60
|
it "should normalize the urls correctly without scheme" do
|
@@ -62,6 +65,9 @@ describe CommonCrawlIndex do
|
|
62
65
|
it "should denormalize the urls correctly" do
|
63
66
|
url = CommonCrawlIndex::Client.denormalize_url("com.google.www/test/path:http")
|
64
67
|
url.should == "http://www.google.com/test/path"
|
68
|
+
|
69
|
+
url = CommonCrawlIndex::Client.denormalize_url("com.google.www/cse?cx=009462381166450434430:-woy8fnynf8&ie=UTF-8&q=physician+Cardiology+Diagnostics+md+\"Greater+Atlanta+Area\"+-recruiter&sa=Search&siteurl=www.google.com/cse/home%3Fcx%3D009462381166450434430%253A-woy8fnynf8:http")
|
70
|
+
url.should == "http://www.google.com/cse?cx=009462381166450434430:-woy8fnynf8&ie=UTF-8&q=physician+Cardiology+Diagnostics+md+\"Greater+Atlanta+Area\"+-recruiter&sa=Search&siteurl=www.google.com/cse/home%3Fcx%3D009462381166450434430%253A-woy8fnynf8"
|
65
71
|
end
|
66
72
|
|
67
73
|
it "should denormalize the urls correctly without scheme" do
|
metadata
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: common-crawl-index
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.2
|
5
|
-
prerelease:
|
4
|
+
version: 0.0.2
|
5
|
+
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
8
8
|
- Amit Ambardekar
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-
|
12
|
+
date: 2013-02-02 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: rspec
|
@@ -27,6 +27,38 @@ dependencies:
|
|
27
27
|
- - ! '>='
|
28
28
|
- !ruby/object:Gem::Version
|
29
29
|
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: aws-sdk
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
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'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: addressable
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :runtime
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
30
62
|
description: Access coomon crawl URL index
|
31
63
|
email:
|
32
64
|
- amitamb@gmail.com
|
@@ -61,9 +93,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
61
93
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
62
94
|
none: false
|
63
95
|
requirements:
|
64
|
-
- - ! '
|
96
|
+
- - ! '>='
|
65
97
|
- !ruby/object:Gem::Version
|
66
|
-
version:
|
98
|
+
version: '0'
|
67
99
|
requirements: []
|
68
100
|
rubyforge_project:
|
69
101
|
rubygems_version: 1.8.24
|