factbook 0.1.0 → 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +17 -4
- data/Rakefile +48 -0
- data/lib/factbook/page.rb +10 -1
- data/lib/factbook/version.rb +1 -1
- metadata +11 -11
data/README.md
CHANGED
@@ -10,7 +10,7 @@
|
|
10
10
|
|
11
11
|
## What's the World Factbook?
|
12
12
|
|
13
|
-
The World Factbook published by the Central Intelligence Agency (CIA)
|
13
|
+
The World Factbook [1][2] published by the Central Intelligence Agency (CIA)
|
14
14
|
offers free country profiles in the public domain (that is, no copyright(s), no rights reserved).
|
15
15
|
|
16
16
|
- [1] [The World Factbook](https://www.cia.gov/library/publications/the-world-factbook/)
|
@@ -19,7 +19,7 @@ offers free country profiles in the public domain (that is, no copyright(s), no
|
|
19
19
|
|
20
20
|
## Usage
|
21
21
|
|
22
|
-
### Get page as a hash (that is, structured data e.g. nested key/values)
|
22
|
+
### Get country profile page as a hash (that is, structured data e.g. nested key/values)
|
23
23
|
|
24
24
|
page = Factbook::Page.new( 'br' )
|
25
25
|
pp page.data # pretty print hash
|
@@ -28,7 +28,7 @@ offers free country profiles in the public domain (that is, no copyright(s), no
|
|
28
28
|
|
29
29
|
page = Factbook::Page.new( 'br' )
|
30
30
|
File.open( 'br.json', 'w') do |f|
|
31
|
-
f.write
|
31
|
+
f.write page.to_json( pretty: true )
|
32
32
|
end
|
33
33
|
|
34
34
|
|
@@ -39,11 +39,24 @@ Just install the gem:
|
|
39
39
|
$ gem install factbook
|
40
40
|
|
41
41
|
|
42
|
+
## Ready-To-Use Public Domain Datasets (Generated by `factbook`)
|
42
43
|
|
43
|
-
|
44
|
+
[openmundi/factbook.json](https://github.com/openmundi/factbook.json) - open (public domain)
|
45
|
+
factbook country profiles in JSON for all the world's countries (using internet domain names
|
46
|
+
for country codes e.g. Austria is `at.json` not `au.json`, Germany is `de.json` not `gm.json` and so on)
|
47
|
+
|
48
|
+
|
49
|
+
|
50
|
+
## Alternatives Libraries and Gems
|
51
|
+
|
52
|
+
Ruby
|
44
53
|
|
45
54
|
- [worldfactbook gem](https://github.com/sayem/worldfactbook) by sayem (aka Sayem Khan); fetches data from its own mirror, that is, rubyworldfactbook.com (last updated 2011?)
|
46
55
|
|
56
|
+
Others
|
57
|
+
|
58
|
+
TBD
|
59
|
+
|
47
60
|
|
48
61
|
## License
|
49
62
|
|
data/Rakefile
CHANGED
@@ -30,3 +30,51 @@ Hoe.spec 'factbook' do
|
|
30
30
|
}
|
31
31
|
|
32
32
|
end
|
33
|
+
|
34
|
+
|
35
|
+
|
36
|
+
desc 'generate json for factbook.json repo'
|
37
|
+
task :genjson do
|
38
|
+
require 'factbook'
|
39
|
+
|
40
|
+
countries = [
|
41
|
+
'au',
|
42
|
+
'be',
|
43
|
+
'br',
|
44
|
+
'mx',
|
45
|
+
'us'
|
46
|
+
]
|
47
|
+
|
48
|
+
countries.each do |country|
|
49
|
+
gen_json_for( country )
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
|
54
|
+
def gen_json_for( code )
|
55
|
+
Dir.mkdir( 'tmp' ) unless Dir.exists?( 'tmp' )
|
56
|
+
Dir.mkdir( 'tmp/html' ) unless Dir.exists?( 'tmp/html' )
|
57
|
+
Dir.mkdir( 'tmp/json' ) unless Dir.exists?( 'tmp/json' )
|
58
|
+
|
59
|
+
page = Factbook::Page.new( code )
|
60
|
+
|
61
|
+
## print first 600 chars
|
62
|
+
pp page.html[0..600]
|
63
|
+
|
64
|
+
## save for debuging
|
65
|
+
|
66
|
+
puts "saving a copy to #{code}.html for debugging"
|
67
|
+
File.open( "tmp/html/#{code}.html", 'w') do |f|
|
68
|
+
f.write( page.html )
|
69
|
+
end
|
70
|
+
|
71
|
+
h = page.data
|
72
|
+
pp h
|
73
|
+
|
74
|
+
### save to json
|
75
|
+
puts "saving a copy to #{code}.json for debugging"
|
76
|
+
File.open( "tmp/json/#{code}.json", 'w') do |f|
|
77
|
+
f.write( JSON.pretty_generate( h ) )
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
data/lib/factbook/page.rb
CHANGED
@@ -21,6 +21,15 @@ module Factbook
|
|
21
21
|
@doc ||= Nokogiri::HTML( html )
|
22
22
|
end
|
23
23
|
|
24
|
+
def to_json( opts={} )
|
25
|
+
## convenience helper for data.to_json
|
26
|
+
if opts[:pretty] || opts[:pp]
|
27
|
+
JSON.pretty_generate( data )
|
28
|
+
else
|
29
|
+
data.to_json
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
24
33
|
def data
|
25
34
|
if @data.nil?
|
26
35
|
titles = [
|
@@ -263,7 +272,7 @@ module Factbook
|
|
263
272
|
key = key.gsub( '(s)', 's' )
|
264
273
|
key = key.gsub( ':', '' ) # trailing :
|
265
274
|
## remove special chars ()-/,'
|
266
|
-
key = key.gsub( /[()\-\/,]
|
275
|
+
key = key.gsub( /['()\-\/,]/, ' ' )
|
267
276
|
key = key.strip
|
268
277
|
key = key.gsub( /[ ]+/, '_' )
|
269
278
|
key
|
data/lib/factbook/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: factbook
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.1
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -13,7 +13,7 @@ date: 2014-07-12 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: logutils
|
16
|
-
requirement: &
|
16
|
+
requirement: &73732120 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: '0'
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *73732120
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: fetcher
|
27
|
-
requirement: &
|
27
|
+
requirement: &73731730 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ! '>='
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: '0'
|
33
33
|
type: :runtime
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *73731730
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &73731340 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ! '>='
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: '0'
|
44
44
|
type: :runtime
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *73731340
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: rdoc
|
49
|
-
requirement: &
|
49
|
+
requirement: &73730940 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ~>
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '4.0'
|
55
55
|
type: :development
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *73730940
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: hoe
|
60
|
-
requirement: &
|
60
|
+
requirement: &73730530 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ~>
|
@@ -65,7 +65,7 @@ dependencies:
|
|
65
65
|
version: '3.11'
|
66
66
|
type: :development
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *73730530
|
69
69
|
description: factbook - scripts for the world factbook (get open structured data e.g
|
70
70
|
JSON etc.)
|
71
71
|
email: openmundi@googlegroups.com
|