google_scholar 0.0.1
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.
- data/.gitignore +4 -0
- data/Gemfile +4 -0
- data/Rakefile +1 -0
- data/google_scholar.gemspec +25 -0
- data/lib/google_scholar.rb +12 -0
- data/lib/google_scholar/article.rb +43 -0
- data/lib/google_scholar/page.rb +27 -0
- data/lib/google_scholar/version.rb +3 -0
- metadata +120 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "google_scholar/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "google_scholar"
|
7
|
+
s.version = GoogleScholar::VERSION
|
8
|
+
s.authors = ["Antonio Tapiador del Dujo"]
|
9
|
+
s.email = ["atapiador@dit.upm.es"]
|
10
|
+
s.homepage = ""
|
11
|
+
s.summary = %q{A web-scraping API to Google Scholar}
|
12
|
+
s.description = %q{A web-scraping API to Google Scholar}
|
13
|
+
|
14
|
+
s.rubyforge_project = "google_scholar"
|
15
|
+
|
16
|
+
s.files = `git ls-files`.split("\n")
|
17
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
18
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
19
|
+
s.require_paths = ["lib"]
|
20
|
+
|
21
|
+
s.add_development_dependency "rspec"
|
22
|
+
|
23
|
+
s.add_runtime_dependency "nokogiri", "~> 1.5.0"
|
24
|
+
s.add_runtime_dependency "activesupport", "> 3.0.0"
|
25
|
+
end
|
@@ -0,0 +1,43 @@
|
|
1
|
+
module GoogleScholar
|
2
|
+
class Article
|
3
|
+
class << self
|
4
|
+
include ActiveSupport::Memoizable
|
5
|
+
end
|
6
|
+
|
7
|
+
attr_reader :doc
|
8
|
+
|
9
|
+
def initialize(doc)
|
10
|
+
@doc = doc
|
11
|
+
end
|
12
|
+
|
13
|
+
def title
|
14
|
+
doc.css("h3").text
|
15
|
+
end
|
16
|
+
|
17
|
+
def link
|
18
|
+
doc.css('h3 a').first['href']
|
19
|
+
end
|
20
|
+
|
21
|
+
def details
|
22
|
+
doc.css('.gs_a').first.text
|
23
|
+
end
|
24
|
+
|
25
|
+
def cites_element
|
26
|
+
doc.css('.gs_fl a').select{ |l| l.text =~ /^Cited by/ }.first
|
27
|
+
end
|
28
|
+
|
29
|
+
def cites_link
|
30
|
+
cites_element ?
|
31
|
+
GoogleScholar::ROOT_URL + cites_element['href'] :
|
32
|
+
nil
|
33
|
+
end
|
34
|
+
|
35
|
+
def cites_count
|
36
|
+
cites_element ?
|
37
|
+
cites_element.text.gsub("Cited by ", "").to_i :
|
38
|
+
0
|
39
|
+
end
|
40
|
+
|
41
|
+
memoize :title, :link, :details, :cites_link, :cites_count
|
42
|
+
end
|
43
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
|
3
|
+
module GoogleScholar
|
4
|
+
class Page
|
5
|
+
class << self
|
6
|
+
include ActiveSupport::Memoizable
|
7
|
+
end
|
8
|
+
|
9
|
+
attr_reader :url, :doc
|
10
|
+
|
11
|
+
def initialize(url)
|
12
|
+
@url = url
|
13
|
+
end
|
14
|
+
|
15
|
+
def doc
|
16
|
+
Nokogiri::HTML(open(url))
|
17
|
+
end
|
18
|
+
|
19
|
+
def articles
|
20
|
+
doc.css(".gs_r").map{ |e|
|
21
|
+
GoogleScholar::Article.new e
|
22
|
+
}
|
23
|
+
end
|
24
|
+
|
25
|
+
memoize :doc, :articles
|
26
|
+
end
|
27
|
+
end
|
metadata
ADDED
@@ -0,0 +1,120 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: google_scholar
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 29
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 1
|
10
|
+
version: 0.0.1
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Antonio Tapiador del Dujo
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2011-10-23 00:00:00 +02:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: rspec
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 3
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
version: "0"
|
33
|
+
type: :development
|
34
|
+
version_requirements: *id001
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
name: nokogiri
|
37
|
+
prerelease: false
|
38
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ~>
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
hash: 3
|
44
|
+
segments:
|
45
|
+
- 1
|
46
|
+
- 5
|
47
|
+
- 0
|
48
|
+
version: 1.5.0
|
49
|
+
type: :runtime
|
50
|
+
version_requirements: *id002
|
51
|
+
- !ruby/object:Gem::Dependency
|
52
|
+
name: activesupport
|
53
|
+
prerelease: false
|
54
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
55
|
+
none: false
|
56
|
+
requirements:
|
57
|
+
- - ">"
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
hash: 7
|
60
|
+
segments:
|
61
|
+
- 3
|
62
|
+
- 0
|
63
|
+
- 0
|
64
|
+
version: 3.0.0
|
65
|
+
type: :runtime
|
66
|
+
version_requirements: *id003
|
67
|
+
description: A web-scraping API to Google Scholar
|
68
|
+
email:
|
69
|
+
- atapiador@dit.upm.es
|
70
|
+
executables: []
|
71
|
+
|
72
|
+
extensions: []
|
73
|
+
|
74
|
+
extra_rdoc_files: []
|
75
|
+
|
76
|
+
files:
|
77
|
+
- .gitignore
|
78
|
+
- Gemfile
|
79
|
+
- Rakefile
|
80
|
+
- google_scholar.gemspec
|
81
|
+
- lib/google_scholar.rb
|
82
|
+
- lib/google_scholar/article.rb
|
83
|
+
- lib/google_scholar/page.rb
|
84
|
+
- lib/google_scholar/version.rb
|
85
|
+
has_rdoc: true
|
86
|
+
homepage: ""
|
87
|
+
licenses: []
|
88
|
+
|
89
|
+
post_install_message:
|
90
|
+
rdoc_options: []
|
91
|
+
|
92
|
+
require_paths:
|
93
|
+
- lib
|
94
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
95
|
+
none: false
|
96
|
+
requirements:
|
97
|
+
- - ">="
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
hash: 3
|
100
|
+
segments:
|
101
|
+
- 0
|
102
|
+
version: "0"
|
103
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
104
|
+
none: false
|
105
|
+
requirements:
|
106
|
+
- - ">="
|
107
|
+
- !ruby/object:Gem::Version
|
108
|
+
hash: 3
|
109
|
+
segments:
|
110
|
+
- 0
|
111
|
+
version: "0"
|
112
|
+
requirements: []
|
113
|
+
|
114
|
+
rubyforge_project: google_scholar
|
115
|
+
rubygems_version: 1.6.2
|
116
|
+
signing_key:
|
117
|
+
specification_version: 3
|
118
|
+
summary: A web-scraping API to Google Scholar
|
119
|
+
test_files: []
|
120
|
+
|