sq 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.
Files changed (5) hide show
  1. checksums.yaml +7 -0
  2. data/bin/sq +28 -0
  3. data/lib/sq.rb +53 -0
  4. data/tests/tests.rb +28 -0
  5. metadata +146 -0
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 13322e186f26b4bfd9d0d549d9e431d11e5eb204
4
+ data.tar.gz: 27fef1a017cedea1b8f624fa69933197b7914801
5
+ SHA512:
6
+ metadata.gz: c9323f2d65d1dae55a2d0ecceb979f983ef62584759dbcadc4a7c6cd63df1e1091f042c3f748df794ad9fa40e60aa0bbbcbb6c93d4b6e6815e00788c9117b815
7
+ data.tar.gz: 4c1916d0f879fa8e16445e85beaa3545823bdb9e371373429469acdc0adb8ca7ee73d66ad2cdf1405792beb3d9085b091080f6b41f008d01be433d05b5163ddb
data/bin/sq ADDED
@@ -0,0 +1,28 @@
1
+ #! /usr/bin/env ruby
2
+ # -*- coding: UTF-8 -*-
3
+
4
+ require 'trollop'
5
+ require 'sq'
6
+
7
+ opts = Trollop.options do
8
+ version "sq #{SQ.version}"
9
+ banner <<-EOS
10
+ sq is a bulk PDFs downloader
11
+
12
+ Usage:
13
+ sq [options] <uri> [<regex>]
14
+ where [options] are:
15
+ EOS
16
+
17
+ opt :directory, 'Choose the output directory', :short => '-o', :type => :string, :default => '.'
18
+ end
19
+
20
+ if ARGV.empty?
21
+ puts 'Error: No URI provided. Use -h or --help to see the help.'
22
+ exit 1
23
+ end
24
+
25
+ url, *regex_parts = ARGV
26
+ regex = regex_parts.join(' ')
27
+
28
+ SQ.process(url, Regexp.new(regex), opts)
@@ -0,0 +1,53 @@
1
+ #! /usr/bin/env ruby
2
+ # -*- coding: UTF-8 -*-
3
+
4
+ require 'uri'
5
+ require 'open-uri'
6
+ require 'nokogiri'
7
+ require 'fileutils'
8
+
9
+ module SQ
10
+ class << self
11
+ def version
12
+ '0.0.1'
13
+ end
14
+
15
+ def user_agent
16
+ "SQ/#{version} +github.com/bfontaine/sq"
17
+ end
18
+
19
+ def query(uri, regex=/./)
20
+ uri = 'http://' + uri unless uri =~ /^https?:\/\//
21
+
22
+ doc = Nokogiri::HTML(open(uri, 'User-Agent' => user_agent))
23
+ links = doc.css('a[href]')
24
+
25
+ uris = links.map { |a| URI.join(uri, a.attr('href')) }
26
+ uris.select! { |u| u.path =~ /\.pdf$/i && u.to_s =~ regex }
27
+
28
+ uris.map do |u|
29
+ {
30
+ :uri => u.to_s,
31
+ :name => u.path.split('/').last
32
+ }
33
+ end
34
+ end
35
+
36
+ def process(uri, regex=/./, opts={})
37
+ uris = self.query(uri, regex)
38
+ return 0 if uris.empty?
39
+
40
+ out = File.expand_path(opts[:directory] || '.')
41
+
42
+ Dir.mkdir(out) unless Dir.exists?(out)
43
+
44
+ uris.each do |u|
45
+ open("#{out}/#{u[:name]}", 'wb') do |f|
46
+ open(u[:uri], 'rb') do |resp|
47
+ f.write(resp.read)
48
+ end
49
+ end
50
+ end
51
+ end
52
+ end
53
+ end
@@ -0,0 +1,28 @@
1
+ #! /usr/bin/env ruby
2
+ # -*- coding: UTF-8 -*-
3
+
4
+ require 'test/unit'
5
+ require 'simplecov'
6
+
7
+ test_dir = File.expand_path( File.dirname(__FILE__) )
8
+
9
+ SimpleCov.start { add_filter '/tests/' } if ENV['COVERAGE']
10
+
11
+ require 'sq'
12
+
13
+ for t in Dir.glob( File.join( test_dir, '*_tests.rb' ) )
14
+ require t
15
+ end
16
+
17
+ class SQTests < Test::Unit::TestCase
18
+
19
+ # == UD#version == #
20
+
21
+ def test_sq_version
22
+ assert(SQ.version =~ /^\d+\.\d+\.\d+/)
23
+ end
24
+
25
+ end
26
+
27
+
28
+ exit Test::Unit::AutoRunner.run
metadata ADDED
@@ -0,0 +1,146 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: sq
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Baptiste Fontaine
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-01-10 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: nokogiri
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ~>
18
+ - !ruby/object:Gem::Version
19
+ version: 1.6.1
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - ~>
25
+ - !ruby/object:Gem::Version
26
+ version: 1.6.1
27
+ - !ruby/object:Gem::Dependency
28
+ name: trollop
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ~>
32
+ - !ruby/object:Gem::Version
33
+ version: '2.0'
34
+ type: :runtime
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ~>
39
+ - !ruby/object:Gem::Version
40
+ version: '2.0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: colored
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ~>
46
+ - !ruby/object:Gem::Version
47
+ version: '1.2'
48
+ type: :runtime
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ~>
53
+ - !ruby/object:Gem::Version
54
+ version: '1.2'
55
+ - !ruby/object:Gem::Dependency
56
+ name: simplecov
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - '>='
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - '>='
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: rake
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - '>='
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - '>='
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: test-unit
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - '>='
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - '>='
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: fakeweb
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - '>='
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - '>='
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ description: Download all PDFs linked in a Web page
112
+ email: batifon@yahoo.fr
113
+ executables:
114
+ - sq
115
+ extensions: []
116
+ extra_rdoc_files: []
117
+ files:
118
+ - lib/sq.rb
119
+ - tests/tests.rb
120
+ - bin/sq
121
+ homepage: https://github.com/bfontaine/sq
122
+ licenses:
123
+ - MIT
124
+ metadata: {}
125
+ post_install_message:
126
+ rdoc_options: []
127
+ require_paths:
128
+ - lib
129
+ required_ruby_version: !ruby/object:Gem::Requirement
130
+ requirements:
131
+ - - '>='
132
+ - !ruby/object:Gem::Version
133
+ version: '0'
134
+ required_rubygems_version: !ruby/object:Gem::Requirement
135
+ requirements:
136
+ - - '>='
137
+ - !ruby/object:Gem::Version
138
+ version: '0'
139
+ requirements: []
140
+ rubyforge_project:
141
+ rubygems_version: 2.0.3
142
+ signing_key:
143
+ specification_version: 4
144
+ summary: Bulk PDFs downloader
145
+ test_files:
146
+ - tests/tests.rb