image_scraper 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/Gemfile +13 -0
- data/Gemfile.lock +22 -0
- data/LICENSE.txt +20 -0
- data/README.md +43 -0
- data/Rakefile +50 -0
- data/VERSION +1 -0
- data/image_scraper.gemspec +70 -0
- data/lib/image_scraper.rb +17 -0
- data/test/helper.rb +18 -0
- data/test/test_image_scraper.rb +13 -0
- metadata +158 -0
data/.document
ADDED
data/Gemfile
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
source "http://rubygems.org"
|
2
|
+
# Add dependencies required to use your gem here.
|
3
|
+
# Example:
|
4
|
+
# gem "activesupport", ">= 2.3.5"
|
5
|
+
gem "nokogiri"
|
6
|
+
# Add dependencies to develop your gem here.
|
7
|
+
# Include everything needed to run rake, tests, features, etc.
|
8
|
+
group :development do
|
9
|
+
gem "shoulda", ">= 0"
|
10
|
+
gem "bundler", "~> 1.0.0"
|
11
|
+
gem "jeweler", "~> 1.5.2"
|
12
|
+
gem "rcov", ">= 0"
|
13
|
+
end
|
data/Gemfile.lock
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
GEM
|
2
|
+
remote: http://rubygems.org/
|
3
|
+
specs:
|
4
|
+
git (1.2.5)
|
5
|
+
jeweler (1.5.2)
|
6
|
+
bundler (~> 1.0.0)
|
7
|
+
git (>= 1.2.5)
|
8
|
+
rake
|
9
|
+
nokogiri (1.4.4)
|
10
|
+
rake (0.9.0)
|
11
|
+
rcov (0.9.9)
|
12
|
+
shoulda (2.11.3)
|
13
|
+
|
14
|
+
PLATFORMS
|
15
|
+
ruby
|
16
|
+
|
17
|
+
DEPENDENCIES
|
18
|
+
bundler (~> 1.0.0)
|
19
|
+
jeweler (~> 1.5.2)
|
20
|
+
nokogiri
|
21
|
+
rcov
|
22
|
+
shoulda
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2011 John McAliley
|
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 +1,43 @@
|
|
1
|
+
# image_scraper
|
2
|
+
|
3
|
+
Simple utility that pulls image URLS from web page
|
4
|
+
|
5
|
+
## INSTALL
|
6
|
+
|
7
|
+
Add to your gemfile
|
8
|
+
|
9
|
+
gem "image_scraper"
|
10
|
+
|
11
|
+
Install w/ Bundler
|
12
|
+
|
13
|
+
bundle install
|
14
|
+
|
15
|
+
## USAGE
|
16
|
+
|
17
|
+
Pull all the image URLs from a specified URL and convert all images URLs to absolute paths
|
18
|
+
|
19
|
+
ImageScraper.image_urls("http://www.rubygems.org")
|
20
|
+
|
21
|
+
Pull all images URLs from specified URL and use relative URLs
|
22
|
+
|
23
|
+
ImageScraper.image_urls("http://www.rubygems.org",false)
|
24
|
+
|
25
|
+
## TODO
|
26
|
+
|
27
|
+
1. Parse CSS files for images
|
28
|
+
|
29
|
+
## Contributing to image_scraper
|
30
|
+
|
31
|
+
* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
|
32
|
+
* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
|
33
|
+
* Fork the project
|
34
|
+
* Start a feature/bugfix branch
|
35
|
+
* Commit and push until you are happy with your contribution
|
36
|
+
* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
|
37
|
+
* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
|
38
|
+
|
39
|
+
## Copyright
|
40
|
+
|
41
|
+
Copyright (c) 2011 John McAliley. See LICENSE.txt for
|
42
|
+
further details.
|
43
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,50 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'bundler'
|
3
|
+
begin
|
4
|
+
Bundler.setup(:default, :development)
|
5
|
+
rescue Bundler::BundlerError => e
|
6
|
+
$stderr.puts e.message
|
7
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
8
|
+
exit e.status_code
|
9
|
+
end
|
10
|
+
require 'rake'
|
11
|
+
|
12
|
+
require 'jeweler'
|
13
|
+
Jeweler::Tasks.new do |gem|
|
14
|
+
# gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
|
15
|
+
gem.name = "image_scraper"
|
16
|
+
gem.homepage = "http://github.com/charlotte-ruby/image_scraper"
|
17
|
+
gem.license = "MIT"
|
18
|
+
gem.summary = %Q{Simple utility to pull image urls from web page}
|
19
|
+
gem.description = %Q{Simple utility to pull image urls from web page}
|
20
|
+
gem.email = "john.mcaliley@gmail.com"
|
21
|
+
gem.authors = ["John McAliley"]
|
22
|
+
gem.add_dependency "nokogiri"
|
23
|
+
end
|
24
|
+
Jeweler::RubygemsDotOrgTasks.new
|
25
|
+
|
26
|
+
require 'rake/testtask'
|
27
|
+
Rake::TestTask.new(:test) do |test|
|
28
|
+
test.libs << 'lib' << 'test'
|
29
|
+
test.pattern = 'test/**/test_*.rb'
|
30
|
+
test.verbose = true
|
31
|
+
end
|
32
|
+
|
33
|
+
require 'rcov/rcovtask'
|
34
|
+
Rcov::RcovTask.new do |test|
|
35
|
+
test.libs << 'test'
|
36
|
+
test.pattern = 'test/**/test_*.rb'
|
37
|
+
test.verbose = true
|
38
|
+
end
|
39
|
+
|
40
|
+
task :default => :test
|
41
|
+
|
42
|
+
require 'rake/rdoctask'
|
43
|
+
Rake::RDocTask.new do |rdoc|
|
44
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
45
|
+
|
46
|
+
rdoc.rdoc_dir = 'rdoc'
|
47
|
+
rdoc.title = "image_scraper #{version}"
|
48
|
+
rdoc.rdoc_files.include('README*')
|
49
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
50
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.1
|
@@ -0,0 +1,70 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{image_scraper}
|
8
|
+
s.version = "0.0.1"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["John McAliley"]
|
12
|
+
s.date = %q{2011-05-27}
|
13
|
+
s.description = %q{Simple utility to pull image urls from web page}
|
14
|
+
s.email = %q{john.mcaliley@gmail.com}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE.txt",
|
17
|
+
"README.md"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
"Gemfile",
|
22
|
+
"Gemfile.lock",
|
23
|
+
"LICENSE.txt",
|
24
|
+
"README.md",
|
25
|
+
"Rakefile",
|
26
|
+
"VERSION",
|
27
|
+
"image_scraper.gemspec",
|
28
|
+
"lib/image_scraper.rb",
|
29
|
+
"test/helper.rb",
|
30
|
+
"test/test_image_scraper.rb"
|
31
|
+
]
|
32
|
+
s.homepage = %q{http://github.com/charlotte-ruby/image_scraper}
|
33
|
+
s.licenses = ["MIT"]
|
34
|
+
s.require_paths = ["lib"]
|
35
|
+
s.rubygems_version = %q{1.3.7}
|
36
|
+
s.summary = %q{Simple utility to pull image urls from web page}
|
37
|
+
s.test_files = [
|
38
|
+
"test/helper.rb",
|
39
|
+
"test/test_image_scraper.rb"
|
40
|
+
]
|
41
|
+
|
42
|
+
if s.respond_to? :specification_version then
|
43
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
44
|
+
s.specification_version = 3
|
45
|
+
|
46
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
47
|
+
s.add_runtime_dependency(%q<nokogiri>, [">= 0"])
|
48
|
+
s.add_development_dependency(%q<shoulda>, [">= 0"])
|
49
|
+
s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
|
50
|
+
s.add_development_dependency(%q<jeweler>, ["~> 1.5.2"])
|
51
|
+
s.add_development_dependency(%q<rcov>, [">= 0"])
|
52
|
+
s.add_runtime_dependency(%q<nokogiri>, [">= 0"])
|
53
|
+
else
|
54
|
+
s.add_dependency(%q<nokogiri>, [">= 0"])
|
55
|
+
s.add_dependency(%q<shoulda>, [">= 0"])
|
56
|
+
s.add_dependency(%q<bundler>, ["~> 1.0.0"])
|
57
|
+
s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
|
58
|
+
s.add_dependency(%q<rcov>, [">= 0"])
|
59
|
+
s.add_dependency(%q<nokogiri>, [">= 0"])
|
60
|
+
end
|
61
|
+
else
|
62
|
+
s.add_dependency(%q<nokogiri>, [">= 0"])
|
63
|
+
s.add_dependency(%q<shoulda>, [">= 0"])
|
64
|
+
s.add_dependency(%q<bundler>, ["~> 1.0.0"])
|
65
|
+
s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
|
66
|
+
s.add_dependency(%q<rcov>, [">= 0"])
|
67
|
+
s.add_dependency(%q<nokogiri>, [">= 0"])
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
require 'nokogiri'
|
3
|
+
|
4
|
+
module ImageScraper
|
5
|
+
def self.image_urls(url, convert_to_absolute_url=true)
|
6
|
+
uri = URI.parse(url)
|
7
|
+
domain = "#{uri.scheme}://#{uri.host}"
|
8
|
+
doc = Nokogiri::HTML(open url)
|
9
|
+
urls = []
|
10
|
+
doc.xpath("//img").each do |img|
|
11
|
+
image = img["src"]
|
12
|
+
image = domain + image if convert_to_absolute_url and !image.include?("://")
|
13
|
+
urls << image
|
14
|
+
end
|
15
|
+
urls
|
16
|
+
end
|
17
|
+
end
|
data/test/helper.rb
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'bundler'
|
3
|
+
begin
|
4
|
+
Bundler.setup(:default, :development)
|
5
|
+
rescue Bundler::BundlerError => e
|
6
|
+
$stderr.puts e.message
|
7
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
8
|
+
exit e.status_code
|
9
|
+
end
|
10
|
+
require 'test/unit'
|
11
|
+
require 'shoulda'
|
12
|
+
|
13
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
14
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
15
|
+
require 'image_scraper'
|
16
|
+
|
17
|
+
class Test::Unit::TestCase
|
18
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
class TestImageScraper < Test::Unit::TestCase
|
4
|
+
should "return list of all image urls on a web page with absolute paths" do
|
5
|
+
images = ["http://upload.wikimedia.org/wikipedia/en/thumb/2/24/Lenna.png/200px-Lenna.png", "http://bits.wikimedia.org/skins-1.17/common/images/magnify-clip.png", "http://bits.wikimedia.org/skins-1.17/vector/images/search-ltr.png?301-2", "http://en.wikipedia.org/images/wikimedia-button.png", "http://bits.wikimedia.org/skins-1.17/common/images/poweredby_mediawiki_88x31.png"]
|
6
|
+
assert_equal ImageScraper.image_urls("http://en.wikipedia.org/wiki/Standard_test_image"), images
|
7
|
+
end
|
8
|
+
|
9
|
+
should "return list of all image urls on a web page with relative paths" do
|
10
|
+
images = ["http://upload.wikimedia.org/wikipedia/en/thumb/2/24/Lenna.png/200px-Lenna.png","http://bits.wikimedia.org/skins-1.17/common/images/magnify-clip.png","http://bits.wikimedia.org/skins-1.17/vector/images/search-ltr.png?301-2","/images/wikimedia-button.png","http://bits.wikimedia.org/skins-1.17/common/images/poweredby_mediawiki_88x31.png"]
|
11
|
+
assert_equal ImageScraper.image_urls("http://en.wikipedia.org/wiki/Standard_test_image",false), images
|
12
|
+
end
|
13
|
+
end
|
metadata
ADDED
@@ -0,0 +1,158 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: image_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
version: 0.0.1
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- John McAliley
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2011-05-27 00:00:00 -04:00
|
18
|
+
default_executable:
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: nokogiri
|
22
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
23
|
+
none: false
|
24
|
+
requirements:
|
25
|
+
- - ">="
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
segments:
|
28
|
+
- 0
|
29
|
+
version: "0"
|
30
|
+
type: :runtime
|
31
|
+
prerelease: false
|
32
|
+
version_requirements: *id001
|
33
|
+
- !ruby/object:Gem::Dependency
|
34
|
+
name: shoulda
|
35
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
36
|
+
none: false
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
segments:
|
41
|
+
- 0
|
42
|
+
version: "0"
|
43
|
+
type: :development
|
44
|
+
prerelease: false
|
45
|
+
version_requirements: *id002
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: bundler
|
48
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ~>
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
segments:
|
54
|
+
- 1
|
55
|
+
- 0
|
56
|
+
- 0
|
57
|
+
version: 1.0.0
|
58
|
+
type: :development
|
59
|
+
prerelease: false
|
60
|
+
version_requirements: *id003
|
61
|
+
- !ruby/object:Gem::Dependency
|
62
|
+
name: jeweler
|
63
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
64
|
+
none: false
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
segments:
|
69
|
+
- 1
|
70
|
+
- 5
|
71
|
+
- 2
|
72
|
+
version: 1.5.2
|
73
|
+
type: :development
|
74
|
+
prerelease: false
|
75
|
+
version_requirements: *id004
|
76
|
+
- !ruby/object:Gem::Dependency
|
77
|
+
name: rcov
|
78
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
79
|
+
none: false
|
80
|
+
requirements:
|
81
|
+
- - ">="
|
82
|
+
- !ruby/object:Gem::Version
|
83
|
+
segments:
|
84
|
+
- 0
|
85
|
+
version: "0"
|
86
|
+
type: :development
|
87
|
+
prerelease: false
|
88
|
+
version_requirements: *id005
|
89
|
+
- !ruby/object:Gem::Dependency
|
90
|
+
name: nokogiri
|
91
|
+
requirement: &id006 !ruby/object:Gem::Requirement
|
92
|
+
none: false
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
segments:
|
97
|
+
- 0
|
98
|
+
version: "0"
|
99
|
+
type: :runtime
|
100
|
+
prerelease: false
|
101
|
+
version_requirements: *id006
|
102
|
+
description: Simple utility to pull image urls from web page
|
103
|
+
email: john.mcaliley@gmail.com
|
104
|
+
executables: []
|
105
|
+
|
106
|
+
extensions: []
|
107
|
+
|
108
|
+
extra_rdoc_files:
|
109
|
+
- LICENSE.txt
|
110
|
+
- README.md
|
111
|
+
files:
|
112
|
+
- .document
|
113
|
+
- Gemfile
|
114
|
+
- Gemfile.lock
|
115
|
+
- LICENSE.txt
|
116
|
+
- README.md
|
117
|
+
- Rakefile
|
118
|
+
- VERSION
|
119
|
+
- image_scraper.gemspec
|
120
|
+
- lib/image_scraper.rb
|
121
|
+
- test/helper.rb
|
122
|
+
- test/test_image_scraper.rb
|
123
|
+
has_rdoc: true
|
124
|
+
homepage: http://github.com/charlotte-ruby/image_scraper
|
125
|
+
licenses:
|
126
|
+
- MIT
|
127
|
+
post_install_message:
|
128
|
+
rdoc_options: []
|
129
|
+
|
130
|
+
require_paths:
|
131
|
+
- lib
|
132
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
133
|
+
none: false
|
134
|
+
requirements:
|
135
|
+
- - ">="
|
136
|
+
- !ruby/object:Gem::Version
|
137
|
+
hash: -2865953740112575330
|
138
|
+
segments:
|
139
|
+
- 0
|
140
|
+
version: "0"
|
141
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
142
|
+
none: false
|
143
|
+
requirements:
|
144
|
+
- - ">="
|
145
|
+
- !ruby/object:Gem::Version
|
146
|
+
segments:
|
147
|
+
- 0
|
148
|
+
version: "0"
|
149
|
+
requirements: []
|
150
|
+
|
151
|
+
rubyforge_project:
|
152
|
+
rubygems_version: 1.3.7
|
153
|
+
signing_key:
|
154
|
+
specification_version: 3
|
155
|
+
summary: Simple utility to pull image urls from web page
|
156
|
+
test_files:
|
157
|
+
- test/helper.rb
|
158
|
+
- test/test_image_scraper.rb
|