url_extractor 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.rvmrc +1 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +29 -0
- data/Rakefile +2 -0
- data/lib/url_extractor.rb +6 -0
- data/lib/url_extractor/html.rb +33 -0
- data/lib/url_extractor/plain_text.rb +29 -0
- data/lib/url_extractor/util.rb +13 -0
- data/lib/url_extractor/version.rb +3 -0
- data/spec/url_extractor/html_spec.rb +41 -0
- data/spec/url_extractor/plain_text_spec.rb +38 -0
- data/url_extractor.gemspec +20 -0
- metadata +88 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 12e9a39d947f5860ec829d6f3a0c2a2c8829b0b3
|
4
|
+
data.tar.gz: a37afb38367c298689aa194d0945f8c0f82e1318
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: cc38c7af36334af7f4a23b5f63c0af6bf6f658c070f21a35b370d0c5e5a25942861344c61a74fe85dd02d6cbd78636ff45e9ce488752509ea56d38782243f08f
|
7
|
+
data.tar.gz: f8abdf7eae0aa71e35880af91db019970faf3081a3f8363c70a835b9996fb34cef95cfdaef4d0c71852f0c2c0d2e58f3ce3352f90dff8d0abe55aecfe7d6bb0a
|
data/.gitignore
ADDED
data/.rvmrc
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
rvm use 2.1.0@url_extractor --create
|
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Michael Guterl
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# UrlExtractor
|
2
|
+
|
3
|
+
A tool for extracting and replacing URLs from inside a block of text or HTML.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'url_extractor'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install url_extractor
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
|
3
|
+
module UrlExtractor
|
4
|
+
class HTML
|
5
|
+
|
6
|
+
InvalidURL = Class.new(StandardError)
|
7
|
+
|
8
|
+
def initialize(ignore_patterns = [])
|
9
|
+
@ignore_patterns = ignore_patterns
|
10
|
+
end
|
11
|
+
|
12
|
+
def replace_urls(template)
|
13
|
+
document = Nokogiri::HTML(template)
|
14
|
+
|
15
|
+
document.search("a").each do |link|
|
16
|
+
url = link['href']
|
17
|
+
raise InvalidURL, "cannot be blank" if UrlExtractor::Util.blank_string?(url)
|
18
|
+
next if ignored_url?(url)
|
19
|
+
|
20
|
+
link['href'] = yield(url)
|
21
|
+
end
|
22
|
+
|
23
|
+
document.to_s
|
24
|
+
end
|
25
|
+
|
26
|
+
private
|
27
|
+
|
28
|
+
def ignored_url?(url)
|
29
|
+
url !~ /https?:\/\// || @ignore_patterns.any? { |pattern| url =~ pattern }
|
30
|
+
end
|
31
|
+
|
32
|
+
end
|
33
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'uri'
|
2
|
+
|
3
|
+
module UrlExtractor
|
4
|
+
class PlainText
|
5
|
+
|
6
|
+
def initialize(ignore_patterns = [])
|
7
|
+
@ignore_patterns = ignore_patterns
|
8
|
+
end
|
9
|
+
|
10
|
+
def replace_urls(text)
|
11
|
+
urls = URI.extract text
|
12
|
+
|
13
|
+
urls.each do |url|
|
14
|
+
next if ignogred_url?(url)
|
15
|
+
|
16
|
+
text = text.gsub url, yield(url)
|
17
|
+
end
|
18
|
+
|
19
|
+
text
|
20
|
+
end
|
21
|
+
|
22
|
+
private
|
23
|
+
|
24
|
+
def ignogred_url?(url)
|
25
|
+
url !~ /https?:\/\// || @ignore_patterns.any? { |pattern| url =~ pattern }
|
26
|
+
end
|
27
|
+
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,41 @@
|
|
1
|
+
require 'url_extractor'
|
2
|
+
|
3
|
+
describe UrlExtractor::HTML do
|
4
|
+
def html_wrapped_string(string)
|
5
|
+
"<!DOCTYPE html PUBLIC \"-//W3C//DTD HTML 4.0 Transitional//EN\" \"http://www.w3.org/TR/REC-html40/loose.dtd\">\n<html><body>#{string}\n</body></html>\n"
|
6
|
+
end
|
7
|
+
|
8
|
+
it 'returns a string with the modified URLs that were returned in the block' do
|
9
|
+
extractor = UrlExtractor::HTML.new
|
10
|
+
text = html_wrapped_string('foo bar <a href="http://google.com">Google</a>')
|
11
|
+
|
12
|
+
actual = extractor.replace_urls(text) do |extracted|
|
13
|
+
'http://foo.bar'
|
14
|
+
end
|
15
|
+
|
16
|
+
actual.should == html_wrapped_string("foo bar <a href=\"http://foo.bar\">Google</a>")
|
17
|
+
end
|
18
|
+
|
19
|
+
it 'ignores urls that match patterns provided' do
|
20
|
+
extractor = UrlExtractor::HTML.new([/google/])
|
21
|
+
text = html_wrapped_string('foo bar <a href="http://google.com">Stuff</a> <a href="http://bar.baz">Google</a>')
|
22
|
+
|
23
|
+
actual = extractor.replace_urls(text) do |extracted|
|
24
|
+
'http://foo.bar'
|
25
|
+
end
|
26
|
+
|
27
|
+
actual.should == html_wrapped_string("foo bar <a href=\"http://google.com\">Stuff</a> <a href=\"http://foo.bar\">Google</a>")
|
28
|
+
end
|
29
|
+
|
30
|
+
it "ignores URLs that don't match http or https" do
|
31
|
+
extractor = UrlExtractor::HTML.new
|
32
|
+
text = html_wrapped_string("foo bar <a href=\"Reminder:foobar\">Hi</a>")
|
33
|
+
|
34
|
+
actual = extractor.replace_urls(text) do |extracted|
|
35
|
+
'http://foo.bar'
|
36
|
+
end
|
37
|
+
|
38
|
+
actual.should == text
|
39
|
+
end
|
40
|
+
|
41
|
+
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
require 'url_extractor'
|
2
|
+
|
3
|
+
describe UrlExtractor::PlainText do
|
4
|
+
|
5
|
+
it 'returns a string with the modified URLs that were returned in the block' do
|
6
|
+
extractor = UrlExtractor::PlainText.new
|
7
|
+
text = 'foo bar http://google.com'
|
8
|
+
|
9
|
+
actual = extractor.replace_urls(text) do |extracted|
|
10
|
+
'http://foo.bar'
|
11
|
+
end
|
12
|
+
|
13
|
+
actual.should == 'foo bar http://foo.bar'
|
14
|
+
end
|
15
|
+
|
16
|
+
it 'ignores urls that match patterns provided' do
|
17
|
+
extractor = UrlExtractor::PlainText.new([/google/])
|
18
|
+
text = 'http://google.com http://foobar.com'
|
19
|
+
|
20
|
+
actual = extractor.replace_urls(text) do |extracted|
|
21
|
+
'http://foo.bar'
|
22
|
+
end
|
23
|
+
|
24
|
+
actual.should == 'http://google.com http://foo.bar'
|
25
|
+
end
|
26
|
+
|
27
|
+
it "ignores URLs that don't match http or https" do
|
28
|
+
extractor = UrlExtractor::PlainText.new
|
29
|
+
text = "Reminder: Blah"
|
30
|
+
|
31
|
+
actual = extractor.replace_urls(text) do |extracted|
|
32
|
+
'http://foo.bar'
|
33
|
+
end
|
34
|
+
|
35
|
+
actual.should == 'Reminder: Blah'
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/url_extractor/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Michael Guterl"]
|
6
|
+
gem.email = ["michael@diminishing.org"]
|
7
|
+
gem.description = %q{A tool for extracting and replacing URLs from inside a block of text or HTML.}
|
8
|
+
gem.summary = %q{A tool for extracting and replacing URLs from inside a block of text or HTML.}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "url_extractor"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = UrlExtractor::VERSION
|
17
|
+
|
18
|
+
gem.add_development_dependency 'rspec'
|
19
|
+
gem.add_dependency 'nokogiri'
|
20
|
+
end
|
metadata
ADDED
@@ -0,0 +1,88 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: url_extractor
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Michael Guterl
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-04-21 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rspec
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: nokogiri
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
description: A tool for extracting and replacing URLs from inside a block of text
|
42
|
+
or HTML.
|
43
|
+
email:
|
44
|
+
- michael@diminishing.org
|
45
|
+
executables: []
|
46
|
+
extensions: []
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- ".gitignore"
|
50
|
+
- ".rvmrc"
|
51
|
+
- Gemfile
|
52
|
+
- LICENSE
|
53
|
+
- README.md
|
54
|
+
- Rakefile
|
55
|
+
- lib/url_extractor.rb
|
56
|
+
- lib/url_extractor/html.rb
|
57
|
+
- lib/url_extractor/plain_text.rb
|
58
|
+
- lib/url_extractor/util.rb
|
59
|
+
- lib/url_extractor/version.rb
|
60
|
+
- spec/url_extractor/html_spec.rb
|
61
|
+
- spec/url_extractor/plain_text_spec.rb
|
62
|
+
- url_extractor.gemspec
|
63
|
+
homepage: ''
|
64
|
+
licenses: []
|
65
|
+
metadata: {}
|
66
|
+
post_install_message:
|
67
|
+
rdoc_options: []
|
68
|
+
require_paths:
|
69
|
+
- lib
|
70
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '0'
|
75
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
76
|
+
requirements:
|
77
|
+
- - ">="
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: '0'
|
80
|
+
requirements: []
|
81
|
+
rubyforge_project:
|
82
|
+
rubygems_version: 2.2.2
|
83
|
+
signing_key:
|
84
|
+
specification_version: 4
|
85
|
+
summary: A tool for extracting and replacing URLs from inside a block of text or HTML.
|
86
|
+
test_files:
|
87
|
+
- spec/url_extractor/html_spec.rb
|
88
|
+
- spec/url_extractor/plain_text_spec.rb
|