skrape 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/Gemfile +3 -0
- data/LICENSE.txt +22 -0
- data/README.md +57 -0
- data/Rakefile +1 -0
- data/lib/skrape/version.rb +3 -0
- data/lib/skrape.rb +37 -0
- data/skrape.gemspec +26 -0
- data/spec/skrape_spec.rb +39 -0
- data/spec/spec_helper.rb +13 -0
- data/spec/test_data/example_com_raw_response +63 -0
- metadata +114 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: a431f8709c3f19242645f7f2221392417f9a089a
|
4
|
+
data.tar.gz: 878dd97f1c89db56dbbf78db16433ab05deb5e3c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 37f91a440aeb8e90e82e33b069888e9e25dfedbceaef6243666cc6e824bf7da169cac57d28e8724a9393766f0549860fbb85d5a7562f4e4278abbad476140e43
|
7
|
+
data.tar.gz: 543871c6fa15105834452047c1a0076a853d2d7b92487c8d59fafd30a87bee2dd3df3bfdd9069cce1cf319f764f54eeefd2bbac5dbaccb0190828140ce71725b
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Mike Williamson
|
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 +1,57 @@
|
|
1
|
+
# Skrape
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'skrape'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install skrape
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
Skrape provides a cute DSL for extracting information from pages on the
|
22
|
+
web. You give it a url and a block and it gives you back a hash.
|
23
|
+
|
24
|
+
Lets say you have a page like this:
|
25
|
+
|
26
|
+
<html><body><h1>I am a title</h1></body></html>
|
27
|
+
|
28
|
+
And you want a hash like this:
|
29
|
+
|
30
|
+
{title: "I am a title"}
|
31
|
+
|
32
|
+
You can run Skrape like this:
|
33
|
+
|
34
|
+
results = Skrape::Page.new("http://example.com").extract do
|
35
|
+
extract_title with: 'h1'
|
36
|
+
end
|
37
|
+
|
38
|
+
Skrape will give you the elements text by default, but in cases where
|
39
|
+
you are after something else, or need to do some massaging of the data,
|
40
|
+
you can pass a block:
|
41
|
+
|
42
|
+
results = Skrape::Page.new(url).extract do
|
43
|
+
extract_link_href with: 'a', and_run: proc {|link| link.attr('href').value }
|
44
|
+
end
|
45
|
+
|
46
|
+
The element(s) will be passed into the block as a
|
47
|
+
Nokogiri::XML::NodeSet for you to play with. Whatever text you return
|
48
|
+
will be added to the hash of things to return.
|
49
|
+
|
50
|
+
|
51
|
+
## Contributing
|
52
|
+
|
53
|
+
1. Fork it ( http://github.com/sleepycat/skrape/fork )
|
54
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
55
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
56
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
57
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/lib/skrape.rb
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
require "skrape/version"
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'open-uri'
|
4
|
+
require 'pry'
|
5
|
+
|
6
|
+
module Skrape
|
7
|
+
|
8
|
+
class NoElementsFoundError < StandardError; end
|
9
|
+
|
10
|
+
class Page
|
11
|
+
|
12
|
+
def initialize url
|
13
|
+
@extracted_info = {}
|
14
|
+
agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/32.0.1700.102 Chrome/32.0.1700.102 Safari/537.36"
|
15
|
+
@document = Nokogiri::HTML(open(url, "User-Agent" => agent))
|
16
|
+
end
|
17
|
+
|
18
|
+
def extract
|
19
|
+
block = Proc.new
|
20
|
+
instance_eval &block
|
21
|
+
@extracted_info
|
22
|
+
end
|
23
|
+
|
24
|
+
def method_missing name, args
|
25
|
+
feature_name = name.to_s.gsub('extract_', '').to_sym
|
26
|
+
element = @document.css args[:with]
|
27
|
+
raise NoElementsFoundError, "the css selector for '#{feature_name}' did not return anything" if element.empty?
|
28
|
+
if args[:and_run]
|
29
|
+
@extracted_info[feature_name] = args[:and_run].call(element)
|
30
|
+
else
|
31
|
+
@extracted_info[feature_name] = element.text
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
end
|
36
|
+
|
37
|
+
end
|
data/skrape.gemspec
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'skrape/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "skrape"
|
8
|
+
spec.version = Skrape::VERSION
|
9
|
+
spec.authors = ["Mike Williamson"]
|
10
|
+
spec.email = ["mike@korora.ca"]
|
11
|
+
spec.summary = "A tiny DSL for web scraping."
|
12
|
+
spec.description = "A cute little DSL for picking information off of web pages."
|
13
|
+
spec.homepage = "https://github.com/sleepycat/skrape"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.5"
|
22
|
+
spec.add_development_dependency "rspec", "~> 2.14"
|
23
|
+
spec.add_development_dependency "webmock", "~> 1.7"
|
24
|
+
spec.add_development_dependency "pry", "~> 0.9"
|
25
|
+
spec.add_dependency "nokogiri", "~> 1.6"
|
26
|
+
end
|
data/spec/skrape_spec.rb
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe Skrape do
|
4
|
+
|
5
|
+
describe Skrape::Page do
|
6
|
+
|
7
|
+
let(:url){ "http://example.com" }
|
8
|
+
let(:example_response){ File.new('spec/test_data/example_com_raw_response') }
|
9
|
+
|
10
|
+
before(:each) do
|
11
|
+
stub_request(:get, url).to_return(example_response)
|
12
|
+
end
|
13
|
+
|
14
|
+
it "returns the text of the element identifed by the CSS selector" do
|
15
|
+
results = Skrape::Page.new(url).extract do
|
16
|
+
extract_title with: 'h1'
|
17
|
+
end
|
18
|
+
expect(results[:title]).to eq "Example Domain"
|
19
|
+
end
|
20
|
+
|
21
|
+
it "accepts a block so you can do more sophisticated things" do
|
22
|
+
results = Skrape::Page.new(url).extract do
|
23
|
+
extract_link_href with: 'a', and_run: proc {|link| link.attr('href').value }
|
24
|
+
end
|
25
|
+
expect(results[:link_href]).to eq "http://www.iana.org/domains/example"
|
26
|
+
end
|
27
|
+
|
28
|
+
it "raises a helpful error when the CSS selector returns nothing" do
|
29
|
+
expect{
|
30
|
+
Skrape::Page.new(url).extract do
|
31
|
+
extract_nothing with: 'foo'
|
32
|
+
end
|
33
|
+
}.to raise_error Skrape::NoElementsFoundError
|
34
|
+
end
|
35
|
+
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
39
|
+
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
require_relative '../lib/skrape'
|
2
|
+
require 'webmock/rspec'
|
3
|
+
|
4
|
+
RSpec.configure do |config|
|
5
|
+
# Use color in STDOUT
|
6
|
+
config.color_enabled = true
|
7
|
+
|
8
|
+
# Use color not only in STDOUT but also in pagers and files
|
9
|
+
config.tty = true
|
10
|
+
|
11
|
+
# Use the specified formatter
|
12
|
+
config.formatter = :documentation # :progress, :html, :textmate
|
13
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
HTTP/1.1 200 OK
|
2
|
+
Accept-Ranges: bytes
|
3
|
+
Cache-Control: max-age=604800
|
4
|
+
Content-Type: text/html
|
5
|
+
Date: Tue, 11 Feb 2014 15:50:08 GMT
|
6
|
+
Etag: "359670651"
|
7
|
+
Expires: Tue, 18 Feb 2014 15:50:08 GMT
|
8
|
+
Last-Modified: Fri, 09 Aug 2013 23:54:35 GMT
|
9
|
+
Server: ECS (iad/19AB)
|
10
|
+
X-Cache: HIT
|
11
|
+
x-ec-custom-error: 1
|
12
|
+
Content-Length: 1270
|
13
|
+
|
14
|
+
<!doctype html>
|
15
|
+
<html>
|
16
|
+
<head>
|
17
|
+
<title>Example Domain</title>
|
18
|
+
|
19
|
+
<meta charset="utf-8" />
|
20
|
+
<meta http-equiv="Content-type" content="text/html; charset=utf-8" />
|
21
|
+
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
22
|
+
<style type="text/css">
|
23
|
+
body {
|
24
|
+
background-color: #f0f0f2;
|
25
|
+
margin: 0;
|
26
|
+
padding: 0;
|
27
|
+
font-family: "Open Sans", "Helvetica Neue", Helvetica, Arial, sans-serif;
|
28
|
+
|
29
|
+
}
|
30
|
+
div {
|
31
|
+
width: 600px;
|
32
|
+
margin: 5em auto;
|
33
|
+
padding: 50px;
|
34
|
+
background-color: #fff;
|
35
|
+
border-radius: 1em;
|
36
|
+
}
|
37
|
+
a:link, a:visited {
|
38
|
+
color: #38488f;
|
39
|
+
text-decoration: none;
|
40
|
+
}
|
41
|
+
@media (max-width: 700px) {
|
42
|
+
body {
|
43
|
+
background-color: #fff;
|
44
|
+
}
|
45
|
+
div {
|
46
|
+
width: auto;
|
47
|
+
margin: 0 auto;
|
48
|
+
border-radius: 0;
|
49
|
+
padding: 1em;
|
50
|
+
}
|
51
|
+
}
|
52
|
+
</style>
|
53
|
+
</head>
|
54
|
+
|
55
|
+
<body>
|
56
|
+
<div>
|
57
|
+
<h1>Example Domain</h1>
|
58
|
+
<p>This domain is established to be used for illustrative examples in documents. You may use this
|
59
|
+
domain in examples without prior coordination or asking for permission.</p>
|
60
|
+
<p><a href="http://www.iana.org/domains/example">More information...</a></p>
|
61
|
+
</div>
|
62
|
+
</body>
|
63
|
+
</html>
|
metadata
ADDED
@@ -0,0 +1,114 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: skrape
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Mike Williamson
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2014-02-12 00:00:00 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: bundler
|
16
|
+
prerelease: false
|
17
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: "1.5"
|
22
|
+
type: :development
|
23
|
+
version_requirements: *id001
|
24
|
+
- !ruby/object:Gem::Dependency
|
25
|
+
name: rspec
|
26
|
+
prerelease: false
|
27
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
28
|
+
requirements:
|
29
|
+
- - ~>
|
30
|
+
- !ruby/object:Gem::Version
|
31
|
+
version: "2.14"
|
32
|
+
type: :development
|
33
|
+
version_requirements: *id002
|
34
|
+
- !ruby/object:Gem::Dependency
|
35
|
+
name: webmock
|
36
|
+
prerelease: false
|
37
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - ~>
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: "1.7"
|
42
|
+
type: :development
|
43
|
+
version_requirements: *id003
|
44
|
+
- !ruby/object:Gem::Dependency
|
45
|
+
name: pry
|
46
|
+
prerelease: false
|
47
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
48
|
+
requirements:
|
49
|
+
- - ~>
|
50
|
+
- !ruby/object:Gem::Version
|
51
|
+
version: "0.9"
|
52
|
+
type: :development
|
53
|
+
version_requirements: *id004
|
54
|
+
- !ruby/object:Gem::Dependency
|
55
|
+
name: nokogiri
|
56
|
+
prerelease: false
|
57
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: "1.6"
|
62
|
+
type: :runtime
|
63
|
+
version_requirements: *id005
|
64
|
+
description: A cute little DSL for picking information off of web pages.
|
65
|
+
email:
|
66
|
+
- mike@korora.ca
|
67
|
+
executables: []
|
68
|
+
|
69
|
+
extensions: []
|
70
|
+
|
71
|
+
extra_rdoc_files: []
|
72
|
+
|
73
|
+
files:
|
74
|
+
- .gitignore
|
75
|
+
- Gemfile
|
76
|
+
- LICENSE.txt
|
77
|
+
- README.md
|
78
|
+
- Rakefile
|
79
|
+
- lib/skrape.rb
|
80
|
+
- lib/skrape/version.rb
|
81
|
+
- skrape.gemspec
|
82
|
+
- spec/skrape_spec.rb
|
83
|
+
- spec/spec_helper.rb
|
84
|
+
- spec/test_data/example_com_raw_response
|
85
|
+
homepage: https://github.com/sleepycat/skrape
|
86
|
+
licenses:
|
87
|
+
- MIT
|
88
|
+
metadata: {}
|
89
|
+
|
90
|
+
post_install_message:
|
91
|
+
rdoc_options: []
|
92
|
+
|
93
|
+
require_paths:
|
94
|
+
- lib
|
95
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
96
|
+
requirements:
|
97
|
+
- &id006
|
98
|
+
- ">="
|
99
|
+
- !ruby/object:Gem::Version
|
100
|
+
version: "0"
|
101
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- *id006
|
104
|
+
requirements: []
|
105
|
+
|
106
|
+
rubyforge_project:
|
107
|
+
rubygems_version: 2.2.2
|
108
|
+
signing_key:
|
109
|
+
specification_version: 4
|
110
|
+
summary: A tiny DSL for web scraping.
|
111
|
+
test_files:
|
112
|
+
- spec/skrape_spec.rb
|
113
|
+
- spec/spec_helper.rb
|
114
|
+
- spec/test_data/example_com_raw_response
|