quick_scrapper 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
data/.gitignore ADDED
@@ -0,0 +1,5 @@
1
+ *.gem
2
+ .bundle
3
+ Gemfile.lock
4
+ pkg/*
5
+ nbproject
data/Gemfile ADDED
@@ -0,0 +1,4 @@
1
+ source "http://rubygems.org"
2
+
3
+ # Specify your gem's dependencies in quick_scrapper.gemspec
4
+ gemspec
data/Rakefile ADDED
@@ -0,0 +1,2 @@
1
+ require 'bundler'
2
+ Bundler::GemHelper.install_tasks
@@ -0,0 +1,3 @@
1
+ module QuickScrapper
2
+ VERSION = "0.0.1"
3
+ end
@@ -0,0 +1,16 @@
1
+ require 'scrapi'
2
+
3
+ module QuickScrapper
4
+ # Scraps the selection associated to css_selector +selector+ from the page located at +url+
5
+ #
6
+ # Example: QuickScrapper.scrap("http://bvsatyaram.com", div.priceAvail>div>div.PriceCompare>div.BodyS")
7
+ def self.scrap(url, selector)
8
+ scraper = Scraper.define do
9
+ process selector, :selection => :text
10
+ result :selection
11
+ end
12
+
13
+ uri = URI.parse(url)
14
+ return scraper.scrape(uri)
15
+ end
16
+ end
@@ -0,0 +1,23 @@
1
+ # -*- encoding: utf-8 -*-
2
+ $:.push File.expand_path("../lib", __FILE__)
3
+ require "quick_scrapper/version"
4
+
5
+ Gem::Specification.new do |s|
6
+ s.name = "quick_scrapper"
7
+ s.version = QuickScrapper::VERSION
8
+ s.platform = Gem::Platform::RUBY
9
+ s.authors = ["Satyaram B V"]
10
+ s.email = ["bvsatyaram AT gmail DOT com"]
11
+ s.homepage = "http://bvsatyaram.com"
12
+ s.summary = %q{Quickly scraps a selection in a page}
13
+ s.description = %q{Quickly scraps a selection in a page}
14
+
15
+ s.add_dependency "scrapi"
16
+
17
+ s.rubyforge_project = "quick_scrapper"
18
+
19
+ s.files = `git ls-files`.split("\n")
20
+ s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
21
+ s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
22
+ s.require_paths = ["lib"]
23
+ end
@@ -0,0 +1,22 @@
1
+ # To change this template, choose Tools | Templates
2
+ # and open the template in the editor.
3
+
4
+ $:.unshift File.join(File.dirname(__FILE__),'..','lib')
5
+
6
+ require 'test/unit'
7
+ require 'quick_scrapper'
8
+
9
+ class QuickScrapperTest < Test::Unit::TestCase
10
+ def test_tag_selector
11
+ assert_equal "Google", scrap("http://www.google.co.in/", "title")
12
+ end
13
+
14
+ def test_css_selector
15
+ assert_equal "Web", scrap("http://www.google.co.in/", "html body div#mngb div#gog div#gbar nobr a#gb_1.gb1")
16
+ end
17
+
18
+ private
19
+ def scrap(url, selector)
20
+ QuickScrapper.scrap(url, selector)
21
+ end
22
+ end
metadata ADDED
@@ -0,0 +1,80 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: quick_scrapper
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
+ - Satyaram B V
13
+ autorequire:
14
+ bindir: bin
15
+ cert_chain: []
16
+
17
+ date: 2011-03-27 00:00:00 +05:30
18
+ default_executable:
19
+ dependencies:
20
+ - !ruby/object:Gem::Dependency
21
+ name: scrapi
22
+ prerelease: false
23
+ requirement: &id001 !ruby/object:Gem::Requirement
24
+ requirements:
25
+ - - ">="
26
+ - !ruby/object:Gem::Version
27
+ segments:
28
+ - 0
29
+ version: "0"
30
+ type: :runtime
31
+ version_requirements: *id001
32
+ description: Quickly scraps a selection in a page
33
+ email:
34
+ - bvsatyaram AT gmail DOT com
35
+ executables: []
36
+
37
+ extensions: []
38
+
39
+ extra_rdoc_files: []
40
+
41
+ files:
42
+ - .gitignore
43
+ - Gemfile
44
+ - Rakefile
45
+ - lib/quick_scrapper.rb
46
+ - lib/quick_scrapper/version.rb
47
+ - quick_scrapper.gemspec
48
+ - test/quick_scrapper_test.rb
49
+ has_rdoc: true
50
+ homepage: http://bvsatyaram.com
51
+ licenses: []
52
+
53
+ post_install_message:
54
+ rdoc_options: []
55
+
56
+ require_paths:
57
+ - lib
58
+ required_ruby_version: !ruby/object:Gem::Requirement
59
+ requirements:
60
+ - - ">="
61
+ - !ruby/object:Gem::Version
62
+ segments:
63
+ - 0
64
+ version: "0"
65
+ required_rubygems_version: !ruby/object:Gem::Requirement
66
+ requirements:
67
+ - - ">="
68
+ - !ruby/object:Gem::Version
69
+ segments:
70
+ - 0
71
+ version: "0"
72
+ requirements: []
73
+
74
+ rubyforge_project: quick_scrapper
75
+ rubygems_version: 1.3.6
76
+ signing_key:
77
+ specification_version: 3
78
+ summary: Quickly scraps a selection in a page
79
+ test_files: []
80
+