bootleg 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
@@ -0,0 +1,17 @@
1
+ *.gem
2
+ *.rbc
3
+ .bundle
4
+ .config
5
+ .yardoc
6
+ Gemfile.lock
7
+ InstalledFiles
8
+ _yardoc
9
+ coverage
10
+ doc/
11
+ lib/bundler/man
12
+ pkg
13
+ rdoc
14
+ spec/reports
15
+ test/tmp
16
+ test/version_tmp
17
+ tmp
data/Gemfile ADDED
@@ -0,0 +1,8 @@
1
+ source 'https://rubygems.org'
2
+
3
+ gem 'nokogiri'
4
+ gem 'mechanize'
5
+
6
+ # Specify your gem's dependencies in bootleg.gemspec
7
+
8
+ gemspec
@@ -0,0 +1,22 @@
1
+ Copyright (c) 2012 Marius Lucian Pop
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.
@@ -0,0 +1,29 @@
1
+ # Bootleg
2
+
3
+ TODO: Write a gem description
4
+
5
+ ## Installation
6
+
7
+ Add this line to your application's Gemfile:
8
+
9
+ gem 'bootleg'
10
+
11
+ And then execute:
12
+
13
+ $ bundle
14
+
15
+ Or install it yourself as:
16
+
17
+ $ gem install bootleg
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 'Add some feature'`)
28
+ 4. Push to the branch (`git push origin my-new-feature`)
29
+ 5. Create new Pull Request
@@ -0,0 +1,3 @@
1
+ == Bootleg - moviefone scraper
2
+
3
+ This is a gem in development. It's purpose is to scrape theaters, movies, showtimes and other details from moviefone.com .
@@ -0,0 +1 @@
1
+ require "bundler/gem_tasks"
@@ -0,0 +1,23 @@
1
+ # -*- encoding: utf-8 -*-
2
+ lib = File.expand_path('../lib', __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require 'bootleg/version'
5
+
6
+ Gem::Specification.new do |gem|
7
+ gem.name = "bootleg"
8
+ gem.version = Bootleg::VERSION
9
+ gem.authors = ["Marius L. Pop"]
10
+ gem.email = ["marius@mlpinit.com"]
11
+ gem.description = %q{ Scraping theaters, movies, showtimes and other relevant data from movifone.com}
12
+ gem.summary = %q{ ...comming soon...}
13
+ gem.homepage = ""
14
+
15
+ gem.files = `git ls-files`.split($/)
16
+ gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
17
+ gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
18
+ gem.require_paths = ["lib"]
19
+
20
+ gem.add_dependency "nokogiri"
21
+ gem.add_dependency "mechanize"
22
+ gem.add_development_dependency "rspec"
23
+ end
@@ -0,0 +1,5 @@
1
+ require "bootleg/version"
2
+
3
+ module Bootleg
4
+ # Your code goes here...
5
+ end
@@ -0,0 +1,3 @@
1
+ module Bootleg
2
+ VERSION = "0.0.1"
3
+ end
@@ -0,0 +1,30 @@
1
+ require 'mechanize'
2
+ require 'nokogiri'
3
+ require 'open-uri'
4
+ require_relative 'finder'
5
+ require_relative 'modules/theater'
6
+
7
+ class Extractor
8
+
9
+ attr_reader :page_theaters
10
+
11
+ def initialize(page)
12
+ @page = (Nokogiri::HTML(open(page)))
13
+ @page_theaters = []
14
+ extract_movies
15
+ end
16
+
17
+ def extract_movies
18
+ theaters.each do |theater|
19
+ theater.extend Theater
20
+ theater_info = { name: theater.name, href: theater.link, movies: theater.movies}
21
+ @page_theaters << theater_info
22
+ end
23
+ end
24
+
25
+ private
26
+
27
+ def theaters
28
+ @page.css('div.theater')
29
+ end
30
+ end
@@ -0,0 +1,14 @@
1
+ require_relative 'modules/zipcode'
2
+ require_relative 'modules/href'
3
+
4
+ class Finder
5
+ def initialize(zipcode = '20906')
6
+ zipcode.extend Zipcode
7
+ @href = zipcode.search
8
+ end
9
+
10
+ def hrefs
11
+ @href.extend Href
12
+ @href.all
13
+ end
14
+ end
@@ -0,0 +1,21 @@
1
+ require_relative 'finder'
2
+ require_relative 'extractor'
3
+
4
+ class Manager
5
+ def initialize(zipcode)
6
+ @zipcode = zipcode
7
+ @pages ||= find_pages
8
+ @all_theaters = []
9
+ end
10
+
11
+ def find_pages
12
+ Finder.new(@zipcode).hrefs
13
+ end
14
+
15
+ def extract_theaters
16
+ @pages.each do |page|
17
+ @all_theaters << Extractor.new(page).page_theaters
18
+ end
19
+ @all_theaters.flatten
20
+ end
21
+ end
@@ -0,0 +1,18 @@
1
+ module Href
2
+ def all
3
+ pages = []
4
+ count.times { |nr| pages << url + nr.to_s }
5
+ pages
6
+ end
7
+
8
+ private
9
+
10
+ def count
11
+ self.links.select { |link| link.text.size < 3 and link.text =~ /\d/ }.last.text.to_i
12
+ end
13
+
14
+ def url
15
+ self.uri.to_s + '?page='
16
+ end
17
+ end
18
+
@@ -0,0 +1,22 @@
1
+ module Movie
2
+ def details
3
+ self.css('div.movietitle')
4
+ end
5
+
6
+ def name
7
+ details.css('a').text.strip
8
+ end
9
+
10
+ def link
11
+ "http://www.moviefone.com" + details.css('a').attribute('href').value
12
+ end
13
+
14
+ def showtimes
15
+ values = []
16
+ showtimes = self.css('a.gt').empty? ? self.css('span.stDisplay') : self.css('a.gt')
17
+ showtimes.each do |time|
18
+ values << time.text
19
+ end
20
+ values
21
+ end
22
+ end
@@ -0,0 +1,26 @@
1
+ require_relative 'movie'
2
+
3
+ module Theater
4
+ def details
5
+ self.css('h3.title').css('a')
6
+ end
7
+
8
+ def name
9
+ details.text.strip
10
+ end
11
+
12
+ def link
13
+ details.attribute('href').value
14
+ end
15
+
16
+ def movies
17
+ movies = self.css('div.movie-listing.first')
18
+ values = []
19
+ movies.each do |movie|
20
+ movie.extend Movie
21
+ movie_info = { name: movie.name, href: movie.link, showtimes: movie.showtimes }
22
+ values << movie_info
23
+ end
24
+ values
25
+ end
26
+ end
@@ -0,0 +1,12 @@
1
+ require 'mechanize'
2
+
3
+ module Zipcode
4
+ def search
5
+ agent = Mechanize.new
6
+ page = agent.get("http://www.moviefone.com")
7
+ search_form = page.form_with id: 'frm-search'
8
+ search_form.fields[1].value = self
9
+ agent.submit search_form
10
+ end
11
+ end
12
+
@@ -0,0 +1,8 @@
1
+ require_relative 'manager'
2
+ class Presenter
3
+ attr_reader :theaters
4
+
5
+ def initialize(zipcode)
6
+ @theaters ||= Manager.new(zipcode).extract_theaters
7
+ end
8
+ end
metadata ADDED
@@ -0,0 +1,111 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: bootleg
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ prerelease:
6
+ platform: ruby
7
+ authors:
8
+ - Marius L. Pop
9
+ autorequire:
10
+ bindir: bin
11
+ cert_chain: []
12
+ date: 2012-11-08 00:00:00.000000000 Z
13
+ dependencies:
14
+ - !ruby/object:Gem::Dependency
15
+ name: nokogiri
16
+ requirement: !ruby/object:Gem::Requirement
17
+ none: false
18
+ requirements:
19
+ - - ! '>='
20
+ - !ruby/object:Gem::Version
21
+ version: '0'
22
+ type: :runtime
23
+ prerelease: false
24
+ version_requirements: !ruby/object:Gem::Requirement
25
+ none: false
26
+ requirements:
27
+ - - ! '>='
28
+ - !ruby/object:Gem::Version
29
+ version: '0'
30
+ - !ruby/object:Gem::Dependency
31
+ name: mechanize
32
+ requirement: !ruby/object:Gem::Requirement
33
+ none: false
34
+ requirements:
35
+ - - ! '>='
36
+ - !ruby/object:Gem::Version
37
+ version: '0'
38
+ type: :runtime
39
+ prerelease: false
40
+ version_requirements: !ruby/object:Gem::Requirement
41
+ none: false
42
+ requirements:
43
+ - - ! '>='
44
+ - !ruby/object:Gem::Version
45
+ version: '0'
46
+ - !ruby/object:Gem::Dependency
47
+ name: rspec
48
+ requirement: !ruby/object:Gem::Requirement
49
+ none: false
50
+ requirements:
51
+ - - ! '>='
52
+ - !ruby/object:Gem::Version
53
+ version: '0'
54
+ type: :development
55
+ prerelease: false
56
+ version_requirements: !ruby/object:Gem::Requirement
57
+ none: false
58
+ requirements:
59
+ - - ! '>='
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ description: ! ' Scraping theaters, movies, showtimes and other relevant data from
63
+ movifone.com'
64
+ email:
65
+ - marius@mlpinit.com
66
+ executables: []
67
+ extensions: []
68
+ extra_rdoc_files: []
69
+ files:
70
+ - .gitignore
71
+ - Gemfile
72
+ - LICENSE.txt
73
+ - README.md
74
+ - README.rdoc
75
+ - Rakefile
76
+ - bootleg.gemspec
77
+ - lib/bootleg.rb
78
+ - lib/bootleg/version.rb
79
+ - lib/extractor.rb
80
+ - lib/finder.rb
81
+ - lib/manager.rb
82
+ - lib/modules/href.rb
83
+ - lib/modules/movie.rb
84
+ - lib/modules/theater.rb
85
+ - lib/modules/zipcode.rb
86
+ - lib/presenter.rb
87
+ homepage: ''
88
+ licenses: []
89
+ post_install_message:
90
+ rdoc_options: []
91
+ require_paths:
92
+ - lib
93
+ required_ruby_version: !ruby/object:Gem::Requirement
94
+ none: false
95
+ requirements:
96
+ - - ! '>='
97
+ - !ruby/object:Gem::Version
98
+ version: '0'
99
+ required_rubygems_version: !ruby/object:Gem::Requirement
100
+ none: false
101
+ requirements:
102
+ - - ! '>='
103
+ - !ruby/object:Gem::Version
104
+ version: '0'
105
+ requirements: []
106
+ rubyforge_project:
107
+ rubygems_version: 1.8.24
108
+ signing_key:
109
+ specification_version: 3
110
+ summary: ! '...comming soon...'
111
+ test_files: []