omelete 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/omelete/detailed_page.rb +89 -0
- data/lib/omelete/main_page.rb +54 -0
- data/lib/omelete/models/movie.rb +21 -0
- data/lib/omelete/models/showtime.rb +15 -0
- data/lib/omelete/version.rb +3 -0
- data/lib/omelete.rb +21 -0
- metadata +147 -0
@@ -0,0 +1,89 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
#!/usr/bin/env ruby
|
3
|
+
$:.unshift File.expand_path('../models', __FILE__)
|
4
|
+
require 'rubygems'
|
5
|
+
require 'open-uri'
|
6
|
+
require 'nokogiri'
|
7
|
+
require 'mechanize'
|
8
|
+
require 'movie'
|
9
|
+
require 'showtime'
|
10
|
+
|
11
|
+
module Omelete
|
12
|
+
class DetailedPage
|
13
|
+
|
14
|
+
def self.movie_poi(movie,link,page)
|
15
|
+
@page = page.link_with(:href => link).click
|
16
|
+
movie.movie_theaters = movie_theaters(movie) unless @page.search('//div[@class = "programacao_cinema"]').first.nil?
|
17
|
+
movie.showtimes = showtimes(movie) unless @page.search('//div[@class = "programacao_cinema"]').first.nil?
|
18
|
+
movie.synopsis = synopsis(movie) unless @page.search("//div[@id = \"tab_#{movie.id}_sinopse\"]/blockquote").first.nil?
|
19
|
+
unless @page.search("//div[@id = \"tab_#{movie.id}_ficha\"]/dl/dd").first.nil?
|
20
|
+
movie.cast = cast(movie)
|
21
|
+
movie.directed_by = directed_by(movie)
|
22
|
+
end
|
23
|
+
movie
|
24
|
+
end
|
25
|
+
|
26
|
+
def self.movie_theaters(movie)
|
27
|
+
movie_theaters = []
|
28
|
+
@page.search('//div[@class = "programacao_cinema"]/h2/a').each do |movie_theater|
|
29
|
+
movie_theaters << movie_theater.content
|
30
|
+
end
|
31
|
+
movie_theaters
|
32
|
+
end
|
33
|
+
|
34
|
+
def self.showtimes(movie)
|
35
|
+
showtimes = []
|
36
|
+
@page.search('//div[@class = "programacao_cinema"]/h2/a').each do |movie_theater|
|
37
|
+
showtimes << ShowtimeAndTheater.create_showtime_with(@page,movie_theater.content,movie)
|
38
|
+
end
|
39
|
+
showtimes
|
40
|
+
end
|
41
|
+
|
42
|
+
|
43
|
+
def self.synopsis(movie)
|
44
|
+
@page.search("//div[@id = \"tab_#{movie.id}_sinopse\"]/blockquote").first.content
|
45
|
+
end
|
46
|
+
|
47
|
+
def self.cast(movie)
|
48
|
+
@page.search("//div[@id = \"tab_#{movie.id}_ficha\"]/dl/dd").first.content.delete("\r\n")
|
49
|
+
end
|
50
|
+
|
51
|
+
def self.directed_by(movie)
|
52
|
+
directed_by = ""
|
53
|
+
@page.search("//div[@id = \"tab_#{movie.id}_ficha\"]/dl").first.children.each do |child|
|
54
|
+
directed_by = child.content if child.node_name == "dd" && child.previous_element && child.previous_element.content == "Direção:"
|
55
|
+
end
|
56
|
+
directed_by.delete("\r\n")
|
57
|
+
end
|
58
|
+
|
59
|
+
end
|
60
|
+
|
61
|
+
class ShowtimeAndTheater
|
62
|
+
def self.create_showtime_with(page,movie_theater,movie)
|
63
|
+
@page = page
|
64
|
+
showtime = Showtime.new(nil,nil,nil,movie,nil,movie_theater)
|
65
|
+
showtime.time = time
|
66
|
+
showtime.theater = theater
|
67
|
+
showtime.kind = kind
|
68
|
+
showtime.obs = obs
|
69
|
+
showtime
|
70
|
+
end
|
71
|
+
|
72
|
+
def self.time
|
73
|
+
@page.search('//tr[@class = "even"]/td').last.content
|
74
|
+
end
|
75
|
+
|
76
|
+
def self.kind
|
77
|
+
@page.search('//tr[@class = "even"]/td').first.next_element.content
|
78
|
+
end
|
79
|
+
|
80
|
+
def self.theater
|
81
|
+
@page.search('//tr[@class = "even"]/td').first.content
|
82
|
+
end
|
83
|
+
|
84
|
+
def self.obs
|
85
|
+
@page.search('//td[@colspan = "3"]').first.content if @page.search('//td[@colspan = "3"]').first
|
86
|
+
end
|
87
|
+
|
88
|
+
end
|
89
|
+
end
|
@@ -0,0 +1,54 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
#!/usr/bin/env ruby
|
3
|
+
$:.unshift File.expand_path('../', __FILE__)
|
4
|
+
$:.unshift File.expand_path('../models', __FILE__)
|
5
|
+
require 'rubygems'
|
6
|
+
require 'open-uri'
|
7
|
+
require 'nokogiri'
|
8
|
+
require 'mechanize'
|
9
|
+
require 'movie'
|
10
|
+
require 'detailed_page'
|
11
|
+
|
12
|
+
module Omelete
|
13
|
+
class MainPage
|
14
|
+
URL = "http://omelete.uol.com.br/filmes-em-cartaz"
|
15
|
+
|
16
|
+
def initialize(state,city)
|
17
|
+
@state=state
|
18
|
+
@city=city
|
19
|
+
@agent = Mechanize.new {|agent| agent.user_agent_alias = 'Mac Safari'}
|
20
|
+
end
|
21
|
+
|
22
|
+
def movies
|
23
|
+
@movies = []
|
24
|
+
@agent.get(URL + "?uf=#{@state}&cidade=#{@city}&filme=&filme_id=") do |page|
|
25
|
+
page.search('//div[@style = "margin-right: 38%;"]/h2').each do |movie_status|
|
26
|
+
movie_status.search('//div[@class = "programacao_filme"]').each do |movie_doc|
|
27
|
+
status = movie_status.content.delete("\n").strip
|
28
|
+
@movies << create_movie_with(movie_doc,status,page)
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
@movies
|
33
|
+
end
|
34
|
+
|
35
|
+
def create_movie_with(movie_doc,status,page)
|
36
|
+
name = movie_doc.search('h2').first.search('a').first.content.strip
|
37
|
+
info = movie_doc.search('h4').first.content.strip.split('-')
|
38
|
+
genre = info[0]
|
39
|
+
runtime = info[1]
|
40
|
+
age_rating = info[2]
|
41
|
+
link = movie_doc.search('p').first.search('a').first.attr('href')
|
42
|
+
id = id_from(link)
|
43
|
+
image = movie_doc.search('div').first.search('a').first.attr('href').strip unless movie_doc.search('div').first.search('a').first.nil?
|
44
|
+
|
45
|
+
movie = Movie.new(id,name,status,runtime,nil,genre,nil,age_rating,nil,nil,image)
|
46
|
+
complete_movie = DetailedPage.movie_poi(movie,link,page)
|
47
|
+
end
|
48
|
+
|
49
|
+
def id_from(link)
|
50
|
+
link.match(/\d+/)[0]
|
51
|
+
end
|
52
|
+
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
module Omelete
|
2
|
+
class Movie
|
3
|
+
|
4
|
+
attr_accessor :id, :name, :status, :runtime, :cast, :genre, :directed_by
|
5
|
+
attr_accessor :age_rating, :synopsis, :image, :movie_theaters, :showtimes
|
6
|
+
|
7
|
+
def initialize(id, name, status, runtime, cast, genre, directed_by, age_rating, synopsis, image, movie_theaters=[], showtimes=[])
|
8
|
+
@id = id
|
9
|
+
@name = name
|
10
|
+
@status = status
|
11
|
+
@runtime = runtime
|
12
|
+
@cast = cast
|
13
|
+
@genre = genre
|
14
|
+
@directed_by = directed_by
|
15
|
+
@age_rating = age_rating
|
16
|
+
@synopsis = synopsis
|
17
|
+
@image = image
|
18
|
+
@movie_theaters = movie_theaters
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,15 @@
|
|
1
|
+
module Omelete
|
2
|
+
class Showtime
|
3
|
+
|
4
|
+
attr_accessor :time, :obs, :movie, :theater, :kind
|
5
|
+
|
6
|
+
def initialize(time, obs, kind, movie, theater, movie_theater)
|
7
|
+
@time = time
|
8
|
+
@obs = obs
|
9
|
+
@kind = kind
|
10
|
+
@movie = movie
|
11
|
+
@theater = theater
|
12
|
+
@movie_theater = movie_theater
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
data/lib/omelete.rb
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'open-uri'
|
4
|
+
|
5
|
+
|
6
|
+
module Omelete
|
7
|
+
|
8
|
+
class Client
|
9
|
+
|
10
|
+
def initialize(state,city)
|
11
|
+
@state=state
|
12
|
+
@city=city
|
13
|
+
@main_page = MainPage.new(state,city)
|
14
|
+
end
|
15
|
+
|
16
|
+
def movies
|
17
|
+
@main_page.movies
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
21
|
+
end
|
metadata
ADDED
@@ -0,0 +1,147 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: omelete
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Mauricio Voto
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-05-06 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rspec
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '2.7'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '2.7'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: nokogiri
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :development
|
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: mechanize
|
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
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: vcr
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :development
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
- !ruby/object:Gem::Dependency
|
79
|
+
name: webmock
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - '='
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: 1.8.0
|
86
|
+
type: :development
|
87
|
+
prerelease: false
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
89
|
+
none: false
|
90
|
+
requirements:
|
91
|
+
- - '='
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: 1.8.0
|
94
|
+
- !ruby/object:Gem::Dependency
|
95
|
+
name: rake
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
97
|
+
none: false
|
98
|
+
requirements:
|
99
|
+
- - ! '>='
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
type: :development
|
103
|
+
prerelease: false
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
105
|
+
none: false
|
106
|
+
requirements:
|
107
|
+
- - ! '>='
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
110
|
+
description: Ruby web crawler to access omelete informations
|
111
|
+
email:
|
112
|
+
- mauriciovoto@gmail.com
|
113
|
+
executables: []
|
114
|
+
extensions: []
|
115
|
+
extra_rdoc_files: []
|
116
|
+
files:
|
117
|
+
- lib/omelete/detailed_page.rb
|
118
|
+
- lib/omelete/main_page.rb
|
119
|
+
- lib/omelete/models/movie.rb
|
120
|
+
- lib/omelete/models/showtime.rb
|
121
|
+
- lib/omelete/version.rb
|
122
|
+
- lib/omelete.rb
|
123
|
+
homepage: ''
|
124
|
+
licenses: []
|
125
|
+
post_install_message:
|
126
|
+
rdoc_options: []
|
127
|
+
require_paths:
|
128
|
+
- lib
|
129
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
130
|
+
none: false
|
131
|
+
requirements:
|
132
|
+
- - ! '>='
|
133
|
+
- !ruby/object:Gem::Version
|
134
|
+
version: '0'
|
135
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
136
|
+
none: false
|
137
|
+
requirements:
|
138
|
+
- - ! '>='
|
139
|
+
- !ruby/object:Gem::Version
|
140
|
+
version: '0'
|
141
|
+
requirements: []
|
142
|
+
rubyforge_project:
|
143
|
+
rubygems_version: 1.8.23
|
144
|
+
signing_key:
|
145
|
+
specification_version: 3
|
146
|
+
summary: Ruby web crawler to access omelete informations
|
147
|
+
test_files: []
|