floripa-public-transit 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: eb2a054575bd9efd39c453934430bff1791d5846
+  data.tar.gz: 929429e8988ba3a3ecfdc2ec4edb0b3fd5fe0fd0
+SHA512:
+  metadata.gz: 274957610cb4091355b5ccbff52fb161f048d850848c8ea832d117b21f4e7972041edd32de6dc1808fa241cabf2f0217e43f735a67348d1a67c8cbc813db1420
+  data.tar.gz: f4d37e3277ea024a9afb4737c6c294aeb23aa527f9b073c7f3cfaad321071cf5b796828fadfa0219ebfa51d39943e5ce95f10ac673588866a24d1bab949d5679

data/.bundle/config

@@ -0,0 +1,3 @@
+---
+BUNDLE_PATH: vendor/bundle
+BUNDLE_DISABLE_SHARED_GEMS: '1'

data/.gitignore

@@ -0,0 +1 @@
+/vendor/

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+gem 'nokogiri', '1.6.1'
+gem 'rspec'

data/Gemfile.lock

@@ -0,0 +1,22 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    diff-lcs (1.2.5)
+    mini_portile (0.5.3)
+    nokogiri (1.6.1)
+      mini_portile (~> 0.5.0)
+    rspec (2.14.1)
+      rspec-core (~> 2.14.0)
+      rspec-expectations (~> 2.14.0)
+      rspec-mocks (~> 2.14.0)
+    rspec-core (2.14.8)
+    rspec-expectations (2.14.5)
+      diff-lcs (>= 1.1.3, < 2.0)
+    rspec-mocks (2.14.6)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  nokogiri (= 1.6.1)
+  rspec

data/README.md

@@ -0,0 +1,18 @@
+# floripa-public-transit
+
+Ruby gem to fetch public transit information from the [Florianópolis Web Site](http://www.pmf.sc.gov.br/servicos/index.php?pagina=onibus&menu=2).
+
+To fetch information of a specific line:
+
+```ruby
+require 'floripa-public-transit'
+
+FloripaPublicTransit.fetch_line '177'
+```
+
+Where `177` in the number of the 'Santa Monica' bus line.
+
+## Authors
+
+* [Felipe Munhoz](https://github.com/fnmunhoz)
+* [Paulo Ragonha](https://github.com/pirelenito)

data/floripa-public-transit.gemspec

@@ -0,0 +1,19 @@
+Gem::Specification.new do |s|
+  s.name        = 'floripa-public-transit'
+  s.version     = '0.0.1'
+  s.date        = '2014-04-14'
+  s.summary     = 'Fetches public transit information from the Florianopolis city website'
+  s.description = 'Provides a simple API to fetch latest public transit information of the Florianopolis city'
+  s.authors     = ['Paulo Ragonha', 'Felipe Munhoz']
+  s.email       = ['paulo@ragonha.me', 'munhoz@gmail.com']
+
+  s.files       = `git ls-files`.split("\n")
+  s.test_files  = `git ls-files -- spec`.split("\n")
+  s.require_paths = ['lib']
+
+  s.homepage    = 'https://github.com/floripa-mobi/floripa-public-transit'
+  s.license     = 'MIT'
+
+  s.add_runtime_dependency 'nokogiri', '1.6.1'
+  s.add_development_dependency 'rspec', '2.14.1'
+end

data/lib/floripa-public-transit.rb

@@ -0,0 +1,27 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+
+
+require 'rubygems'
+require 'bundler/setup'
+
+
+require 'floripa/bus_list_crawler'
+require 'floripa/bus_crawler'
+
+
+module FloripaPublicTransit
+  def self.fetch_all
+    FloripaPublicTransit::BusListCrawler.new.fetch.map do |line_number|
+      FloripaPublicTransit::BusCrawler.new(line_number).fetch
+    end
+  end
+
+  def self.fetch_line(line_number)
+    FloripaPublicTransit::BusCrawler.new(line_number).fetch
+  end
+
+  def self.fetch_line_numbers
+    FloripaPublicTransit::BusListCrawler.new.fetch
+  end
+end

data/lib/floripa/bus_crawler.rb

@@ -0,0 +1,104 @@
+# encoding: UTF-8
+
+require 'nokogiri'
+require "net/http"
+require 'open-uri'
+require "uri"
+require 'json'
+
+
+module FloripaPublicTransit
+  Bus = Struct.new(:number, :name, :operator, :itinerary, :schedules)
+  Schedule = Struct.new(:period, :hours, :direction, :origin, :destination)
+
+  class BusCrawler
+    PERIODS = ['weekday', 'saturday', 'sunday']
+    GOING = '1'
+    RETURNING = '2'
+
+    def initialize(bus_line_number)
+      @bus_line_number = bus_line_number
+    end
+
+    def fetch
+      name = fetch_name()
+      operator = fetch_operator()
+      itinerary = fetch_itinerary()
+      schedule = fetch_schedule(itinerary)
+
+      Bus.new(bus_line_number, name, operator, itinerary, schedule)
+    end
+
+    private
+
+    attr_reader :bus_line_number
+
+    def fetch_name
+      request_data('1', 'iso8859-1').css('#titulo_pagina').first.content.gsub(/\(.+\)/, '').strip
+    end
+
+    def fetch_operator
+      request_data('1', 'iso8859-1').css('#cabecalho_onibus_linha h4').first.content.gsub('Empresa:', '').strip
+    end
+
+    def fetch_itinerary
+      data = request_data '3'
+
+      data.css('#conteudo_itinerario li').map do |address|
+        address.content.gsub('» ', '').strip
+      end
+    end
+
+    def fetch_schedule(itinerary)
+      going_schedule = fetch_hours(GOING, itinerary)
+      returning_schedule = fetch_hours(RETURNING, itinerary)
+
+      [going_schedule, returning_schedule].flatten.select do |schedule|
+        schedule.hours.length > 0
+      end
+    end
+
+    def fetch_hours(direction, itinerary)
+      data = request_data direction, 'iso8859-1'
+
+      if direction == GOING
+        targets = data.css('#conteudo_horaida b:first-child').first.content.scan(/([\w|\s]+)/).flatten.map &:strip
+        @origin = targets[0]
+        @destination = targets[1]
+      end
+
+      if !@origin || @origin && @origin.empty?
+        @origin = itinerary[direction == GOING ? 0 : itinerary.length-1]
+        @destination = itinerary[direction == GOING ? itinerary.length-1 : 0]
+      end
+
+      origin = direction == GOING ? @origin : @destination
+      destination = direction == GOING ? @destination : @origin
+
+      data.css('.conteudo_abas_ext tr:last-child td').map.with_index do |period, index|
+        hours = period.to_s.split('<br>').map do |hour|
+          match = hour.match(/(\d\d:\d\d)/)
+          match && match[0]
+        end.compact
+
+        Schedule.new(PERIODS[index], hours, direction == GOING ? 'going' : 'returning', origin, destination)
+      end
+    end
+
+    def request_data(direction, encoding = 'utf-8')
+      url = "http://www.pmf.sc.gov.br/servicos/index.php?pagina=onibuslinha&idLinha=#{bus_line_number}"
+      uri = URI.parse(url)
+
+      http = Net::HTTP.new(uri.host, uri.port)
+
+      request = Net::HTTP::Post.new(uri.request_uri)
+      request.set_form_data({ 'passoGeral' => direction })
+
+      response = http.request(request)
+
+      Nokogiri::HTML(response.body, nil, encoding)
+    end
+
+  end
+
+end

data/lib/floripa/bus_list_crawler.rb

@@ -0,0 +1,44 @@
+# encoding: UTF-8
+
+require 'nokogiri'
+require "net/http"
+require 'open-uri'
+require "uri"
+require 'json'
+
+
+module FloripaPublicTransit
+  class BusListCrawler
+    def fetch
+      [
+        *fetch_lines('1'),
+        *fetch_lines('2'),
+        *fetch_lines('3'),
+        *fetch_lines('4'),
+        *fetch_lines('5'),
+        *fetch_lines('6'),
+        *fetch_lines('9'),
+        *fetch_lines('10')
+      ]
+    end
+
+    private
+
+    def fetch_lines(company)
+      uri = URI.parse('http://www.pmf.sc.gov.br/servicos/index.php?pagina=onibus&menu=2')
+
+      http = Net::HTTP.new(uri.host, uri.port)
+
+      request = Net::HTTP::Post.new(uri.request_uri)
+      request.set_form_data({ 'passoGeral' => '1', 'passoEmpresa' => '1', 'empresa' => company, 'opcao' => '1' })
+
+      response = http.request(request)
+
+      doc = Nokogiri::HTML(response.body, nil, 'utf-8')
+
+      doc.css('ul.listagem a').collect do |link|
+        link[:href].split("idLinha=").last.split("&menu=2").first.strip
+      end
+    end
+  end
+end

data/spec/floripa/bus_crawler_spec.rb

@@ -0,0 +1,96 @@
+# encoding: UTF-8
+
+require 'spec_helper'
+
+describe "bus_crawler" do
+  describe "when fetching the data of a bus" do
+    subject { FloripaPublicTransit::BusCrawler.new('330').fetch }
+
+    it "should contain three different schedules" do
+      expect(subject.schedules.length).to eq 6
+    end
+
+    it "should have the periods" do
+      expect(subject.schedules[0].period).to eq 'weekday'
+      expect(subject.schedules[1].period).to eq 'saturday'
+      expect(subject.schedules[2].period).to eq 'sunday'
+      expect(subject.schedules[3].period).to eq 'weekday'
+      expect(subject.schedules[4].period).to eq 'saturday'
+      expect(subject.schedules[5].period).to eq 'sunday'
+    end
+
+    it "should have the hours" do
+      expect(subject.schedules[3].hours.length).to eq 47
+      expect(subject.schedules[4].hours.length).to eq 46
+      expect(subject.schedules[5].hours.length).to eq 35
+
+      expect(subject.schedules[0].hours[0]).to eq '05:32'
+      expect(subject.schedules[3].hours[0]).to eq '05:47'
+    end
+
+    it "should have the direction" do
+      expect(subject.schedules[0].direction).to eq 'going'
+      expect(subject.schedules[1].direction).to eq 'going'
+      expect(subject.schedules[2].direction).to eq 'going'
+      expect(subject.schedules[3].direction).to eq 'returning'
+      expect(subject.schedules[4].direction).to eq 'returning'
+      expect(subject.schedules[5].direction).to eq 'returning'
+    end
+
+    it "should have the origin and destination" do
+      expect(subject.schedules[0].origin).to eq 'TILAG'
+      expect(subject.schedules[0].destination).to eq 'TICEN'
+
+      expect(subject.schedules[3].origin).to eq 'TICEN'
+      expect(subject.schedules[3].destination).to eq 'TILAG'
+    end
+
+    it "should have the name of the bus" do
+      expect(subject.name).to eq('LAGOA DA CONCEIÇÃO')
+    end
+
+    it "should have the number" do
+      expect(subject.number).to eq('330')
+    end
+
+    it "should have the operator" do
+      expect(subject.operator).to eq('TRANSOL TRANSPORTE COLETIVO LTDA')
+    end
+
+    it "should have the itinerary" do
+      expected_itinerary = [
+        'TICEN',
+        'RUA PROCURADOR ABELARDO GOMES',
+        'AVENIDA PAULO FONTES',
+        'RUA DOUTOR ÁLVARO MILLEN DA SILVEIRA',
+        'RUA DOUTOR JORGE DA LUZ FONTES',
+        'RUA SILVA JARDIM',
+        'AVENIDA MAURO RAMOS',
+        'AVENIDA JORNALISTA RUBENS DE ARRUDA RAMOS',
+        'RUA COMANDANTE CONSTANTINO NICOLAU SPYRIDES',
+        'RUA DELMINDA SILVEIRA',
+        'RUA IDALINA PEREIRA DOS SANTOS',
+        'AVENIDA GOVERNADOR IRINEU BORNHAUSEN',
+        'AVENIDA DA SAUDADE',
+        'RODOVIA ADMAR GONZAGA',
+        'AVENIDA AFONSO DELAMBERT NETO',
+        'TILAG',
+        'TILAG',
+        'AVENIDA AFONSO DELAMBERT NETO',
+        'RODOVIA SC 404',
+        'ELEVADO DO ITACOROBI',
+        'AVENIDA DA SAUDADE',
+        'RUA DELMINDA SILVEIRA',
+        'RUA RUI BARBOSA',
+        'RUA FREI CANECA',
+        'RUA HEITOR LUZ',
+        'AVENIDA MAURO RAMOS',
+        'RUA SILVA JARDIM',
+        'AVENIDA GOVERNADOR GUSTAVO RICHARD',
+        'TICEN'
+      ]
+
+      expect(subject.itinerary).to eq expected_itinerary
+    end
+  end
+end

data/spec/floripa/bus_line_crawler_spec.rb

@@ -0,0 +1,16 @@
+# encoding: UTF-8
+
+require 'spec_helper'
+
+describe "bus_list_crawler" do
+  describe "when fetching the data of a lines" do
+    subject { FloripaPublicTransit::BusListCrawler.new.fetch }
+
+    it "should contain all bus line numbers" do
+      expect(subject.length).to eq 255
+      expect(subject).to include('330')
+      expect(subject).to include('320')
+      expect(subject).to include('D766')
+    end
+  end
+end

data/spec/floripa/edge_cases/bus_line_crawler_360_spec.rb

@@ -0,0 +1,13 @@
+# encoding: UTF-8
+
+require 'spec_helper'
+
+describe "bus_crawler" do
+  describe "when fetching the data of the 360 line" do
+    subject { FloripaPublicTransit::BusCrawler.new('360').fetch }
+
+    it "should work (was breaking because of encoding issues)" do
+      expect(subject.name).to eq 'BARRA DA LAGOA'
+    end
+  end
+end

data/spec/floripa/edge_cases/bus_m230_should_not_break.spec.rb

@@ -0,0 +1,13 @@
+# encoding: UTF-8
+
+require 'spec_helper'
+
+describe "bus_crawler" do
+  describe "when fetching the data of the M230 line" do
+    subject { FloripaPublicTransit::BusCrawler.new('M230').fetch }
+
+    it "should work (was breaking because of encoding issues)" do
+      expect(subject.number).to eq 'M230'
+    end
+  end
+end

data/spec/floripa/edge_cases/bus_operator_cooperbarco.spec.rb

@@ -0,0 +1,13 @@
+# encoding: UTF-8
+
+require 'spec_helper'
+
+describe "bus_crawler" do
+  describe "when fetching the data of a Cooperbarco operator" do
+    subject { FloripaPublicTransit::BusCrawler.new('10').fetch }
+
+    it "should work (was breaking because of encoding issues)" do
+      expect(subject.operator).to eq 'HIDROVIÁRIO COOPERBARCO'
+    end
+  end
+end

data/spec/floripa/edge_cases/bus_origin_and_destination_separated_with_a_slash.spec.rb

@@ -0,0 +1,14 @@
+# encoding: UTF-8
+
+require 'spec_helper'
+
+describe "bus_crawler" do
+  describe "when fetching the data of the a bus where the origin/destination separator is a slash (like the 276)" do
+    subject { FloripaPublicTransit::BusCrawler.new('276').fetch }
+
+    it "should have the origin and destination taken from the itinerary" do
+      expect(subject.schedules[0].origin).to eq 'TICAN'
+      expect(subject.schedules[0].destination).to eq 'TICAN'
+    end
+  end
+end

data/spec/floripa/edge_cases/bus_without_defined_origin_and_destination.spec.rb

@@ -0,0 +1,20 @@
+# encoding: UTF-8
+
+require 'spec_helper'
+
+describe "bus_crawler" do
+  describe "when fetching the data of the a bus without defined origin or destination (like the 177)" do
+    subject { FloripaPublicTransit::BusCrawler.new('177').fetch }
+
+    it "should have the origin and destination taken from the itinerary" do
+      expect(subject.schedules[0].origin).to eq 'TITRI'
+      expect(subject.schedules[0].destination).to eq 'TITRI'
+    end
+
+    it "should only have schedules defined that have hours" do
+      subject.schedules.each do |schedule|
+        expect(schedule.hours.length).not_to eq 0
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,25 @@
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+
+require 'rubygems'
+require 'bundler/setup'
+
+require 'floripa-public-transit'
+
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# Require this file using `require "spec_helper"` to ensure that it is only
+# loaded once.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = 'random'
+end

metadata

@@ -0,0 +1,101 @@
+--- !ruby/object:Gem::Specification
+name: floripa-public-transit
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Paulo Ragonha
+- Felipe Munhoz
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-04-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 1.6.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 1.6.1
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 2.14.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 2.14.1
+description: Provides a simple API to fetch latest public transit information of the
+  Florianopolis city
+email:
+- paulo@ragonha.me
+- munhoz@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".bundle/config"
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- Gemfile.lock
+- README.md
+- floripa-public-transit.gemspec
+- lib/floripa-public-transit.rb
+- lib/floripa/bus_crawler.rb
+- lib/floripa/bus_list_crawler.rb
+- spec/floripa/bus_crawler_spec.rb
+- spec/floripa/bus_line_crawler_spec.rb
+- spec/floripa/edge_cases/bus_line_crawler_360_spec.rb
+- spec/floripa/edge_cases/bus_m230_should_not_break.spec.rb
+- spec/floripa/edge_cases/bus_operator_cooperbarco.spec.rb
+- spec/floripa/edge_cases/bus_origin_and_destination_separated_with_a_slash.spec.rb
+- spec/floripa/edge_cases/bus_without_defined_origin_and_destination.spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/floripa-mobi/floripa-public-transit
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Fetches public transit information from the Florianopolis city website
+test_files:
+- spec/floripa/bus_crawler_spec.rb
+- spec/floripa/bus_line_crawler_spec.rb
+- spec/floripa/edge_cases/bus_line_crawler_360_spec.rb
+- spec/floripa/edge_cases/bus_m230_should_not_break.spec.rb
+- spec/floripa/edge_cases/bus_operator_cooperbarco.spec.rb
+- spec/floripa/edge_cases/bus_origin_and_destination_separated_with_a_slash.spec.rb
+- spec/floripa/edge_cases/bus_without_defined_origin_and_destination.spec.rb
+- spec/spec_helper.rb