amtrak 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 893ffef1c08c1763b3a34c0f70d9dd303f89385f
+  data.tar.gz: c2e940a65b8bf344359b2ca25a15b0c853776c3a
+SHA512:
+  metadata.gz: f98144098bbe5944ababe3817acc7713a838279dc63b1a9cacf5af17a34584faaf879c8ebce826a462867ddab44bce7fb5db5e1fca9ad4acce5ad05a60edf442
+  data.tar.gz: 42ce40b14aeb3341e0d46e20512b2275fb80e02d51cdf03ff475314974084db1190244c340f79cf6c175add675cc2d261e0d3a28bf1cd6249008c109cc10dd84

data/.gitignore

@@ -0,0 +1,2 @@
+Gemfile.lock
+coverage

data/.rubocop.yml

@@ -0,0 +1,6 @@
+Lint/AssignmentInCondition:
+  Enabled: false
+Metrics/MethodLength:
+  Max: 12
+Metrics/LineLength:
+  Max: 100

data/.travis.yml

@@ -0,0 +1,5 @@
+language: ruby
+rvm:
+    - 2.0.0
+    - 2.1.1
+script: bundle exec rake

data/Gemfile

@@ -0,0 +1,3 @@
+source 'https://rubygems.org'
+
+gemspec

data/README.markdown

@@ -0,0 +1,3 @@
+# Amtrak
+
+Pulls down the train times from the Amtrak website

data/Rakefile

@@ -0,0 +1,23 @@
+require 'rake'
+
+default_tasks = []
+
+begin
+  require 'rubocop/rake_task'
+  RuboCop::RakeTask.new(:rubocop) do |task|
+    task.patterns = ['lib/**/*.rb','spec/**/*.rb']
+  end
+
+  default_tasks << :rubocop
+rescue LoadError
+end
+
+begin
+  require 'rspec/core/rake_task'
+  RSpec::Core::RakeTask.new(:spec)
+
+  default_tasks << :spec
+rescue LoadError
+end
+
+task default: default_tasks

data/amtrak.gemspec

@@ -0,0 +1,29 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'amtrak/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'amtrak'
+  spec.version       = Amtrak::Version::VERSION
+  spec.authors       = ['Todd Lunter']
+  spec.email         = ['tlunter@gmail.com']
+  spec.description   = %q{Scrape train times from Amtrak.com}
+  spec.summary       = %q{Scrape train times from Amtrak.com}
+  spec.homepage      = 'https://github.com/tlunter/amtrak_gem'
+  spec.license       = 'MIT'
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%{^bin/_}) { File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'excon', '~> 0.41.0'
+  spec.add_dependency 'nokogiri', '~> 1.6.4'
+
+  spec.add_development_dependency 'rake'
+  spec.add_development_dependency 'pry'
+  spec.add_development_dependency 'rspec', '~> 3.0.0'
+  spec.add_development_dependency 'rubocop', '~> 0.25.0'
+  spec.add_development_dependency 'simplecov', '~> 0.8.2'
+  spec.add_development_dependency 'vcr', '~> 2.9.2'
+end

data/lib/amtrak.rb

@@ -0,0 +1,14 @@
+# Main Amtrak module
+module Amtrak
+  class Error < StandardError; end
+
+  def self.get(from, to, date: nil)
+    Amtrak::TrainFetcher.get(from, to, date: date).map do |html|
+      Amtrak::TrainParser.parse(html)
+    end.flatten
+  end
+end
+
+require 'amtrak/train_parser'
+require 'amtrak/train_fetcher'
+require 'amtrak/version'

data/lib/amtrak/train_fetcher.rb

@@ -0,0 +1,39 @@
+module Amtrak
+  # Service for getting train time HTML page from the Amtrak website
+  class TrainFetcher
+    class Error < Amtrak::Error; end
+
+    def self.get(*args)
+      new(*args).get
+    end
+
+    attr_reader :from, :to, :date
+
+    def initialize(from, to, date: nil)
+      @from = from
+      @to = to
+      @date = date
+    end
+
+    def get
+      (1..total_pages).map do |page|
+        Amtrak::TrainFetcher::TrainPage.get(session_id, page)
+      end
+    end
+
+    def first_page
+      @first_page ||= Amtrak::TrainFetcher::MainPage.new(from, to, date: date)
+    end
+
+    def session_id
+      @session_id ||= first_page.session_id
+    end
+
+    def total_pages
+      @total_pages ||= first_page.total_pages
+    end
+  end
+end
+
+require 'amtrak/train_fetcher/main_page'
+require 'amtrak/train_fetcher/train_page'

data/lib/amtrak/train_fetcher/main_page.rb

@@ -0,0 +1,70 @@
+require 'excon'
+require 'date'
+
+module Amtrak
+  class TrainFetcher
+    # Service for getting train time results/cookies from the Amtrak website
+    class MainPage
+      attr_reader :from, :to
+
+      def initialize(from, to, date: nil)
+        @from = from
+        @to = to
+        @date = date
+      end
+
+      def page
+        @page ||= Excon.post(
+          'http://tickets.amtrak.com/itd/amtrak',
+          headers: headers,
+          body: URI.encode_www_form(body),
+          expects: [200]
+        )
+      rescue Excon::Errors::ClientError, Excon::Errors::ServerError => ex
+        raise Amtrak::TrainFetcher::Error, "#{ex.class} #{ex.message}"
+      end
+
+      def headers
+        { 'Content-Type' => 'application/x-www-form-urlencoded' }
+      end
+
+      # rubocop:disable all
+      def body
+        {
+          "_handler=amtrak.presentation.handler.request.rail.AmtrakRailTrainStatusSearchRequestHandler/_xpath=/sessionWorkflow/productWorkflow[@product='Rail']" => '',
+          "/sessionWorkflow/productWorkflow[@product='Rail']/tripRequirements/journeyRequirements[1]/departDate.date" => departure_date,
+          'requestor'        => 'amtrak.presentation.handler.page.rail.AmtrakRailGetTrainStatusPageHandler',
+          'xwdf_trainNumber' => "/sessionWorkflow/productWorkflow[@product='Rail']/tripRequirements/journeyRequirements[1]/segmentRequirements[1]/serviceCode",
+          'wdf_trainNumber'  => 'optional',
+          'xwdf_SortBy'      => "/sessionWorkflow/productWorkflow[@product='Rail']/tripRequirements/journeyRequirements[1]/departDate/@radioSelect",
+          'wdf_SortBy'       => 'arrivalTime',
+          'xwdf_origin'      => "/sessionWorkflow/productWorkflow[@product='Rail']/travelSelection/journeySelection[1]/departLocation/search",
+          'wdf_origin'       => from.to_s,
+          'xwdf_destination' => "/sessionWorkflow/productWorkflow[@product='Rail']/travelSelection/journeySelection[1]/arriveLocation/search",
+          'wdf_destination'  => to.to_s,
+        }
+      end
+      # rubocop:enable all
+
+      def departure_date
+        date.strftime('%a, %b %-d, %Y')
+      end
+
+      def date
+        @date ||= Date.today
+      end
+
+      def session_id
+        page.headers['Set-Cookie'].match(/JSESSIONID=([^;]*)/)[1]
+      end
+
+      def total_pages
+        (Float(extract_listing_length) / 10).ceil
+      end
+
+      def extract_listing_length
+        page.body.match(/var availabilityLength = '(\d+)';/)[1]
+      end
+    end
+  end
+end

data/lib/amtrak/train_fetcher/train_page.rb

@@ -0,0 +1,41 @@
+require 'excon'
+
+module Amtrak
+  class TrainFetcher
+    # Service for getting per page train time HTML from the Amtrak website
+    class TrainPage
+      def self.get(*args)
+        new(*args).get
+      end
+
+      attr_reader :session_id, :page
+
+      def initialize(session_id, page)
+        @session_id = session_id
+        @page = page
+      end
+
+      def get
+        request.body
+      end
+
+      def request
+        @request ||= Excon.get(
+          'https://tickets.amtrak.com/itd/amtrak/TrainStatusRequest',
+          headers: headers,
+          query: query
+        )
+      rescue Excon::Errors::ClientError, Excon::Errors::ServerError => ex
+        raise Amtrak::TrainFetcher::Error, "#{ex.class} #{ex.message}"
+      end
+
+      def headers
+        { 'Cookie' => "JSESSIONID=#{session_id}" }
+      end
+
+      def query
+        { '_trainstatuspage' => page }
+      end
+    end
+  end
+end

data/lib/amtrak/train_parser.rb

@@ -0,0 +1,90 @@
+require 'nokogiri'
+
+module Amtrak
+  # Will take in an HTML document as a string and parse out the train schedule
+  class TrainParser
+    # Error raised when the parser runs into an issue
+    class Error < Amtrak::Error; end
+
+    def self.parse(text)
+      new(text).parse
+    end
+
+    attr_reader :document
+
+    def initialize(document)
+      @document = Nokogiri::HTML.parse(document)
+    end
+
+    def parse
+      trains = []
+
+      until train_nodes.empty?
+        departure, arrival = train_nodes.shift(2)
+        trains << {
+          number: parse_train_number(departure),
+          departure: parse_train(departure),
+          arrival: parse_train(arrival)
+        }
+      end
+
+      trains
+    rescue Nokogiri::SyntaxError => ex
+      raise Amtrak::TrainParser::Error, "#{ex.class} #{ex.message}"
+    end
+
+    def train_nodes
+      @train_nodes ||= document.search(
+        "//tr[contains(@class, 'status_result')]"
+      ).tap { |results| fail 'No trains found' unless results.count > 0 }.to_a
+    end
+
+    def parse_train_number(node)
+      find!(
+        node, ".//th[@class='service']/div[@class='route_num']/text()"
+      ).to_s.to_i
+    end
+
+    def parse_train(node) # rubocop:disable Metrics/MethodLength
+      scheduled_date = find!(
+        node, ".//td[@class='scheduled']/div[@class='date']/text()"
+      ).to_s
+      estimated_date = find!(
+        node, ".//td[@class='act_est']/div[@class='date']/text()"
+      ).to_s
+      scheduled_time = remove_parentheses(
+        find!(node, ".//td[@class='scheduled']/div[@class='time']/text()").to_s
+      )
+      estimated_time = remove_parentheses(
+        find!(node, ".//td[@class='act_est']/div[@class='time']/text()").to_s
+      )
+
+      {
+        scheduled_date: scheduled_date,
+        estimated_date: estimated_date,
+        scheduled_time: scheduled_time,
+        estimated_time: estimated_time
+      }
+    end
+
+    def find!(node, xpath)
+      node.search(xpath).tap { |rs| fail "#{rs.count} results" if rs.count > 1 }
+    end
+
+    def make_datetime(date, time)
+      if date.nil? || time.nil?
+        return
+      else
+        DateTime.parse("#{date} at #{time}")
+      end
+    end
+
+    def remove_parentheses(time_string)
+      if matches = /\(([^)]+)\)/.match(time_string)
+        matches[1]
+      else
+        time_string
+      end
+    end
+  end
+end

data/lib/amtrak/version.rb

@@ -0,0 +1,6 @@
+module Amtrak
+  # This module holds the Amtrak version
+  module Version
+    VERSION = '0.0.1'
+  end
+end

data/spec/amtrak/train_fetcher/main_page_spec.rb

@@ -0,0 +1,75 @@
+require 'spec_helper'
+
+describe Amtrak::TrainFetcher::MainPage do
+  describe '#departure_date' do
+    subject { described_class.new('', '', date: date) }
+    let(:date) { Date.parse('2014-11-12') }
+
+    it 'prints out a formatted date' do
+      expect(subject.departure_date).to eq('Wed, Nov 12, 2014')
+    end
+  end
+
+  describe '#date' do
+    subject { described_class.new('', '', date: date) }
+
+    context 'on an instance with a date' do
+      let(:date) { Date.parse('2014-11-12') }
+
+      it 'returns the set date' do
+        expect(subject.date).to eq(date)
+      end
+    end
+
+    context 'on an instance without a date' do
+      let(:date) { nil }
+      let(:stubbed_date) { Date.parse('2014-11-12') }
+
+      it 'returns the current date' do
+        expect(Date).to receive(:today).and_return(stubbed_date)
+        expect(subject.date).to eq(stubbed_date)
+      end
+    end
+  end
+
+  describe '#total_pages' do
+    context 'when only one page exists on the website' do
+      subject { described_class.new('pvd', 'bby', date: Date.parse('2014-11-28')) }
+
+      it 'returns 1', :vcr do
+        expect(subject.total_pages).to eq(1)
+      end
+    end
+
+    context 'when more than one page exists on the website' do
+      subject { described_class.new('pvd', 'bby', date: Date.parse('2014-11-27')) }
+
+      it 'returns 2', :vcr do
+        expect(subject.total_pages).to eq(2)
+      end
+    end
+  end
+
+  describe '#session_id' do
+    subject { described_class.new('pvd', 'bby', date: Date.parse('2014-11-28')) }
+    it 'pulls the session id from the cookies', :vcr do
+      expect(subject.session_id).to eq('0000kOxPFtO4mDoSiIGk2yzvAz6:187j4dq9a')
+    end
+  end
+
+  describe '#page' do
+    context 'when Excon raises' do
+      subject { described_class.new('', '') }
+
+      it 'returns a TrainFetcher::Error' do
+        expect(Excon).to receive(:post) { fail Excon::Errors::ClientError, '' }
+        expect { subject.page }.to raise_error(Amtrak::TrainFetcher::Error)
+      end
+
+      it 'returns a TrainFetcher::Error' do
+        expect(Excon).to receive(:post) { fail Excon::Errors::ServerError, '' }
+        expect { subject.page }.to raise_error(Amtrak::TrainFetcher::Error)
+      end
+    end
+  end
+end

data/spec/amtrak/train_fetcher/train_page_spec.rb

@@ -0,0 +1,37 @@
+require 'spec_helper'
+
+describe Amtrak::TrainFetcher::TrainPage do
+  subject { described_class.get(session_id, page) }
+
+  describe '#get', :vcr do
+    context 'when it works' do
+      let(:session_id) { '0000ITjAiGUWm-mBBpAyeGZ43Rv:187j4ddrq' }
+      let(:page) { '1' }
+
+      it 'includes various classes' do
+        expect(subject).to include('route_num')
+        expect(subject).to include('scheduled')
+        expect(subject).to include('act_est')
+      end
+    end
+
+    context 'when Excon raises an error' do
+      let(:session_id) { '0000ITjAiGUWm-mBBpAyeGZ43Rv:187j4ddrq' }
+      let(:page) { '1' }
+
+      it 'reraises as a TrainFetcher::Error' do
+        expect(Excon).to receive(:get) {
+          fail Excon::Errors::ClientError, ''
+        }
+        expect { subject }.to raise_error(Amtrak::TrainFetcher::Error)
+      end
+
+      it 'reraises as a TrainFetcher::Error' do
+        expect(Excon).to receive(:get) {
+          fail Excon::Errors::ServerError, ''
+        }
+        expect { subject }.to raise_error(Amtrak::TrainFetcher::Error)
+      end
+    end
+  end
+end