lobbyliste 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1e86dd5685124c61635591609e624a896545ba97
-  data.tar.gz: c2bdca53a150b9a9d927d72e393dba7e6ddedde3
+  metadata.gz: 760a270ddbd57ea8ccf471e37383f550f1abbd7d
+  data.tar.gz: 2da7a0cce32f6e6defde7c69ea937052c84dc770
 SHA512:
-  metadata.gz: 1fc5c3473db62e0a230d0b1bd07d7022766052d87445178183494ea98c768b86bc71b9d446b23f0557791fb88a2403986e228d5571fc4ae3b2daff2be74ac941
-  data.tar.gz: 06afc4ba373e8710ff511fba0efd728b5f1706587b1973af4bea0c17e10e292187a88254945600970a437c82529dc992c7bef64291e80a516a58c9a551ac4b4f
+  metadata.gz: dacbb13d833b08291962f514da796039e74949737597ab02ff8f53080fe5343e262423696782827cd2d99544d577ab085d3dee548c177d32499bde63026fadea
+  data.tar.gz: cc9fa586a5ec1b7cdea7b5c4b7dcfb2ed238254cf6fbdf3d551991df0c06c8fa2cc1e242decc1ef455fe87767bc9376609014b720df62c11d18fa04793de563f

data/bin/lobbyliste

@@ -2,6 +2,22 @@
 
 require "bundler/setup"
 require "lobbyliste"
+require 'optparse'
 
-list = Lobbyliste.fetch_and_parse
+$url = nil
+
+OptionParser.new do |opts|
+  opts.banner = "Usage: lobbyliste [options]"
+
+  opts.on("-u","--url URL","Specify link to Lobbyliste pdf") do |url|
+   $url = url
+  end
+
+  opts.on("-h", "--help", "Prints this help") do
+      puts opts
+      exit
+  end
+end.parse!
+
+list = Lobbyliste.fetch_and_parse($url)
 puts list.to_json

data/lib/lobbyliste/downloader.rb

@@ -6,6 +6,12 @@ module Lobbyliste
   # This class finds the lobbyliste pdf on the Bundestag website, downloads it and extracts the pdf content
   class Downloader
 
+    # Creates a new Downloader
+    # @param [String] link that will be used to fetch the lobbylist pdf, defaults to nil
+    def initialize(pdf_link=nil)
+      @pdf_link = pdf_link
+    end
+
     # @return [String] raw content of pdf file
     def pdf_data
       retrieve_pdf unless @pdf_data
@@ -25,18 +31,25 @@ module Lobbyliste
       @html_data
     end
 
+    # @return [String] link to Lobbyliste pdf
+    def pdf_link
+      fetch_pdf_link unless @pdf_link
+      @pdf_link
+    end
+
     private
 
     # Since this link changes with every new version we download the Lobbyliste website and try to extract the link
     # @return [String] the link to the Lobbyliste pdf
-    def pdf_link
+    def fetch_pdf_link
       website = Nokogiri::HTML(open("https://www.bundestag.de/dokumente/lobbyliste"))
       link = website.css(".inhalt a[title^='Aktuelle Fassung']").first
 
       raise "Could no find PDF link on the website!" unless link
-      "https://bundestag.de#{link['href']}"
+      @pdf_link = "https://bundestag.de#{link['href']}"
     end
 
+
     def retrieve_pdf
       @pdf_data = open(pdf_link) {|f| f.read}
     end

data/lib/lobbyliste/factories/person_factory.rb

@@ -33,7 +33,7 @@ module Lobbyliste
       # @return [Lobbylist::Person] builds a new person, might be nil if the line does not represent a person
       def self.build(raw_data)
         factory = new(raw_data)
-        factory.is_person? ? ::Lobbyliste::Person.new(factory.name,factory.titles) : nil
+        factory.is_person? ? ::Lobbyliste::Person.new(factory.name,factory.titles,raw_data) : nil
       end
 
       def initialize(raw_data)

data/lib/lobbyliste/person.rb

@@ -8,13 +8,17 @@ module Lobbyliste
     # @return [Array] list of all titles (job, academic, positions)
     attr_reader :titles
 
-    def initialize(name, titles)
+    # @return [String] the original name with titles as stated in the document
+    attr_reader :original_name
+
+    def initialize(name, titles, original_name)
       @name = name
       @titles = titles
+      @original_name = original_name
     end
 
     def ==(other)
-      name==other.name && titles==other.titles
+      original_name==other.original_name
     end
 
     def to_json(*a)

data/lib/lobbyliste/version.rb

@@ -1,3 +1,3 @@
 module Lobbyliste
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

data/lib/lobbyliste.rb

@@ -11,9 +11,10 @@ require 'json'
 module Lobbyliste
 
   # Download the PDF and parse it
+  # @param [String] link to Lobbyliste pdf, if left out pdf link is retrieved automatically from Bundestag website
   # @return [Lobbyliste::Liste]
-  def self.fetch_and_parse
-    downloader = Lobbyliste::Downloader.new
+  def self.fetch_and_parse(pdf_link=nil)
+    downloader = Lobbyliste::Downloader.new(pdf_link)
     Lobbyliste::Factories::ListFactory.build(downloader.text_data,downloader.html_data)
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: lobbyliste
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - DarthMax
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-06-29 00:00:00.000000000 Z
+date: 2016-06-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri