tf2r 0.1.1 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 53baabcfbcb2844a14bd53e3e37a7d5d82d80894
-  data.tar.gz: 0085e3ec2ef5d5f51f1b5172cff907f5752a199f
+  metadata.gz: 4c5bd71115ed3cebd26737dc98ab7dcc23355253
+  data.tar.gz: 1eef157620f392d7f5247cc262eef47a02451fcd
 SHA512:
-  metadata.gz: 380c2b12de5cf17a5152f32aca08d0a7fc3962339abcb318a8e6669bcdb370f283c155a3dd6ad916fe888a8910415c1f8838fe76cb41b750b55410b85540987f
-  data.tar.gz: 0b3e807888dff2cff5501a132418d8bfefb6b19745b0647736ee64d3eaa366317b2ec476c20692908745f90d20bb0f9426b47bb5b60063a75e41d13139e6073b
+  metadata.gz: dab7f6734488422f90ca4defcd8af4f071eb6778a36f90551721b5a778bee9bb9e96f3b41d03f7126b42574b09274251efbcc3a7510277ceed2f95c339282d7b
+  data.tar.gz: e3755809104357d54bdfec5bc792565914d1e9c6ab230d0f349dcfb3cb54f51da60e4101b6c0820ad8abbebeeabe420bc6c5e2d68e2742660283046df7ad8c95

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    tf2r (0.1.1)
+    tf2r (0.2.0)
       mechanize (~> 2.7)
 
 GEM

data/lib/tf2r.rb

@@ -2,6 +2,7 @@ require 'mechanize'
 require 'pry'
 
 require 'tf2r/api'
+require 'tf2r/raffle'
 require 'tf2r/scraper'
 require 'tf2r/version'
 

data/lib/tf2r/api.rb

@@ -1,13 +1,15 @@
 module TF2R
+  # This class handles interaction with TF2R's "API", which is really just an
+  # open endpoint located at http://tf2r.com/job.php, in use all over the site
+  # to have dynamically updating pages.
   class API
     HOST = 'http://tf2r.com'
     ENDPOINT = '/job.php'
 
-    def self.get_raffle_info(link_snippet)
+    def self.raffle_info(link_snippet)
       params = {checkraffle: true, rid: link_snippet[1..-1],
                 lastentrys: 0, lastchat: 0}
-      response = request(params).body
-      JSON.parse(response)['message']
+      request(params)['message']
     end
 
     private
@@ -20,7 +22,8 @@ module TF2R
       request = Net::HTTP::Post.new(ENDPOINT)
       request.body = URI.encode_www_form(params)
 
-      response = http.request(request)
+      response = http.request(request).body
+      JSON.parse(response)
     end
   end
 end

data/lib/tf2r/raffle.rb

@@ -0,0 +1,64 @@
+module TF2R
+  # This class provides a simple wrapper around grabbing information for a
+  # raffle from the Scraper and API.
+  # TODO: make this an actuall wrapper instead of accepting pre-made info.
+  class Raffle
+    attr_reader :link_snippet, :api_info, :scraper_info
+
+    def initialize(link_snippet, api_info, scraper_info)
+      @link_snippet = link_snippet
+      @api_info     = api_info
+      @scraper_info = scraper_info
+    end
+
+    def info
+      @info ||= {link_snippet: @link_snippet, title: title,
+                 description: description, start_time: start_time,
+                 end_time: end_time, win_chance: win_chance,
+                 current_entries: current_entries, max_entries: max_entries,
+                 is_done: is_done}
+    end
+
+    def creator
+      @scraper_info[1]
+    end
+
+    def participants
+      @api_info['newentry']
+    end
+
+    private
+
+    def title
+      @scraper_info[0][:title]
+    end
+
+    def description
+      @scraper_info[0][:description]
+    end
+
+    def start_time
+      @scraper_info[0][:start_time]
+    end
+
+    def end_time
+      @scraper_info[0][:end_time]
+    end
+
+    def current_entries
+      @api_info['cur_entry']
+    end
+
+    def max_entries
+      @api_info['max_entry']
+    end
+
+    def win_chance
+      (@api_info['wc'] / 100.0).round(5)
+    end
+
+    def is_done
+      @api_info['ended']
+    end
+  end
+end

data/lib/tf2r/scraper.rb

@@ -1,6 +1,7 @@
 module TF2R
   # @author Justin Kim
   class Scraper
+    class InvalidUserPage < StandardError; end
     # Creates a Scraper. Pass values using the options hash.
     #
     #   :user_agent a String used for the User-Agent header
@@ -78,8 +79,7 @@ module TF2R
     #   s.scrape_raffle_for_creator(p) #=>
     #   {:steam_id=>76561198061719848,
     #    :username=>"Yulli",
-    #    :avatar_link=>
-    #    "http://media.steampowered.com/steamcommunity/public/images/avatars/bc/bc9dc4302d23f2e2f37f59c59f29c27dbc8cade6_full.jpg",
+    #    :avatar_link=>"http://media.steampowered.com/steamcommunity/public/images/avatars/bc/bc9dc4302d23f2e2f37f59c59f29c27dbc8cade6_full.jpg",
     #    :posrep=>11458,
     #    :negrep=>0,
     #    :colour=>"70b01b"}
@@ -106,13 +106,16 @@ module TF2R
       negrep = /(\d+)/.match(infos.css('.downvb').text)[1].to_i
 
       # The creator's username colour. Corresponds to rank.
-      colour = extract_hex_colour(user_anchor.attribute('style').to_s)
+      colour = extract_colour(user_anchor.attribute('style').to_s)
 
       {steam_id: steam_id, username: username, avatar_link: avatar_link,
        posrep: posrep, negrep: negrep, colour: colour}
     end
 
-    # Scrapes a raffle page for information about the raffle.
+    # Scrapes a raffle page for some information about the raffle.
+    #
+    # The information is incomplete. This should be used in conjunction with
+    # the API as part of TF2R::Raffle.
     #
     # @example
     #   p = s.fetch('http://tf2r.com/kstzcbd.html')
@@ -121,23 +124,15 @@ module TF2R
     #    :title=>"Just one refined [1 hour]",
     #    :description=>"Plain and simple.",
     #    :start_time=>2012-10-29 09:51:45 -0400,
-    #    :end_time=>2012-10-29 09:53:01 -0400,
-    #    :win_chance=>0.1,
-    #    :current_entries=>10,
-    #    :max_entries=>10,
-    #    :is_done=>true}
+    #    :end_time=>2012-10-29 09:53:01 -0400}
     #
     # @param page [Mechanize::Page] the raffle page.
-    # @return [Hash] a representation of the raffle.
+    # @return [Hash] a partial representation of the raffle.
     #   * :link_snippet (+String+) — the "raffle id" in the URL.
     #   * :title (+String+) — the raffle's title.
     #   * :description (+String+) — the raffle's "message".
     #   * :start_time (+Time+) — the creation time of the raffle.
     #   * :end_time (+Time+) — the projects/observed end time for the raffle.
-    #   * :win_chance (+Float+) — a participant's chance to win the raffle.
-    #   * :current_entries (+Fixnum+) — the current number of participants.
-    #   * :max_entries (+Fixnum+) — the maximum number of particpants allowed.
-    #   * :is_done (+Boolean+) — whether new users can enter the raffle.
     def scrape_raffle_for_raffle(page)
       # Reag classed some things "raffle_infomation". That's spelled right.
       infos = page.parser.css('.raffle_infomation')
@@ -146,37 +141,19 @@ module TF2R
       raffle_tds = infos[3].css('td')
 
       # 'kabc123' for http://tf2r.com/kabc123.html'
-      link_snippet = /\/(k.+)\.html/.match(page.uri.path)[1]
-      title = infos[0].text.split('Title: ')[-1]
+      link_snippet = extract_link_snippet(page.uri.path)
+      title = extract_title(infos[0].text)
       description = raffle_tds[1].text
 
       # This doesn't work right now, because Miz just displays "10%" in the
       # page HTML and updates it with JS after a call to the API.
       # win_chance = /(.+)%/.match(infos.css('#winc').text)[1].to_f / 100
 
-      # This is actually horrible. Scraper should not know about API.
-      win_chance = get_win_chance(link_snippet)
-
-      start_time = raffle_tds[9].attribute('data-rstart-unix').to_s
-      start_time = DateTime.strptime(start_time, '%s').to_time
-      end_time = raffle_tds[11].attribute('data-rsend-unix').to_s
-      end_time= DateTime.strptime(end_time, '%s').to_time
-
-      entries = /(\d+)\/(\d+)/.match(infos.css('#entry').text)
-      current_entries = entries[1].to_i
-      max_entries = entries[2].to_i
-
-      text = page.parser.css('.welcome_font').css('div')[3..-1].text
-      is_done = end_time <= Time.now ||
-        current_entries == max_entries ||
-        (page.parser.css('.welcome_font').size > 5 &&
-         page.parser.css('.welcome_font')[5..-1].text.downcase.include?('winner')
-        )
+      start_time = extract_start_time(raffle_tds[9])
+      end_time = extract_end_time(raffle_tds[11])
 
       {link_snippet: link_snippet, title: title, description: description,
-       start_time: start_time, end_time: end_time, win_chance: win_chance,
-       current_entries: current_entries, max_entries: max_entries,
-       is_done: is_done}
+       start_time: start_time, end_time: end_time}
     end
 
     # Scrapes a raffle page for all the participants.
@@ -196,7 +173,7 @@ module TF2R
         user_anchor = participant.children[1]
         steam_id = extract_steam_id(user_anchor.to_s)
         username = participant.text
-        colour = extract_hex_colour(user_anchor.children[0].attribute('style'))
+        colour = extract_colour(user_anchor.children[0].attribute('style'))
 
         participants << {steam_id: steam_id, username: username, colour: colour}
       end
@@ -211,8 +188,7 @@ module TF2R
     #   s.scrape_user(p) #=>
     #   {:steam_id=>76561198061719848,
     #    :username=>"Yulli",
-    #    :avatar_link=>
-    #     "http://media.steampowered.com/steamcommunity/public/images/avatars/bc/bc9dc4302d23f2e2f37f59c59f29c27dbc8cade6_full.jpg",
+    #    :avatar_link=>"http://media.steampowered.com/steamcommunity/public/images/avatars/bc/bc9dc4302d23f2e2f37f59c59f29c27dbc8cade6_full.jpg",
     #     :posrep=>11459,
     #     :negrep=>0,
     #     :colour=>"70b01b"}
@@ -227,21 +203,20 @@ module TF2R
     #   * :colour (+String+) — hex colour code of the user's username.
     def scrape_user(user_page)
       if user_page.parser.css('.profile_info').empty?
-        # TODO: Should raise an exception here
-        steam_id = extract_steam_id(user_page.uri.to_s)
-        username, avatar_link, posrep, negrep, colour = nil, nil, nil, nil, nil
+        raise InvalidUserPage, 'The given page does not correspond to any user.'
       else
         infos = user_page.parser.css('.raffle_infomation') #sic
-        user_anchor = infos[2].css('a')[0]
+        avatar_anchor = infos[0].css('img')[0]
+        user_anchor = infos[1].css('a')[0]
 
         steam_id = extract_steam_id(user_page.uri.to_s)
         username = /TF2R Item Raffles - (.+)/.match(user_page.title)[1]
-        avatar_link = infos[0].css('img')[0].attribute('src').to_s
+        avatar_link = avatar_anchor.attribute('src').to_s
 
         posrep = infos.css('.upvb').text.to_i
         negrep = infos.css('.downvb').text.to_i
 
-        colour = extract_hex_colour(infos[1].css('a')[0].attribute('style').to_s)
+        colour = extract_colour(user_anchor.attribute('style').to_s)
       end
 
       {steam_id: steam_id, username: username, avatar_link: avatar_link,
@@ -255,9 +230,8 @@ module TF2R
     # @example
     #   p = s.fetch('http://tf2r.com/info.html')
     #   s.scrape_user(p) #=>
-    #   [{:colour=>"ebe2ca", :name=>"User", :description=>"Every new or existing user has this rank."},
-    #    {:colour=>"ffd700", :name=>"Trusted", :description=>"This rank can only be assigned on staff approval. Granted for 1,000~ Rep."},
-    #     ...]
+    #   [{:colour=>"ebe2ca", :name=>"User",
+    #     :description=>"Every new or existing user has this rank."}, ...]
     #
     # @param info_page [Mechanize::Page] the info page.
     # @return [Array] contains Hashes representing each of the ranks.
@@ -280,7 +254,7 @@ module TF2R
     def extract_rank(div)
       name = div.children[0].text
       description = div.children[2].text
-      colour = extract_hex_colour(div.children[0].attribute('style').to_s)
+      colour = extract_colour(div.children[0].attribute('style').to_s)
 
       {name: name, description: description, colour: colour}
     end
@@ -297,26 +271,47 @@ module TF2R
       /http:\/\/tf2r.com\/user\/(\d+)\.html/.match(href)[1].to_i
     end
 
-    # Extracts a lowercase hex colour code.
+    # Extracts a hex colour code.
     #
     # @example
-    #   extract_hex_colour('color:#70B01B;') #=> '70b01b'
+    #   extract_colour('color:#70B01B;') #=> '70b01b'
     #
     # @param href [String] Any string containing a hex colour code.
-    # @return [String] The lowercase hex colour code.
-    def extract_hex_colour(str)
+    # @return [String] The hex colour code, downcased.
+    def extract_colour(str)
       /#(\w+)\s*;/.match(str)[1].downcase
     end
 
-    # Gets the win_chance for a raffle as reported by job.php.
+    # Extracts the Time from any String.
     #
-    # @example
-    #   get_win_chance('kabc123') => 0.05
+    # @param [String] a String containing a unix timestamp value.
+    # @return [Time] the time represented by the unix timestamp.
+    def extract_time(str)
+      DateTime.strptime(str, '%s').to_time
+    end
+
+    def extract_start_time(td)
+      extract_time(td.attribute('data-rstart-unix').to_s)
+    end
+
+    def extract_end_time(td)
+      extract_time(td.attribute('data-rsend-unix').to_s)
+    end
+
+    # Extract the link_snippet from a path or link.
+    #
+    # @param [String] any raffle link or path.
+    # @return [String] the raffle's link snippet.
+    def extract_link_snippet(text)
+      /\/(k.+)\.html/.match(text)[1]
+    end
+
+    # Extract the title from a raffle title string.
     #
-    # @param link_snippet [String] the link snippet of the raffle.
-    # @return [Float] the win chance.
-    def get_win_chance(link_snippet)
-      TF2R::API.get_raffle_info(link_snippet)['wc'] / 100.0
+    # @param [String] the raffle title string.
+    # @return [String] the actual raffle title.
+    def extract_title(text)
+      text.split('Title: ')[-1]
     end
   end
 end

data/lib/tf2r/version.rb

@@ -1,3 +1,3 @@
 module TF2R
-  VERSION = '0.1.1'
+  VERSION = '0.2.0'
 end

data/spec/raffle_spec.rb

@@ -0,0 +1,34 @@
+require 'spec_helper'
+
+describe TF2R::Raffle do
+  let(:scraper) { TF2R::Scraper.new({}) }
+  let(:scraper_info) {
+    VCR.use_cassette('kstzcbd') do
+      scraper.scrape_raffle(scraper.fetch('http://tf2r.com/kstzcbd.html'))
+    end
+  }
+  let(:raffle) {
+    TF2R::Raffle.new('kstzcbd', TF2R::API.raffle_info('kstzcbd'), scraper_info)
+  }
+
+  describe '#info' do
+    let(:result) { raffle.info }
+
+    it 'returns correct values' do
+      expect(result[:link_snippet]).to eql('kstzcbd')
+      expect(result[:title]).to eql('Just one refined [1 hour]')
+      expect(result[:description]).to eql('Plain and simple.')
+      expect(result[:start_time]).to eql(
+        Time.new(2012, 10, 29, 14, 51, 45, '+01:00')
+      )
+      expect(result[:end_time]).to eql(
+        Time.new(2012, 10, 29, 14, 53, 01, '+01:00')
+      )
+      expect(result[:win_chance]).to eql(0.1)
+      # TODO: use a raffle where current_entries != max_entries
+      expect(result[:current_entries]).to eql(10)
+      expect(result[:max_entries]).to eql(10)
+      expect(result[:is_done]).to eql(true)
+    end
+  end
+end

data/spec/scraper_spec.rb

@@ -2,6 +2,11 @@ require 'spec_helper'
 
 describe TF2R::Scraper do
   let(:scraper) { TF2R::Scraper.new({}) }
+  let(:raffle_page) {
+    VCR.use_cassette('raffle_kstzcbd') do
+      scraper.fetch('http://tf2r.com/kstzcbd.html')
+    end
+  }
 
   it 'is instantiable' do
     expect{
@@ -60,26 +65,25 @@ describe TF2R::Scraper do
   end
 
   describe '#scrape_raffle' do
-    let(:page) {
-      VCR.use_cassette('scrape_raffle_for_raffle') do
-        scraper.fetch('http://tf2r.com/kstzcbd.html')
-      end
-    }
-    let(:result) { scraper.scrape_raffle(page) }
+    let(:result) { scraper.scrape_raffle(raffle_page) }
 
     it 'returns an Array' do
       expect(result).to be_an(Array)
     end
 
     it 'returns the same as its child methods' do
-      expect(result[0]).to eql(scraper.scrape_raffle_for_raffle(page))
-      expect(result[1]).to eql(scraper.scrape_raffle_for_creator(page))
-      expect(result[2]).to eql(scraper.scrape_raffle_for_participants(page))
+      expect(result[0]).to eql(scraper.scrape_raffle_for_raffle(raffle_page))
+      expect(result[1]).to eql(scraper.scrape_raffle_for_creator(raffle_page))
+      expect(result[2]).to eql(scraper.scrape_raffle_for_participants(raffle_page))
     end
   end
 
   describe '#scrape_main_page' do
-    let(:result) { scraper.scrape_main_page }
+    let(:result) {
+      VCR.use_cassette('raffle_kstzcbd') do
+        scraper.scrape_main_page
+      end
+    }
 
     before(:each) do
       raffles_file = File.new(File.join(File.dirname(__FILE__), 'raffles.html'))
@@ -90,11 +94,9 @@ describe TF2R::Scraper do
     end
 
     it 'returns an Array of Strings' do
-      VCR.use_cassette('raffles') do
-        expect(result).to be_an(Array)
-        expect(result[0]).to be_a(String)
-        expect(result[-1]).to be_a(String)
-      end
+      expect(result).to be_an(Array)
+      expect(result[0]).to be_a(String)
+      expect(result[-1]).to be_a(String)
     end
 
     it 'returns raffle links in reverse chronological order' do
@@ -105,12 +107,7 @@ describe TF2R::Scraper do
   end
 
   describe '#scrape_raffle_for_creator' do
-    let(:page) {
-      VCR.use_cassette('scrape_raffle_for_creator') do
-        scraper.fetch('http://tf2r.com/kstzcbd.html')
-      end
-    }
-    let(:result) { scraper.scrape_raffle_for_creator(page) }
+    let(:result) { scraper.scrape_raffle_for_creator(raffle_page) }
 
     it 'returns a Hash representation of a user' do
       expect(result).to be_a(Hash)
@@ -138,12 +135,7 @@ describe TF2R::Scraper do
 
 
   describe '#scrape_raffle_for_raffle' do
-    let(:page) {
-      VCR.use_cassette('scrape_raffle_for_raffle') do
-        scraper.fetch('http://tf2r.com/kstzcbd.html')
-      end
-    }
-    let(:result) { scraper.scrape_raffle_for_raffle(page) }
+    let(:result) { scraper.scrape_raffle_for_raffle(raffle_page) }
 
     it 'returns a Hash representation of a raffle' do
       expect(result).to be_a(Hash)
@@ -153,19 +145,18 @@ describe TF2R::Scraper do
       expect(result[:link_snippet]).to eql('kstzcbd')
       expect(result[:title]).to eql('Just one refined [1 hour]')
       expect(result[:description]).to eql('Plain and simple.')
-      expect(result[:start_time]).to eql(DateTime.strptime('Mon, 29 Oct 2012 14:51:45 +0100', '%a, %d %b %Y %H:%M:%S %z').to_time)
-      expect(result[:end_time]).to eql(DateTime.strptime('Mon, 29 Oct 2012 14:53:01 +0100', '%a, %d %b %Y %H:%M:%S %z').to_time)
-      expect(result[:win_chance]).to eql(0.1)
-      # TODO: use a raffle where current_entries != max_entries
-      expect(result[:current_entries]).to eql(10)
-      expect(result[:max_entries]).to eql(10)
-      expect(result[:is_done]).to eql(true)
+      expect(result[:start_time]).to eql(
+        Time.new(2012, 10, 29, 14, 51, 45, '+01:00')
+      )
+      expect(result[:end_time]).to eql(
+        Time.new(2012, 10, 29, 14, 53, 01, '+01:00')
+      )
     end
   end
 
   describe '#scrape_raffle_for_participants' do
     let(:page) {
-      VCR.use_cassette('scrape_raffle_for_participants') do
+      VCR.use_cassette('raffle_kstzcbd_full') do
         scraper.fetch('http://tf2r.com/kstzcbd.html?full')
       end
     }
@@ -190,19 +181,19 @@ describe TF2R::Scraper do
 
   describe '#scrape_user' do
     context 'a real user page is given' do
-      let(:page) {
-        VCR.use_cassette('scrape_user_real') do
+      let(:user_page) {
+        VCR.use_cassette('user_76561198061719848') do
           scraper.fetch('http://tf2r.com/user/76561198061719848.html')
         end
       }
-      let(:result) { scraper.scrape_user(page) }
+      let(:result) { scraper.scrape_user(user_page) }
 
       it 'returns a Hash' do
         expect(result).to be_a(Hash)
       end
 
-      # This spec is also brittle. It relies on my user account, which is updated
-      # constantly.
+      # This spec is also brittle. It relies on my TF2R user account, which is
+      # updated constantly.
       # TODO: use a stagnant alt account
       it 'returns correct values' do
         expect(result[:steam_id]).to eql(76561198061719848)
@@ -215,38 +206,28 @@ describe TF2R::Scraper do
     end
 
     context 'a user page for a non-existent user is given' do
-      let(:page) {
-        VCR.use_cassette('scrape_user_not_found') do
+      let(:user_page) {
+        VCR.use_cassette('user_fake') do
           scraper.fetch('http://tf2r.com/user/123456.html')
         end
       }
-      let(:result) { scraper.scrape_user(page) }
-      it 'returns a Hash' do
-        expect(result).to be_a(Hash)
-      end
 
-      it 'returns the attempted Steam ID' do
-        expect(result[:steam_id]).to eql(123456)
-      end
-
-      it 'returns mostly nil values' do
-        expect(result[:username]).to be_nil
-        expect(result[:avatar_link]).to be_nil
-        expect(result[:posrep]).to be_nil
-        expect(result[:negrep]).to be_nil
-        expect(result[:colour]).to be_nil
+      it 'raises InvalidUserPage' do
+        expect {
+          scraper.scrape_user(user_page)
+        }.to raise_error(TF2R::Scraper::InvalidUserPage)
       end
     end
   end
 
 
   describe '#scrape_ranks' do
-    let(:page) {
-      VCR.use_cassette('scrape_ranks') do
+    let(:info_page) {
+      VCR.use_cassette('info_page') do
         scraper.fetch('http://tf2r.com/info.html')
       end
     }
-    let(:result) { scraper.scrape_ranks(page) }
+    let(:result) { scraper.scrape_ranks(info_page) }
 
     it 'returns an Array of Hashes' do
       expect(result).to be_an(Array)
@@ -256,7 +237,9 @@ describe TF2R::Scraper do
 
     it 'returns correct values' do
       expect(result[0][:name]).to eql('User')
-      expect(result[0][:description]).to eql('Every new or existing user has this rank.')
+      expect(result[0][:description]).to eql(
+        'Every new or existing user has this rank.'
+      )
       expect(result[0][:colour]).to eql('ebe2ca')
 
       # This is brittle. Every time a new rank is added, this fails.