tf2r 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 143e9f53a0a365e8bf98ac186a8b81acc7a3f5a0
-  data.tar.gz: f417eab178af88208690c7f257389ae84bf49cf3
+  metadata.gz: cda160e8773382ca326bd42ad5f6469cbf63fd57
+  data.tar.gz: 3a43402a23424491b50559b27fbde5f2c72fd2a0
 SHA512:
-  metadata.gz: 3030e85ac97ab0a5726f8b7aa4f5b0e03bfacd540fcdc581d3f92428432580c50ad9cb9c7975031e68f0fd24e35816258283ca4329bc32697e1c4dffd7082776
-  data.tar.gz: 1cf2a0eeae95a3d7b83e248039e706ccbdb96c1cd59421550433a5c5848eff185abc65b5afece44c0254ab1781239485d36b2bf08860b5de73d02a3a22e17976
+  metadata.gz: 5a76b5c1c173ca4190a1c4e6197feacfe0a00d4304aa11d07d3de6e5e0f6c9eb9e8a5e335f4b93a594d4adbc50b150c6a9111fdd0f8f683ac9c571ae67cd632d
+  data.tar.gz: 5d1aa559bcb08c0b1479b99d56301987289732c15431056dfab4e458814bb39767a2e149577ec4e862fc3a5e129920e519472909ef44863e17a2f30b0cf472cf

data/.gitignore

@@ -11,3 +11,6 @@
 *.o
 *.a
 mkmf.log
+
+cookies.txt
+tf2r-*.gem

data/.ruby-gemset

@@ -1 +1 @@
-tf2r_scraper
+tf2r

data/.travis.yml

@@ -0,0 +1,3 @@
+language: ruby
+rvm:
+  - "2.1.2"

data/Gemfile.lock

@@ -1,14 +1,26 @@
 PATH
   remote: .
   specs:
-    tf2r (0.0.1)
+    tf2r (0.1.0)
       mechanize (~> 2.7)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    addressable (2.3.6)
+    cane (2.6.2)
+      parallel
     coderay (1.1.0)
+    coveralls (0.7.0)
+      multi_json (~> 1.3)
+      rest-client
+      simplecov (>= 0.7)
+      term-ansicolor
+      thor
+    crack (0.4.2)
+      safe_yaml (~> 1.0.0)
     diff-lcs (1.2.5)
+    docile (1.1.5)
     domain_name (0.5.19)
       unf (>= 0.0.5, < 1.0.0)
     http-cookie (1.0.2)
@@ -25,16 +37,22 @@ GEM
     method_source (0.8.2)
     mime-types (2.3)
     mini_portile (0.6.0)
+    multi_json (1.10.1)
     net-http-digest_auth (1.4)
     net-http-persistent (2.9.4)
+    netrc (0.7.7)
     nokogiri (1.6.3.1)
       mini_portile (= 0.6.0)
     ntlm-http (0.1.1)
+    parallel (1.1.2)
     pry (0.10.0)
       coderay (~> 1.1.0)
       method_source (~> 0.8.1)
       slop (~> 3.4)
     rake (10.3.2)
+    rest-client (1.7.2)
+      mime-types (>= 1.16, < 3.0)
+      netrc (~> 0.7)
     rspec (3.0.0)
       rspec-core (~> 3.0.0)
       rspec-expectations (~> 3.0.0)
@@ -47,18 +65,36 @@ GEM
     rspec-mocks (3.0.3)
       rspec-support (~> 3.0.0)
     rspec-support (3.0.3)
+    safe_yaml (1.0.3)
+    simplecov (0.9.0)
+      docile (~> 1.1.0)
+      multi_json
+      simplecov-html (~> 0.8.0)
+    simplecov-html (0.8.0)
     slop (3.6.0)
+    term-ansicolor (1.3.0)
+      tins (~> 1.0)
+    thor (0.19.1)
+    tins (1.3.0)
     unf (0.1.4)
       unf_ext
     unf_ext (0.0.6)
+    vcr (2.9.2)
+    webmock (1.18.0)
+      addressable (>= 2.3.6)
+      crack (>= 0.3.2)
     webrobots (0.1.1)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
-  bundler (~> 1.6)
+  bundler (~> 1.3)
+  cane (~> 2.6)
+  coveralls (~> 0.7)
   pry (~> 0.10)
   rake (~> 10.0)
   rspec (~> 3.0)
   tf2r!
+  vcr (~> 2.9)
+  webmock (~> 1.18)

data/README.md

@@ -1,8 +1,31 @@
-# TF2R [![Code Climate](https://codeclimate.com/github/justinkim/tf2r/badges/gpa.svg)](https://codeclimate.com/github/justinkim/tf2r)
+# TF2R - [tf2r.com][tf2r] interaction gem
 
+[tf2r]: http://tf2r.com
+
+[![Gem Version](http://img.shields.io/gem/v/tf2r.svg)][gem]
+[![Build Status](http://img.shields.io/travis/justinkim/tf2r.svg)][travis]
+[![Dependency Status](http://img.shields.io/gemnasium/justinkim/tf2r.svg)][gemnasium]
+[![Coverage Status](https://img.shields.io/coveralls/justinkim/tf2r.svg)][coveralls]
+[![Code Climate](http://img.shields.io/codeclimate/github/justinkim/tf2r.svg)][codeclimate]
+
+[codeclimate]:https://codeclimate.com/github/justinkim/tf2r
+[coveralls]: https://coveralls.io/r/justinkim/tf2r
+[gem]: http://badge.fury.io/rb/tf2r
+[gemnasium]: https://gemnasium.com/justinkim/tf2r
+[travis]: https://travis-ci.org/justinkim/tf2r
+
+GitHub: [https://github.com/justinkim/tf2r](https://github.com/justinkim/tf2r)
+
+Documentation: [http://www.rubydoc.info/github/justinkim/tf2r](http://www.rubydoc.info/github/justinkim/tf2r)
+
+Bugs: [https://github.com/justinkim/tf2r/issues](https://github.com/justinkim/tf2r/issues)
+
+## Description
 This gem provides a `TF2R::Scraper` that has the ability to scrape various pages on [TF2R](http://tf2r.com) into usable data.
 
-Yes, this gem is [semantically versioned](http://semver.org/)!
+Yes, this gem is [semantically versioned][semver]!
+
+[semver]: http://semver.org
 
 ## Installation
 
@@ -31,3 +54,8 @@ TODO: Write usage instructions here
 3. Commit your changes (`git commit -am 'Add some feature'`)
 4. Push to the branch (`git push origin my-new-feature`)
 5. Create a new Pull Request
+
+## License
+Released under the ISC license. See the [LICENSE][] for further details.
+
+[license]: LICENSE.md

data/Rakefile

@@ -1,2 +1,9 @@
-require "bundler/gem_tasks"
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
 
+desc 'Run specs'
+RSpec::Core::RakeTask.new
+
+desc 'Default: run specs'
+task :default => :spec
+task :test => :spec

data/lib/tf2r/scraper.rb

@@ -1,195 +1,291 @@
 module TF2R
+  # @author Justin Kim
   class Scraper
+    # Creates a Scraper. Pass values using the options hash.
+    #
+    #   :user_agent a String used for the User-Agent header
+    #   :cookies_txt a File containing cookies to load into the Mechanize agent
+    #
+    # @param opts [Hash] options to create a Scraper with
+    # @option opts [String] :user_agent a custom User-Agent header content
+    # @option opts [File] :cookies_txt a cookies.txt to load the Mechanize
+    #   agent with
     def initialize(options)
       @mech = Mechanize.new { |mech|
         mech.user_agent = options[:user_agent] || "TF2R::Scraper #{VERSION}"
       }
 
-      @mech.cookie_jar.load(options[:cookies_txt], :cookiestxt) if options[:cookies_txt]
+      load_cookies(options[:cookies_txt]) if options[:cookies_txt]
     end
 
+    # Loads the Mechanize agent with cookies from a cookies.txt.
+    #
+    # Certain pages on TF2R require a session with a logged-in user.
+    # This requires a Netscape-style cookies.txt that contains a valid
+    # "session" cookie for "tf2r.com".
+    #
+    # @param cookies_txt [File] the cookies.txt file.
+    # @return [Mechanize::CookieJar] the CookieJar of the Mechanize agent.
+    def load_cookies(cookies_txt)
+      @mech.cookie_jar.load(cookies_txt, :cookiestxt)
+    end
+
+    # Fetches the page at the given URL.
+    #
+    # @param url [String] the desired URL.
+    # @return [Mechanize::Page] the page given by Mechanize.
     def fetch(url)
       @mech.get(url)
     end
-  end
-end
 
-__END__
-
-# This is the old Scraper from NervyPipe.
-class Scraper
-  def initialize(cookies_txt_path)
-    @cookies_txt_path = cookies_txt_path
-
-    @main = Mechanize.new { |agent|
-      # the User-Agent field in headers
-      agent.user_agent = 'Jenna Bot'
-    }
-
-    auth_cookies(@main)
-  end
-
-  def auth_cookies(mech)
-    # Before anything, load our auth cookies into the cookie jar
-    # This requires a Netscape-style cookies.txt to be in the working dir
+    # Scrapes TF2R for all active raffles.
     #
-    # cookies.txt must include at least a valid "session" cookie from tf2r.com
-    mech.cookie_jar.load_cookiestxt(@cookies_txt_path)
-  end
-
-  # Simply return the Mechanize::Page for a url
-  def fetch(url)
-    @main.get(url)
-  end
-
-  def run(type)
-    case type
-    when :raffle
-      scrape_raffle(@main.get 'http://tf2r.com/kblf84f.html')
-    when :user
-      scrape_user(@main.get 'http://tf2r.com/user/76561198061719848.html')
-    when :main
-      scrape_main_page
-    when :ranks
-      scrape_ranks
+    # See http://tf2r.com/raffles.html
+    #
+    # @example
+    #   s.scrape_main_page #=> ['http://tf2r.com/kold.html',
+    #                           'http://tf2r.com/knew.html',
+    #                           'http://tf2r.com/knewest.html']
+    #
+    # @return [Hash] String links of all active raffles in chronological
+    #   order (oldest to newest by creation time).
+    def scrape_main_page
+      page = fetch('http://tf2r.com/raffles.html')
+
+      # All raffle links begin with 'tf2r.com/k'
+      raffle_links = page.links_with(href: /tf2r\.com\/k/)
+      raffle_links.map! { |x| x.uri.to_s }
+      raffle_links.reverse!
     end
-  end
-
-  def scrape_main_page
-    page = @main.get('http://tf2r.com/raffles.html')
-
-    # This regex matches all Mechanize::Page::Links on the main raffles page that are actual raffles
-    raffle_mech_links = page.links_with(href: /tf2r\.com\/k/)
-
-    # an array of strings, which are raffle links
-    raffle_links = raffle_mech_links.map { |x| x.uri.to_s }
-
-    # the array should have raffles from bottom-to-top, old-to-new
-    raffle_links.reverse!
-  end
-
-  def scrape_raffle_for_user(page)
-    # This is an array of all things Reag was nice enough to class "raffle_infomation"
-    # Reag made a typo, so the class really is "raffle_infomation"
-    raffle_infos = page.parser.css('.raffle_infomation')
-
-    # User information
-    steam_id = raffle_infos[2].css('a')[0].attributes['href'].text.split('/')[-1].split('.')[0].to_i
-    username = raffle_infos[2].css('a').text
-    avatar_link = raffle_infos[1].css('a')[0].css('img')[0].attributes['src'].text
-
-    # posrept will be nil if the Scraper's user has already voted on a user's rep in the raffle
-    posrepa = raffle_infos.css('.upvb').text.split
-    posrepa.delete('+')
-    posrep = posrepa[-1].to_i.to_s
-
-    negrepa = raffle_infos.css('.downvb').text.split
-    negrepa.delete('+')
-    negrep = negrepa[-1].to_i.to_s
-
-    colour = raffle_infos[2].css('a')[0].attributes['style'].value.split('#')[-1].split(';')[0].downcase.chomp
-    # The creator of the raffle, using above
-    userhash = {steam_id: steam_id, username: username, avatar_link: avatar_link, posrep: posrep, negrep: negrep, colour: colour}
-  end
-
-  def scrape_raffle_for_raffle(page)
-    # This is an array of all things Reag was nice enough to class "raffle_infomation"
-    # Reag made a typo, so the class really is "raffle_infomation"
-    raffle_infos = page.parser.css('.raffle_infomation')
-
-    # Raffle information
-    uri = page.uri # is a URI:HTTP
-    path = uri.path # is "/welcome.html" for "http://tf2r.com/welcome.html"
-    link_snippet = path.split('/')[1].split('.html')[0] # is 'kabc123' for 'http://tf2r.com/kabc123.html'
 
-    title = raffle_infos[0].text.split('Title: ')[-1]
-    # Lots of info in a single table
-    raffle_tds = raffle_infos[3].css('td')
-    description = raffle_tds[1].text
-
-    start_time_string = raffle_tds[9].text
-    start_time = DateTime.strptime(start_time_string, '%a, %d %b %Y %H:%M:%S %z').to_time
-    end_time_string = raffle_tds[11].text
-    end_time = DateTime.strptime(end_time_string, '%a, %d %b %Y %H:%M:%S %z').to_time
-
-    win_chance_pre_round = raffle_tds[5].text.to_f / 100 # also #winc
-    win_chance = win_chance_pre_round.round(5)
-
-    entries = raffle_tds[7].text # also #entry
-    # Entries looks like "42/123", as "current/max"
-    # Split by slash, multiple assignment to array with elements mapped to integers
-    # Equivalent to a = b[0].to_i; c = b[1].to_i
-    current_entries, max_entries = entries.split('/').map { |x| x.to_i }
-
-    is_done = end_time <= Time.now || current_entries == max_entries || page.parser.css('.welcome_font').text.include?('No winners') || page.parser.css('.welcome_font').text.include?('Winner(s):')
-
-    rafflehash = {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 scrape_raffle_for_participants(page)
-    participants = []
-    participant_divs = page.parser.css('.pentry')
-    participant_divs.each do |participant|
-      steam_id = participant.css('a')[-1].attributes['href'].text.split('/')[-1].split('.')[0].to_i
-      username = participant.text
-      colour = participant.css('a')[-1].attributes['style'].text.split('#')[-1].split(';')[0].downcase.chomp
-
-      participants << {steam_id: steam_id, username: username, colour: colour}
+    # Scrapes a raffle page for information about the creator.
+    #
+    # @example
+    #   p = s.fetch('http://tf2r.com/kstzcbd.html')
+    #   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",
+    #    :posrep=>11458,
+    #    :negrep=>0,
+    #    :colour=>"70b01b"}
+    #
+    # @param page [Mechanize::Page] the raffle page.
+    # @return [Hash] a representation of a user, the raffle creator.
+    #   * :steam_id (+Fixnum+) — the creator's SteamID64.
+    #   * :username (+String+) — the creator's username.
+    #   * :avatar_link (+String+) — a link to the creator's avatar.
+    #   * :posrep (+Fixnum+) — the creator's positive rep.
+    #   * :negrep (+Fixnum+) — the creator's negative rep.
+    #   * :colour (+String+) — hex colour code of the creator's username.
+    def scrape_raffle_for_creator(page)
+      # Reag classed some things "raffle_infomation". That's spelled right.
+      infos = page.parser.css('.raffle_infomation')
+
+      # The main 'a' element, containing the creator's username.
+      user_anchor = infos[2].css('a')[0]
+
+      steam_id = extract_steam_id(user_anchor.attribute('href').to_s)
+      username = user_anchor.text
+      avatar_link = infos[1].css('img')[0].attribute('src').to_s
+      posrep = /(\d+)/.match(infos.css('.upvb').text)[1].to_i
+      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)
+
+      {steam_id: steam_id, username: username, avatar_link: avatar_link,
+       posrep: posrep, negrep: negrep, colour: colour}
     end
 
-    participants.uniq.reverse
-  end
-
-  def scrape_raffle(page, portions = :all)
-    userhash, rafflehash, participants = {}, {}, []
-
-    case portions
-    when :core
-      userhash = scrape_raffle_for_user(page)
-      rafflehash = scrape_raffle_for_raffle(page)
-    when :participants
-      participants = scrape_raffle_for_participants(page)
-    else
-      userhash = scrape_raffle_for_user(page)
-      rafflehash = scrape_raffle_for_raffle(page)
-      participants = scrape_raffle_for_participants(page)
+    # Scrapes a raffle page for information about the raffle.
+    #
+    # @example
+    #   p = s.fetch('http://tf2r.com/kstzcbd.html')
+    #   s.scrape_raffle_for_raffle(p) #=>
+    #   {:link_snippet=>"kstzcbd",
+    #    :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}
+    #
+    # @param page [Mechanize::Page] the raffle page.
+    # @return [Hash] a 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')
+
+      # Elements of the main raffle info table.
+      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]
+      description = raffle_tds[1].text
+
+      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
+
+      win_chance = /(.+)%/.match(infos.css('#winc').text)[1].to_f / 100
+
+      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')[5..-1].text.downcase.include?('winner')
+
+      {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
 
-    [userhash, rafflehash, participants]
-  end
+    # Scrapes a raffle page for all the participants.
+    #
+    # TODO: add an example
+    #
+    # @param page [Mechanize::Page] the raffle page.
+    # @return [Array] contains Hashes representing each of the participants,
+    # in chronological order (first entered to last).
+    #   * :steam_id (+Fixnum+) — the participant's SteamID64.
+    #   * :username (+String+) — the participant's username.
+    #   * :colour (+String+) — hex colour code of the participant's username.
+    def scrape_raffle_for_participants(page)
+      participants = []
+      participant_divs = page.parser.css('.pentry')
+      participant_divs.each do |participant|
+        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'))
+
+        participants << {steam_id: steam_id, username: username, colour: colour}
+      end
+
+      participants.reverse!
+    end
 
-  def scrape_user(user_page)
-    if user_page.parser.css('.profile_info').empty?
-      username, avatar_link, posrep, negrep, colour = nil, nil, nil, nil, nil
-      steam_id = user_page.uri.path.split('/')[-1].split('.')[0].to_i
-    else
-      pp user_page.parser.css('.profile_info')
-      raffle_infos = user_page.parser.css('.raffle_infomation') # sic
+    # Scrapes a user page for information about the user.
+    #
+    # @example
+    #   p = s.fetch('http://tf2r.com/user/76561198061719848.html')
+    #   s.scrape_user(p) #=>
+    #   {:steam_id=>76561198061719848,
+    #    :username=>"Yulli",
+    #    :avatar_link=>
+    #     "http://media.steampowered.com/steamcommunity/public/images/avatars/bc/bc9dc4302d23f2e2f37f59c59f29c27dbc8cade6_full.jpg",
+    #     :posrep=>11459,
+    #     :negrep=>0,
+    #     :colour=>"70b01b"}
+    #
+    # @param user_page [Mechanize::Page] the user page.
+    # @return [Hash] a representation of the user.
+    #   * :steam_id (+Fixnum+) — the user's SteamID64.
+    #   * :username (+String+) — the user's username.
+    #   * :avatar_link (+String+) — a link to the user's avatar.
+    #   * :posrep (+Fixnum+) — the user's positive rep.
+    #   * :negrep (+Fixnum+) — the user's negative rep.
+    #   * :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
+      else
+        infos = user_page.parser.css('.raffle_infomation') #sic
+        user_anchor = infos[2].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
+
+        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)
+      end
+
+      {steam_id: steam_id, username: username, avatar_link: avatar_link,
+       posrep: posrep, negrep: negrep, colour: colour}
+    end
 
-      steam_id = user_page.uri.path.split('/')[-1].split('.')[0].to_i
-      username = user_page.parser.title.split('TF2R Item Raffles - ')[-1]
-      avatar_link = raffle_infos[0].css('img')[0].attributes['src'].text
+    # Scrapes the TF2R info page for available user ranks.
+    #
+    # See http://tf2r.com/info.html.
+    #
+    # @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."},
+    #     ...]
+    #
+    # @param info_page [Mechanize::Page] the info page.
+    # @return [Array] contains Hashes representing each of the ranks.
+    #   * :name (+String+) — the rank's name.
+    #   * :description (+String+) — the rank's description.
+    #   * :colour (+String+) — the rank's hex colour code.
+    def scrape_ranks(info_page)
+      rank_divs = info_page.parser.css('#ranks').children
+      ranks = rank_divs.select { |div| div.children.size == 3 }
+      ranks.map { |div| extract_rank(div) }
+    end
 
-      posrep = raffle_infos.css('.upvb').text.to_i.to_s
-      negrep = raffle_infos.css('.downvb').text.to_i.to_s
+    private
 
-      colour = raffle_infos[1].css('a')[0].attributes['style'].value.split('#')[-1].split(';')[0].downcase.chomp
+    # Extracts a rank hash from a rank div.
+    # Only for use by #scrape_ranks.
+    #
+    # @param rank_div [Nokogiri::XML::Element] a div containing the rank info.
+    # @return [Hash] a representation of a rank as outlined in #scrape_ranks.
+    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)
+
+      {name: name, description: description, colour: colour}
     end
 
-    userhash = {steam_id: steam_id, username: username, avatar_link: avatar_link, posrep: posrep, negrep: negrep, colour: colour}
-  end
+    # Extracts a SteamID64 from a TF2R user link.
+    #
+    # @example
+    #   extract_steam_id('http://tf2r.com/user/76561198061719848.html')
+    #     #=> 76561198061719848
+    #
+    # @param href [String] The full user profile link.
+    # @return [Fixnum] The Steam ID.
+    def extract_steam_id(href)
+      /http:\/\/tf2r.com\/user\/(\d+)\.html/.match(href)[1].to_i
+    end
 
-  def scrape_ranks
-    # This scrapes the info page for the various ranks that exist
-    page = @main.get('http://tf2r.com/info.html')
-
-    ranks_div = page.parser.css('#ranks')
-    divs = ranks_div.css('div')
-    rank_divs = []
-    divs.each { |div|
-      rank_divs << div unless div.attributes['style'].nil? || !(div.attributes['style'].value.include? 'color')
-    }
-    colours = rank_divs.map {|div| div.attributes['style'].value.split('color:#')[-1].split(';')[0].downcase.chomp }
+    # Extracts a lowercase hex colour code.
+    #
+    # @example
+    #   extract_hex_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)
+      /#(\w+)\s*;/.match(str)[1].downcase
+    end
   end
 end

data/lib/tf2r/version.rb

@@ -1,3 +1,3 @@
 module TF2R
-  VERSION = "0.0.1"
+  VERSION = '0.1.0'
 end