craiggy 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 6ddd12ddb0d4c32992b841a92965ee0fca1234fb
+  data.tar.gz: b45d8d31c309b16e26ee0751cb78097b215e09fd
+SHA512:
+  metadata.gz: 1d9dbbf75ef9b0373214ab58fe3b7c6b02298428ad15bf80b39f3c56b4a30327cf1dfdcdeba91325666298921f1f74fd496c7a05ccbedef5a57d03a51ef17c66
+  data.tar.gz: ffbc5d0af69dec30fb7b1e2ae4d976ead60bdd76794f9e86f326de6c753ed1466e00e07c4d51f445e3c87bc0467531eff0e43451ffc748c051c13d242062056c

data/lib/craiggy.rb

@@ -0,0 +1,42 @@
+require "mechanize"
+
+require "craiggy/post"
+require "craiggy/post_url"
+require "craiggy/categories"
+
+class Craiggy
+  CATEGORY = "sss"
+
+  def self.get(item, *arguments)
+    initialize(item, *arguments)
+    scrape_posts
+  end
+
+  def self.categories
+    self::CATEGORIES.keys
+  end
+
+  class << self
+    private
+      attr_reader :url
+
+      def initialize(item, *arguments)
+        @url = PostUrl.new(item, self::CATEGORY, *arguments).url
+      end
+
+      def scrape_posts
+        matching_links.map { |link| Post.new(link.click) }
+      end
+
+      def matching_links
+        mech.get(url).links_with(dom_class: "result-title hdrlnk")
+      end
+
+      def mech
+        Mechanize.new do |agent|
+          agent.robots = false
+          agent.user_agent_alias = "Mac Safari"
+        end
+      end
+  end
+end

data/lib/craiggy/categories.rb

@@ -0,0 +1,20 @@
+class Craiggy
+  CATEGORIES = {
+    "Community" => "ccc",
+    "Events"    => "eee",
+    "ForSale"   => "sss",
+    "Gigs"      => "ggg",
+    "Housing"   => "hhh",
+    "Jobs"      => "jjj",
+    "Personals" => "ppp",
+    "Resumes"   => "rrr",
+    "Services"  => "bbb",
+  }.freeze
+end
+
+Craiggy::CATEGORIES.each do |namespace, category_code|
+  Craiggy.const_set(
+    namespace,
+    Class.new(Craiggy) { self::CATEGORY = category_code },
+  )
+end

data/lib/craiggy/post.rb

@@ -0,0 +1,70 @@
+# Used for packaging Craigslist post data
+class Craiggy
+  class Post
+    attr_reader :title, :image, :price, :location, :url, :description
+
+    def initialize(page)
+      post_params  = PostScraper.new(page).post_params
+      @title       = post_params[:title]
+      @image       = post_params[:image]
+      @price       = post_params[:price]
+      @location    = post_params[:location]
+      @description = post_params[:description]
+      @url         = post_params[:url]
+    end
+
+    def has_image?
+      image != ""
+    end
+  end
+
+
+  # Scrapes and formats `post_params` for easy `Post` initialization
+  class PostScraper
+    def initialize(page)
+      @page = page
+    end
+
+    def post_params
+      {
+        image: image,
+        title: title,
+        price: price,
+        location: location,
+        description: description,
+        url: page.uri.to_s,
+      }
+    end
+
+    private
+
+    attr_reader :page
+
+    def posting_title
+      page.at('span.postingtitletext')
+    end
+
+    def image
+      image = page.at('img')
+      image ? image['src'] : ''
+    end
+
+    def title
+      page.at("#titletextonly").text
+    end
+
+    def price
+      price = posting_title.at('span.price')
+      price ? price.text.gsub(/\$/, '').to_i : 0
+    end
+
+    def location
+      location = posting_title.at('small')
+      location = location ? location.text.gsub(/ ?[\(\)]/, '') : ''
+    end
+
+    def description
+      page.at('section#postingbody').children[2].text.strip
+    end
+  end
+end

data/lib/craiggy/post_url.rb

@@ -0,0 +1,41 @@
+class Craiggy
+  class PostUrl
+    def initialize(item, category, *options)
+      @item      = item
+      @category  = category
+      @options   = options.first || {}
+    end
+
+    def url
+      "#{base_url}/search/#{category}?sort=rel&"\
+      "#{price_range}query="\
+      "#{item.downcase.split(' ') * '+'}"
+    end
+
+    private
+      attr_reader :item, :category, :options
+
+      def base_url
+        "https://#{area}.craigslist.org"
+      end
+
+      def price_range
+        query = ""
+        query += "min_price=#{min_price}&" unless min_price.nil?
+        query += "max_price=#{max_price}&" unless max_price.nil?
+        query
+      end
+
+      def area
+        options[:area] || "sfbay"
+      end
+
+      def min_price
+        options[:min_price]
+      end
+
+      def max_price
+        options[:max_price]
+      end
+  end
+end

metadata

@@ -0,0 +1,104 @@
+--- !ruby/object:Gem::Specification
+name: craiggy
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Chris Scott
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-01-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.22'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.22'
+- !ruby/object:Gem::Dependency
+  name: vcr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: All you need is an item title and Craiggy will scrape Craigslist and
+  return an array of Posts pertaining to the item.
+email: christo247@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/craiggy.rb
+- lib/craiggy/categories.rb
+- lib/craiggy/post.rb
+- lib/craiggy/post_url.rb
+homepage: https://github.com/steezyduzit/craiggy
+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: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Scrape posts from Craigslist with an easy API
+test_files: []