cdb-crawlr 0.0.3 → 0.0.4

data/lib/cdb-crawlr.rb

@@ -10,7 +10,7 @@ require 'cdb/issue'
 require 'cdb/title'
 
 module CDB
-  VERSION = '0.0.3'
+  VERSION = '0.0.4'
 
   BASE_URL = 'http://www.comicbookdb.com'
   REQUEST_HEADERS = {'Connection' => 'keep-alive'}
@@ -24,9 +24,7 @@ module CDB
         form_search: query
       )
       url = "#{BASE_URL}/#{SEARCH_PATH}?#{data}"
-      content = open(url, REQUEST_HEADERS).read
-      content.force_encoding('ISO-8859-1').encode!('UTF-8')
-      doc = Nokogiri::HTML(content)
+      doc = read_page(url)
       node = doc.css('h2:contains("Search Results")').first.parent
       {
         :titles => CDB::Title.parse_results(node),
@@ -34,5 +32,20 @@ module CDB
       }
     end
 
+    def show(id, type)
+      data = URI.encode_www_form('ID' => id)
+      url = "#{BASE_URL}/#{type::WEB_PATH}?#{data}"
+      page = read_page(url)
+      type.parse_data(id, page)
+    end
+
+  private
+
+    def read_page(url)
+      content = open(url, REQUEST_HEADERS).read
+      content.force_encoding('ISO-8859-1').encode!('UTF-8')
+      Nokogiri::HTML(content)
+    end
+
   end
 end

data/lib/cdb/cli.rb

@@ -14,15 +14,15 @@ module CDB
     end
 
     def []=(k, v)
+      v = v.to_s.strip
       case k
       when :command
-        v = v.to_s.strip.downcase
+        v = v.downcase
         raise unless COMMANDS.include?(v)
       when :scope
-        v = v.to_s.strip.downcase.gsub(/^=|s$/, '')
+        v = v.downcase.gsub(/^=|s$/, '')
         raise unless SCOPES.include?(v)
       when :args
-        v = v.to_s.strip
         if self[:command] == 'search'
           raise "invalid search query" if v.empty?
         end
@@ -40,8 +40,8 @@ module CDB
       case self[:scope] || 'all'
       when 'all'
         CDB.search(self[:args]).each do |key, res|
-          puts key.to_s.capitalize
-          res.each{|r| puts r.to_json}
+          puts key.to_s.capitalize+':'
+          res.each{|r| puts '  '+r.to_json}
         end
       when 'title'
         CDB::Title.search(self[:args]).each{|r| puts r.to_json}

data/lib/cdb/issue.rb

@@ -1,5 +1,5 @@
 module CDB
-  class Issue < Struct.new(:cdb_id, :title, :num, :name, :cover_date)
+  class Issue < Struct.new(:cdb_id, :title, :num, :name, :story_arc, :cover_date)
     FORM_SEARCHTYPE = 'IssueName'
     WEB_PATH = 'issue.php'
 
@@ -15,12 +15,24 @@ module CDB
           id = link.attr('href').split('=').last.to_i
           text = link.child.text.strip
           match = text.match(/^(.* \(\d{4}\)) (.*)$/)
-          title, num = match[1..2]
+          title = match[1]
+          num = match[2].gsub(/^#/, '')
           name = link.next_sibling.text.strip.gsub(/^-\s*"|"$/, '').strip
           new(:cdb_id => id, :title => title, :num => num, :name => name)
         end.sort_by(&:cdb_id)
       end
 
+      def from_tr(node, title)
+        tds = node.css('td')
+        link = tds[0].css("a[href^=\"#{WEB_PATH}\"]").first
+        new(:cdb_id => link['href'].split('=').last.strip,
+            :title => title,
+            :num => link.text.strip,
+            :name => tds[2].text.strip,
+            :story_arc => tds[4].text.strip,
+            :cover_date => tds[6].text.strip)
+      end
+
     end
   end
 end

data/lib/cdb/struct.rb

@@ -8,7 +8,7 @@ module CDB
       h.each{|k,v| send("#{k}=", v)}
     end
 
-    def as_json
+    def as_json(*)
       members.inject({}){|map, m|
         map[m] = self[m]; map
       }

data/lib/cdb/title.rb

@@ -1,5 +1,5 @@
 module CDB
-  class Title < Struct.new(:cdb_id, :name, :publisher, :begin_date, :end_date)
+  class Title < Struct.new(:cdb_id, :name, :issues, :publisher, :imprint, :begin_date, :end_date, :country, :language)
     FORM_SEARCHTYPE = 'Title'
     WEB_PATH = 'title.php'
 
@@ -10,6 +10,10 @@ module CDB
         results[:titles]
       end
 
+      def show(id)
+        CDB.show(id, self)
+      end
+
       def parse_results(node)
         node.css("a[href^=\"#{WEB_PATH}\"]").map do |link|
           id = link.attr('href').split('=').last.to_i
@@ -21,6 +25,26 @@ module CDB
         end.sort_by(&:cdb_id)
       end
 
+      def parse_data(id, page)
+        dates = page.css('strong:contains("Publication Date: ")').first.next_sibling.text.strip
+        start_d, end_d = dates.split('-').map(&:strip)
+
+        title = new(
+          :cdb_id => id,
+          :name => page.css('.page_headline').first.text.strip,
+          :publisher => page.css('a[href^="publisher.php"]').first.text.strip,
+          :imprint => page.css('a[href^="imprint.php"]').first.text.strip,
+          :begin_date => start_d,
+          :end_date => end_d,
+          :country => page.css('strong:contains("Country: ")').first.next_sibling.text.strip,
+          :language => page.css('strong:contains("Language: ")').first.next_sibling.text.strip
+        )
+        title.issues = page.css("td[width='726'] a.page_link[href^=\"#{CDB::Issue::WEB_PATH}\"]").map do |link|
+          tr = link.parent.parent
+          CDB::Issue.from_tr(tr, title)
+        end
+        title
+      end
     end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: cdb-crawlr
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-11-02 00:00:00.000000000Z
+date: 2012-11-03 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &18435060 !ruby/object:Gem::Requirement
+  requirement: &23392700 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,7 +21,7 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *18435060
+  version_requirements: *23392700
 description: cdb-crawlr is a Ruby gem and command-line tool for querying ComicBookDB.com
 email:
 - sgt.floydpepper@gmail.com