four-chan 0.0.1

data/lib/four-chan.rb

@@ -0,0 +1,62 @@
+require "string-enumerable"
+require "net/http"
+require "nokogiri"
+require "open-uri"
+#A method should probably be made specifically to pull/process data.
+#Main class
+#Pages variable holds data concerning which pages are in this object
+#Data should hold the actual data
+#Everything else should be methods that extract stuff from data
+class Fourchan
+	#Pull data from 4chan to create new Fourchan object
+	#Pages must be an array, each element being an array with two elements: a symbol corresponding to the board you wish to pull data from (without slashes, (ex :b or :sci)
+	#and an array containing the numbers of the pages to be pulled
+	def initialize(pages)
+		@pages = pages
+		@data = Hash[]
+		for i in pages
+			board = i[0]
+			for j in i[1]
+				key = [board, j]
+				path = "http://boards.4chan.org/" + board.to_s + "/" + j
+				doc = Nokogiri::Doc.new(open(path))
+				@data[key] = doc
+			end
+		end
+	end
+	#Resets all page data in the current object, pulling it from the web anew
+	def reset
+		self = Fourchan.new(@pages)
+	end
+	#Pulls a new page from the web, adding the data to the present object. Note: when #reset is called, pages added with this function are also reset.
+	#The format of page must be the same as one of the elements in the pages argument in the initialization function(2-element array containing symbol denoting board and enumerable denoting pages)
+	def addPage(page)
+		found = false
+		for i in @pages
+			if i[0] == page[0]
+				i[1] = (i[1] + page[1]).uniq
+				found = true
+				break
+			end
+		end
+		@pages += page unless found
+		board = page[0]
+		for i in page[1]
+			key = [board, i]
+			path = "http://boards.4chan.org/" + board.to_s + "/" + i
+			doc = Nokogiri::Doc.new(open(path))
+			@data[key] = doc
+		end
+	end
+	#Returns an array, each element being the text from one post on the given page
+	def postsText(board, page)
+		key = [board, page]
+		doc = @data[key]
+		raw = doc.xpath("//blockquote")
+		raw.delete do |a|
+			not (a["class"].include? "post")
+		end
+		raw
+	end
+	attr_accessor :data
+end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: four-chan
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Eigil Rischel
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-08-22 00:00:00.000000000 Z
+dependencies: []
+description: A very simplistic interface to pull data from the popular website fourchan
+email: ayegill@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/four-chan.rb
+homepage: http://rubygems.org/gems/four-chan
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: fourchan interface
+test_files: []