words-counter 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 0ae11e255506c68483eba2d508dc15de6180d478
+  data.tar.gz: 5909ee55bef283a08a14d07d73c1f547a59fdde7
+SHA512:
+  metadata.gz: 7e3b61dbab34311fa6819f35fb274122421621eb8b6349f1c43f8c30cdcacdc282abb2d42dff1a6ea845af2e61ee9c35b0d757251e06fbe06bb505f2ad8a8bd3
+  data.tar.gz: 27d73795e2a2225cfbbaa4214952403144003268e6ced0dd68ce274aa008e1d3552c85ab8a63ac39f7c52e947f0835963d981da6b32b3d2fb33b9848d8afadcc

data/lib/words_counter.rb

@@ -0,0 +1,57 @@
+require 'nokogiri'
+require 'open-uri'
+
+module WordsCounter
+    def self.analyse(url)  # the analyse method takes the url and number of times a word should appear as a parameter 
+        
+        url = url.to_s()
+        url = URI.parse(URI.encode(url.strip)) # make sure the url is fromated correctly 
+        page = Nokogiri::HTML(open(url)) # use the nokogiri gem to scrape the content of the webpage
+        text = page.css("p").text + " " + page.css("h1").text + " "# create a string from the words of the array 
+
+        words = text.split(/[^a-zA-Z]/)# open stated file, split the words and write them to an array  
+        words.map!(&:capitalize) #capitlize every word in the array
+
+        words.delete("A")
+        words.delete("An")
+        words.delete("And")
+        words.delete("Are")
+        words.delete("As")
+        words.delete("Be")
+        words.delete("For")
+        words.delete("Have")
+        words.delete("I")
+        words.delete("In")
+        words.delete("Is")
+        words.delete("It")
+        words.delete("Its")
+        words.delete("Of")
+        words.delete("On")
+        words.delete("Or")
+        words.delete("Our")
+        words.delete("That")
+        words.delete("The")
+        words.delete("These")
+        words.delete("This")
+        words.delete("To")
+        words.delete("We")
+        words.delete("Will")
+        words.delete("With")
+        words.delete("You")
+        words.delete("Your")
+        words.delete(" ")
+        words.delete("")# Delete several commonly used words
+
+        freqs = Hash.new(0)
+        words.each do |word|
+                    freqs[word] += 1
+        end # create a hash and populate it with the words and the number of times they appear
+
+
+        freqs = freqs.sort_by {|key,value| value }
+        freqs.reverse!  #organise the hash by frequency and sort it largest to smallest
+
+        result = freqs # return the hash as a result 
+        return result
+    end
+end

metadata

@@ -0,0 +1,43 @@
+--- !ruby/object:Gem::Specification
+name: words-counter
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Fiachra Murray
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-04-15 00:00:00.000000000 Z
+dependencies: []
+description: returns a hash with the words on the page and their incident.
+email: fiachra.murray.2014@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/words_counter.rb
+homepage: http://rubygems.org/gems/words-counter
+licenses: []
+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: counts the number of times a word appears on a webpage.
+test_files: []