gimme_poc 0.0.0.beta → 0.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5863cfeab7d822a42e8a69f6bc304a7f93feb475
-  data.tar.gz: be4262c816f306de6fc53fd088317d552dd3ce70
+  metadata.gz: 0e6506c640bcafe56d6906bfaae60f8a17e72865
+  data.tar.gz: 21e4fc7176c2d5aa28a0fe31ab993889a7fbf74d
 SHA512:
-  metadata.gz: ca6993932877a4b6c1a8f02c6dfa11cee7848cd232d0083ba4b9ef1c5e39439fd785eb3bfc17fee52c641021ab2d144c210134fc4ec46ab6be2cf3b0147d2a9d
-  data.tar.gz: 702e680dc3f8f44a67bec6d08258b8ebe9a3c6b9dcfed58872a8ac56d53a8298ce8b40b0f1230970cc2f85e093c5957013c13ce67bc2d07f89fa65533632bbd8
+  metadata.gz: 39c35961983b31246c7414067d607bbc6c7a6dbddc5af9dfa97122ff094b881248db7a4a9c6415c33e393b3f59e5c632f0b06c3fe04e70dd9035892c5c2b11cf
+  data.tar.gz: b1a194c4f0d51d7b3ea77f81786cc5b2d981b7c27f22dbeb6db98f8c1cca688437d04a1af5c9193d25e92072f88c664468d59ff89a2a853695e59809792ee457

data/README.md

@@ -1,3 +1,77 @@
-## gimme_poc
+# Gimme POC
 
-MTF
+Gimme POC (Point of Contact) simplifies the process of extracting the common 'contact us' information from a website.
+
+## Usage
+
+Gimme POC simply looks for a contact page and extracts social media contact information, if present.  Due to CAN-SPAM Act of 2003, emails are not harvested.  Instead Gimme POC will return True or False if an email or contact form is available.
+
+## Installation
+
+```
+gem install gimme_poc
+
+```
+
+## How it works
+
+Gimme POC is easy to use! Simply run this command.
+
+```ruby
+
+Gimme.poc 'http://example.com'
+
+# => returns this:
+#
+# {
+#   :contactpage=>"http://example.com/contact/", 
+#   :phone_present?=>"true", 
+#   :contact_form?=>"true",
+#   :facebook=>"http://www.facebook.com/example",
+#   :twitter=>"http://twitter.com/@example",
+#   :googleplus=>"http://plus.google.com/+example",
+#   :linkedin=>"http://www.linkedin.com/in/example"
+#  }
+#
+#
+
+
+```
+
+## Searching more than one site
+
+ You also have the ability to pass multiple urls in the form of array.  For example, you could run the command below and get contact information from each site all at once.
+
+```ruby
+
+Gimme.poc(['http://example.com', 'http://foo.com', 'http://bar.com'])
+
+```
+
+## Referencing the search results
+
+ To use your search results, simply run:
+
+```ruby
+
+Gimme.memory
+
+```
+
+## Clearing the search results
+
+ To clear search results and start afresh, simply run:
+
+```ruby
+
+Gimme.reset!
+
+```
+
+## To do:
+
+ - Convenience methods for returning specific information from all sites, (ie. just facebook or just twitter)
+ - Work on false positives of bad urls.  (DNS redirects don't give 404 errors)
+
+
+More to follow...

data/lib/gimme_poc/version.rb

@@ -1,3 +1,3 @@
 module Gimme
-  VERSION = "0.0.0.beta"
-end
+  VERSION = '0.0.1'
+end

data/lib/gimme_poc.rb

@@ -6,23 +6,24 @@ require_relative './gimme_poc/version'
 module Gimme
   class << self
     attr_accessor :page, :contact, :contact_links, :url
-    
+
     # Simple regex that looks for ###.#### or ###-####
     PHONE_REGEX = /\d{3}[-]\d{4}|\d{3}[.]\d{4}/
-    
+
     ## ----------------------------------------------------------------
-    # Questions 
+    # Questions
     #
     #
     #
-    
+
     # Boolean, returns true if contact link is present.
     def contact_link?
       @url = link_with_href('contact')
-      !!(@url != nil)
+
+      !@url.nil?
     end
-    
-    # Check if contact page '../contact' gets a 404 error.
+
+    # True if contact page '../contact' does NOT get a 404 error.
     def contact_page?
       @url = page.uri.merge('../contact').to_s
       begin
@@ -31,16 +32,16 @@ module Gimme
         false
       end
     end
-    
 
     # Boolean, returns true if link to English version is present.
     def english_link?
       return false if page.link_with(href: /english/).nil?
       @url = page.uri.merge(page.link_with(href: /english/).uri.to_s).to_s
-      !!(@url != nil)
+
+      !@url.nil?
     end
-    
-    # Check if english page '../en' gets a 404 error.
+
+    # True if english page '../en' does NOT get a 404 error.
     def en_page?
       @url = page.uri.merge('../en').to_s
       begin
@@ -50,8 +51,7 @@ module Gimme
       end
     end
 
-
-    # Check if english page '../english' gets a 404 error.
+    # True if english page '../english' does NOT get a 404 error.
     def english_page?
       @url = page.uri.merge('../english').to_s
       begin
@@ -66,18 +66,17 @@ module Gimme
     def something_to_save?
       scan_for_contacts.any?
     end
-    
+
     # Boolean, returns true if email is present.
     def email_available?
-      !!(link_with_href('mailto') != nil)
+      !link_with_href('mailto').nil?
     end
-    
-    
+
     # Boolean, returns true if phone number is present.
     def phone_available?
-      !!(page.body =~ PHONE_REGEX)
+      !(page.body =~ PHONE_REGEX).nil?
     end
-    
+
     # TODO: build better conditional to prevent false positives.
     # There could be other forms like newsletter signup, etc.
     #
@@ -86,11 +85,11 @@ module Gimme
     #
     # Boolean, returns true if form is present on page.
     def contactform_available?
-      !!(page.forms.select {|x| x.fields.length > 1}.empty? != true)
+      !(page.forms.select { |x| x.fields.length > 1 }.empty?)
     end
-    
+
     ## ----------------------------------------------------------------
-    # Actions 
+    # Actions
     #
     #
     #
@@ -100,68 +99,72 @@ module Gimme
     def poc(arr)
       arr = arr.split unless arr.is_a?(Array)
       arr.each do |url|
+        puts '-' * 50
+        puts "starting: #{url}"
         get(url)
         start_contact_links
         go_to_contact_page
         save_available_contacts
       end
-      puts "\nexited each url iteration and about to return final result"
-      puts 'press RETURN'
-      gets
-      p @contacts_links # need to add to an overall array at some point.
+      Search.all_sites
     end
-    
-    # Go to a page using Mechanize.  Doing this reinitializes the hash.
+
+    # Go to a page using Mechanize.
     def get(url)
-      puts "getting: #{url}"
-      @page = Mechanize.new.get(url)
+      puts "sending GET request: #{url}..."
+      @page = Mechanize.new { |a| a.user_agent_alias = 'Mac Safari' }.get(url)
     end
-    
+
     # Starts/Restarts @contacts_links hash
     def start_contact_links
-      puts "starting contact links hash."
+      puts 'setting contact links hash to {}'
       @contact_links = {}
     end
-    
-    # Scans for contact page.  If it doesn't work on the first try, 
+
+    # Scans for contact page.  If it doesn't work on the first try,
     # It will look for english versions and try again.
     #
     # If contact page is found, go directly there and don't try again.
     def go_to_contact_page
       1.times do
-        if contact_link?
-          puts "found contact link!".green
+        case
+        when contact_link?
+          puts 'found contact link!'.green
           get(@url)
-        elsif contact_page?
-          puts "found contact page!".green
+        when contact_page?
+          puts 'found contact page!'.green
           get(@url)
-        elsif english_link? # look for link first
-          puts "found english link!"
-          get(@url); redo
-        elsif en_page?
-          puts "found en page!"
-          get(@url); redo
-        elsif english_page?
-          puts "found english page!"
-          get(@url); redo
+        else
+          if english_link? # look for link first, not check the page.
+            puts 'found english link!'
+            get(@url)
+            redo
+          elsif en_page?
+            puts 'found en page!'
+            get(@url)
+            redo
+          elsif english_page?
+            puts 'found english page!'
+            redo
+          end
         end
       end
     end
 
-    # Expects relative paths and merges everything. 
+    # Expects relative paths and merges everything.
     # Returns a string.  If there's nothing, return nil.
     def link_with_href(str)
       page.uri.merge(page.link_with(href: /#{str}/).uri.to_s).to_s rescue nil
-    end    
+    end
 
     # Returns anything that is possible to save, otherwise returns nil.
     # Booleans for phone, email, or contact form will display True or False.
     def scan_for_contacts
       {
         contactpage: link_with_href('contact'),
-        email_present?: "#{email_available?}",
-        phone_present?: "#{phone_available?}",
-        contact_form?: "#{contactform_available?}",
+        email_present: "#{email_available?}",
+        phone_present: "#{phone_available?}",
+        contact_form: "#{contactform_available?}",
         facebook: link_with_href('facebook'),
         twitter: link_with_href('twitter'),
         youtube: link_with_href('youtube'),
@@ -175,28 +178,55 @@ module Gimme
       return if key.nil? || url.nil?
       @contact_links[key] = url
     end
-    
+
     # Remove negatives from the contacts hash.
     # Deletes a key value pair with a value of either nil or false.
     # Remember that false is a string.
     def delete_failures(hsh)
-      hsh.delete_if {|k, v| v == nil || v == 'false'}
+      hsh.delete_if { |_k, v| v.nil? || v == 'false' }
     end
 
     # Saves any available contact info to @contact_links.
     def save_available_contacts(hsh = scan_for_contacts)
-      puts 'starting save of available contact information...'
+      puts 'saving available contact information...'
       return unless something_to_save?
       if hsh.is_a?(Hash)
         hsh.each do |k, v|
-          save_link(k, v)
+          save_link(k, v) # saves to @contact_links
         end
-        delete_failures(hsh)
-        puts "this is hsh after nil strip:"
-        puts "#{hsh}".cyan
-      else  
-        raise ArgumentError, "expected hash but got #{hsh.class}"
+        delete_failures(@contact_links)
+        puts "#{@contact_links}".cyan # same as @contact_links
+      else
+        fail ArgumentError, "expected hash but got #{hsh.class}"
       end
+      Search::POC.new(@contact_links)
+    end
+
+    # Convenience method
+    def memory
+      Search.all_sites
+    end
+
+    # Clears entire collection.
+    def reset!
+      Search.all_sites = []
+    end
+  end
+end
+
+# Collectino of sites searched
+class Search
+  @all_sites = []
+
+  class << self
+    attr_accessor :all_sites
+  end
+
+  # Each site is saved to this class
+  class POC
+    def initialize(contact_info_hsh)
+      @contact_info = contact_info_hsh
+      Search.all_sites << self
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gimme_poc
 version: !ruby/object:Gem::Version
-  version: 0.0.0.beta
+  version: 0.0.1
 platform: ruby
 authors:
 - John Mason
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-08 00:00:00.000000000 Z
+date: 2015-10-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize
@@ -93,12 +93,12 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.3
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
 summary: Get a point of contact.  Given a url or array of urls, extracts social media